From d751c169e9a6f0f853346f1184881422bd10b3c2 Mon Sep 17 00:00:00 2001
From: Michael Davidson <md@google.com>
Date: Thu, 10 Oct 2013 18:39:54 -0700
Subject: x86, relocs: Add more per-cpu gold special cases

The "gold" linker doesn't seem to put some additional per-cpu cases in
the right place. Add these to the per-cpu check. Without this, the kASLR
patch series fails to correctly apply relocations, and fails to boot.

Signed-off-by: Michael Davidson <md@google.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/20131011013954.GA28902@www.outflux.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index f7bab68..71a2533 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -722,15 +722,23 @@ static void percpu_init(void)
 
 /*
  * Check to see if a symbol lies in the .data..percpu section.
- * For some as yet not understood reason the "__init_begin"
- * symbol which immediately preceeds the .data..percpu section
- * also shows up as it it were part of it so we do an explict
- * check for that symbol name and ignore it.
+ *
+ * The linker incorrectly associates some symbols with the
+ * .data..percpu section so we also need to check the symbol
+ * name to make sure that we classify the symbol correctly.
+ *
+ * The GNU linker incorrectly associates:
+ *	__init_begin
+ *
+ * The "gold" linker incorrectly associates:
+ *	init_per_cpu__irq_stack_union
+ *	init_per_cpu__gdt_page
  */
 static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)
 {
 	return (sym->st_shndx == per_cpu_shndx) &&
-		strcmp(symname, "__init_begin");
+		strcmp(symname, "__init_begin") &&
+		strncmp(symname, "init_per_cpu_", 13);
 }
 
 
-- 
cgit v0.10.2


From dd78b97367bd575918204cc89107c1479d3fc1a7 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 10 Oct 2013 17:18:13 -0700
Subject: x86, boot: Move CPU flags out of cpucheck

Refactor the CPU flags handling out of the cpucheck routines so that
they can be reused by the future ASLR routines (in order to detect CPU
features like RDRAND and RDTSC).

This reworks has_eflag() and has_fpu() to be used on both 32-bit and
64-bit, and refactors the calls to cpuid to make them PIC-safe on 32-bit.

Signed-off-by: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/1381450698-28710-2-git-send-email-keescook@chromium.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 379814b..0da2e37 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -20,7 +20,7 @@ targets		:= vmlinux.bin setup.bin setup.elf bzImage
 targets		+= fdimage fdimage144 fdimage288 image.iso mtools.conf
 subdir-		:= compressed
 
-setup-y		+= a20.o bioscall.o cmdline.o copy.o cpu.o cpucheck.o
+setup-y		+= a20.o bioscall.o cmdline.o copy.o cpu.o cpuflags.o cpucheck.o
 setup-y		+= early_serial_console.o edd.o header.o main.o mca.o memory.o
 setup-y		+= pm.o pmjump.o printf.o regs.o string.o tty.o video.o
 setup-y		+= video-mode.o version.o
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index ef72bae..50f8c5e 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -26,9 +26,8 @@
 #include <asm/boot.h>
 #include <asm/setup.h>
 #include "bitops.h"
-#include <asm/cpufeature.h>
-#include <asm/processor-flags.h>
 #include "ctype.h"
+#include "cpuflags.h"
 
 /* Useful macros */
 #define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
@@ -307,14 +306,7 @@ static inline int cmdline_find_option_bool(const char *option)
 	return __cmdline_find_option_bool(cmd_line_ptr, option);
 }
 
-
 /* cpu.c, cpucheck.c */
-struct cpu_features {
-	int level;		/* Family, or 64 for x86-64 */
-	int model;
-	u32 flags[NCAPINTS];
-};
-extern struct cpu_features cpu;
 int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr);
 int validate_cpu(void);
 
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index dcd90df..3312f1be 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -27,7 +27,7 @@ HOST_EXTRACFLAGS += -I$(srctree)/tools/include
 
 VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
 	$(obj)/string.o $(obj)/cmdline.o $(obj)/early_serial_console.o \
-	$(obj)/piggy.o
+	$(obj)/piggy.o $(obj)/cpuflags.o
 
 $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
 
diff --git a/arch/x86/boot/compressed/cpuflags.c b/arch/x86/boot/compressed/cpuflags.c
new file mode 100644
index 0000000..931cba6
--- /dev/null
+++ b/arch/x86/boot/compressed/cpuflags.c
@@ -0,0 +1,12 @@
+#ifdef CONFIG_RANDOMIZE_BASE
+
+#include "../cpuflags.c"
+
+bool has_cpuflag(int flag)
+{
+	get_flags();
+
+	return test_bit(flag, cpu.flags);
+}
+
+#endif
diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c
index 4d3ff03..e1f3c16 100644
--- a/arch/x86/boot/cpucheck.c
+++ b/arch/x86/boot/cpucheck.c
@@ -28,8 +28,6 @@
 #include <asm/required-features.h>
 #include <asm/msr-index.h>
 
-struct cpu_features cpu;
-static u32 cpu_vendor[3];
 static u32 err_flags[NCAPINTS];
 
 static const int req_level = CONFIG_X86_MINIMUM_CPU_FAMILY;
@@ -69,90 +67,6 @@ static int is_transmeta(void)
 	       cpu_vendor[2] == A32('M', 'x', '8', '6');
 }
 
-static int has_fpu(void)
-{
-	u16 fcw = -1, fsw = -1;
-	u32 cr0;
-
-	asm("movl %%cr0,%0" : "=r" (cr0));
-	if (cr0 & (X86_CR0_EM|X86_CR0_TS)) {
-		cr0 &= ~(X86_CR0_EM|X86_CR0_TS);
-		asm volatile("movl %0,%%cr0" : : "r" (cr0));
-	}
-
-	asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
-		     : "+m" (fsw), "+m" (fcw));
-
-	return fsw == 0 && (fcw & 0x103f) == 0x003f;
-}
-
-static int has_eflag(u32 mask)
-{
-	u32 f0, f1;
-
-	asm("pushfl ; "
-	    "pushfl ; "
-	    "popl %0 ; "
-	    "movl %0,%1 ; "
-	    "xorl %2,%1 ; "
-	    "pushl %1 ; "
-	    "popfl ; "
-	    "pushfl ; "
-	    "popl %1 ; "
-	    "popfl"
-	    : "=&r" (f0), "=&r" (f1)
-	    : "ri" (mask));
-
-	return !!((f0^f1) & mask);
-}
-
-static void get_flags(void)
-{
-	u32 max_intel_level, max_amd_level;
-	u32 tfms;
-
-	if (has_fpu())
-		set_bit(X86_FEATURE_FPU, cpu.flags);
-
-	if (has_eflag(X86_EFLAGS_ID)) {
-		asm("cpuid"
-		    : "=a" (max_intel_level),
-		      "=b" (cpu_vendor[0]),
-		      "=d" (cpu_vendor[1]),
-		      "=c" (cpu_vendor[2])
-		    : "a" (0));
-
-		if (max_intel_level >= 0x00000001 &&
-		    max_intel_level <= 0x0000ffff) {
-			asm("cpuid"
-			    : "=a" (tfms),
-			      "=c" (cpu.flags[4]),
-			      "=d" (cpu.flags[0])
-			    : "a" (0x00000001)
-			    : "ebx");
-			cpu.level = (tfms >> 8) & 15;
-			cpu.model = (tfms >> 4) & 15;
-			if (cpu.level >= 6)
-				cpu.model += ((tfms >> 16) & 0xf) << 4;
-		}
-
-		asm("cpuid"
-		    : "=a" (max_amd_level)
-		    : "a" (0x80000000)
-		    : "ebx", "ecx", "edx");
-
-		if (max_amd_level >= 0x80000001 &&
-		    max_amd_level <= 0x8000ffff) {
-			u32 eax = 0x80000001;
-			asm("cpuid"
-			    : "+a" (eax),
-			      "=c" (cpu.flags[6]),
-			      "=d" (cpu.flags[1])
-			    : : "ebx");
-		}
-	}
-}
-
 /* Returns a bitmask of which words we have error bits in */
 static int check_flags(void)
 {
diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c
new file mode 100644
index 0000000..b02544a
--- /dev/null
+++ b/arch/x86/boot/cpuflags.c
@@ -0,0 +1,104 @@
+#include <linux/types.h>
+#include "bitops.h"
+
+#include <asm/processor-flags.h>
+#include <asm/required-features.h>
+#include <asm/msr-index.h>
+#include "cpuflags.h"
+
+struct cpu_features cpu;
+u32 cpu_vendor[3];
+
+static bool loaded_flags;
+
+static int has_fpu(void)
+{
+	u16 fcw = -1, fsw = -1;
+	unsigned long cr0;
+
+	asm volatile("mov %%cr0,%0" : "=r" (cr0));
+	if (cr0 & (X86_CR0_EM|X86_CR0_TS)) {
+		cr0 &= ~(X86_CR0_EM|X86_CR0_TS);
+		asm volatile("mov %0,%%cr0" : : "r" (cr0));
+	}
+
+	asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
+		     : "+m" (fsw), "+m" (fcw));
+
+	return fsw == 0 && (fcw & 0x103f) == 0x003f;
+}
+
+int has_eflag(unsigned long mask)
+{
+	unsigned long f0, f1;
+
+	asm volatile("pushf	\n\t"
+		     "pushf	\n\t"
+		     "pop %0	\n\t"
+		     "mov %0,%1	\n\t"
+		     "xor %2,%1	\n\t"
+		     "push %1	\n\t"
+		     "popf	\n\t"
+		     "pushf	\n\t"
+		     "pop %1	\n\t"
+		     "popf"
+		     : "=&r" (f0), "=&r" (f1)
+		     : "ri" (mask));
+
+	return !!((f0^f1) & mask);
+}
+
+/* Handle x86_32 PIC using ebx. */
+#if defined(__i386__) && defined(__PIC__)
+# define EBX_REG "=r"
+#else
+# define EBX_REG "=b"
+#endif
+
+static inline void cpuid(u32 id, u32 *a, u32 *b, u32 *c, u32 *d)
+{
+	asm volatile(".ifnc %%ebx,%3 ; movl  %%ebx,%3 ; .endif	\n\t"
+		     "cpuid					\n\t"
+		     ".ifnc %%ebx,%3 ; xchgl %%ebx,%3 ; .endif	\n\t"
+		    : "=a" (*a), "=c" (*c), "=d" (*d), EBX_REG (*b)
+		    : "a" (id)
+	);
+}
+
+void get_flags(void)
+{
+	u32 max_intel_level, max_amd_level;
+	u32 tfms;
+	u32 ignored;
+
+	if (loaded_flags)
+		return;
+	loaded_flags = true;
+
+	if (has_fpu())
+		set_bit(X86_FEATURE_FPU, cpu.flags);
+
+	if (has_eflag(X86_EFLAGS_ID)) {
+		cpuid(0x0, &max_intel_level, &cpu_vendor[0], &cpu_vendor[2],
+		      &cpu_vendor[1]);
+
+		if (max_intel_level >= 0x00000001 &&
+		    max_intel_level <= 0x0000ffff) {
+			cpuid(0x1, &tfms, &ignored, &cpu.flags[4],
+			      &cpu.flags[0]);
+			cpu.level = (tfms >> 8) & 15;
+			cpu.model = (tfms >> 4) & 15;
+			if (cpu.level >= 6)
+				cpu.model += ((tfms >> 16) & 0xf) << 4;
+		}
+
+		cpuid(0x80000000, &max_amd_level, &ignored, &ignored,
+		      &ignored);
+
+		if (max_amd_level >= 0x80000001 &&
+		    max_amd_level <= 0x8000ffff) {
+			cpuid(0x80000001, &ignored, &ignored, &cpu.flags[6],
+			      &cpu.flags[1]);
+		}
+	}
+}
diff --git a/arch/x86/boot/cpuflags.h b/arch/x86/boot/cpuflags.h
new file mode 100644
index 0000000..9bb4e25
--- /dev/null
+++ b/arch/x86/boot/cpuflags.h
@@ -0,0 +1,19 @@
+#ifndef BOOT_CPUFLAGS_H
+#define BOOT_CPUFLAGS_H
+
+#include <asm/cpufeature.h>
+#include <asm/processor-flags.h>
+
+struct cpu_features {
+	int level;		/* Family, or 64 for x86-64 */
+	int model;
+	u32 flags[NCAPINTS];
+};
+
+extern struct cpu_features cpu;
+extern u32 cpu_vendor[3];
+
+int has_eflag(unsigned long mask);
+void get_flags(void);
+
+#endif
-- 
cgit v0.10.2


From 8ab3820fd5b2896d66da7bb2a906bc382e63e7bc Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 10 Oct 2013 17:18:14 -0700
Subject: x86, kaslr: Return location from decompress_kernel

This allows decompress_kernel to return a new location for the kernel to
be relocated to. Additionally, enforces CONFIG_PHYSICAL_START as the
minimum relocation position when building with CONFIG_RELOCATABLE.

With CONFIG_RANDOMIZE_BASE set, the choose_kernel_location routine
will select a new location to decompress the kernel, though here it is
presently a no-op. The kernel command line option "nokaslr" is introduced
to bypass these routines.

Signed-off-by: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/1381450698-28710-3-git-send-email-keescook@chromium.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index fcbb736..773fc4c 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1975,6 +1975,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	noapic		[SMP,APIC] Tells the kernel to not make use of any
 			IOAPICs that may be present in the system.
 
+	nokaslr		[X86]
+			Disable kernel base offset ASLR (Address Space
+			Layout Randomization) if built into the kernel.
+
 	noautogroup	Disable scheduler automatic task group creation.
 
 	nobats		[PPC] Do not use BATs for mapping kernel lowmem
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ee2fb9d..992701d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1722,16 +1722,46 @@ config RELOCATABLE
 
 	  Note: If CONFIG_RELOCATABLE=y, then the kernel runs from the address
 	  it has been loaded at and the compile time physical address
-	  (CONFIG_PHYSICAL_START) is ignored.
+	  (CONFIG_PHYSICAL_START) is used as the minimum location.
 
-# Relocation on x86-32 needs some additional build support
+config RANDOMIZE_BASE
+	bool "Randomize the address of the kernel image"
+	depends on RELOCATABLE
+	depends on !HIBERNATION
+	default n
+	---help---
+	   Randomizes the physical and virtual address at which the
+	   kernel image is decompressed, as a security feature that
+	   deters exploit attempts relying on knowledge of the location
+	   of kernel internals.
+
+	   Entropy is generated using the RDRAND instruction if it
+	   is supported.  If not, then RDTSC is used, if supported. If
+	   neither RDRAND nor RDTSC are supported, then no randomness
+	   is introduced.
+
+	   The kernel will be offset by up to RANDOMIZE_BASE_MAX_OFFSET,
+	   and aligned according to PHYSICAL_ALIGN.
+
+config RANDOMIZE_BASE_MAX_OFFSET
+	hex "Maximum ASLR offset allowed"
+	depends on RANDOMIZE_BASE
+	default "0x10000000"
+	range 0x0 0x10000000
+	---help---
+	 Determines the maximal offset in bytes that will be applied to the
+	 kernel when Address Space Layout Randomization (ASLR) is active.
+	 Must be less than or equal to the actual physical memory on the
+	 system. This must be a power of two.
+
+# Relocation on x86 needs some additional build support
 config X86_NEED_RELOCS
 	def_bool y
-	depends on X86_32 && RELOCATABLE
+	depends on RANDOMIZE_BASE || (X86_32 && RELOCATABLE)
 
 config PHYSICAL_ALIGN
 	hex "Alignment value to which kernel should be aligned"
-	default "0x1000000"
+	default "0x200000"
 	range 0x2000 0x1000000 if X86_32
 	range 0x200000 0x1000000 if X86_64
 	---help---
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 3312f1be..ae8b5db 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -27,7 +27,7 @@ HOST_EXTRACFLAGS += -I$(srctree)/tools/include
 
 VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
 	$(obj)/string.o $(obj)/cmdline.o $(obj)/early_serial_console.o \
-	$(obj)/piggy.o $(obj)/cpuflags.o
+	$(obj)/piggy.o $(obj)/cpuflags.o $(obj)/aslr.o
 
 $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
 
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
new file mode 100644
index 0000000..b73cc66
--- /dev/null
+++ b/arch/x86/boot/compressed/aslr.c
@@ -0,0 +1,23 @@
+#include "misc.h"
+
+#ifdef CONFIG_RANDOMIZE_BASE
+
+unsigned char *choose_kernel_location(unsigned char *input,
+				      unsigned long input_size,
+				      unsigned char *output,
+				      unsigned long output_size)
+{
+	unsigned long choice = (unsigned long)output;
+
+	if (cmdline_find_option_bool("nokaslr")) {
+		debug_putstr("KASLR disabled...\n");
+		goto out;
+	}
+
+	/* XXX: choose random location. */
+
+out:
+	return (unsigned char *)choice;
+}
+
+#endif /* CONFIG_RANDOMIZE_BASE */
diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c
index bffd73b..b68e303 100644
--- a/arch/x86/boot/compressed/cmdline.c
+++ b/arch/x86/boot/compressed/cmdline.c
@@ -1,6 +1,6 @@
 #include "misc.h"
 
-#ifdef CONFIG_EARLY_PRINTK
+#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE
 
 static unsigned long fs;
 static inline void set_fs(unsigned long seg)
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 5d6f6891..9116aac 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -117,9 +117,11 @@ preferred_addr:
 	addl    %eax, %ebx
 	notl	%eax
 	andl    %eax, %ebx
-#else
-	movl	$LOAD_PHYSICAL_ADDR, %ebx
+	cmpl	$LOAD_PHYSICAL_ADDR, %ebx
+	jge	1f
 #endif
+	movl	$LOAD_PHYSICAL_ADDR, %ebx
+1:
 
 	/* Target address to relocate to for decompression */
 	addl	$z_extract_offset, %ebx
@@ -191,14 +193,14 @@ relocated:
 	leal	boot_heap(%ebx), %eax
 	pushl	%eax		/* heap area */
 	pushl	%esi		/* real mode pointer */
-	call	decompress_kernel
+	call	decompress_kernel /* returns kernel location in %eax */
 	addl	$24, %esp
 
 /*
  * Jump to the decompressed kernel.
  */
 	xorl	%ebx, %ebx
-	jmp	*%ebp
+	jmp	*%eax
 
 /*
  * Stack and heap for uncompression
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index c337422..c5c1ae0 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -94,9 +94,11 @@ ENTRY(startup_32)
 	addl	%eax, %ebx
 	notl	%eax
 	andl	%eax, %ebx
-#else
-	movl	$LOAD_PHYSICAL_ADDR, %ebx
+	cmpl	$LOAD_PHYSICAL_ADDR, %ebx
+	jge	1f
 #endif
+	movl	$LOAD_PHYSICAL_ADDR, %ebx
+1:
 
 	/* Target address to relocate to for decompression */
 	addl	$z_extract_offset, %ebx
@@ -269,9 +271,11 @@ preferred_addr:
 	addq	%rax, %rbp
 	notq	%rax
 	andq	%rax, %rbp
-#else
-	movq	$LOAD_PHYSICAL_ADDR, %rbp
+	cmpq	$LOAD_PHYSICAL_ADDR, %rbp
+	jge	1f
 #endif
+	movq	$LOAD_PHYSICAL_ADDR, %rbp
+1:
 
 	/* Target address to relocate to for decompression */
 	leaq	z_extract_offset(%rbp), %rbx
@@ -339,13 +343,13 @@ relocated:
 	movl	$z_input_len, %ecx	/* input_len */
 	movq	%rbp, %r8		/* output target address */
 	movq	$z_output_len, %r9	/* decompressed length */
-	call	decompress_kernel
+	call	decompress_kernel	/* returns kernel location in %rax */
 	popq	%rsi
 
 /*
  * Jump to the decompressed kernel.
  */
-	jmp	*%rbp
+	jmp	*%rax
 
 	.code32
 no_longmode:
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 434f077..7138768 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -395,7 +395,7 @@ static void parse_elf(void *output)
 	free(phdrs);
 }
 
-asmlinkage void decompress_kernel(void *rmode, memptr heap,
+asmlinkage void *decompress_kernel(void *rmode, memptr heap,
 				  unsigned char *input_data,
 				  unsigned long input_len,
 				  unsigned char *output,
@@ -422,6 +422,10 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 	free_mem_ptr     = heap;	/* Heap */
 	free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
 
+	output = choose_kernel_location(input_data, input_len,
+					output, output_len);
+
+	/* Validate memory location choices. */
 	if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1))
 		error("Destination address inappropriately aligned");
 #ifdef CONFIG_X86_64
@@ -441,5 +445,5 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 	parse_elf(output);
 	handle_relocations(output, output_len);
 	debug_putstr("done.\nBooting the kernel.\n");
-	return;
+	return output;
 }
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 674019d..9077af7 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -39,23 +39,38 @@ static inline void debug_putstr(const char *s)
 
 #endif
 
-#ifdef CONFIG_EARLY_PRINTK
-
+#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE
 /* cmdline.c */
 int cmdline_find_option(const char *option, char *buffer, int bufsize);
 int cmdline_find_option_bool(const char *option);
+#endif
 
-/* early_serial_console.c */
-extern int early_serial_base;
-void console_init(void);
 
+#if CONFIG_RANDOMIZE_BASE
+/* aslr.c */
+unsigned char *choose_kernel_location(unsigned char *input,
+				      unsigned long input_size,
+				      unsigned char *output,
+				      unsigned long output_size);
 #else
+static inline
+unsigned char *choose_kernel_location(unsigned char *input,
+				      unsigned long input_size,
+				      unsigned char *output,
+				      unsigned long output_size)
+{
+	return output;
+}
+#endif
 
+#ifdef CONFIG_EARLY_PRINTK
 /* early_serial_console.c */
+extern int early_serial_base;
+void console_init(void);
+#else
 static const int early_serial_base;
 static inline void console_init(void)
 { }
-
 #endif
 
 #endif
-- 
cgit v0.10.2


From 5bfce5ef55cbe78ee2ee6e97f2e26a8a582008f3 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 10 Oct 2013 17:18:15 -0700
Subject: x86, kaslr: Provide randomness functions

Adds potential sources of randomness: RDRAND, RDTSC, or the i8254.

This moves the pre-alternatives inline rdrand function into the header so
both pieces of code can use it. Availability of RDRAND is then controlled
by CONFIG_ARCH_RANDOM, if someone wants to disable it even for kASLR.

Signed-off-by: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/1381450698-28710-4-git-send-email-keescook@chromium.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index b73cc66..14b24e0 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -1,6 +1,59 @@
 #include "misc.h"
 
 #ifdef CONFIG_RANDOMIZE_BASE
+#include <asm/msr.h>
+#include <asm/archrandom.h>
+
+#define I8254_PORT_CONTROL	0x43
+#define I8254_PORT_COUNTER0	0x40
+#define I8254_CMD_READBACK	0xC0
+#define I8254_SELECT_COUNTER0	0x02
+#define I8254_STATUS_NOTREADY	0x40
+static inline u16 i8254(void)
+{
+	u16 status, timer;
+
+	do {
+		outb(I8254_PORT_CONTROL,
+		     I8254_CMD_READBACK | I8254_SELECT_COUNTER0);
+		status = inb(I8254_PORT_COUNTER0);
+		timer  = inb(I8254_PORT_COUNTER0);
+		timer |= inb(I8254_PORT_COUNTER0) << 8;
+	} while (status & I8254_STATUS_NOTREADY);
+
+	return timer;
+}
+
+static unsigned long get_random_long(void)
+{
+	unsigned long random;
+
+	if (has_cpuflag(X86_FEATURE_RDRAND)) {
+		debug_putstr("KASLR using RDRAND...\n");
+		if (rdrand_long(&random))
+			return random;
+	}
+
+	if (has_cpuflag(X86_FEATURE_TSC)) {
+		uint32_t raw;
+
+		debug_putstr("KASLR using RDTSC...\n");
+		rdtscl(raw);
+
+		/* Only use the low bits of rdtsc. */
+		random = raw & 0xffff;
+	} else {
+		debug_putstr("KASLR using i8254...\n");
+		random = i8254();
+	}
+
+	/* Extend timer bits poorly... */
+	random |= (random << 16);
+#ifdef CONFIG_X86_64
+	random |= (random << 32);
+#endif
+	return random;
+}
 
 unsigned char *choose_kernel_location(unsigned char *input,
 				      unsigned long input_size,
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 9077af7..0782eb0 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -52,6 +52,8 @@ unsigned char *choose_kernel_location(unsigned char *input,
 				      unsigned long input_size,
 				      unsigned char *output,
 				      unsigned long output_size);
+/* cpuflags.c */
+bool has_cpuflag(int flag);
 #else
 static inline
 unsigned char *choose_kernel_location(unsigned char *input,
diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h
index 0d9ec77..e6a9245 100644
--- a/arch/x86/include/asm/archrandom.h
+++ b/arch/x86/include/asm/archrandom.h
@@ -39,6 +39,20 @@
 
 #ifdef CONFIG_ARCH_RANDOM
 
+/* Instead of arch_get_random_long() when alternatives haven't run. */
+static inline int rdrand_long(unsigned long *v)
+{
+	int ok;
+	asm volatile("1: " RDRAND_LONG "\n\t"
+		     "jc 2f\n\t"
+		     "decl %0\n\t"
+		     "jnz 1b\n\t"
+		     "2:"
+		     : "=r" (ok), "=a" (*v)
+		     : "0" (RDRAND_RETRY_LOOPS));
+	return ok;
+}
+
 #define GET_RANDOM(name, type, rdrand, nop)			\
 static inline int name(type *v)					\
 {								\
@@ -68,6 +82,13 @@ GET_RANDOM(arch_get_random_int, unsigned int, RDRAND_INT, ASM_NOP3);
 
 #endif /* CONFIG_X86_64 */
 
+#else
+
+static inline int rdrand_long(unsigned long *v)
+{
+	return 0;
+}
+
 #endif  /* CONFIG_ARCH_RANDOM */
 
 extern void x86_init_rdrand(struct cpuinfo_x86 *c);
diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c
index 88db010..384df51 100644
--- a/arch/x86/kernel/cpu/rdrand.c
+++ b/arch/x86/kernel/cpu/rdrand.c
@@ -31,20 +31,6 @@ static int __init x86_rdrand_setup(char *s)
 }
 __setup("nordrand", x86_rdrand_setup);
 
-/* We can't use arch_get_random_long() here since alternatives haven't run */
-static inline int rdrand_long(unsigned long *v)
-{
-	int ok;
-	asm volatile("1: " RDRAND_LONG "\n\t"
-		     "jc 2f\n\t"
-		     "decl %0\n\t"
-		     "jnz 1b\n\t"
-		     "2:"
-		     : "=r" (ok), "=a" (*v)
-		     : "0" (RDRAND_RETRY_LOOPS));
-	return ok;
-}
-
 /*
  * Force a reseed cycle; we are architecturally guaranteed a reseed
  * after no more than 512 128-bit chunks of random data.  This also
-- 
cgit v0.10.2


From 82fa9637a2ba285bcc7c5050c73010b2c1b3d803 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 10 Oct 2013 17:18:16 -0700
Subject: x86, kaslr: Select random position from e820 maps

Counts available alignment positions across all e820 maps, and chooses
one randomly for the new kernel base address, making sure not to collide
with unsafe memory areas.

Signed-off-by: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/1381450698-28710-5-git-send-email-keescook@chromium.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 14b24e0..0595798 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -3,6 +3,7 @@
 #ifdef CONFIG_RANDOMIZE_BASE
 #include <asm/msr.h>
 #include <asm/archrandom.h>
+#include <asm/e820.h>
 
 #define I8254_PORT_CONTROL	0x43
 #define I8254_PORT_COUNTER0	0x40
@@ -55,20 +56,210 @@ static unsigned long get_random_long(void)
 	return random;
 }
 
+struct mem_vector {
+	unsigned long start;
+	unsigned long size;
+};
+
+#define MEM_AVOID_MAX 5
+struct mem_vector mem_avoid[MEM_AVOID_MAX];
+
+static bool mem_contains(struct mem_vector *region, struct mem_vector *item)
+{
+	/* Item at least partially before region. */
+	if (item->start < region->start)
+		return false;
+	/* Item at least partially after region. */
+	if (item->start + item->size > region->start + region->size)
+		return false;
+	return true;
+}
+
+static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two)
+{
+	/* Item one is entirely before item two. */
+	if (one->start + one->size <= two->start)
+		return false;
+	/* Item one is entirely after item two. */
+	if (one->start >= two->start + two->size)
+		return false;
+	return true;
+}
+
+static void mem_avoid_init(unsigned long input, unsigned long input_size,
+			   unsigned long output, unsigned long output_size)
+{
+	u64 initrd_start, initrd_size;
+	u64 cmd_line, cmd_line_size;
+	unsigned long unsafe, unsafe_len;
+	char *ptr;
+
+	/*
+	 * Avoid the region that is unsafe to overlap during
+	 * decompression (see calculations at top of misc.c).
+	 */
+	unsafe_len = (output_size >> 12) + 32768 + 18;
+	unsafe = (unsigned long)input + input_size - unsafe_len;
+	mem_avoid[0].start = unsafe;
+	mem_avoid[0].size = unsafe_len;
+
+	/* Avoid initrd. */
+	initrd_start  = (u64)real_mode->ext_ramdisk_image << 32;
+	initrd_start |= real_mode->hdr.ramdisk_image;
+	initrd_size  = (u64)real_mode->ext_ramdisk_size << 32;
+	initrd_size |= real_mode->hdr.ramdisk_size;
+	mem_avoid[1].start = initrd_start;
+	mem_avoid[1].size = initrd_size;
+
+	/* Avoid kernel command line. */
+	cmd_line  = (u64)real_mode->ext_cmd_line_ptr << 32;
+	cmd_line |= real_mode->hdr.cmd_line_ptr;
+	/* Calculate size of cmd_line. */
+	ptr = (char *)(unsigned long)cmd_line;
+	for (cmd_line_size = 0; ptr[cmd_line_size++]; )
+		;
+	mem_avoid[2].start = cmd_line;
+	mem_avoid[2].size = cmd_line_size;
+
+	/* Avoid heap memory. */
+	mem_avoid[3].start = (unsigned long)free_mem_ptr;
+	mem_avoid[3].size = BOOT_HEAP_SIZE;
+
+	/* Avoid stack memory. */
+	mem_avoid[4].start = (unsigned long)free_mem_end_ptr;
+	mem_avoid[4].size = BOOT_STACK_SIZE;
+}
+
+/* Does this memory vector overlap a known avoided area? */
+bool mem_avoid_overlap(struct mem_vector *img)
+{
+	int i;
+
+	for (i = 0; i < MEM_AVOID_MAX; i++) {
+		if (mem_overlaps(img, &mem_avoid[i]))
+			return true;
+	}
+
+	return false;
+}
+
+unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET / CONFIG_PHYSICAL_ALIGN];
+unsigned long slot_max = 0;
+
+static void slots_append(unsigned long addr)
+{
+	/* Overflowing the slots list should be impossible. */
+	if (slot_max >= CONFIG_RANDOMIZE_BASE_MAX_OFFSET /
+			CONFIG_PHYSICAL_ALIGN)
+		return;
+
+	slots[slot_max++] = addr;
+}
+
+static unsigned long slots_fetch_random(void)
+{
+	/* Handle case of no slots stored. */
+	if (slot_max == 0)
+		return 0;
+
+	return slots[get_random_long() % slot_max];
+}
+
+static void process_e820_entry(struct e820entry *entry,
+			       unsigned long minimum,
+			       unsigned long image_size)
+{
+	struct mem_vector region, img;
+
+	/* Skip non-RAM entries. */
+	if (entry->type != E820_RAM)
+		return;
+
+	/* Ignore entries entirely above our maximum. */
+	if (entry->addr >= CONFIG_RANDOMIZE_BASE_MAX_OFFSET)
+		return;
+
+	/* Ignore entries entirely below our minimum. */
+	if (entry->addr + entry->size < minimum)
+		return;
+
+	region.start = entry->addr;
+	region.size = entry->size;
+
+	/* Potentially raise address to minimum location. */
+	if (region.start < minimum)
+		region.start = minimum;
+
+	/* Potentially raise address to meet alignment requirements. */
+	region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN);
+
+	/* Did we raise the address above the bounds of this e820 region? */
+	if (region.start > entry->addr + entry->size)
+		return;
+
+	/* Reduce size by any delta from the original address. */
+	region.size -= region.start - entry->addr;
+
+	/* Reduce maximum size to fit end of image within maximum limit. */
+	if (region.start + region.size > CONFIG_RANDOMIZE_BASE_MAX_OFFSET)
+		region.size = CONFIG_RANDOMIZE_BASE_MAX_OFFSET - region.start;
+
+	/* Walk each aligned slot and check for avoided areas. */
+	for (img.start = region.start, img.size = image_size ;
+	     mem_contains(&region, &img) ;
+	     img.start += CONFIG_PHYSICAL_ALIGN) {
+		if (mem_avoid_overlap(&img))
+			continue;
+		slots_append(img.start);
+	}
+}
+
+static unsigned long find_random_addr(unsigned long minimum,
+				      unsigned long size)
+{
+	int i;
+	unsigned long addr;
+
+	/* Make sure minimum is aligned. */
+	minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
+
+	/* Verify potential e820 positions, appending to slots list. */
+	for (i = 0; i < real_mode->e820_entries; i++) {
+		process_e820_entry(&real_mode->e820_map[i], minimum, size);
+	}
+
+	return slots_fetch_random();
+}
+
 unsigned char *choose_kernel_location(unsigned char *input,
 				      unsigned long input_size,
 				      unsigned char *output,
 				      unsigned long output_size)
 {
 	unsigned long choice = (unsigned long)output;
+	unsigned long random;
 
 	if (cmdline_find_option_bool("nokaslr")) {
 		debug_putstr("KASLR disabled...\n");
 		goto out;
 	}
 
-	/* XXX: choose random location. */
+	/* Record the various known unsafe memory ranges. */
+	mem_avoid_init((unsigned long)input, input_size,
+		       (unsigned long)output, output_size);
+
+	/* Walk e820 and find a random address. */
+	random = find_random_addr(choice, output_size);
+	if (!random) {
+		debug_putstr("KASLR could not find suitable E820 region...\n");
+		goto out;
+	}
+
+	/* Always enforce the minimum. */
+	if (random < choice)
+		goto out;
 
+	choice = random;
 out:
 	return (unsigned char *)choice;
 }
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 7138768..196eaf3 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -112,14 +112,8 @@ struct boot_params *real_mode;		/* Pointer to real-mode data */
 void *memset(void *s, int c, size_t n);
 void *memcpy(void *dest, const void *src, size_t n);
 
-#ifdef CONFIG_X86_64
-#define memptr long
-#else
-#define memptr unsigned
-#endif
-
-static memptr free_mem_ptr;
-static memptr free_mem_end_ptr;
+memptr free_mem_ptr;
+memptr free_mem_end_ptr;
 
 static char *vidmem;
 static int vidport;
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 0782eb0..24e3e56 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -23,7 +23,15 @@
 #define BOOT_BOOT_H
 #include "../ctype.h"
 
+#ifdef CONFIG_X86_64
+#define memptr long
+#else
+#define memptr unsigned
+#endif
+
 /* misc.c */
+extern memptr free_mem_ptr;
+extern memptr free_mem_end_ptr;
 extern struct boot_params *real_mode;		/* Pointer to real-mode data */
 void __putstr(const char *s);
 #define error_putstr(__x)  __putstr(__x)
-- 
cgit v0.10.2


From f32360ef6608434a032dc7ad262d45e9693c27f3 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 10 Oct 2013 17:18:17 -0700
Subject: x86, kaslr: Report kernel offset on panic

When the system panics, include the kernel offset in the report to assist
in debugging.

Signed-off-by: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/1381450698-28710-6-git-send-email-keescook@chromium.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index f0de629..1708862 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -824,6 +824,20 @@ static void __init trim_low_memory_range(void)
 }
 	
 /*
+ * Dump out kernel offset information on panic.
+ */
+static int
+dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
+{
+	pr_emerg("Kernel Offset: 0x%lx from 0x%lx "
+		 "(relocation range: 0x%lx-0x%lx)\n",
+		 (unsigned long)&_text - __START_KERNEL, __START_KERNEL,
+		 __START_KERNEL_map, MODULES_VADDR-1);
+
+	return 0;
+}
+
+/*
  * Determine if we were loaded by an EFI loader.  If so, then we have also been
  * passed the efi memmap, systab, etc., so we should use these data structures
  * for initialization.  Note, the efi init code path is determined by the
@@ -1242,3 +1256,15 @@ void __init i386_reserve_resources(void)
 }
 
 #endif /* CONFIG_X86_32 */
+
+static struct notifier_block kernel_offset_notifier = {
+	.notifier_call = dump_kernel_offset
+};
+
+static int __init register_kernel_offset_dumper(void)
+{
+	atomic_notifier_chain_register(&panic_notifier_list,
+					&kernel_offset_notifier);
+	return 0;
+}
+__initcall(register_kernel_offset_dumper);
-- 
cgit v0.10.2


From 6145cfe394a7f138f6b64491c5663f97dba12450 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 10 Oct 2013 17:18:18 -0700
Subject: x86, kaslr: Raise the maximum virtual address to -1 GiB on x86_64

On 64-bit, this raises the maximum location to -1 GiB (from -1.5 GiB),
the upper limit currently, since the kernel fixmap page mappings need
to be moved to use the other 1 GiB (which would be the theoretical
limit when building with -mcmodel=kernel).

Signed-off-by: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/1381450698-28710-7-git-send-email-keescook@chromium.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 992701d..51f4399 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1746,13 +1746,23 @@ config RANDOMIZE_BASE
 config RANDOMIZE_BASE_MAX_OFFSET
 	hex "Maximum ASLR offset allowed"
 	depends on RANDOMIZE_BASE
-	default "0x10000000"
-	range 0x0 0x10000000
+	range 0x0 0x20000000 if X86_32
+	default "0x20000000" if X86_32
+	range 0x0 0x40000000 if X86_64
+	default "0x40000000" if X86_64
 	---help---
 	 Determines the maximal offset in bytes that will be applied to the
 	 kernel when Address Space Layout Randomization (ASLR) is active.
 	 Must be less than or equal to the actual physical memory on the
-	 system. This must be a power of two.
+	 system. This must be a multiple of CONFIG_PHYSICAL_ALIGN.
+
+	 On 32-bit this is limited to 512MiB.
+
+	 On 64-bit this is limited by how the kernel fixmap page table is
+	 positioned, so this cannot be larger that 1GiB currently. Normally
+	 there is a 512MiB to 1.5GiB split between kernel and modules. When
+	 this is raised above the 512MiB default, the modules area will
+	 shrink to compensate, up to the current maximum 1GiB to 1GiB split.
 
 # Relocation on x86 needs some additional build support
 config X86_NEED_RELOCS
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 43dcd80..8de6d9c 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -39,9 +39,18 @@
 #define __VIRTUAL_MASK_SHIFT	47
 
 /*
- * Kernel image size is limited to 512 MB (see level2_kernel_pgt in
- * arch/x86/kernel/head_64.S), and it is mapped here:
+ * Kernel image size is limited to 1GiB due to the fixmap living in the
+ * next 1GiB (see level2_kernel_pgt in arch/x86/kernel/head_64.S). Use
+ * 512MiB by default, leaving 1.5GiB for modules once the page tables
+ * are fully set up. If kernel ASLR is configured, it can extend the
+ * kernel page table mapping, reducing the size of the modules area.
  */
-#define KERNEL_IMAGE_SIZE	(512 * 1024 * 1024)
+#define KERNEL_IMAGE_SIZE_DEFAULT      (512 * 1024 * 1024)
+#if defined(CONFIG_RANDOMIZE_BASE) && \
+	CONFIG_RANDOMIZE_BASE_MAX_OFFSET > KERNEL_IMAGE_SIZE_DEFAULT
+#define KERNEL_IMAGE_SIZE   CONFIG_RANDOMIZE_BASE_MAX_OFFSET
+#else
+#define KERNEL_IMAGE_SIZE      KERNEL_IMAGE_SIZE_DEFAULT
+#endif
 
 #endif /* _ASM_X86_PAGE_64_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 2d88344..c883bf7 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -58,7 +58,7 @@ typedef struct { pteval_t pte; } pte_t;
 #define VMALLOC_START    _AC(0xffffc90000000000, UL)
 #define VMALLOC_END      _AC(0xffffe8ffffffffff, UL)
 #define VMEMMAP_START	 _AC(0xffffea0000000000, UL)
-#define MODULES_VADDR    _AC(0xffffffffa0000000, UL)
+#define MODULES_VADDR    (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
 #define MODULES_END      _AC(0xffffffffff000000, UL)
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)
 
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 4287f1f..5bdc543 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -806,6 +806,9 @@ void __init mem_init(void)
 	BUILD_BUG_ON(VMALLOC_START			>= VMALLOC_END);
 #undef high_memory
 #undef __FIXADDR_TOP
+#ifdef CONFIG_RANDOMIZE_BASE
+	BUILD_BUG_ON(CONFIG_RANDOMIZE_BASE_MAX_OFFSET > KERNEL_IMAGE_SIZE);
+#endif
 
 #ifdef CONFIG_HIGHMEM
 	BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE	> FIXADDR_START);
-- 
cgit v0.10.2


From 6e6a4932b0f569b1a5bb4fcbf5dde1b1a42f01bb Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@linux.intel.com>
Date: Sun, 13 Oct 2013 04:08:56 -0700
Subject: x86, boot: Rename get_flags() and check_flags() to *_cpuflags()

When a function is used in more than one file it may not be possible
to immediately tell from context what the intended meaning is.  As
such, it is more important that the naming be self-evident.  Thus,
change get_flags() to get_cpuflags().

For consistency, change check_flags() to check_cpuflags() even though
it is only used in cpucheck.c.

Link: http://lkml.kernel.org/r/1381450698-28710-2-git-send-email-keescook@chromium.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/boot/compressed/cpuflags.c b/arch/x86/boot/compressed/cpuflags.c
index 931cba6..aa31346 100644
--- a/arch/x86/boot/compressed/cpuflags.c
+++ b/arch/x86/boot/compressed/cpuflags.c
@@ -4,7 +4,7 @@
 
 bool has_cpuflag(int flag)
 {
-	get_flags();
+	get_cpuflags();
 
 	return test_bit(flag, cpu.flags);
 }
diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c
index e1f3c16..100a9a1 100644
--- a/arch/x86/boot/cpucheck.c
+++ b/arch/x86/boot/cpucheck.c
@@ -68,7 +68,7 @@ static int is_transmeta(void)
 }
 
 /* Returns a bitmask of which words we have error bits in */
-static int check_flags(void)
+static int check_cpuflags(void)
 {
 	u32 err;
 	int i;
@@ -101,8 +101,8 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
 	if (has_eflag(X86_EFLAGS_AC))
 		cpu.level = 4;
 
-	get_flags();
-	err = check_flags();
+	get_cpuflags();
+	err = check_cpuflags();
 
 	if (test_bit(X86_FEATURE_LM, cpu.flags))
 		cpu.level = 64;
@@ -121,8 +121,8 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
 		eax &= ~(1 << 15);
 		asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx));
 
-		get_flags();	/* Make sure it really did something */
-		err = check_flags();
+		get_cpuflags();	/* Make sure it really did something */
+		err = check_cpuflags();
 	} else if (err == 0x01 &&
 		   !(err_flags[0] & ~(1 << X86_FEATURE_CX8)) &&
 		   is_centaur() && cpu.model >= 6) {
@@ -137,7 +137,7 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
 		asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx));
 
 		set_bit(X86_FEATURE_CX8, cpu.flags);
-		err = check_flags();
+		err = check_cpuflags();
 	} else if (err == 0x01 && is_transmeta()) {
 		/* Transmeta might have masked feature bits in word 0 */
 
@@ -152,7 +152,7 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
 		    : : "ecx", "ebx");
 		asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx));
 
-		err = check_flags();
+		err = check_cpuflags();
 	}
 
 	if (err_flags_ptr)
diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c
index b02544a..a9fcb7c 100644
--- a/arch/x86/boot/cpuflags.c
+++ b/arch/x86/boot/cpuflags.c
@@ -65,7 +65,7 @@ static inline void cpuid(u32 id, u32 *a, u32 *b, u32 *c, u32 *d)
 	);
 }
 
-void get_flags(void)
+void get_cpuflags(void)
 {
 	u32 max_intel_level, max_amd_level;
 	u32 tfms;
diff --git a/arch/x86/boot/cpuflags.h b/arch/x86/boot/cpuflags.h
index 9bb4e25..ea97697 100644
--- a/arch/x86/boot/cpuflags.h
+++ b/arch/x86/boot/cpuflags.h
@@ -14,6 +14,6 @@ extern struct cpu_features cpu;
 extern u32 cpu_vendor[3];
 
 int has_eflag(unsigned long mask);
-void get_flags(void);
+void get_cpuflags(void);
 
 #endif
-- 
cgit v0.10.2


From aec58bafaf89279522c44ec8ca9211eabb2b6976 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 15 Oct 2013 23:43:14 -0700
Subject: x86/relocs: Add percpu fixup for GNU ld 2.23

The GNU linker tries to put __per_cpu_load into the percpu area,
resulting in a lack of its relocation. Force this symbol to be
relocated. Seen starting with GNU ld 2.23 and later.

Reported-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Cc: Michael Davidson <md@google.com>
Cc: Cong Ding <dinggnu@gmail.com>
Link: http://lkml.kernel.org/r/20131016064314.GA2739@www.outflux.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 71a2533..11f9285 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -729,6 +729,7 @@ static void percpu_init(void)
  *
  * The GNU linker incorrectly associates:
  *	__init_begin
+ *	__per_cpu_load
  *
  * The "gold" linker incorrectly associates:
  *	init_per_cpu__irq_stack_union
@@ -738,6 +739,7 @@ static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)
 {
 	return (sym->st_shndx == per_cpu_shndx) &&
 		strcmp(symname, "__init_begin") &&
+		strcmp(symname, "__per_cpu_load") &&
 		strncmp(symname, "init_per_cpu_", 13);
 }
 
-- 
cgit v0.10.2


From f4fccac05f7f6bacb8e481a84d175e85ffcf9fe2 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Thu, 31 Oct 2013 17:24:59 +0100
Subject: x86/efi: Simplify EFI_DEBUG

... and lose one #ifdef .. #endif sandwich.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 1d3372a..f396163 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -51,7 +51,7 @@
 #include <asm/x86_init.h>
 #include <asm/rtc.h>
 
-#define EFI_DEBUG	1
+#define EFI_DEBUG
 
 #define EFI_MIN_RESERVE 5120
 
@@ -398,9 +398,9 @@ int __init efi_memblock_x86_reserve_range(void)
 	return 0;
 }
 
-#if EFI_DEBUG
 static void __init print_efi_memmap(void)
 {
+#ifdef EFI_DEBUG
 	efi_memory_desc_t *md;
 	void *p;
 	int i;
@@ -415,8 +415,8 @@ static void __init print_efi_memmap(void)
 			md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT),
 			(md->num_pages >> (20 - EFI_PAGE_SHIFT)));
 	}
-}
 #endif  /*  EFI_DEBUG  */
+}
 
 void __init efi_reserve_boot_services(void)
 {
@@ -696,10 +696,7 @@ void __init efi_init(void)
 		x86_platform.set_wallclock = efi_set_rtc_mmss;
 	}
 #endif
-
-#if EFI_DEBUG
 	print_efi_memmap();
-#endif
 }
 
 void __init efi_late_init(void)
-- 
cgit v0.10.2


From 0fd64c23fdf556e9e68580cff03b3505797bbf53 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Thu, 31 Oct 2013 17:25:00 +0100
Subject: x86/mm/pageattr: Lookup address in an arbitrary PGD

This is preparatory work in order to be able to map pages into a
specified PGD and not implicitly and only into init_mm.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index bb32480..c53de62 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -30,6 +30,7 @@
  */
 struct cpa_data {
 	unsigned long	*vaddr;
+	pgd_t		*pgd;
 	pgprot_t	mask_set;
 	pgprot_t	mask_clr;
 	int		numpages;
@@ -322,17 +323,9 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 	return prot;
 }
 
-/*
- * Lookup the page table entry for a virtual address. Return a pointer
- * to the entry and the level of the mapping.
- *
- * Note: We return pud and pmd either when the entry is marked large
- * or when the present bit is not set. Otherwise we would return a
- * pointer to a nonexisting mapping.
- */
-pte_t *lookup_address(unsigned long address, unsigned int *level)
+static pte_t *__lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
+				      unsigned int *level)
 {
-	pgd_t *pgd = pgd_offset_k(address);
 	pud_t *pud;
 	pmd_t *pmd;
 
@@ -361,8 +354,31 @@ pte_t *lookup_address(unsigned long address, unsigned int *level)
 
 	return pte_offset_kernel(pmd, address);
 }
+
+/*
+ * Lookup the page table entry for a virtual address. Return a pointer
+ * to the entry and the level of the mapping.
+ *
+ * Note: We return pud and pmd either when the entry is marked large
+ * or when the present bit is not set. Otherwise we would return a
+ * pointer to a nonexisting mapping.
+ */
+pte_t *lookup_address(unsigned long address, unsigned int *level)
+{
+        return __lookup_address_in_pgd(pgd_offset_k(address), address, level);
+}
 EXPORT_SYMBOL_GPL(lookup_address);
 
+static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address,
+				  unsigned int *level)
+{
+        if (cpa->pgd)
+		return __lookup_address_in_pgd(cpa->pgd + pgd_index(address),
+					       address, level);
+
+        return lookup_address(address, level);
+}
+
 /*
  * This is necessary because __pa() does not work on some
  * kinds of memory, like vmalloc() or the alloc_remap()
-- 
cgit v0.10.2


From f3f729661e8db476ac427a97de015307aebb7404 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Thu, 31 Oct 2013 17:25:01 +0100
Subject: x86/mm/pageattr: Add a PGD pagetable populating function

This allocates, if necessary, and populates the corresponding PGD entry
with a PUD page. The next population level is a dummy macro which will
be removed by the next patch and it is added here to keep the patch
small and easily reviewable but not break bisection, at the same time.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index c53de62..4b47ae0 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -666,6 +666,45 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 	return 0;
 }
 
+#define populate_pud(cpa, addr, pgd, pgprot)	(-1)
+
+/*
+ * Restrictions for kernel page table do not necessarily apply when mapping in
+ * an alternate PGD.
+ */
+static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
+{
+	pgprot_t pgprot = __pgprot(_KERNPG_TABLE);
+	bool allocd_pgd = false;
+	pgd_t *pgd_entry;
+	pud_t *pud = NULL;	/* shut up gcc */
+	int ret;
+
+	pgd_entry = cpa->pgd + pgd_index(addr);
+
+	/*
+	 * Allocate a PUD page and hand it down for mapping.
+	 */
+	if (pgd_none(*pgd_entry)) {
+		pud = (pud_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
+		if (!pud)
+			return -1;
+
+		set_pgd(pgd_entry, __pgd(__pa(pud) | _KERNPG_TABLE));
+		allocd_pgd = true;
+	}
+
+	pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr);
+	pgprot_val(pgprot) |=  pgprot_val(cpa->mask_set);
+
+	ret = populate_pud(cpa, addr, pgd_entry, pgprot);
+	if (ret < 0)
+		return ret;
+
+	cpa->numpages = ret;
+	return 0;
+}
+
 static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr,
 			       int primary)
 {
-- 
cgit v0.10.2


From 4b23538d88c87d9c693ad87c8c808e92a505a6e6 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Thu, 31 Oct 2013 17:25:02 +0100
Subject: x86/mm/pageattr: Add a PUD pagetable populating function

Add the next level of the pagetable populating function, we handle
chunks around a 1G boundary by mapping them with the lower level
functions - otherwise we use 1G pages for the mappings, thus using as
less amount of pagetable pages as possible.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 4b47ae0..81deca7 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -666,7 +666,92 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 	return 0;
 }
 
-#define populate_pud(cpa, addr, pgd, pgprot)	(-1)
+static int alloc_pmd_page(pud_t *pud)
+{
+	pmd_t *pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
+	if (!pmd)
+		return -1;
+
+	set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
+	return 0;
+}
+
+#define populate_pmd(cpa, start, end, pages, pud, pgprot)	(-1)
+
+static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
+			pgprot_t pgprot)
+{
+	pud_t *pud;
+	unsigned long end;
+	int cur_pages = 0;
+
+	end = start + (cpa->numpages << PAGE_SHIFT);
+
+	/*
+	 * Not on a Gb page boundary? => map everything up to it with
+	 * smaller pages.
+	 */
+	if (start & (PUD_SIZE - 1)) {
+		unsigned long pre_end;
+		unsigned long next_page = (start + PUD_SIZE) & PUD_MASK;
+
+		pre_end   = min_t(unsigned long, end, next_page);
+		cur_pages = (pre_end - start) >> PAGE_SHIFT;
+		cur_pages = min_t(int, (int)cpa->numpages, cur_pages);
+
+		pud = pud_offset(pgd, start);
+
+		/*
+		 * Need a PMD page?
+		 */
+		if (pud_none(*pud))
+			if (alloc_pmd_page(pud))
+				return -1;
+
+		cur_pages = populate_pmd(cpa, start, pre_end, cur_pages,
+					 pud, pgprot);
+		if (cur_pages < 0)
+			return cur_pages;
+
+		start = pre_end;
+	}
+
+	/* We mapped them all? */
+	if (cpa->numpages == cur_pages)
+		return cur_pages;
+
+	pud = pud_offset(pgd, start);
+
+	/*
+	 * Map everything starting from the Gb boundary, possibly with 1G pages
+	 */
+	while (end - start >= PUD_SIZE) {
+		set_pud(pud, __pud(cpa->pfn | _PAGE_PSE | massage_pgprot(pgprot)));
+
+		start	  += PUD_SIZE;
+		cpa->pfn  += PUD_SIZE;
+		cur_pages += PUD_SIZE >> PAGE_SHIFT;
+		pud++;
+	}
+
+	/* Map trailing leftover */
+	if (start < end) {
+		int tmp;
+
+		pud = pud_offset(pgd, start);
+		if (pud_none(*pud))
+			if (alloc_pmd_page(pud))
+				return -1;
+
+		tmp = populate_pmd(cpa, start, end, cpa->numpages - cur_pages,
+				   pud, pgprot);
+		if (tmp < 0)
+			return cur_pages;
+
+		cur_pages += tmp;
+	}
+	return cur_pages;
+}
 
 /*
  * Restrictions for kernel page table do not necessarily apply when mapping in
-- 
cgit v0.10.2


From f900a4b8ab0f462d89a9fcb6173cac1403415b16 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Thu, 31 Oct 2013 17:25:03 +0100
Subject: x86/mm/pageattr: Add a PMD pagetable populating function

Handle PMD-level mappings the same as PUD ones.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 81deca7..968398b 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -666,6 +666,16 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 	return 0;
 }
 
+static int alloc_pte_page(pmd_t *pmd)
+{
+	pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
+	if (!pte)
+		return -1;
+
+	set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
+	return 0;
+}
+
 static int alloc_pmd_page(pud_t *pud)
 {
 	pmd_t *pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
@@ -676,7 +686,77 @@ static int alloc_pmd_page(pud_t *pud)
 	return 0;
 }
 
-#define populate_pmd(cpa, start, end, pages, pud, pgprot)	(-1)
+#define populate_pte(cpa, start, end, pages, pmd, pgprot)	do {} while (0)
+
+static int populate_pmd(struct cpa_data *cpa,
+			unsigned long start, unsigned long end,
+			unsigned num_pages, pud_t *pud, pgprot_t pgprot)
+{
+	unsigned int cur_pages = 0;
+	pmd_t *pmd;
+
+	/*
+	 * Not on a 2M boundary?
+	 */
+	if (start & (PMD_SIZE - 1)) {
+		unsigned long pre_end = start + (num_pages << PAGE_SHIFT);
+		unsigned long next_page = (start + PMD_SIZE) & PMD_MASK;
+
+		pre_end   = min_t(unsigned long, pre_end, next_page);
+		cur_pages = (pre_end - start) >> PAGE_SHIFT;
+		cur_pages = min_t(unsigned int, num_pages, cur_pages);
+
+		/*
+		 * Need a PTE page?
+		 */
+		pmd = pmd_offset(pud, start);
+		if (pmd_none(*pmd))
+			if (alloc_pte_page(pmd))
+				return -1;
+
+		populate_pte(cpa, start, pre_end, cur_pages, pmd, pgprot);
+
+		start = pre_end;
+	}
+
+	/*
+	 * We mapped them all?
+	 */
+	if (num_pages == cur_pages)
+		return cur_pages;
+
+	while (end - start >= PMD_SIZE) {
+
+		/*
+		 * We cannot use a 1G page so allocate a PMD page if needed.
+		 */
+		if (pud_none(*pud))
+			if (alloc_pmd_page(pud))
+				return -1;
+
+		pmd = pmd_offset(pud, start);
+
+		set_pmd(pmd, __pmd(cpa->pfn | _PAGE_PSE | massage_pgprot(pgprot)));
+
+		start	  += PMD_SIZE;
+		cpa->pfn  += PMD_SIZE;
+		cur_pages += PMD_SIZE >> PAGE_SHIFT;
+	}
+
+	/*
+	 * Map trailing 4K pages.
+	 */
+	if (start < end) {
+		pmd = pmd_offset(pud, start);
+		if (pmd_none(*pmd))
+			if (alloc_pte_page(pmd))
+				return -1;
+
+		populate_pte(cpa, start, end, num_pages - cur_pages,
+			     pmd, pgprot);
+	}
+	return num_pages;
+}
 
 static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
 			pgprot_t pgprot)
-- 
cgit v0.10.2


From c6b6f363f7b24aa448994e3a65c4d5b3116acfcc Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Thu, 31 Oct 2013 17:25:04 +0100
Subject: x86/mm/pageattr: Add a PTE pagetable populating function

Handle last level by unconditionally writing the PTEs into the PTE page
while paying attention to the NX bit.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 968398b..2a1308a 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -686,7 +686,27 @@ static int alloc_pmd_page(pud_t *pud)
 	return 0;
 }
 
-#define populate_pte(cpa, start, end, pages, pmd, pgprot)	do {} while (0)
+static void populate_pte(struct cpa_data *cpa,
+			 unsigned long start, unsigned long end,
+			 unsigned num_pages, pmd_t *pmd, pgprot_t pgprot)
+{
+	pte_t *pte;
+
+	pte = pte_offset_kernel(pmd, start);
+
+	while (num_pages-- && start < end) {
+
+		/* deal with the NX bit */
+		if (!(pgprot_val(pgprot) & _PAGE_NX))
+			cpa->pfn &= ~_PAGE_NX;
+
+		set_pte(pte, pfn_pte(cpa->pfn >> PAGE_SHIFT, pgprot));
+
+		start	 += PAGE_SIZE;
+		cpa->pfn += PAGE_SIZE;
+		pte++;
+	}
+}
 
 static int populate_pmd(struct cpa_data *cpa,
 			unsigned long start, unsigned long end,
-- 
cgit v0.10.2


From 0bb8aeee7b73b21e09d3ea12f2120d974f70b669 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Thu, 31 Oct 2013 17:25:05 +0100
Subject: x86/mm/pageattr: Add a PUD error unwinding path

In case we encounter an error during the mapping of a region, we want to
unwind what we've established so far exactly the way we did the mapping.
This is the PUD part kept deliberately small for easier review.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 2a1308a..1cbdbbc 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -666,6 +666,51 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 	return 0;
 }
 
+#define unmap_pmd_range(pud, start, pre_end)		do {} while (0)
+
+static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
+{
+	pud_t *pud = pud_offset(pgd, start);
+
+	/*
+	 * Not on a GB page boundary?
+	 */
+	if (start & (PUD_SIZE - 1)) {
+		unsigned long next_page = (start + PUD_SIZE) & PUD_MASK;
+		unsigned long pre_end	= min_t(unsigned long, end, next_page);
+
+		unmap_pmd_range(pud, start, pre_end);
+
+		start = pre_end;
+		pud++;
+	}
+
+	/*
+	 * Try to unmap in 1G chunks?
+	 */
+	while (end - start >= PUD_SIZE) {
+
+		if (pud_large(*pud))
+			pud_clear(pud);
+		else
+			unmap_pmd_range(pud, start, start + PUD_SIZE);
+
+		start += PUD_SIZE;
+		pud++;
+	}
+
+	/*
+	 * 2M leftovers?
+	 */
+	if (start < end)
+		unmap_pmd_range(pud, start, end);
+
+	/*
+	 * No need to try to free the PUD page because we'll free it in
+	 * populate_pgd's error path
+	 */
+}
+
 static int alloc_pte_page(pmd_t *pmd)
 {
 	pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
@@ -883,9 +928,20 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
 	pgprot_val(pgprot) |=  pgprot_val(cpa->mask_set);
 
 	ret = populate_pud(cpa, addr, pgd_entry, pgprot);
-	if (ret < 0)
-		return ret;
+	if (ret < 0) {
+		unmap_pud_range(pgd_entry, addr,
+				addr + (cpa->numpages << PAGE_SHIFT));
 
+		if (allocd_pgd) {
+			/*
+			 * If I allocated this PUD page, I can just as well
+			 * free it in this error path.
+			 */
+			pgd_clear(pgd_entry);
+			free_page((unsigned long)pud);
+		}
+		return ret;
+	}
 	cpa->numpages = ret;
 	return 0;
 }
-- 
cgit v0.10.2


From 52a628fb454d13d944bb3c8a89a314cc3affa417 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Thu, 31 Oct 2013 17:25:06 +0100
Subject: x86/mm/pageattr: Add last levels of error path

We try to free the pagetable pages once we've unmapped our portion.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 1cbdbbc..db8ace2 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -666,7 +666,99 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 	return 0;
 }
 
-#define unmap_pmd_range(pud, start, pre_end)		do {} while (0)
+static bool try_to_free_pte_page(pte_t *pte)
+{
+	int i;
+
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		if (!pte_none(pte[i]))
+			return false;
+
+	free_page((unsigned long)pte);
+	return true;
+}
+
+static bool try_to_free_pmd_page(pmd_t *pmd)
+{
+	int i;
+
+	for (i = 0; i < PTRS_PER_PMD; i++)
+		if (!pmd_none(pmd[i]))
+			return false;
+
+	free_page((unsigned long)pmd);
+	return true;
+}
+
+static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end)
+{
+	pte_t *pte = pte_offset_kernel(pmd, start);
+
+	while (start < end) {
+		set_pte(pte, __pte(0));
+
+		start += PAGE_SIZE;
+		pte++;
+	}
+
+	if (try_to_free_pte_page((pte_t *)pmd_page_vaddr(*pmd))) {
+		pmd_clear(pmd);
+		return true;
+	}
+	return false;
+}
+
+static void __unmap_pmd_range(pud_t *pud, pmd_t *pmd,
+			      unsigned long start, unsigned long end)
+{
+	if (unmap_pte_range(pmd, start, end))
+		if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud)))
+			pud_clear(pud);
+}
+
+static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end)
+{
+	pmd_t *pmd = pmd_offset(pud, start);
+
+	/*
+	 * Not on a 2MB page boundary?
+	 */
+	if (start & (PMD_SIZE - 1)) {
+		unsigned long next_page = (start + PMD_SIZE) & PMD_MASK;
+		unsigned long pre_end = min_t(unsigned long, end, next_page);
+
+		__unmap_pmd_range(pud, pmd, start, pre_end);
+
+		start = pre_end;
+		pmd++;
+	}
+
+	/*
+	 * Try to unmap in 2M chunks.
+	 */
+	while (end - start >= PMD_SIZE) {
+		if (pmd_large(*pmd))
+			pmd_clear(pmd);
+		else
+			__unmap_pmd_range(pud, pmd, start, start + PMD_SIZE);
+
+		start += PMD_SIZE;
+		pmd++;
+	}
+
+	/*
+	 * 4K leftovers?
+	 */
+	if (start < end)
+		return __unmap_pmd_range(pud, pmd, start, end);
+
+	/*
+	 * Try again to free the PMD page if haven't succeeded above.
+	 */
+	if (!pud_none(*pud))
+		if (try_to_free_pmd_page((pmd_t *)pud_page_vaddr(*pud)))
+			pud_clear(pud);
+}
 
 static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
 {
-- 
cgit v0.10.2


From 82f0712ca0f947170e785300b5c39d9c25e2f6ff Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Thu, 31 Oct 2013 17:25:07 +0100
Subject: x86/mm/cpa: Map in an arbitrary pgd

Add the ability to map pages in an arbitrary pgd. This wires in the
remaining stuff so that there's a new interface with which you can map a
region into an arbitrary PGD.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index db8ace2..b3b19f4 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -453,7 +453,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	 * Check for races, another CPU might have split this page
 	 * up already:
 	 */
-	tmp = lookup_address(address, &level);
+	tmp = _lookup_address_cpa(cpa, address, &level);
 	if (tmp != kpte)
 		goto out_unlock;
 
@@ -559,7 +559,8 @@ out_unlock:
 }
 
 static int
-__split_large_page(pte_t *kpte, unsigned long address, struct page *base)
+__split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
+		   struct page *base)
 {
 	pte_t *pbase = (pte_t *)page_address(base);
 	unsigned long pfn, pfninc = 1;
@@ -572,7 +573,7 @@ __split_large_page(pte_t *kpte, unsigned long address, struct page *base)
 	 * Check for races, another CPU might have split this page
 	 * up for us already:
 	 */
-	tmp = lookup_address(address, &level);
+	tmp = _lookup_address_cpa(cpa, address, &level);
 	if (tmp != kpte) {
 		spin_unlock(&pgd_lock);
 		return 1;
@@ -648,7 +649,8 @@ __split_large_page(pte_t *kpte, unsigned long address, struct page *base)
 	return 0;
 }
 
-static int split_large_page(pte_t *kpte, unsigned long address)
+static int split_large_page(struct cpa_data *cpa, pte_t *kpte,
+			    unsigned long address)
 {
 	struct page *base;
 
@@ -660,7 +662,7 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 	if (!base)
 		return -ENOMEM;
 
-	if (__split_large_page(kpte, address, base))
+	if (__split_large_page(cpa, kpte, address, base))
 		__free_page(base);
 
 	return 0;
@@ -1041,6 +1043,9 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
 static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr,
 			       int primary)
 {
+	if (cpa->pgd)
+		return populate_pgd(cpa, vaddr);
+
 	/*
 	 * Ignore all non primary paths.
 	 */
@@ -1085,7 +1090,7 @@ static int __change_page_attr(struct cpa_data *cpa, int primary)
 	else
 		address = *cpa->vaddr;
 repeat:
-	kpte = lookup_address(address, &level);
+	kpte = _lookup_address_cpa(cpa, address, &level);
 	if (!kpte)
 		return __cpa_process_fault(cpa, address, primary);
 
@@ -1149,7 +1154,7 @@ repeat:
 	/*
 	 * We have to split the large page:
 	 */
-	err = split_large_page(kpte, address);
+	err = split_large_page(cpa, kpte, address);
 	if (!err) {
 		/*
 	 	 * Do a global flush tlb after splitting the large page
@@ -1298,6 +1303,8 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 	int ret, cache, checkalias;
 	unsigned long baddr = 0;
 
+	memset(&cpa, 0, sizeof(cpa));
+
 	/*
 	 * Check, if we are requested to change a not supported
 	 * feature:
@@ -1744,6 +1751,7 @@ static int __set_pages_p(struct page *page, int numpages)
 {
 	unsigned long tempaddr = (unsigned long) page_address(page);
 	struct cpa_data cpa = { .vaddr = &tempaddr,
+				.pgd = NULL,
 				.numpages = numpages,
 				.mask_set = __pgprot(_PAGE_PRESENT | _PAGE_RW),
 				.mask_clr = __pgprot(0),
@@ -1762,6 +1770,7 @@ static int __set_pages_np(struct page *page, int numpages)
 {
 	unsigned long tempaddr = (unsigned long) page_address(page);
 	struct cpa_data cpa = { .vaddr = &tempaddr,
+				.pgd = NULL,
 				.numpages = numpages,
 				.mask_set = __pgprot(0),
 				.mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW),
@@ -1822,6 +1831,36 @@ bool kernel_page_present(struct page *page)
 
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 
+int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
+			    unsigned numpages, unsigned long page_flags)
+{
+	int retval = -EINVAL;
+
+	struct cpa_data cpa = {
+		.vaddr = &address,
+		.pfn = pfn,
+		.pgd = pgd,
+		.numpages = numpages,
+		.mask_set = __pgprot(0),
+		.mask_clr = __pgprot(0),
+		.flags = 0,
+	};
+
+	if (!(__supported_pte_mask & _PAGE_NX))
+		goto out;
+
+	if (!(page_flags & _PAGE_NX))
+		cpa.mask_clr = __pgprot(_PAGE_NX);
+
+	cpa.mask_set = __pgprot(_PAGE_PRESENT | page_flags);
+
+	retval = __change_page_attr_set_clr(&cpa, 0);
+	__flush_tlb_all();
+
+out:
+	return retval;
+}
+
 /*
  * The testcases use internal knowledge of the implementation that shouldn't
  * be exposed to the rest of the kernel. Include these directly here.
-- 
cgit v0.10.2


From d2f7cbe7b26a74dbbbf8f325b2a6fd01bc34032c Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Thu, 31 Oct 2013 17:25:08 +0100
Subject: x86/efi: Runtime services virtual mapping

We map the EFI regions needed for runtime services non-contiguously,
with preserved alignment on virtual addresses starting from -4G down
for a total max space of 64G. This way, we provide for stable runtime
services addresses across kernels so that a kexec'd kernel can still use
them.

Thus, they're mapped in a separate pagetable so that we don't pollute
the kernel namespace.

Add an efi= kernel command line parameter for passing miscellaneous
options and chicken bits from the command line.

While at it, add a chicken bit called "efi=old_map" which can be used as
a fallback to the old runtime services mapping method in case there's
some b0rkage with a particular EFI implementation (haha, it is hard to
hold up the sarcasm here...).

Also, add the UEFI RT VA space to Documentation/x86/x86_64/mm.txt.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 7a0f202..ed43e92 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -835,6 +835,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	edd=		[EDD]
 			Format: {"off" | "on" | "skip[mbr]"}
 
+	efi=		[EFI]
+			Format: { "old_map" }
+			old_map [X86-64]: switch to the old ioremap-based EFI
+			runtime services mapping. 32-bit still uses this one by
+			default.
+
 	efi_no_storage_paranoia [EFI; X86]
 			Using this parameter you can use more than 50% of
 			your efi variable storage. Use this parameter only if
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 881582f..c584a51 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -28,4 +28,11 @@ reference.
 Current X86-64 implementations only support 40 bits of address space,
 but we support up to 46 bits. This expands into MBZ space in the page tables.
 
+->trampoline_pgd:
+
+We map EFI runtime services in the aforementioned PGD in the virtual
+range of 64Gb (arbitrarily set, can be raised if needed)
+
+0xffffffef00000000 - 0xffffffff00000000
+
 -Andi Kleen, Jul 2004
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 65c6e6e..89a05b0 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -1,6 +1,24 @@
 #ifndef _ASM_X86_EFI_H
 #define _ASM_X86_EFI_H
 
+/*
+ * We map the EFI regions needed for runtime services non-contiguously,
+ * with preserved alignment on virtual addresses starting from -4G down
+ * for a total max space of 64G. This way, we provide for stable runtime
+ * services addresses across kernels so that a kexec'd kernel can still
+ * use them.
+ *
+ * This is the main reason why we're doing stable VA mappings for RT
+ * services.
+ *
+ * This flag is used in conjuction with a chicken bit called
+ * "efi=old_map" which can be used as a fallback to the old runtime
+ * services mapping method in case there's some b0rkage with a
+ * particular EFI implementation (haha, it is hard to hold up the
+ * sarcasm here...).
+ */
+#define EFI_OLD_MEMMAP		EFI_ARCH_1
+
 #ifdef CONFIG_X86_32
 
 #define EFI_LOADER_SIGNATURE	"EL32"
@@ -69,24 +87,31 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3,
 	efi_call6((f), (u64)(a1), (u64)(a2), (u64)(a3),		\
 		  (u64)(a4), (u64)(a5), (u64)(a6))
 
+#define _efi_call_virtX(x, f, ...)					\
+({									\
+	efi_status_t __s;						\
+									\
+	efi_sync_low_kernel_mappings();					\
+	preempt_disable();						\
+	__s = efi_call##x((void *)efi.systab->runtime->f, __VA_ARGS__);	\
+	preempt_enable();						\
+	__s;								\
+})
+
 #define efi_call_virt0(f)				\
-	efi_call0((efi.systab->runtime->f))
-#define efi_call_virt1(f, a1)					\
-	efi_call1((efi.systab->runtime->f), (u64)(a1))
-#define efi_call_virt2(f, a1, a2)					\
-	efi_call2((efi.systab->runtime->f), (u64)(a1), (u64)(a2))
-#define efi_call_virt3(f, a1, a2, a3)					\
-	efi_call3((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
-		  (u64)(a3))
-#define efi_call_virt4(f, a1, a2, a3, a4)				\
-	efi_call4((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
-		  (u64)(a3), (u64)(a4))
-#define efi_call_virt5(f, a1, a2, a3, a4, a5)				\
-	efi_call5((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
-		  (u64)(a3), (u64)(a4), (u64)(a5))
-#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6)			\
-	efi_call6((efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
-		  (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
+	_efi_call_virtX(0, f)
+#define efi_call_virt1(f, a1)				\
+	_efi_call_virtX(1, f, (u64)(a1))
+#define efi_call_virt2(f, a1, a2)			\
+	_efi_call_virtX(2, f, (u64)(a1), (u64)(a2))
+#define efi_call_virt3(f, a1, a2, a3)			\
+	_efi_call_virtX(3, f, (u64)(a1), (u64)(a2), (u64)(a3))
+#define efi_call_virt4(f, a1, a2, a3, a4)		\
+	_efi_call_virtX(4, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4))
+#define efi_call_virt5(f, a1, a2, a3, a4, a5)		\
+	_efi_call_virtX(5, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4), (u64)(a5))
+#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6)	\
+	_efi_call_virtX(6, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
 
 extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
 				 u32 type, u64 attribute);
@@ -95,12 +120,17 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
 
 extern int add_efi_memmap;
 extern unsigned long x86_efi_facility;
+extern struct efi_scratch efi_scratch;
 extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
 extern int efi_memblock_x86_reserve_range(void);
 extern void efi_call_phys_prelog(void);
 extern void efi_call_phys_epilog(void);
 extern void efi_unmap_memmap(void);
 extern void efi_memory_uc(u64 addr, unsigned long size);
+extern void __init efi_map_region(efi_memory_desc_t *md);
+extern void efi_sync_low_kernel_mappings(void);
+extern void efi_setup_page_tables(void);
+extern void __init old_map_region(efi_memory_desc_t *md);
 
 #ifdef CONFIG_EFI
 
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index f4843e0..028e28b 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -379,7 +379,8 @@ static inline void update_page_count(int level, unsigned long pages) { }
  */
 extern pte_t *lookup_address(unsigned long address, unsigned int *level);
 extern phys_addr_t slow_virt_to_phys(void *__address);
-
+extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
+				   unsigned numpages, unsigned long page_flags);
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* _ASM_X86_PGTABLE_DEFS_H */
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index f396163..b453069 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -12,6 +12,8 @@
  *	Bibo Mao <bibo.mao@intel.com>
  *	Chandramouli Narayanan <mouli@linux.intel.com>
  *	Huang Ying <ying.huang@intel.com>
+ * Copyright (C) 2013 SuSE Labs
+ *	Borislav Petkov <bp@suse.de> - runtime services VA mapping
  *
  * Copied from efi_32.c to eliminate the duplicated code between EFI
  * 32/64 support code. --ying 2007-10-26
@@ -745,21 +747,56 @@ void efi_memory_uc(u64 addr, unsigned long size)
 	set_memory_uc(addr, npages);
 }
 
+void __init old_map_region(efi_memory_desc_t *md)
+{
+	u64 start_pfn, end_pfn, end;
+	unsigned long size;
+	void *va;
+
+	start_pfn = PFN_DOWN(md->phys_addr);
+	size	  = md->num_pages << PAGE_SHIFT;
+	end	  = md->phys_addr + size;
+	end_pfn   = PFN_UP(end);
+
+	if (pfn_range_is_mapped(start_pfn, end_pfn)) {
+		va = __va(md->phys_addr);
+
+		if (!(md->attribute & EFI_MEMORY_WB))
+			efi_memory_uc((u64)(unsigned long)va, size);
+	} else
+		va = efi_ioremap(md->phys_addr, size,
+				 md->type, md->attribute);
+
+	md->virt_addr = (u64) (unsigned long) va;
+	if (!va)
+		pr_err("ioremap of 0x%llX failed!\n",
+		       (unsigned long long)md->phys_addr);
+}
+
 /*
  * This function will switch the EFI runtime services to virtual mode.
- * Essentially, look through the EFI memmap and map every region that
- * has the runtime attribute bit set in its memory descriptor and update
- * that memory descriptor with the virtual address obtained from ioremap().
- * This enables the runtime services to be called without having to
+ * Essentially, we look through the EFI memmap and map every region that
+ * has the runtime attribute bit set in its memory descriptor into the
+ * ->trampoline_pgd page table using a top-down VA allocation scheme.
+ *
+ * The old method which used to update that memory descriptor with the
+ * virtual address obtained from ioremap() is still supported when the
+ * kernel is booted with efi=old_map on its command line. Same old
+ * method enabled the runtime services to be called without having to
  * thunk back into physical mode for every invocation.
+ *
+ * The new method does a pagetable switch in a preemption-safe manner
+ * so that we're in a different address space when calling a runtime
+ * function. For function arguments passing we do copy the PGDs of the
+ * kernel page table into ->trampoline_pgd prior to each call.
  */
 void __init efi_enter_virtual_mode(void)
 {
 	efi_memory_desc_t *md, *prev_md = NULL;
-	efi_status_t status;
+	void *p, *new_memmap = NULL;
 	unsigned long size;
-	u64 end, systab, start_pfn, end_pfn;
-	void *p, *va, *new_memmap = NULL;
+	efi_status_t status;
+	u64 end, systab;
 	int count = 0;
 
 	efi.systab = NULL;
@@ -768,7 +805,6 @@ void __init efi_enter_virtual_mode(void)
 	 * We don't do virtual mode, since we don't do runtime services, on
 	 * non-native EFI
 	 */
-
 	if (!efi_is_native()) {
 		efi_unmap_memmap();
 		return;
@@ -799,6 +835,7 @@ void __init efi_enter_virtual_mode(void)
 			continue;
 		}
 		prev_md = md;
+
 	}
 
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
@@ -808,33 +845,18 @@ void __init efi_enter_virtual_mode(void)
 		    md->type != EFI_BOOT_SERVICES_DATA)
 			continue;
 
+		efi_map_region(md);
+
 		size = md->num_pages << EFI_PAGE_SHIFT;
 		end = md->phys_addr + size;
 
-		start_pfn = PFN_DOWN(md->phys_addr);
-		end_pfn = PFN_UP(end);
-		if (pfn_range_is_mapped(start_pfn, end_pfn)) {
-			va = __va(md->phys_addr);
-
-			if (!(md->attribute & EFI_MEMORY_WB))
-				efi_memory_uc((u64)(unsigned long)va, size);
-		} else
-			va = efi_ioremap(md->phys_addr, size,
-					 md->type, md->attribute);
-
-		md->virt_addr = (u64) (unsigned long) va;
-
-		if (!va) {
-			pr_err("ioremap of 0x%llX failed!\n",
-			       (unsigned long long)md->phys_addr);
-			continue;
-		}
-
 		systab = (u64) (unsigned long) efi_phys.systab;
 		if (md->phys_addr <= systab && systab < end) {
 			systab += md->virt_addr - md->phys_addr;
+
 			efi.systab = (efi_system_table_t *) (unsigned long) systab;
 		}
+
 		new_memmap = krealloc(new_memmap,
 				      (count + 1) * memmap.desc_size,
 				      GFP_KERNEL);
@@ -845,6 +867,9 @@ void __init efi_enter_virtual_mode(void)
 
 	BUG_ON(!efi.systab);
 
+	efi_setup_page_tables();
+	efi_sync_low_kernel_mappings();
+
 	status = phys_efi_set_virtual_address_map(
 		memmap.desc_size * count,
 		memmap.desc_size,
@@ -877,7 +902,8 @@ void __init efi_enter_virtual_mode(void)
 	efi.query_variable_info = virt_efi_query_variable_info;
 	efi.update_capsule = virt_efi_update_capsule;
 	efi.query_capsule_caps = virt_efi_query_capsule_caps;
-	if (__supported_pte_mask & _PAGE_NX)
+
+	if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX))
 		runtime_code_page_mkexec();
 
 	kfree(new_memmap);
@@ -1007,3 +1033,15 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size)
 	return EFI_SUCCESS;
 }
 EXPORT_SYMBOL_GPL(efi_query_variable_store);
+
+static int __init parse_efi_cmdline(char *str)
+{
+	if (*str == '=')
+		str++;
+
+	if (!strncmp(str, "old_map", 7))
+		set_bit(EFI_OLD_MEMMAP, &x86_efi_facility);
+
+	return 0;
+}
+early_param("efi", parse_efi_cmdline);
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index 40e4469..e94557c 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -37,9 +37,16 @@
  * claim EFI runtime service handler exclusively and to duplicate a memory in
  * low memory space say 0 - 3G.
  */
-
 static unsigned long efi_rt_eflags;
 
+void efi_sync_low_kernel_mappings(void) {}
+void efi_setup_page_tables(void) {}
+
+void __init efi_map_region(efi_memory_desc_t *md)
+{
+	old_map_region(md);
+}
+
 void efi_call_phys_prelog(void)
 {
 	struct desc_ptr gdt_descr;
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 39a0e7f..bf286c3 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -38,10 +38,28 @@
 #include <asm/efi.h>
 #include <asm/cacheflush.h>
 #include <asm/fixmap.h>
+#include <asm/realmode.h>
 
 static pgd_t *save_pgd __initdata;
 static unsigned long efi_flags __initdata;
 
+/*
+ * We allocate runtime services regions bottom-up, starting from -4G, i.e.
+ * 0xffff_ffff_0000_0000 and limit EFI VA mapping space to 64G.
+ */
+static u64 efi_va	= -4 * (1UL << 30);
+#define EFI_VA_END	(-68 * (1UL << 30))
+
+/*
+ * Scratch space used for switching the pagetable in the EFI stub
+ */
+struct efi_scratch {
+	u64 r15;
+	u64 prev_cr3;
+	pgd_t *efi_pgt;
+	bool use_pgd;
+};
+
 static void __init early_code_mapping_set_exec(int executable)
 {
 	efi_memory_desc_t *md;
@@ -65,6 +83,9 @@ void __init efi_call_phys_prelog(void)
 	int pgd;
 	int n_pgds;
 
+	if (!efi_enabled(EFI_OLD_MEMMAP))
+		return;
+
 	early_code_mapping_set_exec(1);
 	local_irq_save(efi_flags);
 
@@ -86,6 +107,10 @@ void __init efi_call_phys_epilog(void)
 	 */
 	int pgd;
 	int n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
+
+	if (!efi_enabled(EFI_OLD_MEMMAP))
+		return;
+
 	for (pgd = 0; pgd < n_pgds; pgd++)
 		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), save_pgd[pgd]);
 	kfree(save_pgd);
@@ -94,6 +119,90 @@ void __init efi_call_phys_epilog(void)
 	early_code_mapping_set_exec(0);
 }
 
+/*
+ * Add low kernel mappings for passing arguments to EFI functions.
+ */
+void efi_sync_low_kernel_mappings(void)
+{
+	unsigned num_pgds;
+	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+
+	if (efi_enabled(EFI_OLD_MEMMAP))
+		return;
+
+	num_pgds = pgd_index(MODULES_END - 1) - pgd_index(PAGE_OFFSET);
+
+	memcpy(pgd + pgd_index(PAGE_OFFSET),
+		init_mm.pgd + pgd_index(PAGE_OFFSET),
+		sizeof(pgd_t) * num_pgds);
+}
+
+void efi_setup_page_tables(void)
+{
+	efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd;
+
+	if (!efi_enabled(EFI_OLD_MEMMAP))
+		efi_scratch.use_pgd = true;
+}
+
+static void __init __map_region(efi_memory_desc_t *md, u64 va)
+{
+	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+	unsigned long pf = 0, size;
+	u64 end;
+
+	if (!(md->attribute & EFI_MEMORY_WB))
+		pf |= _PAGE_PCD;
+
+	size = md->num_pages << PAGE_SHIFT;
+	end  = va + size;
+
+	if (kernel_map_pages_in_pgd(pgd, md->phys_addr, va, md->num_pages, pf))
+		pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n",
+			   md->phys_addr, va);
+}
+
+void __init efi_map_region(efi_memory_desc_t *md)
+{
+	unsigned long size = md->num_pages << PAGE_SHIFT;
+	u64 pa = md->phys_addr;
+
+	if (efi_enabled(EFI_OLD_MEMMAP))
+		return old_map_region(md);
+
+	/*
+	 * Make sure the 1:1 mappings are present as a catch-all for b0rked
+	 * firmware which doesn't update all internal pointers after switching
+	 * to virtual mode and would otherwise crap on us.
+	 */
+	__map_region(md, md->phys_addr);
+
+	efi_va -= size;
+
+	/* Is PA 2M-aligned? */
+	if (!(pa & (PMD_SIZE - 1))) {
+		efi_va &= PMD_MASK;
+	} else {
+		u64 pa_offset = pa & (PMD_SIZE - 1);
+		u64 prev_va = efi_va;
+
+		/* get us the same offset within this 2M page */
+		efi_va = (efi_va & PMD_MASK) + pa_offset;
+
+		if (efi_va > prev_va)
+			efi_va -= PMD_SIZE;
+	}
+
+	if (efi_va < EFI_VA_END) {
+		pr_warn(FW_WARN "VA address range overflow!\n");
+		return;
+	}
+
+	/* Do the VA map */
+	__map_region(md, efi_va);
+	md->virt_addr = efi_va;
+}
+
 void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
 				 u32 type, u64 attribute)
 {
diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S
index 4c07cca..88073b1 100644
--- a/arch/x86/platform/efi/efi_stub_64.S
+++ b/arch/x86/platform/efi/efi_stub_64.S
@@ -34,10 +34,47 @@
 	mov %rsi, %cr0;			\
 	mov (%rsp), %rsp
 
+	/* stolen from gcc */
+	.macro FLUSH_TLB_ALL
+	movq %r15, efi_scratch(%rip)
+	movq %r14, efi_scratch+8(%rip)
+	movq %cr4, %r15
+	movq %r15, %r14
+	andb $0x7f, %r14b
+	movq %r14, %cr4
+	movq %r15, %cr4
+	movq efi_scratch+8(%rip), %r14
+	movq efi_scratch(%rip), %r15
+	.endm
+
+	.macro SWITCH_PGT
+	cmpb $0, efi_scratch+24(%rip)
+	je 1f
+	movq %r15, efi_scratch(%rip)		# r15
+	# save previous CR3
+	movq %cr3, %r15
+	movq %r15, efi_scratch+8(%rip)		# prev_cr3
+	movq efi_scratch+16(%rip), %r15		# EFI pgt
+	movq %r15, %cr3
+	1:
+	.endm
+
+	.macro RESTORE_PGT
+	cmpb $0, efi_scratch+24(%rip)
+	je 2f
+	movq efi_scratch+8(%rip), %r15
+	movq %r15, %cr3
+	movq efi_scratch(%rip), %r15
+	FLUSH_TLB_ALL
+	2:
+	.endm
+
 ENTRY(efi_call0)
 	SAVE_XMM
 	subq $32, %rsp
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $32, %rsp
 	RESTORE_XMM
 	ret
@@ -47,7 +84,9 @@ ENTRY(efi_call1)
 	SAVE_XMM
 	subq $32, %rsp
 	mov  %rsi, %rcx
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $32, %rsp
 	RESTORE_XMM
 	ret
@@ -57,7 +96,9 @@ ENTRY(efi_call2)
 	SAVE_XMM
 	subq $32, %rsp
 	mov  %rsi, %rcx
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $32, %rsp
 	RESTORE_XMM
 	ret
@@ -68,7 +109,9 @@ ENTRY(efi_call3)
 	subq $32, %rsp
 	mov  %rcx, %r8
 	mov  %rsi, %rcx
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $32, %rsp
 	RESTORE_XMM
 	ret
@@ -80,7 +123,9 @@ ENTRY(efi_call4)
 	mov %r8, %r9
 	mov %rcx, %r8
 	mov %rsi, %rcx
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $32, %rsp
 	RESTORE_XMM
 	ret
@@ -93,7 +138,9 @@ ENTRY(efi_call5)
 	mov %r8, %r9
 	mov %rcx, %r8
 	mov %rsi, %rcx
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $48, %rsp
 	RESTORE_XMM
 	ret
@@ -109,8 +156,15 @@ ENTRY(efi_call6)
 	mov %r8, %r9
 	mov %rcx, %r8
 	mov %rsi, %rcx
+	SWITCH_PGT
 	call *%rdi
+	RESTORE_PGT
 	addq $48, %rsp
 	RESTORE_XMM
 	ret
 ENDPROC(efi_call6)
+
+	.data
+ENTRY(efi_scratch)
+	.fill 3,8,0
+	.byte 0
diff --git a/include/linux/efi.h b/include/linux/efi.h
index bc5687d..6c0ca52 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -653,6 +653,7 @@ extern int __init efi_setup_pcdp_console(char *);
 #define EFI_RUNTIME_SERVICES	3	/* Can we use runtime services? */
 #define EFI_MEMMAP		4	/* Can we use EFI memory map? */
 #define EFI_64BIT		5	/* Is the firmware 64-bit? */
+#define EFI_ARCH_1		6	/* First arch-specific bit */
 
 #ifdef CONFIG_EFI
 # ifdef CONFIG_X86
-- 
cgit v0.10.2


From ee41143027706d9f342dfe05487a00b20887fde7 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Thu, 31 Oct 2013 17:25:09 +0100
Subject: x86/efi: Check krealloc return value

Check it just in case. We might just as well panic there because runtime
won't be functioning anyway.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index b453069..3fac4de 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -860,6 +860,9 @@ void __init efi_enter_virtual_mode(void)
 		new_memmap = krealloc(new_memmap,
 				      (count + 1) * memmap.desc_size,
 				      GFP_KERNEL);
+		if (!new_memmap)
+			goto err_out;
+
 		memcpy(new_memmap + (count * memmap.desc_size), md,
 		       memmap.desc_size);
 		count++;
@@ -914,6 +917,11 @@ void __init efi_enter_virtual_mode(void)
 			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
 			 EFI_VARIABLE_RUNTIME_ACCESS,
 			 0, NULL);
+
+	return;
+
+ err_out:
+	pr_err("Error reallocating memory, EFI runtime non-functional!\n");
 }
 
 /*
-- 
cgit v0.10.2


From a653f3563c51c7bb7de63d607bef09d3baddaeb8 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Mon, 11 Nov 2013 14:28:39 -0800
Subject: x86, kaslr: Mix entropy sources together as needed

Depending on availability, mix the RDRAND and RDTSC entropy together with
XOR. Only when neither is available should the i8254 be used. Update
the Kconfig documentation to reflect this. Additionally, since bits
used for entropy is masked elsewhere, drop the needless masking in
the get_random_long(). Similarly, use the entire TSC, not just the low
32 bits.

Finally, to improve the starting entropy, do a simple hashing of a
build-time versions string and the boot-time boot_params structure for
some additional level of unpredictability.

Signed-off-by: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/20131111222839.GA28616@www.outflux.net
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 51f4399..596cd9e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1735,13 +1735,17 @@ config RANDOMIZE_BASE
 	   deters exploit attempts relying on knowledge of the location
 	   of kernel internals.
 
-	   Entropy is generated using the RDRAND instruction if it
-	   is supported.  If not, then RDTSC is used, if supported. If
-	   neither RDRAND nor RDTSC are supported, then no randomness
-	   is introduced.
+	   Entropy is generated using the RDRAND instruction if it is
+	   supported. If RDTSC is supported, it is used as well. If
+	   neither RDRAND nor RDTSC are supported, then randomness is
+	   read from the i8254 timer.
 
 	   The kernel will be offset by up to RANDOMIZE_BASE_MAX_OFFSET,
-	   and aligned according to PHYSICAL_ALIGN.
+	   and aligned according to PHYSICAL_ALIGN. Since the kernel is
+	   built using 2GiB addressing, and PHYSICAL_ALGIN must be at a
+	   minimum of 2MiB, only 10 bits of entropy is theoretically
+	   possible. At best, due to page table layouts, 64-bit can use
+	   9 bits of entropy and 32-bit uses 8 bits.
 
 config RANDOMIZE_BASE_MAX_OFFSET
 	hex "Maximum ASLR offset allowed"
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 0595798..8746487 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -5,6 +5,17 @@
 #include <asm/archrandom.h>
 #include <asm/e820.h>
 
+#include <generated/compile.h>
+#include <linux/module.h>
+#include <linux/uts.h>
+#include <linux/utsname.h>
+#include <generated/utsrelease.h>
+#include <linux/version.h>
+
+/* Simplified build-specific string for starting entropy. */
+static const char *build_str = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
+		LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;
+
 #define I8254_PORT_CONTROL	0x43
 #define I8254_PORT_COUNTER0	0x40
 #define I8254_CMD_READBACK	0xC0
@@ -25,34 +36,62 @@ static inline u16 i8254(void)
 	return timer;
 }
 
+static unsigned long rotate_xor(unsigned long hash, const void *area,
+				size_t size)
+{
+	size_t i;
+	unsigned long *ptr = (unsigned long *)area;
+
+	for (i = 0; i < size / sizeof(hash); i++) {
+		/* Rotate by odd number of bits and XOR. */
+		hash = (hash << ((sizeof(hash) * 8) - 7)) | (hash >> 7);
+		hash ^= ptr[i];
+	}
+
+	return hash;
+}
+
+/* Attempt to create a simple but unpredictable starting entropy. */
+static unsigned long get_random_boot(void)
+{
+	unsigned long hash = 0;
+
+	hash = rotate_xor(hash, build_str, sizeof(build_str));
+	hash = rotate_xor(hash, real_mode, sizeof(*real_mode));
+
+	return hash;
+}
+
 static unsigned long get_random_long(void)
 {
-	unsigned long random;
+	unsigned long raw, random = get_random_boot();
+	bool use_i8254 = true;
+
+	debug_putstr("KASLR using");
 
 	if (has_cpuflag(X86_FEATURE_RDRAND)) {
-		debug_putstr("KASLR using RDRAND...\n");
-		if (rdrand_long(&random))
-			return random;
+		debug_putstr(" RDRAND");
+		if (rdrand_long(&raw)) {
+			random ^= raw;
+			use_i8254 = false;
+		}
 	}
 
 	if (has_cpuflag(X86_FEATURE_TSC)) {
-		uint32_t raw;
+		debug_putstr(" RDTSC");
+		rdtscll(raw);
 
-		debug_putstr("KASLR using RDTSC...\n");
-		rdtscl(raw);
+		random ^= raw;
+		use_i8254 = false;
+	}
 
-		/* Only use the low bits of rdtsc. */
-		random = raw & 0xffff;
-	} else {
-		debug_putstr("KASLR using i8254...\n");
-		random = i8254();
+	if (use_i8254) {
+		debug_putstr(" i8254");
+		random ^= i8254();
 	}
 
-	/* Extend timer bits poorly... */
-	random |= (random << 16);
-#ifdef CONFIG_X86_64
-	random |= (random << 32);
-#endif
+	debug_putstr("...\n");
+
 	return random;
 }
 
-- 
cgit v0.10.2


From e8236c4d9338d52d0f2fcecc0b792ac0542e4ee9 Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@zytor.com>
Date: Mon, 11 Nov 2013 22:45:20 -0800
Subject: x86, kaslr: Add a circular multiply for better bit diffusion

If we don't have RDRAND (in which case nothing else *should* matter),
most sources have a highly biased entropy distribution.  Use a
circular multiply to diffuse the entropic bits.  A circular multiply
is a good operation for this: it is cheap on standard hardware and
because it is symmetric (unlike an ordinary multiply) it doesn't
introduce its own bias.

Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Link: http://lkml.kernel.org/r/20131111222839.GA28616@www.outflux.net

diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 8746487..38a07cc 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -64,6 +64,11 @@ static unsigned long get_random_boot(void)
 
 static unsigned long get_random_long(void)
 {
+#ifdef CONFIG_X86_64
+	const unsigned long mix_const = 0x5d6008cbf3848dd3UL;
+#else
+	const unsigned long mix_const = 0x3f39e593UL;
+#endif
 	unsigned long raw, random = get_random_boot();
 	bool use_i8254 = true;
 
@@ -90,6 +95,12 @@ static unsigned long get_random_long(void)
 		random ^= i8254();
 	}
 
+	/* Circular multiply for better bit diffusion */
+	asm("mul %3"
+	    : "=a" (random), "=d" (raw)
+	    : "a" (random), "rm" (mix_const));
+	random += raw;
+
 	debug_putstr("...\n");
 
 	return random;
-- 
cgit v0.10.2


From 327f7d72454aecdc7a4a1c847a291a3f224b730f Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 12 Nov 2013 08:56:07 -0800
Subject: x86, kaslr: Use char array to gain sizeof sanity

The build_str needs to be char [] not char * for the sizeof() to report
the string length.

Reported-by: Mathias Krause <minipli@googlemail.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/20131112165607.GA5921@www.outflux.net
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 38a07cc..84be175 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -13,7 +13,7 @@
 #include <linux/version.h>
 
 /* Simplified build-specific string for starting entropy. */
-static const char *build_str = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
+static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
 		LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;
 
 #define I8254_PORT_CONTROL	0x43
-- 
cgit v0.10.2


From 9dd1220114e00d8ec5cdc20085bbe198b21e1985 Mon Sep 17 00:00:00 2001
From: Josh Boyer <jwboyer@redhat.com>
Date: Mon, 11 Nov 2013 09:08:15 -0500
Subject: smp/cpumask: Make CONFIG_CPUMASK_OFFSTACK=y usable without debug
 dependency

When CONFIG_CPUMASK_OFFSTACK was added in 2008, it was dependent upon
CONFIG_DEBUG_PER_CPU_MAPS being enabled, or an architecture could
select it.

The debug dependency adds additional overhead that isn't required
for operation of the feature and which is undesirable for distro
kernels. CONFIG_CPUMASK_OFFSTACK=y is needed to increase the
CONFIG_NR_CPUS value beyond 512 on x86.

So drop the current dependency, its only real dependency is CONFIG_SMP=y.

Signed-off-by: Josh Boyer <jwboyer@fedoraproject.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20131111140815.GB20328@hansolo.jdub.homelinux.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/lib/Kconfig b/lib/Kconfig
index b3c8be0..50b47cd 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -342,7 +342,8 @@ config CHECK_SIGNATURE
 	bool
 
 config CPUMASK_OFFSTACK
-	bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS
+	bool "Force CPU masks off stack"
+	depends on SMP
 	help
 	  Use dynamic allocation for cpumask_var_t, instead of putting
 	  them on the stack.  This is a bit more expensive, but avoids
-- 
cgit v0.10.2


From f4cb1cc18f364d761d5614eb6293cccc6647f259 Mon Sep 17 00:00:00 2001
From: Fenghua Yu <fenghua.yu@intel.com>
Date: Sat, 16 Nov 2013 12:37:01 -0800
Subject: x86-64, copy_user: Remove zero byte check before copy user buffer.

Operation of rep movsb instruction handles zero byte copy. As pointed out by
Linus, there is no need to check zero size in kernel. Removing this redundant
check saves a few cycles in copy user functions.

Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Link: http://lkml.kernel.org/r/1384634221-6006-1-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index a30ca15..ffe4eb9 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -236,8 +236,6 @@ ENDPROC(copy_user_generic_unrolled)
 ENTRY(copy_user_generic_string)
 	CFI_STARTPROC
 	ASM_STAC
-	andl %edx,%edx
-	jz 4f
 	cmpl $8,%edx
 	jb 2f		/* less than 8 bytes, go to byte copy loop */
 	ALIGN_DESTINATION
@@ -249,7 +247,7 @@ ENTRY(copy_user_generic_string)
 2:	movl %edx,%ecx
 3:	rep
 	movsb
-4:	xorl %eax,%eax
+	xorl %eax,%eax
 	ASM_CLAC
 	ret
 
@@ -279,12 +277,10 @@ ENDPROC(copy_user_generic_string)
 ENTRY(copy_user_enhanced_fast_string)
 	CFI_STARTPROC
 	ASM_STAC
-	andl %edx,%edx
-	jz 2f
 	movl %edx,%ecx
 1:	rep
 	movsb
-2:	xorl %eax,%eax
+	xorl %eax,%eax
 	ASM_CLAC
 	ret
 
-- 
cgit v0.10.2


From 5305ca10e7f44333e46c1ce57fb87306cb437891 Mon Sep 17 00:00:00 2001
From: Cyrill Gorcunov <gorcunov@gmail.com>
Date: Fri, 15 Nov 2013 14:14:00 -0800
Subject: x86/mm: Unify pte_to_pgoff() and pgoff_to_pte() helpers

Use unified pte_bitop() helper to manipulate bits in pte/pgoff
bitfields and convert pte_to_pgoff()/pgoff_to_pte() to inlines.

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
index 3bf2dd0..0d193e2 100644
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -55,6 +55,13 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 #define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp)
 #endif
 
+/* Bit manipulation helper on pte/pgoff entry */
+static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshift,
+				      unsigned long mask, unsigned int leftshift)
+{
+	return ((value >> rightshift) & mask) << leftshift;
+}
+
 #ifdef CONFIG_MEM_SOFT_DIRTY
 
 /*
@@ -71,31 +78,34 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 #define PTE_FILE_BITS2		(PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1)
 #define PTE_FILE_BITS3		(PTE_FILE_SHIFT4 - PTE_FILE_SHIFT3 - 1)
 
-#define pte_to_pgoff(pte)						\
-	((((pte).pte_low >> (PTE_FILE_SHIFT1))				\
-	  & ((1U << PTE_FILE_BITS1) - 1)))				\
-	+ ((((pte).pte_low >> (PTE_FILE_SHIFT2))			\
-	    & ((1U << PTE_FILE_BITS2) - 1))				\
-	   << (PTE_FILE_BITS1))						\
-	+ ((((pte).pte_low >> (PTE_FILE_SHIFT3))			\
-	    & ((1U << PTE_FILE_BITS3) - 1))				\
-	   << (PTE_FILE_BITS1 + PTE_FILE_BITS2))			\
-	+ ((((pte).pte_low >> (PTE_FILE_SHIFT4)))			\
-	    << (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3))
-
-#define pgoff_to_pte(off)						\
-	((pte_t) { .pte_low =						\
-	 ((((off)) & ((1U << PTE_FILE_BITS1) - 1)) << PTE_FILE_SHIFT1)	\
-	 + ((((off) >> PTE_FILE_BITS1)					\
-	     & ((1U << PTE_FILE_BITS2) - 1))				\
-	    << PTE_FILE_SHIFT2)						\
-	 + ((((off) >> (PTE_FILE_BITS1 + PTE_FILE_BITS2))		\
-	     & ((1U << PTE_FILE_BITS3) - 1))				\
-	    << PTE_FILE_SHIFT3)						\
-	 + ((((off) >>							\
-	      (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3)))	\
-	    << PTE_FILE_SHIFT4)						\
-	 + _PAGE_FILE })
+#define PTE_FILE_MASK1		((1U << PTE_FILE_BITS1) - 1)
+#define PTE_FILE_MASK2		((1U << PTE_FILE_BITS2) - 1)
+#define PTE_FILE_MASK3		((1U << PTE_FILE_BITS3) - 1)
+
+#define PTE_FILE_LSHIFT2	(PTE_FILE_BITS1)
+#define PTE_FILE_LSHIFT3	(PTE_FILE_BITS1 + PTE_FILE_BITS2)
+#define PTE_FILE_LSHIFT4	(PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3)
+
+static __always_inline pgoff_t pte_to_pgoff(pte_t pte)
+{
+	return (pgoff_t)
+		(pte_bitop(pte.pte_low, PTE_FILE_SHIFT1, PTE_FILE_MASK1,  0)		    +
+		 pte_bitop(pte.pte_low, PTE_FILE_SHIFT2, PTE_FILE_MASK2,  PTE_FILE_LSHIFT2) +
+		 pte_bitop(pte.pte_low, PTE_FILE_SHIFT3, PTE_FILE_MASK3,  PTE_FILE_LSHIFT3) +
+		 pte_bitop(pte.pte_low, PTE_FILE_SHIFT4,           -1UL,  PTE_FILE_LSHIFT4));
+}
+
+static __always_inline pte_t pgoff_to_pte(pgoff_t off)
+{
+	return (pte_t){
+		.pte_low =
+			pte_bitop(off,                0, PTE_FILE_MASK1,  PTE_FILE_SHIFT1) +
+			pte_bitop(off, PTE_FILE_LSHIFT2, PTE_FILE_MASK2,  PTE_FILE_SHIFT2) +
+			pte_bitop(off, PTE_FILE_LSHIFT3, PTE_FILE_MASK3,  PTE_FILE_SHIFT3) +
+			pte_bitop(off, PTE_FILE_LSHIFT4,           -1UL,  PTE_FILE_SHIFT4) +
+			_PAGE_FILE,
+	};
+}
 
 #else /* CONFIG_MEM_SOFT_DIRTY */
 
@@ -115,22 +125,30 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 #define PTE_FILE_BITS1		(PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1)
 #define PTE_FILE_BITS2		(PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1)
 
-#define pte_to_pgoff(pte)						\
-	((((pte).pte_low >> PTE_FILE_SHIFT1)				\
-	  & ((1U << PTE_FILE_BITS1) - 1))				\
-	 + ((((pte).pte_low >> PTE_FILE_SHIFT2)				\
-	     & ((1U << PTE_FILE_BITS2) - 1)) << PTE_FILE_BITS1)		\
-	 + (((pte).pte_low >> PTE_FILE_SHIFT3)				\
-	    << (PTE_FILE_BITS1 + PTE_FILE_BITS2)))
-
-#define pgoff_to_pte(off)						\
-	((pte_t) { .pte_low =						\
-	 (((off) & ((1U << PTE_FILE_BITS1) - 1)) << PTE_FILE_SHIFT1)	\
-	 + ((((off) >> PTE_FILE_BITS1) & ((1U << PTE_FILE_BITS2) - 1))	\
-	    << PTE_FILE_SHIFT2)						\
-	 + (((off) >> (PTE_FILE_BITS1 + PTE_FILE_BITS2))		\
-	    << PTE_FILE_SHIFT3)						\
-	 + _PAGE_FILE })
+#define PTE_FILE_MASK1		((1U << PTE_FILE_BITS1) - 1)
+#define PTE_FILE_MASK2		((1U << PTE_FILE_BITS2) - 1)
+
+#define PTE_FILE_LSHIFT2	(PTE_FILE_BITS1)
+#define PTE_FILE_LSHIFT3	(PTE_FILE_BITS1 + PTE_FILE_BITS2)
+
+static __always_inline pgoff_t pte_to_pgoff(pte_t pte)
+{
+	return (pgoff_t)
+		(pte_bitop(pte.pte_low, PTE_FILE_SHIFT1, PTE_FILE_MASK1,  0)		    +
+		 pte_bitop(pte.pte_low, PTE_FILE_SHIFT2, PTE_FILE_MASK2,  PTE_FILE_LSHIFT2) +
+		 pte_bitop(pte.pte_low, PTE_FILE_SHIFT3,           -1UL,  PTE_FILE_LSHIFT3));
+}
+
+static __always_inline pte_t pgoff_to_pte(pgoff_t off)
+{
+	return (pte_t){
+		.pte_low =
+			pte_bitop(off,                0, PTE_FILE_MASK1,  PTE_FILE_SHIFT1) +
+			pte_bitop(off, PTE_FILE_LSHIFT2, PTE_FILE_MASK2,  PTE_FILE_SHIFT2) +
+			pte_bitop(off, PTE_FILE_LSHIFT3,           -1UL,  PTE_FILE_SHIFT3) +
+			_PAGE_FILE,
+	};
+}
 
 #endif /* CONFIG_MEM_SOFT_DIRTY */
 
-- 
cgit v0.10.2


From fd8526ad14c182605e42b64646344b95befd9f94 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Tue, 19 Nov 2013 15:17:50 +0200
Subject: x86/mm: Implement ASLR for hugetlb mappings

Matthew noticed that hugetlb mappings don't participate in ASLR on x86-64:

  %  for i in `seq 3`; do
  > tools/testing/selftests/vm/map_hugetlb | grep address
  > done
  Returned address is 0x2aaaaac00000
  Returned address is 0x2aaaaac00000
  Returned address is 0x2aaaaac00000

/proc/PID/maps entries for the mapping are always the same
(except inode number):

  2aaaaac00000-2aaabac00000 rw-p 00000000 00:0c 8200              /anon_hugepage (deleted)
  2aaaaac00000-2aaabac00000 rw-p 00000000 00:0c 256               /anon_hugepage (deleted)
  2aaaaac00000-2aaabac00000 rw-p 00000000 00:0c 7180              /anon_hugepage (deleted)

The reason is the generic hugetlb_get_unmapped_area() function
which is used on x86-64.  It doesn't support randomization and
use bottom-up unmapped area lookup, instead of usual top-down
on x86-64.

x86 has arch-specific hugetlb_get_unmapped_area(), but it's used
only on x86-32.

Let's use arch-specific hugetlb_get_unmapped_area() on x86-64
too. That adds ASLR and switches hugetlb mappings to use top-down
unmapped area lookup:

  %  for i in `seq 3`; do
  > tools/testing/selftests/vm/map_hugetlb | grep address
  > done
  Returned address is 0x7f4f08a00000
  Returned address is 0x7fdda4200000
  Returned address is 0x7febe0000000

/proc/PID/maps entries:

  7f4f08a00000-7f4f18a00000 rw-p 00000000 00:0c 1168              /anon_hugepage (deleted)
  7fdda4200000-7fddb4200000 rw-p 00000000 00:0c 7092              /anon_hugepage (deleted)
  7febe0000000-7febf0000000 rw-p 00000000 00:0c 7183              /anon_hugepage (deleted)

Unmapped area lookup policy for hugetlb mappings is consistent
with normal mappings now -- the only difference is alignment
requirements for huge pages.

libhugetlbfs test-suite didn't detect any regressions with the
patch applied (although it shows few failures on my machine
regardless the patch).

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mel Gorman <mgorman@suse.de>
Link: http://lkml.kernel.org/r/20131119131750.EA45CE0090@blue.fi.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index c878924..775873d 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -71,6 +71,7 @@ extern bool __virt_addr_valid(unsigned long kaddr);
 #include <asm-generic/getorder.h>
 
 #define __HAVE_ARCH_GATE_AREA 1
+#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
 
 #endif	/* __KERNEL__ */
 #endif /* _ASM_X86_PAGE_H */
diff --git a/arch/x86/include/asm/page_32.h b/arch/x86/include/asm/page_32.h
index 4d550d0..904f528 100644
--- a/arch/x86/include/asm/page_32.h
+++ b/arch/x86/include/asm/page_32.h
@@ -5,10 +5,6 @@
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_HUGETLB_PAGE
-#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
-#endif
-
 #define __phys_addr_nodebug(x)	((x) - PAGE_OFFSET)
 #ifdef CONFIG_DEBUG_VIRTUAL
 extern unsigned long __phys_addr(unsigned long);
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 9d980d8..8c9f647 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -87,9 +87,7 @@ int pmd_huge_support(void)
 }
 #endif
 
-/* x86_64 also uses this file */
-
-#ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+#ifdef CONFIG_HUGETLB_PAGE
 static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
 		unsigned long addr, unsigned long len,
 		unsigned long pgoff, unsigned long flags)
@@ -99,7 +97,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
 
 	info.flags = 0;
 	info.length = len;
-	info.low_limit = TASK_UNMAPPED_BASE;
+	info.low_limit = current->mm->mmap_legacy_base;
 	info.high_limit = TASK_SIZE;
 	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
 	info.align_offset = 0;
@@ -172,8 +170,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		return hugetlb_get_unmapped_area_topdown(file, addr, len,
 				pgoff, flags);
 }
-
-#endif /*HAVE_ARCH_HUGETLB_UNMAPPED_AREA*/
+#endif /* CONFIG_HUGETLB_PAGE */
 
 #ifdef CONFIG_X86_64
 static __init int setup_hugepagesz(char *opt)
-- 
cgit v0.10.2


From f1a83e652bedef88d6d77d3dc58250e08e7062bd Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 19 Nov 2013 16:42:47 +0100
Subject: lockdep: Correctly annotate hardirq context in irq_exit()

There was a reported deadlock on -rt which lockdep didn't report.

It turns out that in irq_exit() we tell lockdep that the hardirq
context ends and then do all kinds of locking afterwards.

To fix it, move trace_hardirq_exit() to the very end of irq_exit(), this
ensures all locking in tick_irq_exit() and rcu_irq_exit() are properly
recorded as happening from hardirq context.

This however leads to the 'fun' little problem of running softirqs
while in hardirq context. To cure this make the softirq code a little
more complex (in the CONFIG_TRACE_IRQFLAGS case).

Due to stack swizzling arch dependent trickery we cannot pass an
argument to __do_softirq() to tell it if it was done from hardirq
context or not; so use a side-band argument.

When we do __do_softirq() from hardirq context, 'atomically' flip to
softirq context and back, so that no locking goes without being in
either hard- or soft-irq context.

I didn't find any new problems in mainline using this patch, but it
did show the -rt problem.

Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-dgwc5cdksbn0jk09vbmcc9sa@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/softirq.c b/kernel/softirq.c
index b249883..eb0acf4 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -213,14 +213,52 @@ EXPORT_SYMBOL(local_bh_enable_ip);
 #define MAX_SOFTIRQ_TIME  msecs_to_jiffies(2)
 #define MAX_SOFTIRQ_RESTART 10
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+/*
+ * Convoluted means of passing __do_softirq() a message through the various
+ * architecture execute_on_stack() bits.
+ *
+ * When we run softirqs from irq_exit() and thus on the hardirq stack we need
+ * to keep the lockdep irq context tracking as tight as possible in order to
+ * not miss-qualify lock contexts and miss possible deadlocks.
+ */
+static DEFINE_PER_CPU(int, softirq_from_hardirq);
+
+static inline void lockdep_softirq_from_hardirq(void)
+{
+	this_cpu_write(softirq_from_hardirq, 1);
+}
+
+static inline void lockdep_softirq_start(void)
+{
+	if (this_cpu_read(softirq_from_hardirq))
+		trace_hardirq_exit();
+	lockdep_softirq_enter();
+}
+
+static inline void lockdep_softirq_end(void)
+{
+	lockdep_softirq_exit();
+	if (this_cpu_read(softirq_from_hardirq)) {
+		this_cpu_write(softirq_from_hardirq, 0);
+		trace_hardirq_enter();
+	}
+}
+
+#else
+static inline void lockdep_softirq_from_hardirq(void) { }
+static inline void lockdep_softirq_start(void) { }
+static inline void lockdep_softirq_end(void) { }
+#endif
+
 asmlinkage void __do_softirq(void)
 {
-	struct softirq_action *h;
-	__u32 pending;
 	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
-	int cpu;
 	unsigned long old_flags = current->flags;
 	int max_restart = MAX_SOFTIRQ_RESTART;
+	struct softirq_action *h;
+	__u32 pending;
+	int cpu;
 
 	/*
 	 * Mask out PF_MEMALLOC s current task context is borrowed for the
@@ -233,7 +271,7 @@ asmlinkage void __do_softirq(void)
 	account_irq_enter_time(current);
 
 	__local_bh_disable(_RET_IP_, SOFTIRQ_OFFSET);
-	lockdep_softirq_enter();
+	lockdep_softirq_start();
 
 	cpu = smp_processor_id();
 restart:
@@ -280,16 +318,13 @@ restart:
 		wakeup_softirqd();
 	}
 
-	lockdep_softirq_exit();
-
+	lockdep_softirq_end();
 	account_irq_exit_time(current);
 	__local_bh_enable(SOFTIRQ_OFFSET);
 	WARN_ON_ONCE(in_interrupt());
 	tsk_restore_flags(current, old_flags, PF_MEMALLOC);
 }
 
-
-
 asmlinkage void do_softirq(void)
 {
 	__u32 pending;
@@ -332,6 +367,7 @@ void irq_enter(void)
 static inline void invoke_softirq(void)
 {
 	if (!force_irqthreads) {
+		lockdep_softirq_from_hardirq();
 #ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK
 		/*
 		 * We can safely execute softirq on the current stack if
@@ -377,13 +413,13 @@ void irq_exit(void)
 #endif
 
 	account_irq_exit_time(current);
-	trace_hardirq_exit();
 	preempt_count_sub(HARDIRQ_OFFSET);
 	if (!in_interrupt() && local_softirq_pending())
 		invoke_softirq();
 
 	tick_irq_exit();
 	rcu_irq_exit();
+	trace_hardirq_exit(); /* must be last! */
 }
 
 /*
-- 
cgit v0.10.2


From 3247343118daa73f2b94b7fa565425d1d9f9ac84 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Fri, 8 Nov 2013 18:52:21 +0100
Subject: uprobes: Add uprobe_task->dup_xol_work/dup_xol_addr

uprobe_task->vaddr is a bit strange. The generic code uses it only
to pass the additional argument to arch_uprobe_pre_xol(), and since
it is always equal to instruction_pointer() this looks even more
strange.

And both utask->vaddr and and utask->autask have the same scope,
they only have the meaning when the task executes the probed insn
out-of-line, so it is safe to reuse both in UTASK_RUNNING state.

This all means that logically ->vaddr belongs to arch_uprobe_task
and we should probably move it there, arch_uprobe_pre_xol() can
record instruction_pointer() itself.

OTOH, it is also used by uprobe_copy_process() and dup_xol_work()
for another purpose, this doesn't look clean and doesn't allow to
move this member into arch_uprobe_task.

This patch adds the union with 2 anonymous structs into uprobe_task.

The first struct is autask + vaddr, this way we "almost" move vaddr
into autask.

The second struct has 2 new members for uprobe_copy_process() paths:
->dup_xol_addr which can be used instead ->vaddr, and ->dup_xol_work
which can be used to avoid kmalloc() and simplify the code.

Note that this union will likely have another member(s), we need
something like "private_data_for_handlers" so that the tracing
handlers could use it to communicate with call_fetch() methods.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>

diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 319eae7..2225542 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -26,6 +26,7 @@
 
 #include <linux/errno.h>
 #include <linux/rbtree.h>
+#include <linux/types.h>
 
 struct vm_area_struct;
 struct mm_struct;
@@ -72,14 +73,24 @@ enum uprobe_task_state {
  */
 struct uprobe_task {
 	enum uprobe_task_state		state;
-	struct arch_uprobe_task		autask;
 
-	struct return_instance		*return_instances;
-	unsigned int			depth;
-	struct uprobe			*active_uprobe;
+	union {
+		struct {
+			struct arch_uprobe_task	autask;
+			unsigned long		vaddr;
+		};
+
+		struct {
+			struct callback_head	dup_xol_work;
+			unsigned long		dup_xol_addr;
+		};
+	};
 
+	struct uprobe			*active_uprobe;
 	unsigned long			xol_vaddr;
-	unsigned long			vaddr;
+
+	struct return_instance		*return_instances;
+	unsigned int			depth;
 };
 
 /*
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 24b7d6c..df4ef09 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1403,12 +1403,10 @@ static void uprobe_warn(struct task_struct *t, const char *msg)
 
 static void dup_xol_work(struct callback_head *work)
 {
-	kfree(work);
-
 	if (current->flags & PF_EXITING)
 		return;
 
-	if (!__create_xol_area(current->utask->vaddr))
+	if (!__create_xol_area(current->utask->dup_xol_addr))
 		uprobe_warn(current, "dup xol area");
 }
 
@@ -1419,7 +1417,6 @@ void uprobe_copy_process(struct task_struct *t, unsigned long flags)
 {
 	struct uprobe_task *utask = current->utask;
 	struct mm_struct *mm = current->mm;
-	struct callback_head *work;
 	struct xol_area *area;
 
 	t->utask = NULL;
@@ -1441,14 +1438,9 @@ void uprobe_copy_process(struct task_struct *t, unsigned long flags)
 	if (mm == t->mm)
 		return;
 
-	/* TODO: move it into the union in uprobe_task */
-	work = kmalloc(sizeof(*work), GFP_KERNEL);
-	if (!work)
-		return uprobe_warn(t, "dup xol area");
-
-	t->utask->vaddr = area->vaddr;
-	init_task_work(work, dup_xol_work);
-	task_work_add(t, work, true);
+	t->utask->dup_xol_addr = area->vaddr;
+	init_task_work(&t->utask->dup_xol_work, dup_xol_work);
+	task_work_add(t, &t->utask->dup_xol_work, true);
 }
 
 /*
-- 
cgit v0.10.2


From 803200e24abf0f9ec18631290d26b2185477f3a6 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Sat, 9 Nov 2013 17:58:54 +0100
Subject: uprobes: Don't assume that arch_uprobe->insn/ixol is
 u8[MAX_UINSN_BYTES]

arch_uprobe should be opaque as much as possible to the generic
code, but currently it assumes that insn/ixol must be u8[] of the
known size. Remove this unnecessary dependency, we can use "&" and
and sizeof() with the same effect.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index df4ef09..445962a 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -330,7 +330,7 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned
 int __weak
 set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
 {
-	return uprobe_write_opcode(mm, vaddr, *(uprobe_opcode_t *)auprobe->insn);
+	return uprobe_write_opcode(mm, vaddr, *(uprobe_opcode_t *)&auprobe->insn);
 }
 
 static int match_uprobe(struct uprobe *l, struct uprobe *r)
@@ -529,8 +529,8 @@ static int copy_insn(struct uprobe *uprobe, struct file *filp)
 {
 	struct address_space *mapping = uprobe->inode->i_mapping;
 	loff_t offs = uprobe->offset;
-	void *insn = uprobe->arch.insn;
-	int size = MAX_UINSN_BYTES;
+	void *insn = &uprobe->arch.insn;
+	int size = sizeof(uprobe->arch.insn);
 	int len, err = -EIO;
 
 	/* Copy only available bytes, -EIO if nothing was read */
@@ -569,7 +569,7 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file,
 		goto out;
 
 	ret = -ENOTSUPP;
-	if (is_trap_insn((uprobe_opcode_t *)uprobe->arch.insn))
+	if (is_trap_insn((uprobe_opcode_t *)&uprobe->arch.insn))
 		goto out;
 
 	ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr);
@@ -1264,7 +1264,7 @@ static unsigned long xol_get_insn_slot(struct uprobe *uprobe)
 
 	/* Initialize the slot */
 	copy_to_page(area->page, xol_vaddr,
-			uprobe->arch.ixol, sizeof(uprobe->arch.ixol));
+			&uprobe->arch.ixol, sizeof(uprobe->arch.ixol));
 	/*
 	 * We probably need flush_icache_user_range() but it needs vma.
 	 * This should work on supported architectures too.
-- 
cgit v0.10.2


From 3d78e945b6249d4ef2308192343f8b203b1d7ea5 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Sat, 9 Nov 2013 18:44:19 +0100
Subject: uprobes/powerpc: Kill arch_uprobe->ainsn

powerpc has both arch_uprobe->insn and arch_uprobe->ainsn to
make the generic code happy. This is no longer needed after
the previous change, powerpc can just use "u32 insn".

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Acked-by: Ananth N Mavinakayanahalli <ananth@in.ibm.com>

diff --git a/arch/powerpc/include/asm/uprobes.h b/arch/powerpc/include/asm/uprobes.h
index 75c6ecd..7422a99 100644
--- a/arch/powerpc/include/asm/uprobes.h
+++ b/arch/powerpc/include/asm/uprobes.h
@@ -36,9 +36,8 @@ typedef ppc_opcode_t uprobe_opcode_t;
 
 struct arch_uprobe {
 	union {
-		u8	insn[MAX_UINSN_BYTES];
-		u8	ixol[MAX_UINSN_BYTES];
-		u32	ainsn;
+		u32	insn;
+		u32	ixol;
 	};
 };
 
diff --git a/arch/powerpc/kernel/uprobes.c b/arch/powerpc/kernel/uprobes.c
index 59f419b..003b209 100644
--- a/arch/powerpc/kernel/uprobes.c
+++ b/arch/powerpc/kernel/uprobes.c
@@ -186,7 +186,7 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	 * emulate_step() returns 1 if the insn was successfully emulated.
 	 * For all other cases, we need to single-step in hardware.
 	 */
-	ret = emulate_step(regs, auprobe->ainsn);
+	ret = emulate_step(regs, auprobe->insn);
 	if (ret > 0)
 		return true;
 
-- 
cgit v0.10.2


From c912dae60ae6f659455f239298110adc67a5f3e9 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Sat, 9 Nov 2013 19:49:39 +0100
Subject: uprobes: Cleanup !CONFIG_UPROBES decls, unexport xol_area

1. Don't include asm/uprobes.h unconditionally, we only need
   it if CONFIG_UPROBES.

2. Move the definition of "struct xol_area" into uprobes.c.

   Perhaps we should simply kill struct uprobes_state, it buys
   nothing.

3. Kill the dummy definition of uprobe_get_swbp_addr(), nobody
   except handle_swbp() needs it.

4. Purely cosmetic, but move the decl of uprobe_get_swbp_addr()
   up, close to other __weak helpers.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>

diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 2225542..e32251e 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -33,10 +33,6 @@ struct mm_struct;
 struct inode;
 struct notifier_block;
 
-#ifdef CONFIG_ARCH_SUPPORTS_UPROBES
-# include <asm/uprobes.h>
-#endif
-
 #define UPROBE_HANDLER_REMOVE		1
 #define UPROBE_HANDLER_MASK		1
 
@@ -61,6 +57,8 @@ struct uprobe_consumer {
 };
 
 #ifdef CONFIG_UPROBES
+#include <asm/uprobes.h>
+
 enum uprobe_task_state {
 	UTASK_RUNNING,
 	UTASK_SSTEP,
@@ -93,24 +91,7 @@ struct uprobe_task {
 	unsigned int			depth;
 };
 
-/*
- * On a breakpoint hit, thread contests for a slot.  It frees the
- * slot after singlestep. Currently a fixed number of slots are
- * allocated.
- */
-struct xol_area {
-	wait_queue_head_t 	wq;		/* if all slots are busy */
-	atomic_t 		slot_count;	/* number of in-use slots */
-	unsigned long 		*bitmap;	/* 0 = free slot */
-	struct page 		*page;
-
-	/*
-	 * We keep the vma's vm_start rather than a pointer to the vma
-	 * itself.  The probed process or a naughty kernel module could make
-	 * the vma go away, and we must handle that reasonably gracefully.
-	 */
-	unsigned long 		vaddr;		/* Page(s) of instruction slots */
-};
+struct xol_area;
 
 struct uprobes_state {
 	struct xol_area		*xol_area;
@@ -120,6 +101,7 @@ extern int __weak set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsign
 extern int __weak set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
 extern bool __weak is_swbp_insn(uprobe_opcode_t *insn);
 extern bool __weak is_trap_insn(uprobe_opcode_t *insn);
+extern unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs);
 extern int uprobe_write_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t);
 extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
 extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool);
@@ -131,7 +113,6 @@ extern void uprobe_end_dup_mmap(void);
 extern void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm);
 extern void uprobe_free_utask(struct task_struct *t);
 extern void uprobe_copy_process(struct task_struct *t, unsigned long flags);
-extern unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs);
 extern int uprobe_post_sstep_notifier(struct pt_regs *regs);
 extern int uprobe_pre_sstep_notifier(struct pt_regs *regs);
 extern void uprobe_notify_resume(struct pt_regs *regs);
@@ -187,10 +168,6 @@ static inline bool uprobe_deny_signal(void)
 {
 	return false;
 }
-static inline unsigned long uprobe_get_swbp_addr(struct pt_regs *regs)
-{
-	return 0;
-}
 static inline void uprobe_free_utask(struct task_struct *t)
 {
 }
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 445962a..51a7f53 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -86,6 +86,25 @@ struct return_instance {
 };
 
 /*
+ * On a breakpoint hit, thread contests for a slot.  It frees the
+ * slot after singlestep. Currently a fixed number of slots are
+ * allocated.
+ */
+struct xol_area {
+	wait_queue_head_t 	wq;		/* if all slots are busy */
+	atomic_t 		slot_count;	/* number of in-use slots */
+	unsigned long 		*bitmap;	/* 0 = free slot */
+	struct page 		*page;
+
+	/*
+	 * We keep the vma's vm_start rather than a pointer to the vma
+	 * itself.  The probed process or a naughty kernel module could make
+	 * the vma go away, and we must handle that reasonably gracefully.
+	 */
+	unsigned long 		vaddr;		/* Page(s) of instruction slots */
+};
+
+/*
  * valid_vma: Verify if the specified vma is an executable vma
  * Relax restrictions while unregistering: vm_flags might have
  * changed after breakpoint was inserted.
-- 
cgit v0.10.2


From ad439356ae5ae7688b39f1107fd5b874850fec18 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Tue, 19 Nov 2013 17:20:21 +0100
Subject: uprobes: Document xol_area and arch_uprobe->insn/ixol

Document xol_area and arch_uprobe.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 51a7f53..b886a5e 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -73,6 +73,17 @@ struct uprobe {
 	struct inode		*inode;		/* Also hold a ref to inode */
 	loff_t			offset;
 	unsigned long		flags;
+
+	/*
+	 * The generic code assumes that it has two members of unknown type
+	 * owned by the arch-specific code:
+	 *
+	 * 	insn -	copy_insn() saves the original instruction here for
+	 *		arch_uprobe_analyze_insn().
+	 *
+	 *	ixol -	potentially modified instruction to execute out of
+	 *		line, copied to xol_area by xol_get_insn_slot().
+	 */
 	struct arch_uprobe	arch;
 };
 
@@ -86,6 +97,10 @@ struct return_instance {
 };
 
 /*
+ * Execute out of line area: anonymous executable mapping installed
+ * by the probed task to execute the copy of the original instruction
+ * mangled by set_swbp().
+ *
  * On a breakpoint hit, thread contests for a slot.  It frees the
  * slot after singlestep. Currently a fixed number of slots are
  * allocated.
-- 
cgit v0.10.2


From 661c80192d21269c7fc566f1d547510b0c867677 Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@linux.intel.com>
Date: Wed, 20 Nov 2013 12:50:51 -0800
Subject: x86-64, copy_user: Use leal to produce 32-bit results

When we are using lea to produce a 32-bit result, we can use the leal
form, rather than using leaq and worry about truncation elsewhere.

Make the leal explicit, both to be more obvious and since that is what
gcc generates and thus is less likely to trigger obscure gas bugs.

Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1384634221-6006-1-git-send-email-fenghua.yu@intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index ffe4eb9..dee945d 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -186,7 +186,7 @@ ENTRY(copy_user_generic_unrolled)
 30:	shll $6,%ecx
 	addl %ecx,%edx
 	jmp 60f
-40:	lea (%rdx,%rcx,8),%rdx
+40:	leal (%rdx,%rcx,8),%edx
 	jmp 60f
 50:	movl %ecx,%edx
 60:	jmp copy_user_handle_tail /* ecx is zerorest also */
@@ -252,7 +252,7 @@ ENTRY(copy_user_generic_string)
 	ret
 
 	.section .fixup,"ax"
-11:	lea (%rdx,%rcx,8),%rcx
+11:	leal (%rdx,%rcx,8),%ecx
 12:	movl %ecx,%edx		/* ecx is zerorest also */
 	jmp copy_user_handle_tail
 	.previous
-- 
cgit v0.10.2


From e0edc78f25c020dea66742c05a7fbcb2ff3df629 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Fri, 22 Nov 2013 11:24:53 +0100
Subject: Documentation/memory-barriers.txt: Fix a typo in the data dependency
 description

This typo has been there forever, it is 7.5 years old, looks like this
section of our memory ordering documentation is a place where most eyes
are glazed over already ;-)

[ Also fix some stray spaces and stray tabs while at it, shrinking the
  file by 49 bytes. Visual output unchanged. ]

Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/n/tip-gncea9cb8igosblizfqMXrie@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index c8c42e6..020cccd 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -500,7 +500,7 @@ odd-numbered bank is idle, one can see the new value of the pointer P (&B),
 but the old value of the variable B (2).
 
 
-Another example of where data dependency barriers might by required is where a
+Another example of where data dependency barriers might be required is where a
 number is read from memory and then used to calculate the index for an array
 access:
 
@@ -882,12 +882,12 @@ cache it for later use.
 
 Consider:
 
-	CPU 1	   		CPU 2
+	CPU 1			CPU 2
 	=======================	=======================
-	 	   		LOAD B
-	 	   		DIVIDE		} Divide instructions generally
-	 	   		DIVIDE		} take a long time to perform
-	 	   		LOAD A
+				LOAD B
+				DIVIDE		} Divide instructions generally
+				DIVIDE		} take a long time to perform
+				LOAD A
 
 Which might appear as this:
 
@@ -910,13 +910,13 @@ Which might appear as this:
 Placing a read barrier or a data dependency barrier just before the second
 load:
 
-	CPU 1	   		CPU 2
+	CPU 1			CPU 2
 	=======================	=======================
-	 	   		LOAD B
-	 	   		DIVIDE
-	 	   		DIVIDE
+				LOAD B
+				DIVIDE
+				DIVIDE
 				<read barrier>
-	 	   		LOAD A
+				LOAD A
 
 will force any value speculatively obtained to be reconsidered to an extent
 dependent on the type of barrier used.  If there was no change made to the
@@ -1887,8 +1887,8 @@ functions:
      space should suffice for PCI.
 
      [*] NOTE! attempting to load from the same location as was written to may
-     	 cause a malfunction - consider the 16550 Rx/Tx serial registers for
-     	 example.
+	 cause a malfunction - consider the 16550 Rx/Tx serial registers for
+	 example.
 
      Used with prefetchable I/O memory, an mmiowb() barrier may be required to
      force stores to be ordered.
@@ -1955,19 +1955,19 @@ barriers for the most part act at the interface between the CPU and its cache
 	                          :
 	+--------+    +--------+  :   +--------+    +-----------+
 	|        |    |        |  :   |        |    |           |    +--------+
-	|  CPU   |    | Memory |  :   | CPU    |    |           |    |	      |
-	|  Core  |--->| Access |----->| Cache  |<-->|           |    |	      |
+	|  CPU   |    | Memory |  :   | CPU    |    |           |    |        |
+	|  Core  |--->| Access |----->| Cache  |<-->|           |    |        |
 	|        |    | Queue  |  :   |        |    |           |--->| Memory |
-	|        |    |        |  :   |        |    |           |    |	      |
-	+--------+    +--------+  :   +--------+    |           |    | 	      |
+	|        |    |        |  :   |        |    |           |    |        |
+	+--------+    +--------+  :   +--------+    |           |    |        |
 	                          :                 | Cache     |    +--------+
 	                          :                 | Coherency |
 	                          :                 | Mechanism |    +--------+
 	+--------+    +--------+  :   +--------+    |           |    |	      |
 	|        |    |        |  :   |        |    |           |    |        |
 	|  CPU   |    | Memory |  :   | CPU    |    |           |--->| Device |
-	|  Core  |--->| Access |----->| Cache  |<-->|           |    | 	      |
-	|        |    | Queue  |  :   |        |    |           |    | 	      |
+	|  Core  |--->| Access |----->| Cache  |<-->|           |    |        |
+	|        |    | Queue  |  :   |        |    |           |    |        |
 	|        |    |        |  :   |        |    |           |    +--------+
 	+--------+    +--------+  :   +--------+    +-----------+
 	                          :
@@ -2090,7 +2090,7 @@ CPU's caches by some other cache event:
 	p = &v;		q = p;
 			<D:request p>
 	<B:modify p=&v>	<D:commit p=&v>
-		  	<D:read p>
+			<D:read p>
 			x = *q;
 			<C:read *q>	Reads from v before v updated in cache
 			<C:unbusy>
@@ -2115,7 +2115,7 @@ queue before processing any further requests:
 	p = &v;		q = p;
 			<D:request p>
 	<B:modify p=&v>	<D:commit p=&v>
-		  	<D:read p>
+			<D:read p>
 			smp_read_barrier_depends()
 			<C:unbusy>
 			<C:commit v=2>
-- 
cgit v0.10.2


From c92132f5980666c7a52ecb53d98226c9986d32cd Mon Sep 17 00:00:00 2001
From: Chunhe Lan <Chunhe.Lan@freescale.com>
Date: Mon, 25 Nov 2013 11:28:41 +0100
Subject: edac/85xx: Add PCIe error interrupt edac support

Add pcie error interrupt edac support for mpc85xx, p3041, p4080, and
p5020. The mpc85xx uses the legacy interrupt report mechanism - the
error interrupts are reported directly to mpic. While the p3041/
p4080/p5020 attaches the most of error interrupts to interrupt zero. And
report error interrupts to mpic via interrupt 0.

This patch can handle both of them.

Signed-off-by: Chunhe Lan <Chunhe.Lan@freescale.com>
Link: http://lkml.kernel.org/r/1384712714-8826-3-git-send-email-morbidrsa@gmail.com
Cc: Doug Thompson <dougthompson@xmission.com>
Cc: Dave Jiang <dave.jiang@gmail.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@men.de>
Signed-off-by: Borislav Petkov <bp@suse.de>

diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c
index fd46b0b..8f91821 100644
--- a/drivers/edac/mpc85xx_edac.c
+++ b/drivers/edac/mpc85xx_edac.c
@@ -1,6 +1,8 @@
 /*
  * Freescale MPC85xx Memory Controller kenel module
  *
+ * Parts Copyrighted (c) 2013 by Freescale Semiconductor, Inc.
+ *
  * Author: Dave Jiang <djiang@mvista.com>
  *
  * 2006-2007 (c) MontaVista Software, Inc. This file is licensed under
@@ -196,6 +198,42 @@ static void mpc85xx_pci_check(struct edac_pci_ctl_info *pci)
 		edac_pci_handle_npe(pci, pci->ctl_name);
 }
 
+static void mpc85xx_pcie_check(struct edac_pci_ctl_info *pci)
+{
+	struct mpc85xx_pci_pdata *pdata = pci->pvt_info;
+	u32 err_detect;
+
+	err_detect = in_be32(pdata->pci_vbase + MPC85XX_PCI_ERR_DR);
+
+	pr_err("PCIe error(s) detected\n");
+	pr_err("PCIe ERR_DR register: 0x%08x\n", err_detect);
+	pr_err("PCIe ERR_CAP_STAT register: 0x%08x\n",
+			in_be32(pdata->pci_vbase + MPC85XX_PCI_GAS_TIMR));
+	pr_err("PCIe ERR_CAP_R0 register: 0x%08x\n",
+			in_be32(pdata->pci_vbase + MPC85XX_PCIE_ERR_CAP_R0));
+	pr_err("PCIe ERR_CAP_R1 register: 0x%08x\n",
+			in_be32(pdata->pci_vbase + MPC85XX_PCIE_ERR_CAP_R1));
+	pr_err("PCIe ERR_CAP_R2 register: 0x%08x\n",
+			in_be32(pdata->pci_vbase + MPC85XX_PCIE_ERR_CAP_R2));
+	pr_err("PCIe ERR_CAP_R3 register: 0x%08x\n",
+			in_be32(pdata->pci_vbase + MPC85XX_PCIE_ERR_CAP_R3));
+
+	/* clear error bits */
+	out_be32(pdata->pci_vbase + MPC85XX_PCI_ERR_DR, err_detect);
+}
+
+static int mpc85xx_pcie_find_capability(struct device_node *np)
+{
+	struct pci_controller *hose;
+
+	if (!np)
+		return -EINVAL;
+
+	hose = pci_find_hose_for_OF_device(np);
+
+	return early_find_capability(hose, 0, 0, PCI_CAP_ID_EXP);
+}
+
 static irqreturn_t mpc85xx_pci_isr(int irq, void *dev_id)
 {
 	struct edac_pci_ctl_info *pci = dev_id;
@@ -207,7 +245,10 @@ static irqreturn_t mpc85xx_pci_isr(int irq, void *dev_id)
 	if (!err_detect)
 		return IRQ_NONE;
 
-	mpc85xx_pci_check(pci);
+	if (pdata->is_pcie)
+		mpc85xx_pcie_check(pci);
+	else
+		mpc85xx_pci_check(pci);
 
 	return IRQ_HANDLED;
 }
@@ -239,14 +280,22 @@ int mpc85xx_pci_err_probe(struct platform_device *op)
 	pdata = pci->pvt_info;
 	pdata->name = "mpc85xx_pci_err";
 	pdata->irq = NO_IRQ;
+
+	if (mpc85xx_pcie_find_capability(op->dev.of_node) > 0)
+		pdata->is_pcie = true;
+
 	dev_set_drvdata(&op->dev, pci);
 	pci->dev = &op->dev;
 	pci->mod_name = EDAC_MOD_STR;
 	pci->ctl_name = pdata->name;
 	pci->dev_name = dev_name(&op->dev);
 
-	if (edac_op_state == EDAC_OPSTATE_POLL)
-		pci->edac_check = mpc85xx_pci_check;
+	if (edac_op_state == EDAC_OPSTATE_POLL) {
+		if (pdata->is_pcie)
+			pci->edac_check = mpc85xx_pcie_check;
+		else
+			pci->edac_check = mpc85xx_pci_check;
+	}
 
 	pdata->edac_idx = edac_pci_idx++;
 
@@ -275,16 +324,26 @@ int mpc85xx_pci_err_probe(struct platform_device *op)
 		goto err;
 	}
 
-	orig_pci_err_cap_dr =
-	    in_be32(pdata->pci_vbase + MPC85XX_PCI_ERR_CAP_DR);
+	if (pdata->is_pcie) {
+		orig_pci_err_cap_dr =
+		    in_be32(pdata->pci_vbase + MPC85XX_PCI_ERR_ADDR);
+		out_be32(pdata->pci_vbase + MPC85XX_PCI_ERR_ADDR, ~0);
+		orig_pci_err_en =
+		    in_be32(pdata->pci_vbase + MPC85XX_PCI_ERR_EN);
+		out_be32(pdata->pci_vbase + MPC85XX_PCI_ERR_EN, 0);
+	} else {
+		orig_pci_err_cap_dr =
+		    in_be32(pdata->pci_vbase + MPC85XX_PCI_ERR_CAP_DR);
 
-	/* PCI master abort is expected during config cycles */
-	out_be32(pdata->pci_vbase + MPC85XX_PCI_ERR_CAP_DR, 0x40);
+		/* PCI master abort is expected during config cycles */
+		out_be32(pdata->pci_vbase + MPC85XX_PCI_ERR_CAP_DR, 0x40);
 
-	orig_pci_err_en = in_be32(pdata->pci_vbase + MPC85XX_PCI_ERR_EN);
+		orig_pci_err_en =
+		    in_be32(pdata->pci_vbase + MPC85XX_PCI_ERR_EN);
 
-	/* disable master abort reporting */
-	out_be32(pdata->pci_vbase + MPC85XX_PCI_ERR_EN, ~0x40);
+		/* disable master abort reporting */
+		out_be32(pdata->pci_vbase + MPC85XX_PCI_ERR_EN, ~0x40);
+	}
 
 	/* clear error bits */
 	out_be32(pdata->pci_vbase + MPC85XX_PCI_ERR_DR, ~0);
@@ -297,7 +356,8 @@ int mpc85xx_pci_err_probe(struct platform_device *op)
 	if (edac_op_state == EDAC_OPSTATE_INT) {
 		pdata->irq = irq_of_parse_and_map(op->dev.of_node, 0);
 		res = devm_request_irq(&op->dev, pdata->irq,
-				       mpc85xx_pci_isr, IRQF_DISABLED,
+				       mpc85xx_pci_isr,
+				       IRQF_DISABLED | IRQF_SHARED,
 				       "[EDAC] PCI err", pci);
 		if (res < 0) {
 			printk(KERN_ERR
@@ -312,6 +372,22 @@ int mpc85xx_pci_err_probe(struct platform_device *op)
 		       pdata->irq);
 	}
 
+	if (pdata->is_pcie) {
+		/*
+		 * Enable all PCIe error interrupt & error detect except invalid
+		 * PEX_CONFIG_ADDR/PEX_CONFIG_DATA access interrupt generation
+		 * enable bit and invalid PEX_CONFIG_ADDR/PEX_CONFIG_DATA access
+		 * detection enable bit. Because PCIe bus code to initialize and
+		 * configure these PCIe devices on booting will use some invalid
+		 * PEX_CONFIG_ADDR/PEX_CONFIG_DATA, edac driver prints the much
+		 * notice information. So disable this detect to fix ugly print.
+		 */
+		out_be32(pdata->pci_vbase + MPC85XX_PCI_ERR_EN, ~0
+			 & ~PEX_ERR_ICCAIE_EN_BIT);
+		out_be32(pdata->pci_vbase + MPC85XX_PCI_ERR_ADDR, 0
+			 | PEX_ERR_ICCAD_DISR_BIT);
+	}
+
 	devres_remove_group(&op->dev, mpc85xx_pci_err_probe);
 	edac_dbg(3, "success\n");
 	printk(KERN_INFO EDAC_MOD_STR " PCI err registered\n");
diff --git a/drivers/edac/mpc85xx_edac.h b/drivers/edac/mpc85xx_edac.h
index 932016f..8c62564 100644
--- a/drivers/edac/mpc85xx_edac.h
+++ b/drivers/edac/mpc85xx_edac.h
@@ -134,13 +134,19 @@
 #define MPC85XX_PCI_ERR_DR		0x0000
 #define MPC85XX_PCI_ERR_CAP_DR		0x0004
 #define MPC85XX_PCI_ERR_EN		0x0008
+#define   PEX_ERR_ICCAIE_EN_BIT		0x00020000
 #define MPC85XX_PCI_ERR_ATTRIB		0x000c
 #define MPC85XX_PCI_ERR_ADDR		0x0010
+#define   PEX_ERR_ICCAD_DISR_BIT	0x00020000
 #define MPC85XX_PCI_ERR_EXT_ADDR	0x0014
 #define MPC85XX_PCI_ERR_DL		0x0018
 #define MPC85XX_PCI_ERR_DH		0x001c
 #define MPC85XX_PCI_GAS_TIMR		0x0020
 #define MPC85XX_PCI_PCIX_TIMR		0x0024
+#define MPC85XX_PCIE_ERR_CAP_R0		0x0028
+#define MPC85XX_PCIE_ERR_CAP_R1		0x002c
+#define MPC85XX_PCIE_ERR_CAP_R2		0x0030
+#define MPC85XX_PCIE_ERR_CAP_R3		0x0034
 
 struct mpc85xx_mc_pdata {
 	char *name;
@@ -158,6 +164,7 @@ struct mpc85xx_l2_pdata {
 
 struct mpc85xx_pci_pdata {
 	char *name;
+	bool is_pcie;
 	int edac_idx;
 	void __iomem *pci_vbase;
 	int irq;
-- 
cgit v0.10.2


From cdf8d75818e3cd30746d38f5fbcdb3745fd267a3 Mon Sep 17 00:00:00 2001
From: James Hogan <james.hogan@imgtec.com>
Date: Thu, 14 Nov 2013 10:14:37 +0000
Subject: metag: dma: remove dead code in dma_alloc_init()

Meta has 2 levels of page table so the pmd folds into the pud which
folds into the pgd. Therefore the !pmd check in dma_alloc_init() is dead
code since it essentially checks whether:
  (init_mm->pgd + 0x770) == 0

Remove the check.

Reported-by: Chen Gang <gang.chen@asianux.com>
Signed-off-by: James Hogan <james.hogan@imgtec.com>

diff --git a/arch/metag/kernel/dma.c b/arch/metag/kernel/dma.c
index db589ad..c700d62 100644
--- a/arch/metag/kernel/dma.c
+++ b/arch/metag/kernel/dma.c
@@ -399,11 +399,6 @@ static int __init dma_alloc_init(void)
 		pgd = pgd_offset(&init_mm, CONSISTENT_START);
 		pud = pud_alloc(&init_mm, pgd, CONSISTENT_START);
 		pmd = pmd_alloc(&init_mm, pud, CONSISTENT_START);
-		if (!pmd) {
-			pr_err("%s: no pmd tables\n", __func__);
-			ret = -ENOMEM;
-			break;
-		}
 		WARN_ON(!pmd_none(*pmd));
 
 		pte = pte_alloc_kernel(pmd, CONSISTENT_START);
-- 
cgit v0.10.2


From a4df02a217e9787a4b967197d9d9030c3e3c1088 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Tue, 25 Jun 2013 21:15:24 +0200
Subject: m68k: Mark functions only called from setup_arch() __init

Some functions that are only called (indirectly) from setup_arch() lack
__init annotations.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c
index b819390..93ab423 100644
--- a/arch/m68k/amiga/config.c
+++ b/arch/m68k/amiga/config.c
@@ -140,7 +140,7 @@ static struct resource ram_resource[NUM_MEMINFO];
      *  Parse an Amiga-specific record in the bootinfo
      */
 
-int amiga_parse_bootinfo(const struct bi_record *record)
+int __init amiga_parse_bootinfo(const struct bi_record *record)
 {
 	int unknown = 0;
 	const unsigned long *data = record->data;
diff --git a/arch/m68k/apollo/config.c b/arch/m68k/apollo/config.c
index 3ea56b9..2bdde96 100644
--- a/arch/m68k/apollo/config.c
+++ b/arch/m68k/apollo/config.c
@@ -1,3 +1,4 @@
+#include <linux/init.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
@@ -43,8 +44,8 @@ static const char *apollo_models[] = {
 	[APOLLO_DN4500-APOLLO_DN3000] = "DN4500 (Roadrunner)"
 };
 
-int apollo_parse_bootinfo(const struct bi_record *record) {
-
+int __init apollo_parse_bootinfo(const struct bi_record *record)
+{
 	int unknown = 0;
 	const unsigned long *data = record->data;
 
@@ -60,9 +61,8 @@ int apollo_parse_bootinfo(const struct bi_record *record) {
 	return unknown;
 }
 
-void dn_setup_model(void) {
-
-
+static void __init dn_setup_model(void)
+{
 	printk("Apollo hardware found: ");
 	printk("[%s]\n", apollo_models[apollo_model - APOLLO_DN3000]);
 
diff --git a/arch/m68k/bvme6000/config.c b/arch/m68k/bvme6000/config.c
index 8943aa4..1b9e31e 100644
--- a/arch/m68k/bvme6000/config.c
+++ b/arch/m68k/bvme6000/config.c
@@ -50,7 +50,7 @@ void bvme6000_set_vectors (void);
 static irq_handler_t tick_handler;
 
 
-int bvme6000_parse_bootinfo(const struct bi_record *bi)
+int __init bvme6000_parse_bootinfo(const struct bi_record *bi)
 {
 	if (bi->tag == BI_VME_TYPE)
 		return 0;
diff --git a/arch/m68k/emu/natfeat.c b/arch/m68k/emu/natfeat.c
index 121a666..71b78ec 100644
--- a/arch/m68k/emu/natfeat.c
+++ b/arch/m68k/emu/natfeat.c
@@ -9,6 +9,7 @@
  * the GNU General Public License (GPL), incorporated herein by reference.
  */
 
+#include <linux/init.h>
 #include <linux/types.h>
 #include <linux/console.h>
 #include <linux/string.h>
@@ -70,7 +71,7 @@ static void nf_poweroff(void)
 		nf_call(id);
 }
 
-void nf_init(void)
+void __init nf_init(void)
 {
 	unsigned long id, version;
 	char buf[256];
diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c
index e67e531..99aa988 100644
--- a/arch/m68k/kernel/setup_mm.c
+++ b/arch/m68k/kernel/setup_mm.c
@@ -74,9 +74,9 @@ unsigned long m68k_memoffset;
 struct mem_info m68k_memory[NUM_MEMINFO];
 EXPORT_SYMBOL(m68k_memory);
 
-struct mem_info m68k_ramdisk;
+static struct mem_info m68k_ramdisk __initdata;
 
-static char m68k_command_line[CL_SIZE];
+static char m68k_command_line[CL_SIZE] __initdata;
 
 void (*mach_sched_init) (irq_handler_t handler) __initdata = NULL;
 /* machine dependent irq functions */
diff --git a/arch/m68k/mac/psc.c b/arch/m68k/mac/psc.c
index 6f026fc..cc9f3f0 100644
--- a/arch/m68k/mac/psc.c
+++ b/arch/m68k/mac/psc.c
@@ -54,7 +54,7 @@ static void psc_debug_dump(void)
  * expanded to cover what I think are the other 7 channels.
  */
 
-static void psc_dma_die_die_die(void)
+static __init void psc_dma_die_die_die(void)
 {
 	int i;
 
diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c
index 1c62628..5c99154 100644
--- a/arch/m68k/mvme147/config.c
+++ b/arch/m68k/mvme147/config.c
@@ -51,7 +51,7 @@ static int bcd2int (unsigned char b);
 irq_handler_t tick_handler;
 
 
-int mvme147_parse_bootinfo(const struct bi_record *bi)
+int __init mvme147_parse_bootinfo(const struct bi_record *bi)
 {
 	if (bi->tag == BI_VME_TYPE || bi->tag == BI_VME_BRDINFO)
 		return 0;
diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c
index 080a342..60d8a1b 100644
--- a/arch/m68k/mvme16x/config.c
+++ b/arch/m68k/mvme16x/config.c
@@ -60,7 +60,7 @@ unsigned short mvme16x_config;
 EXPORT_SYMBOL(mvme16x_config);
 
 
-int mvme16x_parse_bootinfo(const struct bi_record *bi)
+int __init mvme16x_parse_bootinfo(const struct bi_record *bi)
 {
 	if (bi->tag == BI_VME_TYPE || bi->tag == BI_VME_BRDINFO)
 		return 0;
diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c
index 078bb74..e90fe90 100644
--- a/arch/m68k/q40/config.c
+++ b/arch/m68k/q40/config.c
@@ -154,7 +154,7 @@ static unsigned int serports[] =
 	0x3f8,0x2f8,0x3e8,0x2e8,0
 };
 
-static void q40_disable_irqs(void)
+static void __init q40_disable_irqs(void)
 {
 	unsigned i, j;
 
@@ -198,7 +198,7 @@ void __init config_q40(void)
 }
 
 
-int q40_parse_bootinfo(const struct bi_record *rec)
+int __init q40_parse_bootinfo(const struct bi_record *rec)
 {
 	return 1;
 }
diff --git a/arch/m68k/sun3/dvma.c b/arch/m68k/sun3/dvma.c
index d522eaa..d95506e 100644
--- a/arch/m68k/sun3/dvma.c
+++ b/arch/m68k/sun3/dvma.c
@@ -7,6 +7,7 @@
  *
  */
 
+#include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/bootmem.h>
@@ -62,10 +63,7 @@ int dvma_map_iommu(unsigned long kaddr, unsigned long baddr,
 
 }
 
-void sun3_dvma_init(void)
+void __init sun3_dvma_init(void)
 {
-
 	memset(ptelist, 0, sizeof(ptelist));
-
-
 }
diff --git a/arch/m68k/sun3/mmu_emu.c b/arch/m68k/sun3/mmu_emu.c
index 8edc510..3f258e2 100644
--- a/arch/m68k/sun3/mmu_emu.c
+++ b/arch/m68k/sun3/mmu_emu.c
@@ -6,6 +6,7 @@
 ** Started 1/16/98 @ 2:22 am
 */
 
+#include <linux/init.h>
 #include <linux/mman.h>
 #include <linux/mm.h>
 #include <linux/kernel.h>
@@ -122,7 +123,7 @@ void print_pte_vaddr (unsigned long vaddr)
 /*
  * Initialise the MMU emulator.
  */
-void mmu_emu_init(unsigned long bootmem_end)
+void __init mmu_emu_init(unsigned long bootmem_end)
 {
 	unsigned long seg, num;
 	int i,j;
diff --git a/arch/m68k/sun3/sun3dvma.c b/arch/m68k/sun3/sun3dvma.c
index cab5448..ca57966 100644
--- a/arch/m68k/sun3/sun3dvma.c
+++ b/arch/m68k/sun3/sun3dvma.c
@@ -6,6 +6,7 @@
  * Contains common routines for sun3/sun3x DVMA management.
  */
 
+#include <linux/init.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/gfp.h>
@@ -245,7 +246,7 @@ static inline int free_baddr(unsigned long baddr)
 
 }
 
-void dvma_init(void)
+void __init dvma_init(void)
 {
 
 	struct hole *hole;
-- 
cgit v0.10.2


From 7b3e8de9b3e9c0ffd5cb1600e6075bede4272868 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Tue, 25 Jun 2013 20:33:44 +0200
Subject: m68k/sun3: Dynamically allocate the table to track IOMMU use

As Sun 3 kernels cannot be multi-platform due to the different Sun 3 MMU
type, it made sense to statically allocate the table to track IOMMU use.

However, Sun 3x kernels can be multi-platform. Furthermore, Sun 3x uses
a larger table than Sun 3 (8192 bytes instead of 512 bytes).

Hence switch to dynamic allocation of this table using the bootmem
allocator to avoid wasting 8192 bytes when not running on a Sun 3x.
As this allocator returns zeroed memory, there's no need to explicitly
initialize the table to zeroes.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/sun3/sun3dvma.c b/arch/m68k/sun3/sun3dvma.c
index ca57966..b37521a 100644
--- a/arch/m68k/sun3/sun3dvma.c
+++ b/arch/m68k/sun3/sun3dvma.c
@@ -6,6 +6,7 @@
  * Contains common routines for sun3/sun3x DVMA management.
  */
 
+#include <linux/bootmem.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
@@ -31,7 +32,7 @@ static inline void dvma_unmap_iommu(unsigned long a, int b)
 extern void sun3_dvma_init(void);
 #endif
 
-static unsigned long iommu_use[IOMMU_TOTAL_ENTRIES];
+static unsigned long *iommu_use;
 
 #define dvma_index(baddr) ((baddr - DVMA_START) >> DVMA_PAGE_SHIFT)
 
@@ -266,7 +267,7 @@ void __init dvma_init(void)
 
 	list_add(&(hole->list), &hole_list);
 
-	memset(iommu_use, 0, sizeof(iommu_use));
+	iommu_use = alloc_bootmem(IOMMU_TOTAL_ENTRIES * sizeof(unsigned long));
 
 	dvma_unmap_iommu(DVMA_START, DVMA_SIZE);
 
-- 
cgit v0.10.2


From f16b89bc3cdf11266b657f2f74f4db255e77b76c Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Wed, 26 Jun 2013 13:18:09 +0200
Subject: m68k/mac: Fix comment about iop_*_present flags setup timing

This is no longer done from iop_init()

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/mac/iop.c b/arch/m68k/mac/iop.c
index 7d8d461..ed0d9b0 100644
--- a/arch/m68k/mac/iop.c
+++ b/arch/m68k/mac/iop.c
@@ -118,9 +118,9 @@
 
 /*#define DEBUG_IOP*/
 
-/* Set to non-zero if the IOPs are present. Set by iop_init() */
+/* Non-zero if the IOPs are present */
 
-int iop_scc_present,iop_ism_present;
+int iop_scc_present, iop_ism_present;
 
 /* structure for tracking channel listeners */
 
-- 
cgit v0.10.2


From 51b9310f0a33d5280a93228475fa95e38fbcba36 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Tue, 17 Sep 2013 09:04:34 +0200
Subject: m68k/defconfig: Make NFS_V4 modular instead of builtin

This reduces the kernel image size by ca. 100 KiB, while still allowing
NFS root.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 19325e1..04432b7 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -385,7 +385,7 @@ CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=y
-CONFIG_NFS_V4=y
+CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 14dc6cc..a018fd7 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -342,7 +342,7 @@ CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=y
-CONFIG_NFS_V4=y
+CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 6d5370c..fa33639 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -360,7 +360,7 @@ CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=y
-CONFIG_NFS_V4=y
+CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index c015ddb..ca310d5 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -334,7 +334,7 @@ CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=y
-CONFIG_NFS_V4=y
+CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index ec7382d..aa98958 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -344,7 +344,7 @@ CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=y
-CONFIG_NFS_V4=y
+CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 7d46fbe..ac2c153 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -367,7 +367,7 @@ CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=y
-CONFIG_NFS_V4=y
+CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index b17a883..61cdb09 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -445,7 +445,7 @@ CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=y
-CONFIG_NFS_V4=y
+CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 5586c65..f89613f 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -334,7 +334,7 @@ CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=y
-CONFIG_NFS_V4=y
+CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index e5e8262..d086acd 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -334,7 +334,7 @@ CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=y
-CONFIG_NFS_V4=y
+CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index be1496e..3662899 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -358,7 +358,7 @@ CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=y
-CONFIG_NFS_V4=y
+CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 54674d6..bb87f17 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -336,7 +336,7 @@ CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=y
-CONFIG_NFS_V4=y
+CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 832d953..b75a0b1 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -336,7 +336,7 @@ CONFIG_QNX6FS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 CONFIG_NFS_FS=y
-CONFIG_NFS_V4=y
+CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=m
-- 
cgit v0.10.2


From 6074a13934202c7a68c77fd5f37da8dce731f181 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Wed, 26 Jun 2013 13:15:58 +0200
Subject: m68k/setup: Use pr_*() and __func__ instead of plain printk()

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c
index 99aa988..9f16a15 100644
--- a/arch/m68k/kernel/setup_mm.c
+++ b/arch/m68k/kernel/setup_mm.c
@@ -161,7 +161,8 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record)
 				m68k_memory[m68k_num_memory].size = data[1];
 				m68k_num_memory++;
 			} else
-				printk("m68k_parse_bootinfo: too many memory chunks\n");
+				pr_warn("%s: too many memory chunks\n",
+					__func__);
 			break;
 
 		case BI_RAMDISK:
@@ -197,8 +198,8 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record)
 				unknown = 1;
 		}
 		if (unknown)
-			printk("m68k_parse_bootinfo: unknown tag 0x%04x ignored\n",
-			       record->tag);
+			pr_warn("%s: unknown tag 0x%04x ignored\n", __func__,
+				   record->tag);
 		record = (struct bi_record *)((unsigned long)record +
 					      record->size);
 	}
@@ -206,8 +207,8 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record)
 	m68k_realnum_memory = m68k_num_memory;
 #ifdef CONFIG_SINGLE_MEMORY_CHUNK
 	if (m68k_num_memory > 1) {
-		printk("Ignoring last %i chunks of physical memory\n",
-		       (m68k_num_memory - 1));
+		pr_warn("%s: ignoring last %i chunks of physical memory\n",
+			__func__, (m68k_num_memory - 1));
 		m68k_num_memory = 1;
 	}
 #endif
@@ -247,7 +248,7 @@ void __init setup_arch(char **cmdline_p)
 		asm (".chip 68060; movec %%pcr,%0; .chip 68k"
 		     : "=d" (pcr));
 		if (((pcr >> 8) & 0xff) <= 5) {
-			printk("Enabling workaround for errata I14\n");
+			pr_warn("Enabling workaround for errata I14\n");
 			asm (".chip 68060; movec %0,%%pcr; .chip 68k"
 			     : : "d" (pcr | 0x20));
 		}
@@ -353,7 +354,7 @@ void __init setup_arch(char **cmdline_p)
 				     BOOTMEM_DEFAULT);
 		initrd_start = (unsigned long)phys_to_virt(m68k_ramdisk.addr);
 		initrd_end = initrd_start + m68k_ramdisk.size;
-		printk("initrd: %08lx - %08lx\n", initrd_start, initrd_end);
+		pr_info("initrd: %08lx - %08lx\n", initrd_start, initrd_end);
 	}
 #endif
 
@@ -538,9 +539,9 @@ void check_bugs(void)
 {
 #ifndef CONFIG_M68KFPU_EMU
 	if (m68k_fputype == 0) {
-		printk(KERN_EMERG "*** YOU DO NOT HAVE A FLOATING POINT UNIT, "
+		pr_emerg("*** YOU DO NOT HAVE A FLOATING POINT UNIT, "
 			"WHICH IS REQUIRED BY LINUX/M68K ***\n");
-		printk(KERN_EMERG "Upgrade your hardware or join the FPU "
+		pr_emerg("Upgrade your hardware or join the FPU "
 			"emulation project\n");
 		panic("no FPU");
 	}
-- 
cgit v0.10.2


From 1ea636eb68322198e08aebdede141244d98e8299 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Thu, 16 Aug 2012 17:05:43 +0200
Subject: Documentation/zorro.txt: Update path to arch-specific header files

  - Arch-specific headers were moved to arch/<arch/>/include/asm,
  - APUS support was dropped a long time ago

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/Documentation/zorro.txt b/Documentation/zorro.txt
index d5829d1..d176704 100644
--- a/Documentation/zorro.txt
+++ b/Documentation/zorro.txt
@@ -95,7 +95,7 @@ The treatment of these regions depends on the type of Zorro space:
 -------------
 
 linux/include/linux/zorro.h
-linux/include/asm-{m68k,ppc}/zorro.h
+linux/arch/m68k/include/asm/zorro.h
 linux/include/linux/zorro_ids.h
 linux/drivers/zorro
 /proc/bus/zorro
-- 
cgit v0.10.2


From c293738e6d8dfb9c941759855b5161fde449644d Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Sat, 29 Jun 2013 10:40:20 +0200
Subject: zorro: Do not allocate zorro_autocon[] statically

Currently the array of Zorro devices is allocated statically, wasting
up to 4.5 KiB when running an Amiga or multi-platform kernel on a machine
with no or a handful of Zorro expansion cards. Convert it to conditional
dynamic memory allocation to fix this.

amiga_parse_bootinfo() still needs to store some information about the
detected Zorro devices, at a time even the bootmem allocator is not yet
available.  This is now handled using a much smaller array (typically less
than 0.5 KiB), which is __initdata and thus freed later.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c
index 93ab423..d956ddb 100644
--- a/arch/m68k/amiga/config.c
+++ b/arch/m68k/amiga/config.c
@@ -174,12 +174,12 @@ int __init amiga_parse_bootinfo(const struct bi_record *record)
 #ifdef CONFIG_ZORRO
 		if (zorro_num_autocon < ZORRO_NUM_AUTO) {
 			const struct ConfigDev *cd = (struct ConfigDev *)data;
-			struct zorro_dev *dev = &zorro_autocon[zorro_num_autocon++];
+			struct zorro_dev_init *dev = &zorro_autocon_init[zorro_num_autocon++];
 			dev->rom = cd->cd_Rom;
 			dev->slotaddr = cd->cd_SlotAddr;
 			dev->slotsize = cd->cd_SlotSize;
-			dev->resource.start = (unsigned long)cd->cd_BoardAddr;
-			dev->resource.end = dev->resource.start + cd->cd_BoardSize - 1;
+			dev->boardaddr = (u32)cd->cd_BoardAddr;
+			dev->boardsize = cd->cd_BoardSize;
 		} else
 			printk("amiga_parse_bootinfo: too many AutoConfig devices\n");
 #endif /* CONFIG_ZORRO */
diff --git a/arch/m68k/amiga/platform.c b/arch/m68k/amiga/platform.c
index dacd9f9..7847b2b 100644
--- a/arch/m68k/amiga/platform.c
+++ b/arch/m68k/amiga/platform.c
@@ -67,8 +67,8 @@ static int __init z_dev_present(zorro_id id)
 	unsigned int i;
 
 	for (i = 0; i < zorro_num_autocon; i++)
-		if (zorro_autocon[i].rom.er_Manufacturer == ZORRO_MANUF(id) &&
-		    zorro_autocon[i].rom.er_Product == ZORRO_PROD(id))
+		if (zorro_autocon_init[i].rom.er_Manufacturer == ZORRO_MANUF(id) &&
+		    zorro_autocon_init[i].rom.er_Product == ZORRO_PROD(id))
 			return 1;
 
 	return 0;
diff --git a/drivers/zorro/zorro.c b/drivers/zorro/zorro.c
index 858c971..10c7f77 100644
--- a/drivers/zorro/zorro.c
+++ b/drivers/zorro/zorro.c
@@ -29,7 +29,8 @@
      */
 
 unsigned int zorro_num_autocon;
-struct zorro_dev zorro_autocon[ZORRO_NUM_AUTO];
+struct zorro_dev_init zorro_autocon_init[ZORRO_NUM_AUTO] __initdata;
+struct zorro_dev *zorro_autocon;
 
 
     /*
@@ -38,6 +39,7 @@ struct zorro_dev zorro_autocon[ZORRO_NUM_AUTO];
 
 struct zorro_bus {
 	struct device dev;
+	struct zorro_dev devices[0];
 };
 
 
@@ -125,16 +127,20 @@ static struct resource __init *zorro_find_parent_resource(
 static int __init amiga_zorro_probe(struct platform_device *pdev)
 {
 	struct zorro_bus *bus;
+	struct zorro_dev_init *zi;
 	struct zorro_dev *z;
 	struct resource *r;
 	unsigned int i;
 	int error;
 
 	/* Initialize the Zorro bus */
-	bus = kzalloc(sizeof(*bus), GFP_KERNEL);
+	bus = kzalloc(sizeof(*bus) +
+		      zorro_num_autocon * sizeof(bus->devices[0]),
+		      GFP_KERNEL);
 	if (!bus)
 		return -ENOMEM;
 
+	zorro_autocon = bus->devices;
 	bus->dev.parent = &pdev->dev;
 	dev_set_name(&bus->dev, "zorro");
 	error = device_register(&bus->dev);
@@ -151,15 +157,22 @@ static int __init amiga_zorro_probe(struct platform_device *pdev)
 
 	/* First identify all devices ... */
 	for (i = 0; i < zorro_num_autocon; i++) {
+		zi = &zorro_autocon_init[i];
 		z = &zorro_autocon[i];
+
+		z->rom = zi->rom;
 		z->id = (z->rom.er_Manufacturer<<16) | (z->rom.er_Product<<8);
 		if (z->id == ZORRO_PROD_GVP_EPC_BASE) {
 			/* GVP quirk */
-			unsigned long magic = zorro_resource_start(z)+0x8000;
+			unsigned long magic = zi->boardaddr + 0x8000;
 			z->id |= *(u16 *)ZTWO_VADDR(magic) & GVP_PRODMASK;
 		}
+		z->slotaddr = zi->slotaddr;
+		z->slotsize = zi->slotsize;
 		sprintf(z->name, "Zorro device %08x", z->id);
 		zorro_name_device(z);
+		z->resource.start = zi->boardaddr;
+		z->resource.end = zi->boardaddr + zi->boardsize - 1;
 		z->resource.name = z->name;
 		r = zorro_find_parent_resource(pdev, z);
 		error = request_resource(r, &z->resource);
diff --git a/include/linux/zorro.h b/include/linux/zorro.h
index dff4202..661cbd2 100644
--- a/include/linux/zorro.h
+++ b/include/linux/zorro.h
@@ -175,7 +175,23 @@ static inline struct zorro_driver *zorro_dev_driver(const struct zorro_dev *z)
 
 
 extern unsigned int zorro_num_autocon;	/* # of autoconfig devices found */
-extern struct zorro_dev zorro_autocon[ZORRO_NUM_AUTO];
+extern struct zorro_dev *zorro_autocon;
+
+
+    /*
+     * Minimal information about a Zorro device, passed from bootinfo
+     * Only available temporarily, i.e. until initmem has been freed!
+     */
+
+struct zorro_dev_init {
+	struct ExpansionRom rom;
+	u16 slotaddr;
+	u16 slotsize;
+	u32 boardaddr;
+	u32 boardsize;
+};
+
+extern struct zorro_dev_init zorro_autocon_init[ZORRO_NUM_AUTO] __initdata;
 
 
     /*
-- 
cgit v0.10.2


From bd79014cd47b3a0fa59a7a17489d8ada56ecab9b Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Sun, 30 Jun 2013 13:01:26 +0200
Subject: zorro: Don't fill in dummy names in zorro_name_device()

If the device is not found in the database, it's not needed to fill in
a dummy name. The caller of zorro_name_device() has already taken care
of that to support CONFIG_ZORRO_NAMES=n.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/drivers/zorro/names.c b/drivers/zorro/names.c
index e8517c3..e44e04c 100644
--- a/drivers/zorro/names.c
+++ b/drivers/zorro/names.c
@@ -69,7 +69,6 @@ void __init zorro_name_device(struct zorro_dev *dev)
 	} while (--i);
 
 	/* Couldn't find either the manufacturer nor the product */
-	sprintf(name, "Zorro device %08x", dev->id);
 	return;
 
 	match_manuf: {
-- 
cgit v0.10.2


From 52182c758f7c9bc34dbee0dfdce13d356de50f03 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Fri, 17 May 2013 14:01:24 +0200
Subject: zorro: Refactor conditional handling of Zorro device name database

Using an empty static inline function in the CONFIG_ZORRO_NAMES=n case
allows to drop compilation of names.c.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/drivers/zorro/Makefile b/drivers/zorro/Makefile
index f621726..7dc5332f 100644
--- a/drivers/zorro/Makefile
+++ b/drivers/zorro/Makefile
@@ -2,8 +2,9 @@
 # Makefile for the Zorro bus specific drivers.
 #
 
-obj-$(CONFIG_ZORRO)	+= zorro.o zorro-driver.o zorro-sysfs.o names.o
+obj-$(CONFIG_ZORRO)	+= zorro.o zorro-driver.o zorro-sysfs.o
 obj-$(CONFIG_PROC_FS)	+= proc.o
+obj-$(CONFIG_ZORRO_NAMES) +=  names.o
 
 hostprogs-y 		:= gen-devlist
 
diff --git a/drivers/zorro/names.c b/drivers/zorro/names.c
index e44e04c..6f3fd99 100644
--- a/drivers/zorro/names.c
+++ b/drivers/zorro/names.c
@@ -15,8 +15,6 @@
 #include <linux/zorro.h>
 
 
-#ifdef CONFIG_ZORRO_NAMES
-
 struct zorro_prod_info {
 	__u16 prod;
 	unsigned short seen;
@@ -97,11 +95,3 @@ void __init zorro_name_device(struct zorro_dev *dev)
 		}
 	}
 }
-
-#else
-
-void __init zorro_name_device(struct zorro_dev *dev)
-{
-}
-
-#endif
diff --git a/drivers/zorro/zorro.h b/drivers/zorro/zorro.h
index b682d5c..34119fb 100644
--- a/drivers/zorro/zorro.h
+++ b/drivers/zorro/zorro.h
@@ -1,4 +1,9 @@
 
+#ifdef CONFIG_ZORRO_NAMES
 extern void zorro_name_device(struct zorro_dev *z);
+#else
+static inline void zorro_name_device(struct zorro_dev *dev) { }
+#endif
+
 extern int zorro_create_sysfs_dev_files(struct zorro_dev *z);
 
-- 
cgit v0.10.2


From 83b7bce3d390f15047e05a186bb4051536ee9dbc Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Wed, 16 Oct 2013 11:28:54 +0200
Subject: zorro: Let the driver core handle device enumeration

Filling in dev_name of the Zorro bus type and dev.id of each device allows
the driver core to enumerate devices, so we don't have to do that
ourselves.

This changes the names of devices in sysfs from "%02x" to "zorro%u".

Note that filling in dev.id is also needed to support MFD Zorro devices.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/drivers/zorro/zorro-driver.c b/drivers/zorro/zorro-driver.c
index ac1db7f..eacae14 100644
--- a/drivers/zorro/zorro-driver.c
+++ b/drivers/zorro/zorro-driver.c
@@ -161,11 +161,12 @@ static int zorro_uevent(struct device *dev, struct kobj_uevent_env *env)
 }
 
 struct bus_type zorro_bus_type = {
-	.name	= "zorro",
-	.match	= zorro_bus_match,
-	.uevent	= zorro_uevent,
-	.probe	= zorro_device_probe,
-	.remove	= zorro_device_remove,
+	.name     = "zorro",
+	.dev_name = "zorro",
+	.match    = zorro_bus_match,
+	.uevent   = zorro_uevent,
+	.probe    = zorro_device_probe,
+	.remove   = zorro_device_remove,
 };
 EXPORT_SYMBOL(zorro_bus_type);
 
diff --git a/drivers/zorro/zorro.c b/drivers/zorro/zorro.c
index 10c7f77..450abf1 100644
--- a/drivers/zorro/zorro.c
+++ b/drivers/zorro/zorro.c
@@ -142,7 +142,7 @@ static int __init amiga_zorro_probe(struct platform_device *pdev)
 
 	zorro_autocon = bus->devices;
 	bus->dev.parent = &pdev->dev;
-	dev_set_name(&bus->dev, "zorro");
+	dev_set_name(&bus->dev, zorro_bus_type.name);
 	error = device_register(&bus->dev);
 	if (error) {
 		pr_err("Zorro: Error registering zorro_bus\n");
@@ -180,9 +180,9 @@ static int __init amiga_zorro_probe(struct platform_device *pdev)
 			dev_err(&bus->dev,
 				"Address space collision on device %s %pR\n",
 				z->name, &z->resource);
-		dev_set_name(&z->dev, "%02x", i);
 		z->dev.parent = &bus->dev;
 		z->dev.bus = &zorro_bus_type;
+		z->dev.id = i;
 	}
 
 	/* ... then register them */
-- 
cgit v0.10.2


From 6112ea0862facaeaeab504ee01c0d04bcd22daaf Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Sun, 9 Jan 2011 11:03:43 +0100
Subject: zorro: ZTWO_VADDR() should return "void __iomem *"

ZTWO_VADDR() converts from physical to virtual I/O addresses, so it should
return "void __iomem *" instead of "unsigned long".

This allows to drop several casts, but requires adding a few casts to
accomodate legacy driver frameworks that store "unsigned long" I/O
addresses.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/amiga/chipram.c b/arch/m68k/amiga/chipram.c
index 99449fb..ba03cec 100644
--- a/arch/m68k/amiga/chipram.c
+++ b/arch/m68k/amiga/chipram.c
@@ -87,7 +87,7 @@ void *amiga_chip_alloc_res(unsigned long size, struct resource *res)
 
 	atomic_sub(size, &chipavail);
 	pr_debug("amiga_chip_alloc_res: returning %pR\n", res);
-	return (void *)ZTWO_VADDR(res->start);
+	return ZTWO_VADDR(res->start);
 }
 
 void amiga_chip_free(void *ptr)
diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c
index d956ddb..acd9c16 100644
--- a/arch/m68k/amiga/config.c
+++ b/arch/m68k/amiga/config.c
@@ -618,7 +618,7 @@ static int __init amiga_savekmsg_setup(char *arg)
 
 	/* Just steal the block, the chipram allocator isn't functional yet */
 	amiga_chip_size -= SAVEKMSG_MAXMEM;
-	savekmsg = (void *)ZTWO_VADDR(CHIP_PHYSADDR + amiga_chip_size);
+	savekmsg = ZTWO_VADDR(CHIP_PHYSADDR + amiga_chip_size);
 	savekmsg->magic1 = SAVEKMSG_MAGIC1;
 	savekmsg->magic2 = SAVEKMSG_MAGIC2;
 	savekmsg->magicptr = ZTWO_PADDR(savekmsg);
diff --git a/arch/m68k/include/asm/amigahw.h b/arch/m68k/include/asm/amigahw.h
index 7a19b56..3bef0b2 100644
--- a/arch/m68k/include/asm/amigahw.h
+++ b/arch/m68k/include/asm/amigahw.h
@@ -266,7 +266,7 @@ struct CIA {
 
 #define zTwoBase (0x80000000)
 #define ZTWO_PADDR(x) (((unsigned long)(x))-zTwoBase)
-#define ZTWO_VADDR(x) (((unsigned long)(x))+zTwoBase)
+#define ZTWO_VADDR(x) ((void __iomem *)(((unsigned long)(x))+zTwoBase))
 
 #define CUSTOM_PHYSADDR     (0xdff000)
 #define amiga_custom ((*(volatile struct CUSTOM *)(zTwoBase+CUSTOM_PHYSADDR)))
diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c
index 5a95baf..8b2a60c 100644
--- a/drivers/block/z2ram.c
+++ b/drivers/block/z2ram.c
@@ -116,8 +116,8 @@ get_z2ram( void )
 	if ( test_bit( i, zorro_unused_z2ram ) )
 	{
 	    z2_count++;
-	    z2ram_map[ z2ram_size++ ] = 
-		ZTWO_VADDR( Z2RAM_START ) + ( i << Z2RAM_CHUNKSHIFT );
+	    z2ram_map[z2ram_size++] = (unsigned long)ZTWO_VADDR(Z2RAM_START) +
+				      (i << Z2RAM_CHUNKSHIFT);
 	    clear_bit( i, zorro_unused_z2ram );
 	}
     }
diff --git a/drivers/ide/buddha.c b/drivers/ide/buddha.c
index b1d3859..46eaf58 100644
--- a/drivers/ide/buddha.c
+++ b/drivers/ide/buddha.c
@@ -198,7 +198,7 @@ fail_base2:
 				continue;
 			}
 		}	  
-		buddha_board = ZTWO_VADDR(board);
+		buddha_board = (unsigned long)ZTWO_VADDR(board);
 		
 		/* write to BUDDHA_IRQ_MR to enable the board IRQ */
 		/* X-Surf doesn't have this.  IRQs are always on */
diff --git a/drivers/net/ethernet/8390/hydra.c b/drivers/net/ethernet/8390/hydra.c
index fb3dd43..f615fde 100644
--- a/drivers/net/ethernet/8390/hydra.c
+++ b/drivers/net/ethernet/8390/hydra.c
@@ -113,7 +113,7 @@ static const struct net_device_ops hydra_netdev_ops = {
 static int hydra_init(struct zorro_dev *z)
 {
     struct net_device *dev;
-    unsigned long board = ZTWO_VADDR(z->resource.start);
+    unsigned long board = (unsigned long)ZTWO_VADDR(z->resource.start);
     unsigned long ioaddr = board+HYDRA_NIC_BASE;
     const char name[] = "NE2000";
     int start_page, stop_page;
diff --git a/drivers/net/ethernet/8390/zorro8390.c b/drivers/net/ethernet/8390/zorro8390.c
index 85ec4c2..ae2a12b 100644
--- a/drivers/net/ethernet/8390/zorro8390.c
+++ b/drivers/net/ethernet/8390/zorro8390.c
@@ -287,7 +287,7 @@ static const struct net_device_ops zorro8390_netdev_ops = {
 };
 
 static int zorro8390_init(struct net_device *dev, unsigned long board,
-			  const char *name, unsigned long ioaddr)
+			  const char *name, void __iomem *ioaddr)
 {
 	int i;
 	int err;
@@ -354,7 +354,7 @@ static int zorro8390_init(struct net_device *dev, unsigned long board,
 	start_page = NESM_START_PG;
 	stop_page = NESM_STOP_PG;
 
-	dev->base_addr = ioaddr;
+	dev->base_addr = (unsigned long)ioaddr;
 	dev->irq = IRQ_AMIGA_PORTS;
 
 	/* Install the Interrupt handler */
diff --git a/drivers/net/ethernet/amd/a2065.c b/drivers/net/ethernet/amd/a2065.c
index 0866e76..f492a19 100644
--- a/drivers/net/ethernet/amd/a2065.c
+++ b/drivers/net/ethernet/amd/a2065.c
@@ -713,8 +713,8 @@ static int a2065_init_one(struct zorro_dev *z,
 	dev->dev_addr[3] = (z->rom.er_SerialNumber >> 16) & 0xff;
 	dev->dev_addr[4] = (z->rom.er_SerialNumber >> 8) & 0xff;
 	dev->dev_addr[5] = z->rom.er_SerialNumber & 0xff;
-	dev->base_addr = ZTWO_VADDR(base_addr);
-	dev->mem_start = ZTWO_VADDR(mem_start);
+	dev->base_addr = (unsigned long)ZTWO_VADDR(base_addr);
+	dev->mem_start = (unsigned long)ZTWO_VADDR(mem_start);
 	dev->mem_end = dev->mem_start + A2065_RAM_SIZE;
 
 	priv->ll = (volatile struct lance_regs *)dev->base_addr;
diff --git a/drivers/net/ethernet/amd/ariadne.c b/drivers/net/ethernet/amd/ariadne.c
index c178eb4..33822cb 100644
--- a/drivers/net/ethernet/amd/ariadne.c
+++ b/drivers/net/ethernet/amd/ariadne.c
@@ -747,8 +747,8 @@ static int ariadne_init_one(struct zorro_dev *z,
 	dev->dev_addr[3] = (z->rom.er_SerialNumber >> 16) & 0xff;
 	dev->dev_addr[4] = (z->rom.er_SerialNumber >> 8) & 0xff;
 	dev->dev_addr[5] = z->rom.er_SerialNumber & 0xff;
-	dev->base_addr = ZTWO_VADDR(base_addr);
-	dev->mem_start = ZTWO_VADDR(mem_start);
+	dev->base_addr = (unsigned long)ZTWO_VADDR(base_addr);
+	dev->mem_start = (unsigned long)ZTWO_VADDR(mem_start);
 	dev->mem_end = dev->mem_start + ARIADNE_RAM_SIZE;
 
 	dev->netdev_ops = &ariadne_netdev_ops;
diff --git a/drivers/parport/parport_mfc3.c b/drivers/parport/parport_mfc3.c
index 7578d79..2f650f6 100644
--- a/drivers/parport/parport_mfc3.c
+++ b/drivers/parport/parport_mfc3.c
@@ -300,7 +300,7 @@ static int __init parport_mfc3_init(void)
 		if (!request_mem_region(piabase, sizeof(struct pia), "PIA"))
 			continue;
 
-		pp = (struct pia *)ZTWO_VADDR(piabase);
+		pp = ZTWO_VADDR(piabase);
 		pp->crb = 0;
 		pp->pddrb = 255; /* all data pins output */
 		pp->crb = PIA_DDR|32|8;
diff --git a/drivers/scsi/a2091.c b/drivers/scsi/a2091.c
index 30fa38a..9176bfb 100644
--- a/drivers/scsi/a2091.c
+++ b/drivers/scsi/a2091.c
@@ -201,7 +201,7 @@ static int a2091_probe(struct zorro_dev *z, const struct zorro_device_id *ent)
 	instance->irq = IRQ_AMIGA_PORTS;
 	instance->unique_id = z->slotaddr;
 
-	regs = (struct a2091_scsiregs *)ZTWO_VADDR(z->resource.start);
+	regs = ZTWO_VADDR(z->resource.start);
 	regs->DAWR = DAWR_A2091;
 
 	wdregs.SASR = &regs->SASR;
diff --git a/drivers/scsi/a3000.c b/drivers/scsi/a3000.c
index c0f4f42..dd5b647 100644
--- a/drivers/scsi/a3000.c
+++ b/drivers/scsi/a3000.c
@@ -220,7 +220,7 @@ static int __init amiga_a3000_scsi_probe(struct platform_device *pdev)
 
 	instance->irq = IRQ_AMIGA_PORTS;
 
-	regs = (struct a3000_scsiregs *)ZTWO_VADDR(res->start);
+	regs = ZTWO_VADDR(res->start);
 	regs->DAWR = DAWR_A3000;
 
 	wdregs.SASR = &regs->SASR;
diff --git a/drivers/scsi/a4000t.c b/drivers/scsi/a4000t.c
index 70c521f..f5a2ab4 100644
--- a/drivers/scsi/a4000t.c
+++ b/drivers/scsi/a4000t.c
@@ -56,7 +56,7 @@ static int __init amiga_a4000t_scsi_probe(struct platform_device *pdev)
 	scsi_addr = res->start + A4000T_SCSI_OFFSET;
 
 	/* Fill in the required pieces of hostdata */
-	hostdata->base = (void __iomem *)ZTWO_VADDR(scsi_addr);
+	hostdata->base = ZTWO_VADDR(scsi_addr);
 	hostdata->clock = 50;
 	hostdata->chip710 = 1;
 	hostdata->dmode_extra = DMODE_FC2;
diff --git a/drivers/scsi/gvp11.c b/drivers/scsi/gvp11.c
index 2203ac2..3b6f83f 100644
--- a/drivers/scsi/gvp11.c
+++ b/drivers/scsi/gvp11.c
@@ -310,7 +310,7 @@ static int gvp11_probe(struct zorro_dev *z, const struct zorro_device_id *ent)
 	if (!request_mem_region(address, 256, "wd33c93"))
 		return -EBUSY;
 
-	regs = (struct gvp11_scsiregs *)(ZTWO_VADDR(address));
+	regs = ZTWO_VADDR(address);
 
 	error = check_wd33c93(regs);
 	if (error)
diff --git a/drivers/scsi/zorro7xx.c b/drivers/scsi/zorro7xx.c
index cbf3476..aff3199 100644
--- a/drivers/scsi/zorro7xx.c
+++ b/drivers/scsi/zorro7xx.c
@@ -104,7 +104,7 @@ static int zorro7xx_init_one(struct zorro_dev *z,
 	if (ioaddr > 0x01000000)
 		hostdata->base = ioremap(ioaddr, zorro_resource_len(z));
 	else
-		hostdata->base = (void __iomem *)ZTWO_VADDR(ioaddr);
+		hostdata->base = ZTWO_VADDR(ioaddr);
 
 	hostdata->clock = 50;
 	hostdata->chip710 = 1;
diff --git a/drivers/video/amifb.c b/drivers/video/amifb.c
index 0dac36c..518f790 100644
--- a/drivers/video/amifb.c
+++ b/drivers/video/amifb.c
@@ -3710,7 +3710,7 @@ default_chipset:
 	if (!videomemory) {
 		dev_warn(&pdev->dev,
 			 "Unable to map videomem cached writethrough\n");
-		info->screen_base = (char *)ZTWO_VADDR(info->fix.smem_start);
+		info->screen_base = ZTWO_VADDR(info->fix.smem_start);
 	} else
 		info->screen_base = (char *)videomemory;
 
diff --git a/drivers/video/cirrusfb.c b/drivers/video/cirrusfb.c
index 5aab9b9..d992aa5 100644
--- a/drivers/video/cirrusfb.c
+++ b/drivers/video/cirrusfb.c
@@ -2256,7 +2256,7 @@ static int cirrusfb_zorro_register(struct zorro_dev *z,
 
 	info->fix.mmio_start = regbase;
 	cinfo->regbase = regbase > 16 * MB_ ? ioremap(regbase, 64 * 1024)
-					    : (caddr_t)ZTWO_VADDR(regbase);
+					    : ZTWO_VADDR(regbase);
 	if (!cinfo->regbase) {
 		dev_err(info->device, "Cannot map registers\n");
 		error = -EIO;
@@ -2266,7 +2266,7 @@ static int cirrusfb_zorro_register(struct zorro_dev *z,
 	info->fix.smem_start = rambase;
 	info->screen_size = ramsize;
 	info->screen_base = rambase > 16 * MB_ ? ioremap(rambase, ramsize)
-					       : (caddr_t)ZTWO_VADDR(rambase);
+					       : ZTWO_VADDR(rambase);
 	if (!info->screen_base) {
 		dev_err(info->device, "Cannot map video RAM\n");
 		error = -EIO;
-- 
cgit v0.10.2


From 986ea58dfb52097999cc388880505fc7a10e4779 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Thu, 3 Oct 2013 10:45:36 +0200
Subject: zorro/UAPI: Disintegrate include/linux/zorro*.h

The Zorro definitions and device IDs are used by bootstraps, hence they
should be exported through UAPI.

Unfortunately zorro.h was never marked for export when headers_install
was introduced, so it was forgotten during the big UAPI disintegration.
In addition, the removal of zorro_ids.h had been sneaked into commit
7e7a43c32a8970ea2bfc3d1af353dcb1a9237769 ("PCI: don't export device IDs to
userspace") before, so it was also forgotten.

Split off and export the Zorro definitions used by bootstraps.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/Documentation/zorro.txt b/Documentation/zorro.txt
index d176704..90a64d5 100644
--- a/Documentation/zorro.txt
+++ b/Documentation/zorro.txt
@@ -95,8 +95,9 @@ The treatment of these regions depends on the type of Zorro space:
 -------------
 
 linux/include/linux/zorro.h
+linux/include/uapi/linux/zorro.h
+linux/include/uapi/linux/zorro_ids.h
 linux/arch/m68k/include/asm/zorro.h
-linux/include/linux/zorro_ids.h
 linux/drivers/zorro
 /proc/bus/zorro
 
diff --git a/include/linux/zorro.h b/include/linux/zorro.h
index 661cbd2..63fbba0 100644
--- a/include/linux/zorro.h
+++ b/include/linux/zorro.h
@@ -11,107 +11,10 @@
 #ifndef _LINUX_ZORRO_H
 #define _LINUX_ZORRO_H
 
-#include <linux/device.h>
-
-
-    /*
-     *  Each Zorro board has a 32-bit ID of the form
-     *
-     *      mmmmmmmmmmmmmmmmppppppppeeeeeeee
-     *
-     *  with
-     *
-     *      mmmmmmmmmmmmmmmm	16-bit Manufacturer ID (assigned by CBM (sigh))
-     *      pppppppp		8-bit Product ID (assigned by manufacturer)
-     *      eeeeeeee		8-bit Extended Product ID (currently only used
-     *				for some GVP boards)
-     */
-
-
-#define ZORRO_MANUF(id)		((id) >> 16)
-#define ZORRO_PROD(id)		(((id) >> 8) & 0xff)
-#define ZORRO_EPC(id)		((id) & 0xff)
-
-#define ZORRO_ID(manuf, prod, epc) \
-    ((ZORRO_MANUF_##manuf << 16) | ((prod) << 8) | (epc))
-
-typedef __u32 zorro_id;
 
+#include <uapi/linux/zorro.h>
 
-/* Include the ID list */
-#include <linux/zorro_ids.h>
-
-
-    /*
-     *  GVP identifies most of its products through the 'extended product code'
-     *  (epc). The epc has to be ANDed with the GVP_PRODMASK before the
-     *  identification.
-     */
-
-#define GVP_PRODMASK			(0xf8)
-#define GVP_SCSICLKMASK			(0x01)
-
-enum GVP_flags {
-    GVP_IO		= 0x01,
-    GVP_ACCEL		= 0x02,
-    GVP_SCSI		= 0x04,
-    GVP_24BITDMA	= 0x08,
-    GVP_25BITDMA	= 0x10,
-    GVP_NOBANK		= 0x20,
-    GVP_14MHZ		= 0x40,
-};
-
-
-struct Node {
-    struct  Node *ln_Succ;	/* Pointer to next (successor) */
-    struct  Node *ln_Pred;	/* Pointer to previous (predecessor) */
-    __u8    ln_Type;
-    __s8    ln_Pri;		/* Priority, for sorting */
-    __s8    *ln_Name;		/* ID string, null terminated */
-} __attribute__ ((packed));
-
-struct ExpansionRom {
-    /* -First 16 bytes of the expansion ROM */
-    __u8  er_Type;		/* Board type, size and flags */
-    __u8  er_Product;		/* Product number, assigned by manufacturer */
-    __u8  er_Flags;		/* Flags */
-    __u8  er_Reserved03;	/* Must be zero ($ff inverted) */
-    __u16 er_Manufacturer;	/* Unique ID, ASSIGNED BY COMMODORE-AMIGA! */
-    __u32 er_SerialNumber;	/* Available for use by manufacturer */
-    __u16 er_InitDiagVec;	/* Offset to optional "DiagArea" structure */
-    __u8  er_Reserved0c;
-    __u8  er_Reserved0d;
-    __u8  er_Reserved0e;
-    __u8  er_Reserved0f;
-} __attribute__ ((packed));
-
-/* er_Type board type bits */
-#define ERT_TYPEMASK	0xc0
-#define ERT_ZORROII	0xc0
-#define ERT_ZORROIII	0x80
-
-/* other bits defined in er_Type */
-#define ERTB_MEMLIST	5		/* Link RAM into free memory list */
-#define ERTF_MEMLIST	(1<<5)
-
-struct ConfigDev {
-    struct Node		cd_Node;
-    __u8		cd_Flags;	/* (read/write) */
-    __u8		cd_Pad;		/* reserved */
-    struct ExpansionRom cd_Rom;		/* copy of board's expansion ROM */
-    void		*cd_BoardAddr;	/* where in memory the board was placed */
-    __u32		cd_BoardSize;	/* size of board in bytes */
-    __u16		cd_SlotAddr;	/* which slot number (PRIVATE) */
-    __u16		cd_SlotSize;	/* number of slots (PRIVATE) */
-    void		*cd_Driver;	/* pointer to node of driver */
-    struct ConfigDev	*cd_NextCD;	/* linked list of drivers to config */
-    __u32		cd_Unused[4];	/* for whatever the driver wants */
-} __attribute__ ((packed));
-
-#define ZORRO_NUM_AUTO		16
-
-#ifdef __KERNEL__
-
+#include <linux/device.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/mod_devicetable.h>
@@ -245,6 +148,4 @@ extern DECLARE_BITMAP(zorro_unused_z2ram, 128);
 #define Z2RAM_CHUNKSHIFT	(16)
 
 
-#endif /* __KERNEL__ */
-
 #endif /* _LINUX_ZORRO_H */
diff --git a/include/linux/zorro_ids.h b/include/linux/zorro_ids.h
deleted file mode 100644
index 74bc53b..0000000
--- a/include/linux/zorro_ids.h
+++ /dev/null
@@ -1,552 +0,0 @@
-/*
- *  Zorro board IDs
- *
- *  Please keep sorted.
- */
-
-
-#define ZORRO_MANUF_PACIFIC_PERIPHERALS				0x00D3
-#define  ZORRO_PROD_PACIFIC_PERIPHERALS_SE_2000_A500		ZORRO_ID(PACIFIC_PERIPHERALS, 0x00, 0)
-#define  ZORRO_PROD_PACIFIC_PERIPHERALS_SCSI			ZORRO_ID(PACIFIC_PERIPHERALS, 0x0A, 0)
-
-#define ZORRO_MANUF_MACROSYSTEMS_USA_2				0x0100
-#define  ZORRO_PROD_MACROSYSTEMS_WARP_ENGINE			ZORRO_ID(MACROSYSTEMS_USA_2, 0x13, 0)
-
-#define ZORRO_MANUF_KUPKE_1					0x00DD
-#define  ZORRO_PROD_KUPKE_GOLEM_RAM_BOX_2MB			ZORRO_ID(KUPKE_1, 0x00, 0)
-
-#define ZORRO_MANUF_MEMPHIS					0x0100
-#define  ZORRO_PROD_MEMPHIS_STORMBRINGER			ZORRO_ID(MEMPHIS, 0x00, 0)
-
-#define ZORRO_MANUF_3_STATE					0x0200
-#define  ZORRO_PROD_3_STATE_MEGAMIX_2000			ZORRO_ID(3_STATE, 0x02, 0)
-
-#define ZORRO_MANUF_COMMODORE_BRAUNSCHWEIG			0x0201
-#define  ZORRO_PROD_CBM_A2088_A2286				ZORRO_ID(COMMODORE_BRAUNSCHWEIG, 0x01, 0)
-#define  ZORRO_PROD_CBM_A2286					ZORRO_ID(COMMODORE_BRAUNSCHWEIG, 0x02, 0)
-#define  ZORRO_PROD_CBM_A4091_1					ZORRO_ID(COMMODORE_BRAUNSCHWEIG, 0x54, 0)
-#define  ZORRO_PROD_CBM_A2386SX_1				ZORRO_ID(COMMODORE_BRAUNSCHWEIG, 0x67, 0)
-
-#define ZORRO_MANUF_COMMODORE_WEST_CHESTER_1			0x0202
-#define  ZORRO_PROD_CBM_A2090A					ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x01, 0)
-#define  ZORRO_PROD_CBM_A590_A2091_1				ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x02, 0)
-#define  ZORRO_PROD_CBM_A590_A2091_2				ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x03, 0)
-#define  ZORRO_PROD_CBM_A2090B					ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x04, 0)
-#define  ZORRO_PROD_CBM_A2060					ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x09, 0)
-#define  ZORRO_PROD_CBM_A590_A2052_A2058_A2091			ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x0A, 0)
-#define  ZORRO_PROD_CBM_A560_RAM				ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x20, 0)
-#define  ZORRO_PROD_CBM_A2232_PROTOTYPE				ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x45, 0)
-#define  ZORRO_PROD_CBM_A2232					ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x46, 0)
-#define  ZORRO_PROD_CBM_A2620					ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x50, 0)
-#define  ZORRO_PROD_CBM_A2630					ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x51, 0)
-#define  ZORRO_PROD_CBM_A4091_2					ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x54, 0)
-#define  ZORRO_PROD_CBM_A2065_1					ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x5A, 0)
-#define  ZORRO_PROD_CBM_ROMULATOR				ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x60, 0)
-#define  ZORRO_PROD_CBM_A3000_TEST_FIXTURE			ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x61, 0)
-#define  ZORRO_PROD_CBM_A2386SX_2				ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x67, 0)
-#define  ZORRO_PROD_CBM_A2065_2					ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x70, 0)
-
-#define ZORRO_MANUF_COMMODORE_WEST_CHESTER_2			0x0203
-#define  ZORRO_PROD_CBM_A2090A_CM				ZORRO_ID(COMMODORE_WEST_CHESTER_2, 0x03, 0)
-
-#define ZORRO_MANUF_PROGRESSIVE_PERIPHERALS_AND_SYSTEMS_2	0x02F4
-#define  ZORRO_PROD_PPS_EXP8000					ZORRO_ID(PROGRESSIVE_PERIPHERALS_AND_SYSTEMS_2, 0x02, 0)
-
-#define ZORRO_MANUF_KOLFF_COMPUTER_SUPPLIES			0x02FF
-#define  ZORRO_PROD_KCS_POWER_PC_BOARD				ZORRO_ID(KOLFF_COMPUTER_SUPPLIES, 0x00, 0)
-
-#define ZORRO_MANUF_CARDCO_1					0x03EC
-#define  ZORRO_PROD_CARDCO_KRONOS_2000_1			ZORRO_ID(CARDCO_1, 0x04, 0)
-#define  ZORRO_PROD_CARDCO_A1000_1				ZORRO_ID(CARDCO_1, 0x0C, 0)
-#define  ZORRO_PROD_CARDCO_ESCORT				ZORRO_ID(CARDCO_1, 0x0E, 0)
-#define  ZORRO_PROD_CARDCO_A2410				ZORRO_ID(CARDCO_1, 0xF5, 0)
-
-#define ZORRO_MANUF_A_SQUARED					0x03ED
-#define  ZORRO_PROD_A_SQUARED_LIVE_2000				ZORRO_ID(A_SQUARED, 0x01, 0)
-
-#define ZORRO_MANUF_COMSPEC_COMMUNICATIONS			0x03EE
-#define  ZORRO_PROD_COMSPEC_COMMUNICATIONS_AX2000		ZORRO_ID(COMSPEC_COMMUNICATIONS, 0x01, 0)
-
-#define ZORRO_MANUF_ANAKIN_RESEARCH				0x03F1
-#define  ZORRO_PROD_ANAKIN_RESEARCH_EASYL			ZORRO_ID(ANAKIN_RESEARCH, 0x01, 0)
-
-#define ZORRO_MANUF_MICROBOTICS					0x03F2
-#define  ZORRO_PROD_MICROBOTICS_STARBOARD_II			ZORRO_ID(MICROBOTICS, 0x00, 0)
-#define  ZORRO_PROD_MICROBOTICS_STARDRIVE			ZORRO_ID(MICROBOTICS, 0x02, 0)
-#define  ZORRO_PROD_MICROBOTICS_8_UP_A				ZORRO_ID(MICROBOTICS, 0x03, 0)
-#define  ZORRO_PROD_MICROBOTICS_8_UP_Z				ZORRO_ID(MICROBOTICS, 0x04, 0)
-#define  ZORRO_PROD_MICROBOTICS_DELTA_RAM			ZORRO_ID(MICROBOTICS, 0x20, 0)
-#define  ZORRO_PROD_MICROBOTICS_8_STAR_RAM			ZORRO_ID(MICROBOTICS, 0x40, 0)
-#define  ZORRO_PROD_MICROBOTICS_8_STAR				ZORRO_ID(MICROBOTICS, 0x41, 0)
-#define  ZORRO_PROD_MICROBOTICS_VXL_RAM_32			ZORRO_ID(MICROBOTICS, 0x44, 0)
-#define  ZORRO_PROD_MICROBOTICS_VXL_68030			ZORRO_ID(MICROBOTICS, 0x45, 0)
-#define  ZORRO_PROD_MICROBOTICS_DELTA				ZORRO_ID(MICROBOTICS, 0x60, 0)
-#define  ZORRO_PROD_MICROBOTICS_MBX_1200_1200Z_RAM		ZORRO_ID(MICROBOTICS, 0x81, 0)
-#define  ZORRO_PROD_MICROBOTICS_HARDFRAME_2000_1		ZORRO_ID(MICROBOTICS, 0x96, 0)
-#define  ZORRO_PROD_MICROBOTICS_HARDFRAME_2000_2		ZORRO_ID(MICROBOTICS, 0x9E, 0)
-#define  ZORRO_PROD_MICROBOTICS_MBX_1200_1200Z			ZORRO_ID(MICROBOTICS, 0xC1, 0)
-
-#define ZORRO_MANUF_ACCESS_ASSOCIATES_ALEGRA			0x03F4
-
-#define ZORRO_MANUF_EXPANSION_TECHNOLOGIES			0x03F6
-
-#define ZORRO_MANUF_ASDG					0x03FF
-#define  ZORRO_PROD_ASDG_MEMORY_1				ZORRO_ID(ASDG, 0x01, 0)
-#define  ZORRO_PROD_ASDG_MEMORY_2				ZORRO_ID(ASDG, 0x02, 0)
-#define  ZORRO_PROD_ASDG_EB920_LAN_ROVER			ZORRO_ID(ASDG, 0xFE, 0)
-#define  ZORRO_PROD_ASDG_GPIB_DUALIEEE488_TWIN_X		ZORRO_ID(ASDG, 0xFF, 0)
-
-#define ZORRO_MANUF_IMTRONICS_1					0x0404
-#define  ZORRO_PROD_IMTRONICS_HURRICANE_2800_1			ZORRO_ID(IMTRONICS_1, 0x39, 0)
-#define  ZORRO_PROD_IMTRONICS_HURRICANE_2800_2			ZORRO_ID(IMTRONICS_1, 0x57, 0)
-
-#define ZORRO_MANUF_CBM_UNIVERSITY_OF_LOWELL			0x0406
-#define  ZORRO_PROD_CBM_A2410					ZORRO_ID(CBM_UNIVERSITY_OF_LOWELL, 0x00, 0)
-
-#define ZORRO_MANUF_AMERISTAR					0x041D
-#define  ZORRO_PROD_AMERISTAR_A2065				ZORRO_ID(AMERISTAR, 0x01, 0)
-#define  ZORRO_PROD_AMERISTAR_A560				ZORRO_ID(AMERISTAR, 0x09, 0)
-#define  ZORRO_PROD_AMERISTAR_A4066				ZORRO_ID(AMERISTAR, 0x0A, 0)
-
-#define ZORRO_MANUF_SUPRA					0x0420
-#define  ZORRO_PROD_SUPRA_SUPRADRIVE_4x4			ZORRO_ID(SUPRA, 0x01, 0)
-#define  ZORRO_PROD_SUPRA_1000_RAM				ZORRO_ID(SUPRA, 0x02, 0)
-#define  ZORRO_PROD_SUPRA_2000_DMA				ZORRO_ID(SUPRA, 0x03, 0)
-#define  ZORRO_PROD_SUPRA_500					ZORRO_ID(SUPRA, 0x05, 0)
-#define  ZORRO_PROD_SUPRA_500_SCSI				ZORRO_ID(SUPRA, 0x08, 0)
-#define  ZORRO_PROD_SUPRA_500XP_2000_RAM			ZORRO_ID(SUPRA, 0x09, 0)
-#define  ZORRO_PROD_SUPRA_500RX_2000_RAM			ZORRO_ID(SUPRA, 0x0A, 0)
-#define  ZORRO_PROD_SUPRA_2400ZI				ZORRO_ID(SUPRA, 0x0B, 0)
-#define  ZORRO_PROD_SUPRA_500XP_SUPRADRIVE_WORDSYNC		ZORRO_ID(SUPRA, 0x0C, 0)
-#define  ZORRO_PROD_SUPRA_SUPRADRIVE_WORDSYNC_II		ZORRO_ID(SUPRA, 0x0D, 0)
-#define  ZORRO_PROD_SUPRA_2400ZIPLUS				ZORRO_ID(SUPRA, 0x10, 0)
-
-#define ZORRO_MANUF_COMPUTER_SYSTEMS_ASSOCIATES			0x0422
-#define  ZORRO_PROD_CSA_MAGNUM					ZORRO_ID(COMPUTER_SYSTEMS_ASSOCIATES, 0x11, 0)
-#define  ZORRO_PROD_CSA_12_GAUGE				ZORRO_ID(COMPUTER_SYSTEMS_ASSOCIATES, 0x15, 0)
-
-#define ZORRO_MANUF_MARC_MICHAEL_GROTH				0x0439
-
-#define ZORRO_MANUF_M_TECH					0x0502
-#define  ZORRO_PROD_MTEC_AT500_1				ZORRO_ID(M_TECH, 0x03, 0)
-
-#define ZORRO_MANUF_GREAT_VALLEY_PRODUCTS_1			0x06E1
-#define  ZORRO_PROD_GVP_IMPACT_SERIES_I				ZORRO_ID(GREAT_VALLEY_PRODUCTS_1, 0x08, 0)
-
-#define ZORRO_MANUF_BYTEBOX					0x07DA
-#define  ZORRO_PROD_BYTEBOX_A500				ZORRO_ID(BYTEBOX, 0x00, 0)
-
-#define ZORRO_MANUF_DKB_POWER_COMPUTING				0x07DC
-#define  ZORRO_PROD_DKB_POWER_COMPUTING_SECUREKEY		ZORRO_ID(DKB_POWER_COMPUTING, 0x09, 0)
-#define  ZORRO_PROD_DKB_POWER_COMPUTING_DKM_3128		ZORRO_ID(DKB_POWER_COMPUTING, 0x0E, 0)
-#define  ZORRO_PROD_DKB_POWER_COMPUTING_RAPID_FIRE		ZORRO_ID(DKB_POWER_COMPUTING, 0x0F, 0)
-#define  ZORRO_PROD_DKB_POWER_COMPUTING_DKM_1202		ZORRO_ID(DKB_POWER_COMPUTING, 0x10, 0)
-#define  ZORRO_PROD_DKB_POWER_COMPUTING_COBRA_VIPER_II_68EC030	ZORRO_ID(DKB_POWER_COMPUTING, 0x12, 0)
-#define  ZORRO_PROD_DKB_POWER_COMPUTING_WILDFIRE_060_1		ZORRO_ID(DKB_POWER_COMPUTING, 0x17, 0)
-#define  ZORRO_PROD_DKB_POWER_COMPUTING_WILDFIRE_060_2		ZORRO_ID(DKB_POWER_COMPUTING, 0xFF, 0)
-
-#define ZORRO_MANUF_GREAT_VALLEY_PRODUCTS_2			0x07E1
-#define  ZORRO_PROD_GVP_IMPACT_SERIES_I_4K			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x01, 0)
-#define  ZORRO_PROD_GVP_IMPACT_SERIES_I_16K_2			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x02, 0)
-#define  ZORRO_PROD_GVP_IMPACT_SERIES_I_16K_3			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x03, 0)
-#define  ZORRO_PROD_GVP_IMPACT_3001_IDE_1			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x08, 0)
-#define  ZORRO_PROD_GVP_IMPACT_3001_RAM				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x09, 0)
-#define  ZORRO_PROD_GVP_IMPACT_SERIES_II_RAM_1			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0A, 0)
-#define  ZORRO_PROD_GVP_EPC_BASE				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0)
-#define  ZORRO_PROD_GVP_GFORCE_040_1				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0x20)
-#define  ZORRO_PROD_GVP_GFORCE_040_SCSI_1			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0x30)
-#define  ZORRO_PROD_GVP_A1291					ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0x40)
-#define  ZORRO_PROD_GVP_COMBO_030_R4				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0x60)
-#define  ZORRO_PROD_GVP_COMBO_030_R4_SCSI			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0x70)
-#define  ZORRO_PROD_GVP_PHONEPAK				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0x78)
-#define  ZORRO_PROD_GVP_IO_EXTENDER				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0x98)
-#define  ZORRO_PROD_GVP_GFORCE_030				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0xa0)
-#define  ZORRO_PROD_GVP_GFORCE_030_SCSI				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0xb0)
-#define  ZORRO_PROD_GVP_A530					ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0xc0)
-#define  ZORRO_PROD_GVP_A530_SCSI				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0xd0)
-#define  ZORRO_PROD_GVP_COMBO_030_R3				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0xe0)
-#define  ZORRO_PROD_GVP_COMBO_030_R3_SCSI			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0xf0)
-#define  ZORRO_PROD_GVP_SERIES_II				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0xf8)
-#define  ZORRO_PROD_GVP_IMPACT_3001_IDE_2			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0D, 0)
-/*#define  ZORRO_PROD_GVP_A2000_030				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0D, 0)*/
-/*#define  ZORRO_PROD_GVP_GFORCE_040_SCSI_2			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0D, 0)*/
-#define  ZORRO_PROD_GVP_GFORCE_040_060				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x16, 0)
-#define  ZORRO_PROD_GVP_IMPACT_VISION_24			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x20, 0)
-#define  ZORRO_PROD_GVP_GFORCE_040_2				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0xFF, 0)
-
-#define ZORRO_MANUF_CALIFORNIA_ACCESS_SYNERGY			0x07E5
-#define  ZORRO_PROD_CALIFORNIA_ACCESS_SYNERGY_MALIBU		ZORRO_ID(CALIFORNIA_ACCESS_SYNERGY, 0x01, 0)
-
-#define ZORRO_MANUF_XETEC					0x07E6
-#define  ZORRO_PROD_XETEC_FASTCARD				ZORRO_ID(XETEC, 0x01, 0)
-#define  ZORRO_PROD_XETEC_FASTCARD_RAM				ZORRO_ID(XETEC, 0x02, 0)
-#define  ZORRO_PROD_XETEC_FASTCARD_PLUS				ZORRO_ID(XETEC, 0x03, 0)
-
-#define ZORRO_MANUF_PROGRESSIVE_PERIPHERALS_AND_SYSTEMS		0x07EA
-#define  ZORRO_PROD_PPS_MERCURY					ZORRO_ID(PROGRESSIVE_PERIPHERALS_AND_SYSTEMS, 0x00, 0)
-#define  ZORRO_PROD_PPS_A3000_68040				ZORRO_ID(PROGRESSIVE_PERIPHERALS_AND_SYSTEMS, 0x01, 0)
-#define  ZORRO_PROD_PPS_A2000_68040				ZORRO_ID(PROGRESSIVE_PERIPHERALS_AND_SYSTEMS, 0x69, 0)
-#define  ZORRO_PROD_PPS_ZEUS					ZORRO_ID(PROGRESSIVE_PERIPHERALS_AND_SYSTEMS, 0x96, 0)
-#define  ZORRO_PROD_PPS_A500_68040				ZORRO_ID(PROGRESSIVE_PERIPHERALS_AND_SYSTEMS, 0xBB, 0)
-
-#define ZORRO_MANUF_XEBEC					0x07EC
-
-#define ZORRO_MANUF_SPIRIT_TECHNOLOGY				0x07F2
-#define  ZORRO_PROD_SPIRIT_TECHNOLOGY_INSIDER_IN1000		ZORRO_ID(SPIRIT_TECHNOLOGY, 0x01, 0)
-#define  ZORRO_PROD_SPIRIT_TECHNOLOGY_INSIDER_IN500		ZORRO_ID(SPIRIT_TECHNOLOGY, 0x02, 0)
-#define  ZORRO_PROD_SPIRIT_TECHNOLOGY_SIN500			ZORRO_ID(SPIRIT_TECHNOLOGY, 0x03, 0)
-#define  ZORRO_PROD_SPIRIT_TECHNOLOGY_HDA_506			ZORRO_ID(SPIRIT_TECHNOLOGY, 0x04, 0)
-#define  ZORRO_PROD_SPIRIT_TECHNOLOGY_AX_S			ZORRO_ID(SPIRIT_TECHNOLOGY, 0x05, 0)
-#define  ZORRO_PROD_SPIRIT_TECHNOLOGY_OCTABYTE			ZORRO_ID(SPIRIT_TECHNOLOGY, 0x06, 0)
-#define  ZORRO_PROD_SPIRIT_TECHNOLOGY_INMATE			ZORRO_ID(SPIRIT_TECHNOLOGY, 0x08, 0)
-
-#define ZORRO_MANUF_SPIRIT_TECHNOLOGY_2				0x07F3
-
-#define ZORRO_MANUF_BSC_ALFADATA_1				0x07FE
-#define  ZORRO_PROD_BSC_ALF_3_1					ZORRO_ID(BSC_ALFADATA_1, 0x03, 0)
-
-#define ZORRO_MANUF_BSC_ALFADATA_2				0x0801
-#define  ZORRO_PROD_BSC_ALF_2_1					ZORRO_ID(BSC_ALFADATA_2, 0x01, 0)
-#define  ZORRO_PROD_BSC_ALF_2_2					ZORRO_ID(BSC_ALFADATA_2, 0x02, 0)
-#define  ZORRO_PROD_BSC_ALF_3_2					ZORRO_ID(BSC_ALFADATA_2, 0x03, 0)
-
-#define ZORRO_MANUF_CARDCO_2					0x0802
-#define  ZORRO_PROD_CARDCO_KRONOS_2000_2			ZORRO_ID(CARDCO_2, 0x04, 0)
-#define  ZORRO_PROD_CARDCO_A1000_2				ZORRO_ID(CARDCO_2, 0x0C, 0)
-
-#define ZORRO_MANUF_JOCHHEIM					0x0804
-#define  ZORRO_PROD_JOCHHEIM_RAM				ZORRO_ID(JOCHHEIM, 0x01, 0)
-
-#define ZORRO_MANUF_CHECKPOINT_TECHNOLOGIES			0x0807
-#define  ZORRO_PROD_CHECKPOINT_TECHNOLOGIES_SERIAL_SOLUTION	ZORRO_ID(CHECKPOINT_TECHNOLOGIES, 0x00, 0)
-
-#define ZORRO_MANUF_EDOTRONIK					0x0810
-#define  ZORRO_PROD_EDOTRONIK_IEEE_488				ZORRO_ID(EDOTRONIK, 0x01, 0)
-#define  ZORRO_PROD_EDOTRONIK_8032				ZORRO_ID(EDOTRONIK, 0x02, 0)
-#define  ZORRO_PROD_EDOTRONIK_MULTISERIAL			ZORRO_ID(EDOTRONIK, 0x03, 0)
-#define  ZORRO_PROD_EDOTRONIK_VIDEODIGITIZER			ZORRO_ID(EDOTRONIK, 0x04, 0)
-#define  ZORRO_PROD_EDOTRONIK_PARALLEL_IO			ZORRO_ID(EDOTRONIK, 0x05, 0)
-#define  ZORRO_PROD_EDOTRONIK_PIC_PROTOYPING			ZORRO_ID(EDOTRONIK, 0x06, 0)
-#define  ZORRO_PROD_EDOTRONIK_ADC				ZORRO_ID(EDOTRONIK, 0x07, 0)
-#define  ZORRO_PROD_EDOTRONIK_VME				ZORRO_ID(EDOTRONIK, 0x08, 0)
-#define  ZORRO_PROD_EDOTRONIK_DSP96000				ZORRO_ID(EDOTRONIK, 0x09, 0)
-
-#define ZORRO_MANUF_NES_INC					0x0813
-#define  ZORRO_PROD_NES_INC_RAM					ZORRO_ID(NES_INC, 0x00, 0)
-
-#define ZORRO_MANUF_ICD						0x0817
-#define  ZORRO_PROD_ICD_ADVANTAGE_2000_SCSI			ZORRO_ID(ICD, 0x01, 0)
-#define  ZORRO_PROD_ICD_ADVANTAGE_IDE				ZORRO_ID(ICD, 0x03, 0)
-#define  ZORRO_PROD_ICD_ADVANTAGE_2080_RAM			ZORRO_ID(ICD, 0x04, 0)
-
-#define ZORRO_MANUF_KUPKE_2					0x0819
-#define  ZORRO_PROD_KUPKE_OMTI					ZORRO_ID(KUPKE_2, 0x01, 0)
-#define  ZORRO_PROD_KUPKE_SCSI_II				ZORRO_ID(KUPKE_2, 0x02, 0)
-#define  ZORRO_PROD_KUPKE_GOLEM_BOX				ZORRO_ID(KUPKE_2, 0x03, 0)
-#define  ZORRO_PROD_KUPKE_030_882				ZORRO_ID(KUPKE_2, 0x04, 0)
-#define  ZORRO_PROD_KUPKE_SCSI_AT				ZORRO_ID(KUPKE_2, 0x05, 0)
-
-#define ZORRO_MANUF_GREAT_VALLEY_PRODUCTS_3			0x081D
-#define  ZORRO_PROD_GVP_A2000_RAM8				ZORRO_ID(GREAT_VALLEY_PRODUCTS_3, 0x09, 0)
-#define  ZORRO_PROD_GVP_IMPACT_SERIES_II_RAM_2			ZORRO_ID(GREAT_VALLEY_PRODUCTS_3, 0x0A, 0)
-
-#define ZORRO_MANUF_INTERWORKS_NETWORK				0x081E
-
-#define ZORRO_MANUF_HARDITAL_SYNTHESIS				0x0820
-#define  ZORRO_PROD_HARDITAL_SYNTHESIS_TQM_68030_68882		ZORRO_ID(HARDITAL_SYNTHESIS, 0x14, 0)
-
-#define ZORRO_MANUF_APPLIED_ENGINEERING				0x0828
-#define  ZORRO_PROD_APPLIED_ENGINEERING_DL2000			ZORRO_ID(APPLIED_ENGINEERING, 0x10, 0)
-#define  ZORRO_PROD_APPLIED_ENGINEERING_RAM_WORKS		ZORRO_ID(APPLIED_ENGINEERING, 0xE0, 0)
-
-#define ZORRO_MANUF_BSC_ALFADATA_3				0x082C
-#define  ZORRO_PROD_BSC_OKTAGON_2008				ZORRO_ID(BSC_ALFADATA_3, 0x05, 0)
-#define  ZORRO_PROD_BSC_TANDEM_AT_2008_508			ZORRO_ID(BSC_ALFADATA_3, 0x06, 0)
-#define  ZORRO_PROD_BSC_ALFA_RAM_1200				ZORRO_ID(BSC_ALFADATA_3, 0x07, 0)
-#define  ZORRO_PROD_BSC_OKTAGON_2008_RAM			ZORRO_ID(BSC_ALFADATA_3, 0x08, 0)
-#define  ZORRO_PROD_BSC_MULTIFACE_I				ZORRO_ID(BSC_ALFADATA_3, 0x10, 0)
-#define  ZORRO_PROD_BSC_MULTIFACE_II				ZORRO_ID(BSC_ALFADATA_3, 0x11, 0)
-#define  ZORRO_PROD_BSC_MULTIFACE_III				ZORRO_ID(BSC_ALFADATA_3, 0x12, 0)
-#define  ZORRO_PROD_BSC_FRAMEMASTER_II				ZORRO_ID(BSC_ALFADATA_3, 0x20, 0)
-#define  ZORRO_PROD_BSC_GRAFFITI_RAM				ZORRO_ID(BSC_ALFADATA_3, 0x21, 0)
-#define  ZORRO_PROD_BSC_GRAFFITI_REG				ZORRO_ID(BSC_ALFADATA_3, 0x22, 0)
-#define  ZORRO_PROD_BSC_ISDN_MASTERCARD				ZORRO_ID(BSC_ALFADATA_3, 0x40, 0)
-#define  ZORRO_PROD_BSC_ISDN_MASTERCARD_II			ZORRO_ID(BSC_ALFADATA_3, 0x41, 0)
-
-#define ZORRO_MANUF_PHOENIX					0x0835
-#define  ZORRO_PROD_PHOENIX_ST506				ZORRO_ID(PHOENIX, 0x21, 0)
-#define  ZORRO_PROD_PHOENIX_SCSI				ZORRO_ID(PHOENIX, 0x22, 0)
-#define  ZORRO_PROD_PHOENIX_RAM					ZORRO_ID(PHOENIX, 0xBE, 0)
-
-#define ZORRO_MANUF_ADVANCED_STORAGE_SYSTEMS			0x0836
-#define  ZORRO_PROD_ADVANCED_STORAGE_SYSTEMS_NEXUS		ZORRO_ID(ADVANCED_STORAGE_SYSTEMS, 0x01, 0)
-#define  ZORRO_PROD_ADVANCED_STORAGE_SYSTEMS_NEXUS_RAM		ZORRO_ID(ADVANCED_STORAGE_SYSTEMS, 0x08, 0)
-
-#define ZORRO_MANUF_IMPULSE					0x0838
-#define  ZORRO_PROD_IMPULSE_FIRECRACKER_24			ZORRO_ID(IMPULSE, 0x00, 0)
-
-#define ZORRO_MANUF_IVS						0x0840
-#define  ZORRO_PROD_IVS_GRANDSLAM_PIC_2				ZORRO_ID(IVS, 0x02, 0)
-#define  ZORRO_PROD_IVS_GRANDSLAM_PIC_1				ZORRO_ID(IVS, 0x04, 0)
-#define  ZORRO_PROD_IVS_OVERDRIVE				ZORRO_ID(IVS, 0x10, 0)
-#define  ZORRO_PROD_IVS_TRUMPCARD_CLASSIC			ZORRO_ID(IVS, 0x30, 0)
-#define  ZORRO_PROD_IVS_TRUMPCARD_PRO_GRANDSLAM			ZORRO_ID(IVS, 0x34, 0)
-#define  ZORRO_PROD_IVS_META_4					ZORRO_ID(IVS, 0x40, 0)
-#define  ZORRO_PROD_IVS_WAVETOOLS				ZORRO_ID(IVS, 0xBF, 0)
-#define  ZORRO_PROD_IVS_VECTOR_1				ZORRO_ID(IVS, 0xF3, 0)
-#define  ZORRO_PROD_IVS_VECTOR_2				ZORRO_ID(IVS, 0xF4, 0)
-
-#define ZORRO_MANUF_VECTOR_1					0x0841
-#define  ZORRO_PROD_VECTOR_CONNECTION_1				ZORRO_ID(VECTOR_1, 0xE3, 0)
-
-#define ZORRO_MANUF_XPERT_PRODEV				0x0845
-#define  ZORRO_PROD_XPERT_PRODEV_VISIONA_RAM			ZORRO_ID(XPERT_PRODEV, 0x01, 0)
-#define  ZORRO_PROD_XPERT_PRODEV_VISIONA_REG			ZORRO_ID(XPERT_PRODEV, 0x02, 0)
-#define  ZORRO_PROD_XPERT_PRODEV_MERLIN_RAM			ZORRO_ID(XPERT_PRODEV, 0x03, 0)
-#define  ZORRO_PROD_XPERT_PRODEV_MERLIN_REG_1			ZORRO_ID(XPERT_PRODEV, 0x04, 0)
-#define  ZORRO_PROD_XPERT_PRODEV_MERLIN_REG_2			ZORRO_ID(XPERT_PRODEV, 0xC9, 0)
-
-#define ZORRO_MANUF_HYDRA_SYSTEMS				0x0849
-#define  ZORRO_PROD_HYDRA_SYSTEMS_AMIGANET			ZORRO_ID(HYDRA_SYSTEMS, 0x01, 0)
-
-#define ZORRO_MANUF_SUNRIZE_INDUSTRIES				0x084F
-#define  ZORRO_PROD_SUNRIZE_INDUSTRIES_AD1012			ZORRO_ID(SUNRIZE_INDUSTRIES, 0x01, 0)
-#define  ZORRO_PROD_SUNRIZE_INDUSTRIES_AD516			ZORRO_ID(SUNRIZE_INDUSTRIES, 0x02, 0)
-#define  ZORRO_PROD_SUNRIZE_INDUSTRIES_DD512			ZORRO_ID(SUNRIZE_INDUSTRIES, 0x03, 0)
-
-#define ZORRO_MANUF_TRICERATOPS					0x0850
-#define  ZORRO_PROD_TRICERATOPS_MULTI_IO			ZORRO_ID(TRICERATOPS, 0x01, 0)
-
-#define ZORRO_MANUF_APPLIED_MAGIC				0x0851
-#define  ZORRO_PROD_APPLIED_MAGIC_DMI_RESOLVER			ZORRO_ID(APPLIED_MAGIC, 0x01, 0)
-#define  ZORRO_PROD_APPLIED_MAGIC_DIGITAL_BROADCASTER		ZORRO_ID(APPLIED_MAGIC, 0x06, 0)
-
-#define ZORRO_MANUF_GFX_BASE					0x085E
-#define  ZORRO_PROD_GFX_BASE_GDA_1_VRAM				ZORRO_ID(GFX_BASE, 0x00, 0)
-#define  ZORRO_PROD_GFX_BASE_GDA_1				ZORRO_ID(GFX_BASE, 0x01, 0)
-
-#define ZORRO_MANUF_ROCTEC					0x0860
-#define  ZORRO_PROD_ROCTEC_RH_800C				ZORRO_ID(ROCTEC, 0x01, 0)
-#define  ZORRO_PROD_ROCTEC_RH_800C_RAM				ZORRO_ID(ROCTEC, 0x01, 0)
-
-#define ZORRO_MANUF_KATO					0x0861
-#define  ZORRO_PROD_KATO_MELODY					ZORRO_ID(KATO, 0x80, 0)
-/* ID clash!! */
-#define ZORRO_MANUF_HELFRICH_1					0x0861
-#define  ZORRO_PROD_HELFRICH_RAINBOW_II				ZORRO_ID(HELFRICH_1, 0x20, 0)
-#define  ZORRO_PROD_HELFRICH_RAINBOW_III			ZORRO_ID(HELFRICH_1, 0x21, 0)
-
-#define ZORRO_MANUF_ATLANTIS					0x0862
-
-#define ZORRO_MANUF_PROTAR					0x0864
-
-#define ZORRO_MANUF_ACS						0x0865
-
-#define ZORRO_MANUF_SOFTWARE_RESULTS_ENTERPRISES		0x0866
-#define  ZORRO_PROD_SOFTWARE_RESULTS_ENTERPRISES_GOLDEN_GATE_2_BUS_PLUS	ZORRO_ID(SOFTWARE_RESULTS_ENTERPRISES, 0x01, 0)
-
-#define ZORRO_MANUF_MASOBOSHI					0x086D
-#define  ZORRO_PROD_MASOBOSHI_MASTER_CARD_SC201			ZORRO_ID(MASOBOSHI, 0x03, 0)
-#define  ZORRO_PROD_MASOBOSHI_MASTER_CARD_MC702			ZORRO_ID(MASOBOSHI, 0x04, 0)
-#define  ZORRO_PROD_MASOBOSHI_MVD_819				ZORRO_ID(MASOBOSHI, 0x07, 0)
-
-#define ZORRO_MANUF_MAINHATTAN_DATA				0x086F
-#define  ZORRO_PROD_MAINHATTAN_DATA_IDE				ZORRO_ID(MAINHATTAN_DATA, 0x01, 0)
-
-#define ZORRO_MANUF_VILLAGE_TRONIC				0x0877
-#define  ZORRO_PROD_VILLAGE_TRONIC_DOMINO_RAM			ZORRO_ID(VILLAGE_TRONIC, 0x01, 0)
-#define  ZORRO_PROD_VILLAGE_TRONIC_DOMINO_REG			ZORRO_ID(VILLAGE_TRONIC, 0x02, 0)
-#define  ZORRO_PROD_VILLAGE_TRONIC_DOMINO_16M_PROTOTYPE		ZORRO_ID(VILLAGE_TRONIC, 0x03, 0)
-#define  ZORRO_PROD_VILLAGE_TRONIC_PICASSO_II_II_PLUS_RAM	ZORRO_ID(VILLAGE_TRONIC, 0x0B, 0)
-#define  ZORRO_PROD_VILLAGE_TRONIC_PICASSO_II_II_PLUS_REG	ZORRO_ID(VILLAGE_TRONIC, 0x0C, 0)
-#define  ZORRO_PROD_VILLAGE_TRONIC_PICASSO_II_II_PLUS_SEGMENTED_MODE	ZORRO_ID(VILLAGE_TRONIC, 0x0D, 0)
-#define  ZORRO_PROD_VILLAGE_TRONIC_PICASSO_IV_Z2_RAM1		ZORRO_ID(VILLAGE_TRONIC, 0x15, 0)
-#define  ZORRO_PROD_VILLAGE_TRONIC_PICASSO_IV_Z2_RAM2		ZORRO_ID(VILLAGE_TRONIC, 0x16, 0)
-#define  ZORRO_PROD_VILLAGE_TRONIC_PICASSO_IV_Z2_REG		ZORRO_ID(VILLAGE_TRONIC, 0x17, 0)
-#define  ZORRO_PROD_VILLAGE_TRONIC_PICASSO_IV_Z3		ZORRO_ID(VILLAGE_TRONIC, 0x18, 0)
-#define  ZORRO_PROD_VILLAGE_TRONIC_ARIADNE			ZORRO_ID(VILLAGE_TRONIC, 0xC9, 0)
-#define  ZORRO_PROD_VILLAGE_TRONIC_ARIADNE2			ZORRO_ID(VILLAGE_TRONIC, 0xCA, 0)
-
-#define ZORRO_MANUF_UTILITIES_UNLIMITED				0x087B
-#define  ZORRO_PROD_UTILITIES_UNLIMITED_EMPLANT_DELUXE		ZORRO_ID(UTILITIES_UNLIMITED, 0x15, 0)
-#define  ZORRO_PROD_UTILITIES_UNLIMITED_EMPLANT_DELUXE2		ZORRO_ID(UTILITIES_UNLIMITED, 0x20, 0)
-
-#define ZORRO_MANUF_AMITRIX					0x0880
-#define  ZORRO_PROD_AMITRIX_MULTI_IO				ZORRO_ID(AMITRIX, 0x01, 0)
-#define  ZORRO_PROD_AMITRIX_CD_RAM				ZORRO_ID(AMITRIX, 0x02, 0)
-
-#define ZORRO_MANUF_ARMAX					0x0885
-#define  ZORRO_PROD_ARMAX_OMNIBUS				ZORRO_ID(ARMAX, 0x00, 0)
-
-#define ZORRO_MANUF_ZEUS					0x088D
-#define  ZORRO_PROD_ZEUS_SPIDER					ZORRO_ID(ZEUS, 0x04, 0)
-
-#define ZORRO_MANUF_NEWTEK					0x088F
-#define  ZORRO_PROD_NEWTEK_VIDEOTOASTER				ZORRO_ID(NEWTEK, 0x00, 0)
-
-#define ZORRO_MANUF_M_TECH_GERMANY				0x0890
-#define  ZORRO_PROD_MTEC_AT500_2				ZORRO_ID(M_TECH_GERMANY, 0x01, 0)
-#define  ZORRO_PROD_MTEC_68030					ZORRO_ID(M_TECH_GERMANY, 0x03, 0)
-#define  ZORRO_PROD_MTEC_68020I					ZORRO_ID(M_TECH_GERMANY, 0x06, 0)
-#define  ZORRO_PROD_MTEC_A1200_T68030_RTC			ZORRO_ID(M_TECH_GERMANY, 0x20, 0)
-#define  ZORRO_PROD_MTEC_VIPER_MK_V_E_MATRIX_530		ZORRO_ID(M_TECH_GERMANY, 0x21, 0)
-#define  ZORRO_PROD_MTEC_8_MB_RAM				ZORRO_ID(M_TECH_GERMANY, 0x22, 0)
-#define  ZORRO_PROD_MTEC_VIPER_MK_V_E_MATRIX_530_SCSI_IDE	ZORRO_ID(M_TECH_GERMANY, 0x24, 0)
-
-#define ZORRO_MANUF_GREAT_VALLEY_PRODUCTS_4			0x0891
-#define  ZORRO_PROD_GVP_EGS_28_24_SPECTRUM_RAM			ZORRO_ID(GREAT_VALLEY_PRODUCTS_4, 0x01, 0)
-#define  ZORRO_PROD_GVP_EGS_28_24_SPECTRUM_REG			ZORRO_ID(GREAT_VALLEY_PRODUCTS_4, 0x02, 0)
-
-#define ZORRO_MANUF_APOLLO_1					0x0892
-#define  ZORRO_PROD_APOLLO_A1200				ZORRO_ID(APOLLO_1, 0x01, 0)
-
-#define ZORRO_MANUF_HELFRICH_2					0x0893
-#define  ZORRO_PROD_HELFRICH_PICCOLO_RAM			ZORRO_ID(HELFRICH_2, 0x05, 0)
-#define  ZORRO_PROD_HELFRICH_PICCOLO_REG			ZORRO_ID(HELFRICH_2, 0x06, 0)
-#define  ZORRO_PROD_HELFRICH_PEGGY_PLUS_MPEG			ZORRO_ID(HELFRICH_2, 0x07, 0)
-#define  ZORRO_PROD_HELFRICH_VIDEOCRUNCHER			ZORRO_ID(HELFRICH_2, 0x08, 0)
-#define  ZORRO_PROD_HELFRICH_SD64_RAM				ZORRO_ID(HELFRICH_2, 0x0A, 0)
-#define  ZORRO_PROD_HELFRICH_SD64_REG				ZORRO_ID(HELFRICH_2, 0x0B, 0)
-
-#define ZORRO_MANUF_MACROSYSTEMS_USA				0x089B
-#define  ZORRO_PROD_MACROSYSTEMS_WARP_ENGINE_40xx		ZORRO_ID(MACROSYSTEMS_USA, 0x13, 0)
-
-#define ZORRO_MANUF_ELBOX_COMPUTER				0x089E
-#define  ZORRO_PROD_ELBOX_COMPUTER_1200_4			ZORRO_ID(ELBOX_COMPUTER, 0x06, 0)
-
-#define ZORRO_MANUF_HARMS_PROFESSIONAL				0x0A00
-#define  ZORRO_PROD_HARMS_PROFESSIONAL_030_PLUS			ZORRO_ID(HARMS_PROFESSIONAL, 0x10, 0)
-#define  ZORRO_PROD_HARMS_PROFESSIONAL_3500			ZORRO_ID(HARMS_PROFESSIONAL, 0xD0, 0)
-
-#define ZORRO_MANUF_MICRONIK					0x0A50
-#define  ZORRO_PROD_MICRONIK_RCA_120				ZORRO_ID(MICRONIK, 0x0A, 0)
-
-#define ZORRO_MANUF_MICRONIK2					0x0F0F
-#define  ZORRO_PROD_MICRONIK2_Z3I				ZORRO_ID(MICRONIK2, 0x01, 0)
-
-#define ZORRO_MANUF_MEGAMICRO					0x1000
-#define  ZORRO_PROD_MEGAMICRO_SCRAM_500				ZORRO_ID(MEGAMICRO, 0x03, 0)
-#define  ZORRO_PROD_MEGAMICRO_SCRAM_500_RAM			ZORRO_ID(MEGAMICRO, 0x04, 0)
-
-#define ZORRO_MANUF_IMTRONICS_2					0x1028
-#define  ZORRO_PROD_IMTRONICS_HURRICANE_2800_3			ZORRO_ID(IMTRONICS_2, 0x39, 0)
-#define  ZORRO_PROD_IMTRONICS_HURRICANE_2800_4			ZORRO_ID(IMTRONICS_2, 0x57, 0)
-
-/* unofficial ID */
-#define ZORRO_MANUF_INDIVIDUAL_COMPUTERS			0x1212
-#define  ZORRO_PROD_INDIVIDUAL_COMPUTERS_BUDDHA			ZORRO_ID(INDIVIDUAL_COMPUTERS, 0x00, 0)
-#define  ZORRO_PROD_INDIVIDUAL_COMPUTERS_X_SURF			ZORRO_ID(INDIVIDUAL_COMPUTERS, 0x17, 0)
-#define  ZORRO_PROD_INDIVIDUAL_COMPUTERS_CATWEASEL		ZORRO_ID(INDIVIDUAL_COMPUTERS, 0x2A, 0)
-
-#define ZORRO_MANUF_KUPKE_3					0x1248
-#define  ZORRO_PROD_KUPKE_GOLEM_HD_3000				ZORRO_ID(KUPKE_3, 0x01, 0)
-
-#define ZORRO_MANUF_ITH						0x1388
-#define  ZORRO_PROD_ITH_ISDN_MASTER_II				ZORRO_ID(ITH, 0x01, 0)
-
-#define ZORRO_MANUF_VMC						0x1389
-#define  ZORRO_PROD_VMC_ISDN_BLASTER_Z2				ZORRO_ID(VMC, 0x01, 0)
-#define  ZORRO_PROD_VMC_HYPERCOM_4				ZORRO_ID(VMC, 0x02, 0)
-
-#define ZORRO_MANUF_INFORMATION					0x157C
-#define  ZORRO_PROD_INFORMATION_ISDN_ENGINE_I			ZORRO_ID(INFORMATION, 0x64, 0)
-
-#define ZORRO_MANUF_VORTEX					0x2017
-#define  ZORRO_PROD_VORTEX_GOLDEN_GATE_80386SX			ZORRO_ID(VORTEX, 0x07, 0)
-#define  ZORRO_PROD_VORTEX_GOLDEN_GATE_RAM			ZORRO_ID(VORTEX, 0x08, 0)
-#define  ZORRO_PROD_VORTEX_GOLDEN_GATE_80486			ZORRO_ID(VORTEX, 0x09, 0)
-
-#define ZORRO_MANUF_EXPANSION_SYSTEMS				0x2062
-#define  ZORRO_PROD_EXPANSION_SYSTEMS_DATAFLYER_4000SX		ZORRO_ID(EXPANSION_SYSTEMS, 0x01, 0)
-#define  ZORRO_PROD_EXPANSION_SYSTEMS_DATAFLYER_4000SX_RAM	ZORRO_ID(EXPANSION_SYSTEMS, 0x02, 0)
-
-#define ZORRO_MANUF_READYSOFT					0x2100
-#define  ZORRO_PROD_READYSOFT_AMAX_II_IV			ZORRO_ID(READYSOFT, 0x01, 0)
-
-#define ZORRO_MANUF_PHASE5					0x2140
-#define  ZORRO_PROD_PHASE5_BLIZZARD_RAM				ZORRO_ID(PHASE5, 0x01, 0)
-#define  ZORRO_PROD_PHASE5_BLIZZARD				ZORRO_ID(PHASE5, 0x02, 0)
-#define  ZORRO_PROD_PHASE5_BLIZZARD_1220_IV			ZORRO_ID(PHASE5, 0x06, 0)
-#define  ZORRO_PROD_PHASE5_FASTLANE_Z3_RAM			ZORRO_ID(PHASE5, 0x0A, 0)
-#define  ZORRO_PROD_PHASE5_BLIZZARD_1230_II_FASTLANE_Z3_CYBERSCSI_CYBERSTORM060	ZORRO_ID(PHASE5, 0x0B, 0)
-#define  ZORRO_PROD_PHASE5_BLIZZARD_1220_CYBERSTORM		ZORRO_ID(PHASE5, 0x0C, 0)
-#define  ZORRO_PROD_PHASE5_BLIZZARD_1230			ZORRO_ID(PHASE5, 0x0D, 0)
-#define  ZORRO_PROD_PHASE5_BLIZZARD_1230_IV_1260		ZORRO_ID(PHASE5, 0x11, 0)
-#define  ZORRO_PROD_PHASE5_BLIZZARD_2060			ZORRO_ID(PHASE5, 0x18, 0)
-#define  ZORRO_PROD_PHASE5_CYBERSTORM_MK_II			ZORRO_ID(PHASE5, 0x19, 0)
-#define  ZORRO_PROD_PHASE5_CYBERVISION64			ZORRO_ID(PHASE5, 0x22, 0)
-#define  ZORRO_PROD_PHASE5_CYBERVISION64_3D_PROTOTYPE		ZORRO_ID(PHASE5, 0x32, 0)
-#define  ZORRO_PROD_PHASE5_CYBERVISION64_3D			ZORRO_ID(PHASE5, 0x43, 0)
-#define  ZORRO_PROD_PHASE5_CYBERSTORM_MK_III			ZORRO_ID(PHASE5, 0x64, 0)
-#define  ZORRO_PROD_PHASE5_BLIZZARD_603E_PLUS			ZORRO_ID(PHASE5, 0x6e, 0)
-
-#define ZORRO_MANUF_DPS						0x2169
-#define  ZORRO_PROD_DPS_PERSONAL_ANIMATION_RECORDER		ZORRO_ID(DPS, 0x01, 0)
-
-#define ZORRO_MANUF_APOLLO_2					0x2200
-#define  ZORRO_PROD_APOLLO_A620_68020_1				ZORRO_ID(APOLLO_2, 0x00, 0)
-#define  ZORRO_PROD_APOLLO_A620_68020_2				ZORRO_ID(APOLLO_2, 0x01, 0)
-
-#define ZORRO_MANUF_APOLLO_3					0x2222
-#define  ZORRO_PROD_APOLLO_AT_APOLLO				ZORRO_ID(APOLLO_3, 0x22, 0)
-#define  ZORRO_PROD_APOLLO_1230_1240_1260_2030_4040_4060	ZORRO_ID(APOLLO_3, 0x23, 0)
-
-#define ZORRO_MANUF_PETSOFF_LP					0x38A5
-#define  ZORRO_PROD_PETSOFF_LP_DELFINA				ZORRO_ID(PETSOFF_LP, 0x00, 0)
-#define  ZORRO_PROD_PETSOFF_LP_DELFINA_LITE			ZORRO_ID(PETSOFF_LP, 0x01, 0)
-
-#define ZORRO_MANUF_UWE_GERLACH					0x3FF7
-#define  ZORRO_PROD_UWE_GERLACH_RAM_ROM				ZORRO_ID(UWE_GERLACH, 0xd4, 0)
-
-#define ZORRO_MANUF_ACT						0x4231
-#define  ZORRO_PROD_ACT_PRELUDE					ZORRO_ID(ACT, 0x01, 0)
-
-#define ZORRO_MANUF_MACROSYSTEMS_GERMANY			0x4754
-#define  ZORRO_PROD_MACROSYSTEMS_MAESTRO			ZORRO_ID(MACROSYSTEMS_GERMANY, 0x03, 0)
-#define  ZORRO_PROD_MACROSYSTEMS_VLAB				ZORRO_ID(MACROSYSTEMS_GERMANY, 0x04, 0)
-#define  ZORRO_PROD_MACROSYSTEMS_MAESTRO_PRO			ZORRO_ID(MACROSYSTEMS_GERMANY, 0x05, 0)
-#define  ZORRO_PROD_MACROSYSTEMS_RETINA				ZORRO_ID(MACROSYSTEMS_GERMANY, 0x06, 0)
-#define  ZORRO_PROD_MACROSYSTEMS_MULTI_EVOLUTION		ZORRO_ID(MACROSYSTEMS_GERMANY, 0x08, 0)
-#define  ZORRO_PROD_MACROSYSTEMS_TOCCATA			ZORRO_ID(MACROSYSTEMS_GERMANY, 0x0C, 0)
-#define  ZORRO_PROD_MACROSYSTEMS_RETINA_Z3			ZORRO_ID(MACROSYSTEMS_GERMANY, 0x10, 0)
-#define  ZORRO_PROD_MACROSYSTEMS_VLAB_MOTION			ZORRO_ID(MACROSYSTEMS_GERMANY, 0x12, 0)
-#define  ZORRO_PROD_MACROSYSTEMS_ALTAIS				ZORRO_ID(MACROSYSTEMS_GERMANY, 0x13, 0)
-#define  ZORRO_PROD_MACROSYSTEMS_FALCON_040			ZORRO_ID(MACROSYSTEMS_GERMANY, 0xFD, 0)
-
-#define ZORRO_MANUF_COMBITEC					0x6766
-
-#define ZORRO_MANUF_SKI_PERIPHERALS				0x8000
-#define  ZORRO_PROD_SKI_PERIPHERALS_MAST_FIREBALL		ZORRO_ID(SKI_PERIPHERALS, 0x08, 0)
-#define  ZORRO_PROD_SKI_PERIPHERALS_SCSI_DUAL_SERIAL		ZORRO_ID(SKI_PERIPHERALS, 0x80, 0)
-
-#define ZORRO_MANUF_REIS_WARE_2					0xA9AD
-#define  ZORRO_PROD_REIS_WARE_SCAN_KING				ZORRO_ID(REIS_WARE_2, 0x11, 0)
-
-#define ZORRO_MANUF_CAMERON					0xAA01
-#define  ZORRO_PROD_CAMERON_PERSONAL_A4				ZORRO_ID(CAMERON, 0x10, 0)
-
-#define ZORRO_MANUF_REIS_WARE					0xAA11
-#define  ZORRO_PROD_REIS_WARE_HANDYSCANNER			ZORRO_ID(REIS_WARE, 0x11, 0)
-
-#define ZORRO_MANUF_PHOENIX_2					0xB5A8
-#define  ZORRO_PROD_PHOENIX_ST506_2				ZORRO_ID(PHOENIX_2, 0x21, 0)
-#define  ZORRO_PROD_PHOENIX_SCSI_2				ZORRO_ID(PHOENIX_2, 0x22, 0)
-#define  ZORRO_PROD_PHOENIX_RAM_2				ZORRO_ID(PHOENIX_2, 0xBE, 0)
-
-#define ZORRO_MANUF_COMBITEC_2					0xC008
-#define  ZORRO_PROD_COMBITEC_HD					ZORRO_ID(COMBITEC_2, 0x2A, 0)
-#define  ZORRO_PROD_COMBITEC_SRAM				ZORRO_ID(COMBITEC_2, 0x2B, 0)
-
-
-    /*
-     *  Test and illegal Manufacturer IDs.
-     */
-
-#define ZORRO_MANUF_HACKER					0x07DB
-#define  ZORRO_PROD_GENERAL_PROTOTYPE				ZORRO_ID(HACKER, 0x00, 0)
-#define  ZORRO_PROD_HACKER_SCSI					ZORRO_ID(HACKER, 0x01, 0)
-#define  ZORRO_PROD_RESOURCE_MANAGEMENT_FORCE_QUICKNET_QN2000	ZORRO_ID(HACKER, 0x02, 0)
-#define  ZORRO_PROD_VECTOR_CONNECTION_2				ZORRO_ID(HACKER, 0xE0, 0)
-#define  ZORRO_PROD_VECTOR_CONNECTION_3				ZORRO_ID(HACKER, 0xE1, 0)
-#define  ZORRO_PROD_VECTOR_CONNECTION_4				ZORRO_ID(HACKER, 0xE2, 0)
-#define  ZORRO_PROD_VECTOR_CONNECTION_5				ZORRO_ID(HACKER, 0xE3, 0)
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 33d2b8f..3ce25b5 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -426,3 +426,5 @@ header-y += x25.h
 header-y += xattr.h
 header-y += xfrm.h
 header-y += hw_breakpoint.h
+header-y += zorro.h
+header-y += zorro_ids.h
diff --git a/include/uapi/linux/zorro.h b/include/uapi/linux/zorro.h
new file mode 100644
index 0000000..36a033e
--- /dev/null
+++ b/include/uapi/linux/zorro.h
@@ -0,0 +1,113 @@
+/*
+ *  linux/zorro.h -- Amiga AutoConfig (Zorro) Bus Definitions
+ *
+ *  Copyright (C) 1995--2003 Geert Uytterhoeven
+ *
+ *  This file is subject to the terms and conditions of the GNU General Public
+ *  License.  See the file COPYING in the main directory of this archive
+ *  for more details.
+ */
+
+#ifndef _UAPI_LINUX_ZORRO_H
+#define _UAPI_LINUX_ZORRO_H
+
+#include <linux/types.h>
+
+
+    /*
+     *  Each Zorro board has a 32-bit ID of the form
+     *
+     *      mmmmmmmmmmmmmmmmppppppppeeeeeeee
+     *
+     *  with
+     *
+     *      mmmmmmmmmmmmmmmm	16-bit Manufacturer ID (assigned by CBM (sigh))
+     *      pppppppp		8-bit Product ID (assigned by manufacturer)
+     *      eeeeeeee		8-bit Extended Product ID (currently only used
+     *				for some GVP boards)
+     */
+
+
+#define ZORRO_MANUF(id)		((id) >> 16)
+#define ZORRO_PROD(id)		(((id) >> 8) & 0xff)
+#define ZORRO_EPC(id)		((id) & 0xff)
+
+#define ZORRO_ID(manuf, prod, epc) \
+	((ZORRO_MANUF_##manuf << 16) | ((prod) << 8) | (epc))
+
+typedef __u32 zorro_id;
+
+
+/* Include the ID list */
+#include <linux/zorro_ids.h>
+
+
+    /*
+     *  GVP identifies most of its products through the 'extended product code'
+     *  (epc). The epc has to be ANDed with the GVP_PRODMASK before the
+     *  identification.
+     */
+
+#define GVP_PRODMASK		(0xf8)
+#define GVP_SCSICLKMASK		(0x01)
+
+enum GVP_flags {
+	GVP_IO			= 0x01,
+	GVP_ACCEL		= 0x02,
+	GVP_SCSI		= 0x04,
+	GVP_24BITDMA		= 0x08,
+	GVP_25BITDMA		= 0x10,
+	GVP_NOBANK		= 0x20,
+	GVP_14MHZ		= 0x40,
+};
+
+
+struct Node {
+	struct  Node *ln_Succ;	/* Pointer to next (successor) */
+	struct  Node *ln_Pred;	/* Pointer to previous (predecessor) */
+	__u8    ln_Type;
+	__s8    ln_Pri;		/* Priority, for sorting */
+	__s8    *ln_Name;	/* ID string, null terminated */
+} __packed;
+
+struct ExpansionRom {
+	/* -First 16 bytes of the expansion ROM */
+	__u8  er_Type;		/* Board type, size and flags */
+	__u8  er_Product;	/* Product number, assigned by manufacturer */
+	__u8  er_Flags;		/* Flags */
+	__u8  er_Reserved03;	/* Must be zero ($ff inverted) */
+	__u16 er_Manufacturer;	/* Unique ID, ASSIGNED BY COMMODORE-AMIGA! */
+	__u32 er_SerialNumber;	/* Available for use by manufacturer */
+	__u16 er_InitDiagVec;	/* Offset to optional "DiagArea" structure */
+	__u8  er_Reserved0c;
+	__u8  er_Reserved0d;
+	__u8  er_Reserved0e;
+	__u8  er_Reserved0f;
+} __packed;
+
+/* er_Type board type bits */
+#define ERT_TYPEMASK	0xc0
+#define ERT_ZORROII	0xc0
+#define ERT_ZORROIII	0x80
+
+/* other bits defined in er_Type */
+#define ERTB_MEMLIST	5		/* Link RAM into free memory list */
+#define ERTF_MEMLIST	(1<<5)
+
+struct ConfigDev {
+	struct Node	cd_Node;
+	__u8		cd_Flags;	/* (read/write) */
+	__u8		cd_Pad;		/* reserved */
+	struct ExpansionRom cd_Rom;	/* copy of board's expansion ROM */
+	void		*cd_BoardAddr;	/* where in memory the board was placed */
+	__u32		cd_BoardSize;	/* size of board in bytes */
+	__u16		cd_SlotAddr;	/* which slot number (PRIVATE) */
+	__u16		cd_SlotSize;	/* number of slots (PRIVATE) */
+	void		*cd_Driver;	/* pointer to node of driver */
+	struct ConfigDev *cd_NextCD;	/* linked list of drivers to config */
+	__u32		cd_Unused[4];	/* for whatever the driver wants */
+} __packed;
+
+#define ZORRO_NUM_AUTO		16
+
+#endif /* _UAPI_LINUX_ZORRO_H */
diff --git a/include/uapi/linux/zorro_ids.h b/include/uapi/linux/zorro_ids.h
new file mode 100644
index 0000000..74bc53b
--- /dev/null
+++ b/include/uapi/linux/zorro_ids.h
@@ -0,0 +1,552 @@
+/*
+ *  Zorro board IDs
+ *
+ *  Please keep sorted.
+ */
+
+
+#define ZORRO_MANUF_PACIFIC_PERIPHERALS				0x00D3
+#define  ZORRO_PROD_PACIFIC_PERIPHERALS_SE_2000_A500		ZORRO_ID(PACIFIC_PERIPHERALS, 0x00, 0)
+#define  ZORRO_PROD_PACIFIC_PERIPHERALS_SCSI			ZORRO_ID(PACIFIC_PERIPHERALS, 0x0A, 0)
+
+#define ZORRO_MANUF_MACROSYSTEMS_USA_2				0x0100
+#define  ZORRO_PROD_MACROSYSTEMS_WARP_ENGINE			ZORRO_ID(MACROSYSTEMS_USA_2, 0x13, 0)
+
+#define ZORRO_MANUF_KUPKE_1					0x00DD
+#define  ZORRO_PROD_KUPKE_GOLEM_RAM_BOX_2MB			ZORRO_ID(KUPKE_1, 0x00, 0)
+
+#define ZORRO_MANUF_MEMPHIS					0x0100
+#define  ZORRO_PROD_MEMPHIS_STORMBRINGER			ZORRO_ID(MEMPHIS, 0x00, 0)
+
+#define ZORRO_MANUF_3_STATE					0x0200
+#define  ZORRO_PROD_3_STATE_MEGAMIX_2000			ZORRO_ID(3_STATE, 0x02, 0)
+
+#define ZORRO_MANUF_COMMODORE_BRAUNSCHWEIG			0x0201
+#define  ZORRO_PROD_CBM_A2088_A2286				ZORRO_ID(COMMODORE_BRAUNSCHWEIG, 0x01, 0)
+#define  ZORRO_PROD_CBM_A2286					ZORRO_ID(COMMODORE_BRAUNSCHWEIG, 0x02, 0)
+#define  ZORRO_PROD_CBM_A4091_1					ZORRO_ID(COMMODORE_BRAUNSCHWEIG, 0x54, 0)
+#define  ZORRO_PROD_CBM_A2386SX_1				ZORRO_ID(COMMODORE_BRAUNSCHWEIG, 0x67, 0)
+
+#define ZORRO_MANUF_COMMODORE_WEST_CHESTER_1			0x0202
+#define  ZORRO_PROD_CBM_A2090A					ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x01, 0)
+#define  ZORRO_PROD_CBM_A590_A2091_1				ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x02, 0)
+#define  ZORRO_PROD_CBM_A590_A2091_2				ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x03, 0)
+#define  ZORRO_PROD_CBM_A2090B					ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x04, 0)
+#define  ZORRO_PROD_CBM_A2060					ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x09, 0)
+#define  ZORRO_PROD_CBM_A590_A2052_A2058_A2091			ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x0A, 0)
+#define  ZORRO_PROD_CBM_A560_RAM				ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x20, 0)
+#define  ZORRO_PROD_CBM_A2232_PROTOTYPE				ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x45, 0)
+#define  ZORRO_PROD_CBM_A2232					ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x46, 0)
+#define  ZORRO_PROD_CBM_A2620					ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x50, 0)
+#define  ZORRO_PROD_CBM_A2630					ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x51, 0)
+#define  ZORRO_PROD_CBM_A4091_2					ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x54, 0)
+#define  ZORRO_PROD_CBM_A2065_1					ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x5A, 0)
+#define  ZORRO_PROD_CBM_ROMULATOR				ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x60, 0)
+#define  ZORRO_PROD_CBM_A3000_TEST_FIXTURE			ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x61, 0)
+#define  ZORRO_PROD_CBM_A2386SX_2				ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x67, 0)
+#define  ZORRO_PROD_CBM_A2065_2					ZORRO_ID(COMMODORE_WEST_CHESTER_1, 0x70, 0)
+
+#define ZORRO_MANUF_COMMODORE_WEST_CHESTER_2			0x0203
+#define  ZORRO_PROD_CBM_A2090A_CM				ZORRO_ID(COMMODORE_WEST_CHESTER_2, 0x03, 0)
+
+#define ZORRO_MANUF_PROGRESSIVE_PERIPHERALS_AND_SYSTEMS_2	0x02F4
+#define  ZORRO_PROD_PPS_EXP8000					ZORRO_ID(PROGRESSIVE_PERIPHERALS_AND_SYSTEMS_2, 0x02, 0)
+
+#define ZORRO_MANUF_KOLFF_COMPUTER_SUPPLIES			0x02FF
+#define  ZORRO_PROD_KCS_POWER_PC_BOARD				ZORRO_ID(KOLFF_COMPUTER_SUPPLIES, 0x00, 0)
+
+#define ZORRO_MANUF_CARDCO_1					0x03EC
+#define  ZORRO_PROD_CARDCO_KRONOS_2000_1			ZORRO_ID(CARDCO_1, 0x04, 0)
+#define  ZORRO_PROD_CARDCO_A1000_1				ZORRO_ID(CARDCO_1, 0x0C, 0)
+#define  ZORRO_PROD_CARDCO_ESCORT				ZORRO_ID(CARDCO_1, 0x0E, 0)
+#define  ZORRO_PROD_CARDCO_A2410				ZORRO_ID(CARDCO_1, 0xF5, 0)
+
+#define ZORRO_MANUF_A_SQUARED					0x03ED
+#define  ZORRO_PROD_A_SQUARED_LIVE_2000				ZORRO_ID(A_SQUARED, 0x01, 0)
+
+#define ZORRO_MANUF_COMSPEC_COMMUNICATIONS			0x03EE
+#define  ZORRO_PROD_COMSPEC_COMMUNICATIONS_AX2000		ZORRO_ID(COMSPEC_COMMUNICATIONS, 0x01, 0)
+
+#define ZORRO_MANUF_ANAKIN_RESEARCH				0x03F1
+#define  ZORRO_PROD_ANAKIN_RESEARCH_EASYL			ZORRO_ID(ANAKIN_RESEARCH, 0x01, 0)
+
+#define ZORRO_MANUF_MICROBOTICS					0x03F2
+#define  ZORRO_PROD_MICROBOTICS_STARBOARD_II			ZORRO_ID(MICROBOTICS, 0x00, 0)
+#define  ZORRO_PROD_MICROBOTICS_STARDRIVE			ZORRO_ID(MICROBOTICS, 0x02, 0)
+#define  ZORRO_PROD_MICROBOTICS_8_UP_A				ZORRO_ID(MICROBOTICS, 0x03, 0)
+#define  ZORRO_PROD_MICROBOTICS_8_UP_Z				ZORRO_ID(MICROBOTICS, 0x04, 0)
+#define  ZORRO_PROD_MICROBOTICS_DELTA_RAM			ZORRO_ID(MICROBOTICS, 0x20, 0)
+#define  ZORRO_PROD_MICROBOTICS_8_STAR_RAM			ZORRO_ID(MICROBOTICS, 0x40, 0)
+#define  ZORRO_PROD_MICROBOTICS_8_STAR				ZORRO_ID(MICROBOTICS, 0x41, 0)
+#define  ZORRO_PROD_MICROBOTICS_VXL_RAM_32			ZORRO_ID(MICROBOTICS, 0x44, 0)
+#define  ZORRO_PROD_MICROBOTICS_VXL_68030			ZORRO_ID(MICROBOTICS, 0x45, 0)
+#define  ZORRO_PROD_MICROBOTICS_DELTA				ZORRO_ID(MICROBOTICS, 0x60, 0)
+#define  ZORRO_PROD_MICROBOTICS_MBX_1200_1200Z_RAM		ZORRO_ID(MICROBOTICS, 0x81, 0)
+#define  ZORRO_PROD_MICROBOTICS_HARDFRAME_2000_1		ZORRO_ID(MICROBOTICS, 0x96, 0)
+#define  ZORRO_PROD_MICROBOTICS_HARDFRAME_2000_2		ZORRO_ID(MICROBOTICS, 0x9E, 0)
+#define  ZORRO_PROD_MICROBOTICS_MBX_1200_1200Z			ZORRO_ID(MICROBOTICS, 0xC1, 0)
+
+#define ZORRO_MANUF_ACCESS_ASSOCIATES_ALEGRA			0x03F4
+
+#define ZORRO_MANUF_EXPANSION_TECHNOLOGIES			0x03F6
+
+#define ZORRO_MANUF_ASDG					0x03FF
+#define  ZORRO_PROD_ASDG_MEMORY_1				ZORRO_ID(ASDG, 0x01, 0)
+#define  ZORRO_PROD_ASDG_MEMORY_2				ZORRO_ID(ASDG, 0x02, 0)
+#define  ZORRO_PROD_ASDG_EB920_LAN_ROVER			ZORRO_ID(ASDG, 0xFE, 0)
+#define  ZORRO_PROD_ASDG_GPIB_DUALIEEE488_TWIN_X		ZORRO_ID(ASDG, 0xFF, 0)
+
+#define ZORRO_MANUF_IMTRONICS_1					0x0404
+#define  ZORRO_PROD_IMTRONICS_HURRICANE_2800_1			ZORRO_ID(IMTRONICS_1, 0x39, 0)
+#define  ZORRO_PROD_IMTRONICS_HURRICANE_2800_2			ZORRO_ID(IMTRONICS_1, 0x57, 0)
+
+#define ZORRO_MANUF_CBM_UNIVERSITY_OF_LOWELL			0x0406
+#define  ZORRO_PROD_CBM_A2410					ZORRO_ID(CBM_UNIVERSITY_OF_LOWELL, 0x00, 0)
+
+#define ZORRO_MANUF_AMERISTAR					0x041D
+#define  ZORRO_PROD_AMERISTAR_A2065				ZORRO_ID(AMERISTAR, 0x01, 0)
+#define  ZORRO_PROD_AMERISTAR_A560				ZORRO_ID(AMERISTAR, 0x09, 0)
+#define  ZORRO_PROD_AMERISTAR_A4066				ZORRO_ID(AMERISTAR, 0x0A, 0)
+
+#define ZORRO_MANUF_SUPRA					0x0420
+#define  ZORRO_PROD_SUPRA_SUPRADRIVE_4x4			ZORRO_ID(SUPRA, 0x01, 0)
+#define  ZORRO_PROD_SUPRA_1000_RAM				ZORRO_ID(SUPRA, 0x02, 0)
+#define  ZORRO_PROD_SUPRA_2000_DMA				ZORRO_ID(SUPRA, 0x03, 0)
+#define  ZORRO_PROD_SUPRA_500					ZORRO_ID(SUPRA, 0x05, 0)
+#define  ZORRO_PROD_SUPRA_500_SCSI				ZORRO_ID(SUPRA, 0x08, 0)
+#define  ZORRO_PROD_SUPRA_500XP_2000_RAM			ZORRO_ID(SUPRA, 0x09, 0)
+#define  ZORRO_PROD_SUPRA_500RX_2000_RAM			ZORRO_ID(SUPRA, 0x0A, 0)
+#define  ZORRO_PROD_SUPRA_2400ZI				ZORRO_ID(SUPRA, 0x0B, 0)
+#define  ZORRO_PROD_SUPRA_500XP_SUPRADRIVE_WORDSYNC		ZORRO_ID(SUPRA, 0x0C, 0)
+#define  ZORRO_PROD_SUPRA_SUPRADRIVE_WORDSYNC_II		ZORRO_ID(SUPRA, 0x0D, 0)
+#define  ZORRO_PROD_SUPRA_2400ZIPLUS				ZORRO_ID(SUPRA, 0x10, 0)
+
+#define ZORRO_MANUF_COMPUTER_SYSTEMS_ASSOCIATES			0x0422
+#define  ZORRO_PROD_CSA_MAGNUM					ZORRO_ID(COMPUTER_SYSTEMS_ASSOCIATES, 0x11, 0)
+#define  ZORRO_PROD_CSA_12_GAUGE				ZORRO_ID(COMPUTER_SYSTEMS_ASSOCIATES, 0x15, 0)
+
+#define ZORRO_MANUF_MARC_MICHAEL_GROTH				0x0439
+
+#define ZORRO_MANUF_M_TECH					0x0502
+#define  ZORRO_PROD_MTEC_AT500_1				ZORRO_ID(M_TECH, 0x03, 0)
+
+#define ZORRO_MANUF_GREAT_VALLEY_PRODUCTS_1			0x06E1
+#define  ZORRO_PROD_GVP_IMPACT_SERIES_I				ZORRO_ID(GREAT_VALLEY_PRODUCTS_1, 0x08, 0)
+
+#define ZORRO_MANUF_BYTEBOX					0x07DA
+#define  ZORRO_PROD_BYTEBOX_A500				ZORRO_ID(BYTEBOX, 0x00, 0)
+
+#define ZORRO_MANUF_DKB_POWER_COMPUTING				0x07DC
+#define  ZORRO_PROD_DKB_POWER_COMPUTING_SECUREKEY		ZORRO_ID(DKB_POWER_COMPUTING, 0x09, 0)
+#define  ZORRO_PROD_DKB_POWER_COMPUTING_DKM_3128		ZORRO_ID(DKB_POWER_COMPUTING, 0x0E, 0)
+#define  ZORRO_PROD_DKB_POWER_COMPUTING_RAPID_FIRE		ZORRO_ID(DKB_POWER_COMPUTING, 0x0F, 0)
+#define  ZORRO_PROD_DKB_POWER_COMPUTING_DKM_1202		ZORRO_ID(DKB_POWER_COMPUTING, 0x10, 0)
+#define  ZORRO_PROD_DKB_POWER_COMPUTING_COBRA_VIPER_II_68EC030	ZORRO_ID(DKB_POWER_COMPUTING, 0x12, 0)
+#define  ZORRO_PROD_DKB_POWER_COMPUTING_WILDFIRE_060_1		ZORRO_ID(DKB_POWER_COMPUTING, 0x17, 0)
+#define  ZORRO_PROD_DKB_POWER_COMPUTING_WILDFIRE_060_2		ZORRO_ID(DKB_POWER_COMPUTING, 0xFF, 0)
+
+#define ZORRO_MANUF_GREAT_VALLEY_PRODUCTS_2			0x07E1
+#define  ZORRO_PROD_GVP_IMPACT_SERIES_I_4K			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x01, 0)
+#define  ZORRO_PROD_GVP_IMPACT_SERIES_I_16K_2			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x02, 0)
+#define  ZORRO_PROD_GVP_IMPACT_SERIES_I_16K_3			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x03, 0)
+#define  ZORRO_PROD_GVP_IMPACT_3001_IDE_1			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x08, 0)
+#define  ZORRO_PROD_GVP_IMPACT_3001_RAM				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x09, 0)
+#define  ZORRO_PROD_GVP_IMPACT_SERIES_II_RAM_1			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0A, 0)
+#define  ZORRO_PROD_GVP_EPC_BASE				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0)
+#define  ZORRO_PROD_GVP_GFORCE_040_1				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0x20)
+#define  ZORRO_PROD_GVP_GFORCE_040_SCSI_1			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0x30)
+#define  ZORRO_PROD_GVP_A1291					ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0x40)
+#define  ZORRO_PROD_GVP_COMBO_030_R4				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0x60)
+#define  ZORRO_PROD_GVP_COMBO_030_R4_SCSI			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0x70)
+#define  ZORRO_PROD_GVP_PHONEPAK				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0x78)
+#define  ZORRO_PROD_GVP_IO_EXTENDER				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0x98)
+#define  ZORRO_PROD_GVP_GFORCE_030				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0xa0)
+#define  ZORRO_PROD_GVP_GFORCE_030_SCSI				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0xb0)
+#define  ZORRO_PROD_GVP_A530					ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0xc0)
+#define  ZORRO_PROD_GVP_A530_SCSI				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0xd0)
+#define  ZORRO_PROD_GVP_COMBO_030_R3				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0xe0)
+#define  ZORRO_PROD_GVP_COMBO_030_R3_SCSI			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0xf0)
+#define  ZORRO_PROD_GVP_SERIES_II				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0B, 0xf8)
+#define  ZORRO_PROD_GVP_IMPACT_3001_IDE_2			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0D, 0)
+/*#define  ZORRO_PROD_GVP_A2000_030				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0D, 0)*/
+/*#define  ZORRO_PROD_GVP_GFORCE_040_SCSI_2			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x0D, 0)*/
+#define  ZORRO_PROD_GVP_GFORCE_040_060				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x16, 0)
+#define  ZORRO_PROD_GVP_IMPACT_VISION_24			ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0x20, 0)
+#define  ZORRO_PROD_GVP_GFORCE_040_2				ZORRO_ID(GREAT_VALLEY_PRODUCTS_2, 0xFF, 0)
+
+#define ZORRO_MANUF_CALIFORNIA_ACCESS_SYNERGY			0x07E5
+#define  ZORRO_PROD_CALIFORNIA_ACCESS_SYNERGY_MALIBU		ZORRO_ID(CALIFORNIA_ACCESS_SYNERGY, 0x01, 0)
+
+#define ZORRO_MANUF_XETEC					0x07E6
+#define  ZORRO_PROD_XETEC_FASTCARD				ZORRO_ID(XETEC, 0x01, 0)
+#define  ZORRO_PROD_XETEC_FASTCARD_RAM				ZORRO_ID(XETEC, 0x02, 0)
+#define  ZORRO_PROD_XETEC_FASTCARD_PLUS				ZORRO_ID(XETEC, 0x03, 0)
+
+#define ZORRO_MANUF_PROGRESSIVE_PERIPHERALS_AND_SYSTEMS		0x07EA
+#define  ZORRO_PROD_PPS_MERCURY					ZORRO_ID(PROGRESSIVE_PERIPHERALS_AND_SYSTEMS, 0x00, 0)
+#define  ZORRO_PROD_PPS_A3000_68040				ZORRO_ID(PROGRESSIVE_PERIPHERALS_AND_SYSTEMS, 0x01, 0)
+#define  ZORRO_PROD_PPS_A2000_68040				ZORRO_ID(PROGRESSIVE_PERIPHERALS_AND_SYSTEMS, 0x69, 0)
+#define  ZORRO_PROD_PPS_ZEUS					ZORRO_ID(PROGRESSIVE_PERIPHERALS_AND_SYSTEMS, 0x96, 0)
+#define  ZORRO_PROD_PPS_A500_68040				ZORRO_ID(PROGRESSIVE_PERIPHERALS_AND_SYSTEMS, 0xBB, 0)
+
+#define ZORRO_MANUF_XEBEC					0x07EC
+
+#define ZORRO_MANUF_SPIRIT_TECHNOLOGY				0x07F2
+#define  ZORRO_PROD_SPIRIT_TECHNOLOGY_INSIDER_IN1000		ZORRO_ID(SPIRIT_TECHNOLOGY, 0x01, 0)
+#define  ZORRO_PROD_SPIRIT_TECHNOLOGY_INSIDER_IN500		ZORRO_ID(SPIRIT_TECHNOLOGY, 0x02, 0)
+#define  ZORRO_PROD_SPIRIT_TECHNOLOGY_SIN500			ZORRO_ID(SPIRIT_TECHNOLOGY, 0x03, 0)
+#define  ZORRO_PROD_SPIRIT_TECHNOLOGY_HDA_506			ZORRO_ID(SPIRIT_TECHNOLOGY, 0x04, 0)
+#define  ZORRO_PROD_SPIRIT_TECHNOLOGY_AX_S			ZORRO_ID(SPIRIT_TECHNOLOGY, 0x05, 0)
+#define  ZORRO_PROD_SPIRIT_TECHNOLOGY_OCTABYTE			ZORRO_ID(SPIRIT_TECHNOLOGY, 0x06, 0)
+#define  ZORRO_PROD_SPIRIT_TECHNOLOGY_INMATE			ZORRO_ID(SPIRIT_TECHNOLOGY, 0x08, 0)
+
+#define ZORRO_MANUF_SPIRIT_TECHNOLOGY_2				0x07F3
+
+#define ZORRO_MANUF_BSC_ALFADATA_1				0x07FE
+#define  ZORRO_PROD_BSC_ALF_3_1					ZORRO_ID(BSC_ALFADATA_1, 0x03, 0)
+
+#define ZORRO_MANUF_BSC_ALFADATA_2				0x0801
+#define  ZORRO_PROD_BSC_ALF_2_1					ZORRO_ID(BSC_ALFADATA_2, 0x01, 0)
+#define  ZORRO_PROD_BSC_ALF_2_2					ZORRO_ID(BSC_ALFADATA_2, 0x02, 0)
+#define  ZORRO_PROD_BSC_ALF_3_2					ZORRO_ID(BSC_ALFADATA_2, 0x03, 0)
+
+#define ZORRO_MANUF_CARDCO_2					0x0802
+#define  ZORRO_PROD_CARDCO_KRONOS_2000_2			ZORRO_ID(CARDCO_2, 0x04, 0)
+#define  ZORRO_PROD_CARDCO_A1000_2				ZORRO_ID(CARDCO_2, 0x0C, 0)
+
+#define ZORRO_MANUF_JOCHHEIM					0x0804
+#define  ZORRO_PROD_JOCHHEIM_RAM				ZORRO_ID(JOCHHEIM, 0x01, 0)
+
+#define ZORRO_MANUF_CHECKPOINT_TECHNOLOGIES			0x0807
+#define  ZORRO_PROD_CHECKPOINT_TECHNOLOGIES_SERIAL_SOLUTION	ZORRO_ID(CHECKPOINT_TECHNOLOGIES, 0x00, 0)
+
+#define ZORRO_MANUF_EDOTRONIK					0x0810
+#define  ZORRO_PROD_EDOTRONIK_IEEE_488				ZORRO_ID(EDOTRONIK, 0x01, 0)
+#define  ZORRO_PROD_EDOTRONIK_8032				ZORRO_ID(EDOTRONIK, 0x02, 0)
+#define  ZORRO_PROD_EDOTRONIK_MULTISERIAL			ZORRO_ID(EDOTRONIK, 0x03, 0)
+#define  ZORRO_PROD_EDOTRONIK_VIDEODIGITIZER			ZORRO_ID(EDOTRONIK, 0x04, 0)
+#define  ZORRO_PROD_EDOTRONIK_PARALLEL_IO			ZORRO_ID(EDOTRONIK, 0x05, 0)
+#define  ZORRO_PROD_EDOTRONIK_PIC_PROTOYPING			ZORRO_ID(EDOTRONIK, 0x06, 0)
+#define  ZORRO_PROD_EDOTRONIK_ADC				ZORRO_ID(EDOTRONIK, 0x07, 0)
+#define  ZORRO_PROD_EDOTRONIK_VME				ZORRO_ID(EDOTRONIK, 0x08, 0)
+#define  ZORRO_PROD_EDOTRONIK_DSP96000				ZORRO_ID(EDOTRONIK, 0x09, 0)
+
+#define ZORRO_MANUF_NES_INC					0x0813
+#define  ZORRO_PROD_NES_INC_RAM					ZORRO_ID(NES_INC, 0x00, 0)
+
+#define ZORRO_MANUF_ICD						0x0817
+#define  ZORRO_PROD_ICD_ADVANTAGE_2000_SCSI			ZORRO_ID(ICD, 0x01, 0)
+#define  ZORRO_PROD_ICD_ADVANTAGE_IDE				ZORRO_ID(ICD, 0x03, 0)
+#define  ZORRO_PROD_ICD_ADVANTAGE_2080_RAM			ZORRO_ID(ICD, 0x04, 0)
+
+#define ZORRO_MANUF_KUPKE_2					0x0819
+#define  ZORRO_PROD_KUPKE_OMTI					ZORRO_ID(KUPKE_2, 0x01, 0)
+#define  ZORRO_PROD_KUPKE_SCSI_II				ZORRO_ID(KUPKE_2, 0x02, 0)
+#define  ZORRO_PROD_KUPKE_GOLEM_BOX				ZORRO_ID(KUPKE_2, 0x03, 0)
+#define  ZORRO_PROD_KUPKE_030_882				ZORRO_ID(KUPKE_2, 0x04, 0)
+#define  ZORRO_PROD_KUPKE_SCSI_AT				ZORRO_ID(KUPKE_2, 0x05, 0)
+
+#define ZORRO_MANUF_GREAT_VALLEY_PRODUCTS_3			0x081D
+#define  ZORRO_PROD_GVP_A2000_RAM8				ZORRO_ID(GREAT_VALLEY_PRODUCTS_3, 0x09, 0)
+#define  ZORRO_PROD_GVP_IMPACT_SERIES_II_RAM_2			ZORRO_ID(GREAT_VALLEY_PRODUCTS_3, 0x0A, 0)
+
+#define ZORRO_MANUF_INTERWORKS_NETWORK				0x081E
+
+#define ZORRO_MANUF_HARDITAL_SYNTHESIS				0x0820
+#define  ZORRO_PROD_HARDITAL_SYNTHESIS_TQM_68030_68882		ZORRO_ID(HARDITAL_SYNTHESIS, 0x14, 0)
+
+#define ZORRO_MANUF_APPLIED_ENGINEERING				0x0828
+#define  ZORRO_PROD_APPLIED_ENGINEERING_DL2000			ZORRO_ID(APPLIED_ENGINEERING, 0x10, 0)
+#define  ZORRO_PROD_APPLIED_ENGINEERING_RAM_WORKS		ZORRO_ID(APPLIED_ENGINEERING, 0xE0, 0)
+
+#define ZORRO_MANUF_BSC_ALFADATA_3				0x082C
+#define  ZORRO_PROD_BSC_OKTAGON_2008				ZORRO_ID(BSC_ALFADATA_3, 0x05, 0)
+#define  ZORRO_PROD_BSC_TANDEM_AT_2008_508			ZORRO_ID(BSC_ALFADATA_3, 0x06, 0)
+#define  ZORRO_PROD_BSC_ALFA_RAM_1200				ZORRO_ID(BSC_ALFADATA_3, 0x07, 0)
+#define  ZORRO_PROD_BSC_OKTAGON_2008_RAM			ZORRO_ID(BSC_ALFADATA_3, 0x08, 0)
+#define  ZORRO_PROD_BSC_MULTIFACE_I				ZORRO_ID(BSC_ALFADATA_3, 0x10, 0)
+#define  ZORRO_PROD_BSC_MULTIFACE_II				ZORRO_ID(BSC_ALFADATA_3, 0x11, 0)
+#define  ZORRO_PROD_BSC_MULTIFACE_III				ZORRO_ID(BSC_ALFADATA_3, 0x12, 0)
+#define  ZORRO_PROD_BSC_FRAMEMASTER_II				ZORRO_ID(BSC_ALFADATA_3, 0x20, 0)
+#define  ZORRO_PROD_BSC_GRAFFITI_RAM				ZORRO_ID(BSC_ALFADATA_3, 0x21, 0)
+#define  ZORRO_PROD_BSC_GRAFFITI_REG				ZORRO_ID(BSC_ALFADATA_3, 0x22, 0)
+#define  ZORRO_PROD_BSC_ISDN_MASTERCARD				ZORRO_ID(BSC_ALFADATA_3, 0x40, 0)
+#define  ZORRO_PROD_BSC_ISDN_MASTERCARD_II			ZORRO_ID(BSC_ALFADATA_3, 0x41, 0)
+
+#define ZORRO_MANUF_PHOENIX					0x0835
+#define  ZORRO_PROD_PHOENIX_ST506				ZORRO_ID(PHOENIX, 0x21, 0)
+#define  ZORRO_PROD_PHOENIX_SCSI				ZORRO_ID(PHOENIX, 0x22, 0)
+#define  ZORRO_PROD_PHOENIX_RAM					ZORRO_ID(PHOENIX, 0xBE, 0)
+
+#define ZORRO_MANUF_ADVANCED_STORAGE_SYSTEMS			0x0836
+#define  ZORRO_PROD_ADVANCED_STORAGE_SYSTEMS_NEXUS		ZORRO_ID(ADVANCED_STORAGE_SYSTEMS, 0x01, 0)
+#define  ZORRO_PROD_ADVANCED_STORAGE_SYSTEMS_NEXUS_RAM		ZORRO_ID(ADVANCED_STORAGE_SYSTEMS, 0x08, 0)
+
+#define ZORRO_MANUF_IMPULSE					0x0838
+#define  ZORRO_PROD_IMPULSE_FIRECRACKER_24			ZORRO_ID(IMPULSE, 0x00, 0)
+
+#define ZORRO_MANUF_IVS						0x0840
+#define  ZORRO_PROD_IVS_GRANDSLAM_PIC_2				ZORRO_ID(IVS, 0x02, 0)
+#define  ZORRO_PROD_IVS_GRANDSLAM_PIC_1				ZORRO_ID(IVS, 0x04, 0)
+#define  ZORRO_PROD_IVS_OVERDRIVE				ZORRO_ID(IVS, 0x10, 0)
+#define  ZORRO_PROD_IVS_TRUMPCARD_CLASSIC			ZORRO_ID(IVS, 0x30, 0)
+#define  ZORRO_PROD_IVS_TRUMPCARD_PRO_GRANDSLAM			ZORRO_ID(IVS, 0x34, 0)
+#define  ZORRO_PROD_IVS_META_4					ZORRO_ID(IVS, 0x40, 0)
+#define  ZORRO_PROD_IVS_WAVETOOLS				ZORRO_ID(IVS, 0xBF, 0)
+#define  ZORRO_PROD_IVS_VECTOR_1				ZORRO_ID(IVS, 0xF3, 0)
+#define  ZORRO_PROD_IVS_VECTOR_2				ZORRO_ID(IVS, 0xF4, 0)
+
+#define ZORRO_MANUF_VECTOR_1					0x0841
+#define  ZORRO_PROD_VECTOR_CONNECTION_1				ZORRO_ID(VECTOR_1, 0xE3, 0)
+
+#define ZORRO_MANUF_XPERT_PRODEV				0x0845
+#define  ZORRO_PROD_XPERT_PRODEV_VISIONA_RAM			ZORRO_ID(XPERT_PRODEV, 0x01, 0)
+#define  ZORRO_PROD_XPERT_PRODEV_VISIONA_REG			ZORRO_ID(XPERT_PRODEV, 0x02, 0)
+#define  ZORRO_PROD_XPERT_PRODEV_MERLIN_RAM			ZORRO_ID(XPERT_PRODEV, 0x03, 0)
+#define  ZORRO_PROD_XPERT_PRODEV_MERLIN_REG_1			ZORRO_ID(XPERT_PRODEV, 0x04, 0)
+#define  ZORRO_PROD_XPERT_PRODEV_MERLIN_REG_2			ZORRO_ID(XPERT_PRODEV, 0xC9, 0)
+
+#define ZORRO_MANUF_HYDRA_SYSTEMS				0x0849
+#define  ZORRO_PROD_HYDRA_SYSTEMS_AMIGANET			ZORRO_ID(HYDRA_SYSTEMS, 0x01, 0)
+
+#define ZORRO_MANUF_SUNRIZE_INDUSTRIES				0x084F
+#define  ZORRO_PROD_SUNRIZE_INDUSTRIES_AD1012			ZORRO_ID(SUNRIZE_INDUSTRIES, 0x01, 0)
+#define  ZORRO_PROD_SUNRIZE_INDUSTRIES_AD516			ZORRO_ID(SUNRIZE_INDUSTRIES, 0x02, 0)
+#define  ZORRO_PROD_SUNRIZE_INDUSTRIES_DD512			ZORRO_ID(SUNRIZE_INDUSTRIES, 0x03, 0)
+
+#define ZORRO_MANUF_TRICERATOPS					0x0850
+#define  ZORRO_PROD_TRICERATOPS_MULTI_IO			ZORRO_ID(TRICERATOPS, 0x01, 0)
+
+#define ZORRO_MANUF_APPLIED_MAGIC				0x0851
+#define  ZORRO_PROD_APPLIED_MAGIC_DMI_RESOLVER			ZORRO_ID(APPLIED_MAGIC, 0x01, 0)
+#define  ZORRO_PROD_APPLIED_MAGIC_DIGITAL_BROADCASTER		ZORRO_ID(APPLIED_MAGIC, 0x06, 0)
+
+#define ZORRO_MANUF_GFX_BASE					0x085E
+#define  ZORRO_PROD_GFX_BASE_GDA_1_VRAM				ZORRO_ID(GFX_BASE, 0x00, 0)
+#define  ZORRO_PROD_GFX_BASE_GDA_1				ZORRO_ID(GFX_BASE, 0x01, 0)
+
+#define ZORRO_MANUF_ROCTEC					0x0860
+#define  ZORRO_PROD_ROCTEC_RH_800C				ZORRO_ID(ROCTEC, 0x01, 0)
+#define  ZORRO_PROD_ROCTEC_RH_800C_RAM				ZORRO_ID(ROCTEC, 0x01, 0)
+
+#define ZORRO_MANUF_KATO					0x0861
+#define  ZORRO_PROD_KATO_MELODY					ZORRO_ID(KATO, 0x80, 0)
+/* ID clash!! */
+#define ZORRO_MANUF_HELFRICH_1					0x0861
+#define  ZORRO_PROD_HELFRICH_RAINBOW_II				ZORRO_ID(HELFRICH_1, 0x20, 0)
+#define  ZORRO_PROD_HELFRICH_RAINBOW_III			ZORRO_ID(HELFRICH_1, 0x21, 0)
+
+#define ZORRO_MANUF_ATLANTIS					0x0862
+
+#define ZORRO_MANUF_PROTAR					0x0864
+
+#define ZORRO_MANUF_ACS						0x0865
+
+#define ZORRO_MANUF_SOFTWARE_RESULTS_ENTERPRISES		0x0866
+#define  ZORRO_PROD_SOFTWARE_RESULTS_ENTERPRISES_GOLDEN_GATE_2_BUS_PLUS	ZORRO_ID(SOFTWARE_RESULTS_ENTERPRISES, 0x01, 0)
+
+#define ZORRO_MANUF_MASOBOSHI					0x086D
+#define  ZORRO_PROD_MASOBOSHI_MASTER_CARD_SC201			ZORRO_ID(MASOBOSHI, 0x03, 0)
+#define  ZORRO_PROD_MASOBOSHI_MASTER_CARD_MC702			ZORRO_ID(MASOBOSHI, 0x04, 0)
+#define  ZORRO_PROD_MASOBOSHI_MVD_819				ZORRO_ID(MASOBOSHI, 0x07, 0)
+
+#define ZORRO_MANUF_MAINHATTAN_DATA				0x086F
+#define  ZORRO_PROD_MAINHATTAN_DATA_IDE				ZORRO_ID(MAINHATTAN_DATA, 0x01, 0)
+
+#define ZORRO_MANUF_VILLAGE_TRONIC				0x0877
+#define  ZORRO_PROD_VILLAGE_TRONIC_DOMINO_RAM			ZORRO_ID(VILLAGE_TRONIC, 0x01, 0)
+#define  ZORRO_PROD_VILLAGE_TRONIC_DOMINO_REG			ZORRO_ID(VILLAGE_TRONIC, 0x02, 0)
+#define  ZORRO_PROD_VILLAGE_TRONIC_DOMINO_16M_PROTOTYPE		ZORRO_ID(VILLAGE_TRONIC, 0x03, 0)
+#define  ZORRO_PROD_VILLAGE_TRONIC_PICASSO_II_II_PLUS_RAM	ZORRO_ID(VILLAGE_TRONIC, 0x0B, 0)
+#define  ZORRO_PROD_VILLAGE_TRONIC_PICASSO_II_II_PLUS_REG	ZORRO_ID(VILLAGE_TRONIC, 0x0C, 0)
+#define  ZORRO_PROD_VILLAGE_TRONIC_PICASSO_II_II_PLUS_SEGMENTED_MODE	ZORRO_ID(VILLAGE_TRONIC, 0x0D, 0)
+#define  ZORRO_PROD_VILLAGE_TRONIC_PICASSO_IV_Z2_RAM1		ZORRO_ID(VILLAGE_TRONIC, 0x15, 0)
+#define  ZORRO_PROD_VILLAGE_TRONIC_PICASSO_IV_Z2_RAM2		ZORRO_ID(VILLAGE_TRONIC, 0x16, 0)
+#define  ZORRO_PROD_VILLAGE_TRONIC_PICASSO_IV_Z2_REG		ZORRO_ID(VILLAGE_TRONIC, 0x17, 0)
+#define  ZORRO_PROD_VILLAGE_TRONIC_PICASSO_IV_Z3		ZORRO_ID(VILLAGE_TRONIC, 0x18, 0)
+#define  ZORRO_PROD_VILLAGE_TRONIC_ARIADNE			ZORRO_ID(VILLAGE_TRONIC, 0xC9, 0)
+#define  ZORRO_PROD_VILLAGE_TRONIC_ARIADNE2			ZORRO_ID(VILLAGE_TRONIC, 0xCA, 0)
+
+#define ZORRO_MANUF_UTILITIES_UNLIMITED				0x087B
+#define  ZORRO_PROD_UTILITIES_UNLIMITED_EMPLANT_DELUXE		ZORRO_ID(UTILITIES_UNLIMITED, 0x15, 0)
+#define  ZORRO_PROD_UTILITIES_UNLIMITED_EMPLANT_DELUXE2		ZORRO_ID(UTILITIES_UNLIMITED, 0x20, 0)
+
+#define ZORRO_MANUF_AMITRIX					0x0880
+#define  ZORRO_PROD_AMITRIX_MULTI_IO				ZORRO_ID(AMITRIX, 0x01, 0)
+#define  ZORRO_PROD_AMITRIX_CD_RAM				ZORRO_ID(AMITRIX, 0x02, 0)
+
+#define ZORRO_MANUF_ARMAX					0x0885
+#define  ZORRO_PROD_ARMAX_OMNIBUS				ZORRO_ID(ARMAX, 0x00, 0)
+
+#define ZORRO_MANUF_ZEUS					0x088D
+#define  ZORRO_PROD_ZEUS_SPIDER					ZORRO_ID(ZEUS, 0x04, 0)
+
+#define ZORRO_MANUF_NEWTEK					0x088F
+#define  ZORRO_PROD_NEWTEK_VIDEOTOASTER				ZORRO_ID(NEWTEK, 0x00, 0)
+
+#define ZORRO_MANUF_M_TECH_GERMANY				0x0890
+#define  ZORRO_PROD_MTEC_AT500_2				ZORRO_ID(M_TECH_GERMANY, 0x01, 0)
+#define  ZORRO_PROD_MTEC_68030					ZORRO_ID(M_TECH_GERMANY, 0x03, 0)
+#define  ZORRO_PROD_MTEC_68020I					ZORRO_ID(M_TECH_GERMANY, 0x06, 0)
+#define  ZORRO_PROD_MTEC_A1200_T68030_RTC			ZORRO_ID(M_TECH_GERMANY, 0x20, 0)
+#define  ZORRO_PROD_MTEC_VIPER_MK_V_E_MATRIX_530		ZORRO_ID(M_TECH_GERMANY, 0x21, 0)
+#define  ZORRO_PROD_MTEC_8_MB_RAM				ZORRO_ID(M_TECH_GERMANY, 0x22, 0)
+#define  ZORRO_PROD_MTEC_VIPER_MK_V_E_MATRIX_530_SCSI_IDE	ZORRO_ID(M_TECH_GERMANY, 0x24, 0)
+
+#define ZORRO_MANUF_GREAT_VALLEY_PRODUCTS_4			0x0891
+#define  ZORRO_PROD_GVP_EGS_28_24_SPECTRUM_RAM			ZORRO_ID(GREAT_VALLEY_PRODUCTS_4, 0x01, 0)
+#define  ZORRO_PROD_GVP_EGS_28_24_SPECTRUM_REG			ZORRO_ID(GREAT_VALLEY_PRODUCTS_4, 0x02, 0)
+
+#define ZORRO_MANUF_APOLLO_1					0x0892
+#define  ZORRO_PROD_APOLLO_A1200				ZORRO_ID(APOLLO_1, 0x01, 0)
+
+#define ZORRO_MANUF_HELFRICH_2					0x0893
+#define  ZORRO_PROD_HELFRICH_PICCOLO_RAM			ZORRO_ID(HELFRICH_2, 0x05, 0)
+#define  ZORRO_PROD_HELFRICH_PICCOLO_REG			ZORRO_ID(HELFRICH_2, 0x06, 0)
+#define  ZORRO_PROD_HELFRICH_PEGGY_PLUS_MPEG			ZORRO_ID(HELFRICH_2, 0x07, 0)
+#define  ZORRO_PROD_HELFRICH_VIDEOCRUNCHER			ZORRO_ID(HELFRICH_2, 0x08, 0)
+#define  ZORRO_PROD_HELFRICH_SD64_RAM				ZORRO_ID(HELFRICH_2, 0x0A, 0)
+#define  ZORRO_PROD_HELFRICH_SD64_REG				ZORRO_ID(HELFRICH_2, 0x0B, 0)
+
+#define ZORRO_MANUF_MACROSYSTEMS_USA				0x089B
+#define  ZORRO_PROD_MACROSYSTEMS_WARP_ENGINE_40xx		ZORRO_ID(MACROSYSTEMS_USA, 0x13, 0)
+
+#define ZORRO_MANUF_ELBOX_COMPUTER				0x089E
+#define  ZORRO_PROD_ELBOX_COMPUTER_1200_4			ZORRO_ID(ELBOX_COMPUTER, 0x06, 0)
+
+#define ZORRO_MANUF_HARMS_PROFESSIONAL				0x0A00
+#define  ZORRO_PROD_HARMS_PROFESSIONAL_030_PLUS			ZORRO_ID(HARMS_PROFESSIONAL, 0x10, 0)
+#define  ZORRO_PROD_HARMS_PROFESSIONAL_3500			ZORRO_ID(HARMS_PROFESSIONAL, 0xD0, 0)
+
+#define ZORRO_MANUF_MICRONIK					0x0A50
+#define  ZORRO_PROD_MICRONIK_RCA_120				ZORRO_ID(MICRONIK, 0x0A, 0)
+
+#define ZORRO_MANUF_MICRONIK2					0x0F0F
+#define  ZORRO_PROD_MICRONIK2_Z3I				ZORRO_ID(MICRONIK2, 0x01, 0)
+
+#define ZORRO_MANUF_MEGAMICRO					0x1000
+#define  ZORRO_PROD_MEGAMICRO_SCRAM_500				ZORRO_ID(MEGAMICRO, 0x03, 0)
+#define  ZORRO_PROD_MEGAMICRO_SCRAM_500_RAM			ZORRO_ID(MEGAMICRO, 0x04, 0)
+
+#define ZORRO_MANUF_IMTRONICS_2					0x1028
+#define  ZORRO_PROD_IMTRONICS_HURRICANE_2800_3			ZORRO_ID(IMTRONICS_2, 0x39, 0)
+#define  ZORRO_PROD_IMTRONICS_HURRICANE_2800_4			ZORRO_ID(IMTRONICS_2, 0x57, 0)
+
+/* unofficial ID */
+#define ZORRO_MANUF_INDIVIDUAL_COMPUTERS			0x1212
+#define  ZORRO_PROD_INDIVIDUAL_COMPUTERS_BUDDHA			ZORRO_ID(INDIVIDUAL_COMPUTERS, 0x00, 0)
+#define  ZORRO_PROD_INDIVIDUAL_COMPUTERS_X_SURF			ZORRO_ID(INDIVIDUAL_COMPUTERS, 0x17, 0)
+#define  ZORRO_PROD_INDIVIDUAL_COMPUTERS_CATWEASEL		ZORRO_ID(INDIVIDUAL_COMPUTERS, 0x2A, 0)
+
+#define ZORRO_MANUF_KUPKE_3					0x1248
+#define  ZORRO_PROD_KUPKE_GOLEM_HD_3000				ZORRO_ID(KUPKE_3, 0x01, 0)
+
+#define ZORRO_MANUF_ITH						0x1388
+#define  ZORRO_PROD_ITH_ISDN_MASTER_II				ZORRO_ID(ITH, 0x01, 0)
+
+#define ZORRO_MANUF_VMC						0x1389
+#define  ZORRO_PROD_VMC_ISDN_BLASTER_Z2				ZORRO_ID(VMC, 0x01, 0)
+#define  ZORRO_PROD_VMC_HYPERCOM_4				ZORRO_ID(VMC, 0x02, 0)
+
+#define ZORRO_MANUF_INFORMATION					0x157C
+#define  ZORRO_PROD_INFORMATION_ISDN_ENGINE_I			ZORRO_ID(INFORMATION, 0x64, 0)
+
+#define ZORRO_MANUF_VORTEX					0x2017
+#define  ZORRO_PROD_VORTEX_GOLDEN_GATE_80386SX			ZORRO_ID(VORTEX, 0x07, 0)
+#define  ZORRO_PROD_VORTEX_GOLDEN_GATE_RAM			ZORRO_ID(VORTEX, 0x08, 0)
+#define  ZORRO_PROD_VORTEX_GOLDEN_GATE_80486			ZORRO_ID(VORTEX, 0x09, 0)
+
+#define ZORRO_MANUF_EXPANSION_SYSTEMS				0x2062
+#define  ZORRO_PROD_EXPANSION_SYSTEMS_DATAFLYER_4000SX		ZORRO_ID(EXPANSION_SYSTEMS, 0x01, 0)
+#define  ZORRO_PROD_EXPANSION_SYSTEMS_DATAFLYER_4000SX_RAM	ZORRO_ID(EXPANSION_SYSTEMS, 0x02, 0)
+
+#define ZORRO_MANUF_READYSOFT					0x2100
+#define  ZORRO_PROD_READYSOFT_AMAX_II_IV			ZORRO_ID(READYSOFT, 0x01, 0)
+
+#define ZORRO_MANUF_PHASE5					0x2140
+#define  ZORRO_PROD_PHASE5_BLIZZARD_RAM				ZORRO_ID(PHASE5, 0x01, 0)
+#define  ZORRO_PROD_PHASE5_BLIZZARD				ZORRO_ID(PHASE5, 0x02, 0)
+#define  ZORRO_PROD_PHASE5_BLIZZARD_1220_IV			ZORRO_ID(PHASE5, 0x06, 0)
+#define  ZORRO_PROD_PHASE5_FASTLANE_Z3_RAM			ZORRO_ID(PHASE5, 0x0A, 0)
+#define  ZORRO_PROD_PHASE5_BLIZZARD_1230_II_FASTLANE_Z3_CYBERSCSI_CYBERSTORM060	ZORRO_ID(PHASE5, 0x0B, 0)
+#define  ZORRO_PROD_PHASE5_BLIZZARD_1220_CYBERSTORM		ZORRO_ID(PHASE5, 0x0C, 0)
+#define  ZORRO_PROD_PHASE5_BLIZZARD_1230			ZORRO_ID(PHASE5, 0x0D, 0)
+#define  ZORRO_PROD_PHASE5_BLIZZARD_1230_IV_1260		ZORRO_ID(PHASE5, 0x11, 0)
+#define  ZORRO_PROD_PHASE5_BLIZZARD_2060			ZORRO_ID(PHASE5, 0x18, 0)
+#define  ZORRO_PROD_PHASE5_CYBERSTORM_MK_II			ZORRO_ID(PHASE5, 0x19, 0)
+#define  ZORRO_PROD_PHASE5_CYBERVISION64			ZORRO_ID(PHASE5, 0x22, 0)
+#define  ZORRO_PROD_PHASE5_CYBERVISION64_3D_PROTOTYPE		ZORRO_ID(PHASE5, 0x32, 0)
+#define  ZORRO_PROD_PHASE5_CYBERVISION64_3D			ZORRO_ID(PHASE5, 0x43, 0)
+#define  ZORRO_PROD_PHASE5_CYBERSTORM_MK_III			ZORRO_ID(PHASE5, 0x64, 0)
+#define  ZORRO_PROD_PHASE5_BLIZZARD_603E_PLUS			ZORRO_ID(PHASE5, 0x6e, 0)
+
+#define ZORRO_MANUF_DPS						0x2169
+#define  ZORRO_PROD_DPS_PERSONAL_ANIMATION_RECORDER		ZORRO_ID(DPS, 0x01, 0)
+
+#define ZORRO_MANUF_APOLLO_2					0x2200
+#define  ZORRO_PROD_APOLLO_A620_68020_1				ZORRO_ID(APOLLO_2, 0x00, 0)
+#define  ZORRO_PROD_APOLLO_A620_68020_2				ZORRO_ID(APOLLO_2, 0x01, 0)
+
+#define ZORRO_MANUF_APOLLO_3					0x2222
+#define  ZORRO_PROD_APOLLO_AT_APOLLO				ZORRO_ID(APOLLO_3, 0x22, 0)
+#define  ZORRO_PROD_APOLLO_1230_1240_1260_2030_4040_4060	ZORRO_ID(APOLLO_3, 0x23, 0)
+
+#define ZORRO_MANUF_PETSOFF_LP					0x38A5
+#define  ZORRO_PROD_PETSOFF_LP_DELFINA				ZORRO_ID(PETSOFF_LP, 0x00, 0)
+#define  ZORRO_PROD_PETSOFF_LP_DELFINA_LITE			ZORRO_ID(PETSOFF_LP, 0x01, 0)
+
+#define ZORRO_MANUF_UWE_GERLACH					0x3FF7
+#define  ZORRO_PROD_UWE_GERLACH_RAM_ROM				ZORRO_ID(UWE_GERLACH, 0xd4, 0)
+
+#define ZORRO_MANUF_ACT						0x4231
+#define  ZORRO_PROD_ACT_PRELUDE					ZORRO_ID(ACT, 0x01, 0)
+
+#define ZORRO_MANUF_MACROSYSTEMS_GERMANY			0x4754
+#define  ZORRO_PROD_MACROSYSTEMS_MAESTRO			ZORRO_ID(MACROSYSTEMS_GERMANY, 0x03, 0)
+#define  ZORRO_PROD_MACROSYSTEMS_VLAB				ZORRO_ID(MACROSYSTEMS_GERMANY, 0x04, 0)
+#define  ZORRO_PROD_MACROSYSTEMS_MAESTRO_PRO			ZORRO_ID(MACROSYSTEMS_GERMANY, 0x05, 0)
+#define  ZORRO_PROD_MACROSYSTEMS_RETINA				ZORRO_ID(MACROSYSTEMS_GERMANY, 0x06, 0)
+#define  ZORRO_PROD_MACROSYSTEMS_MULTI_EVOLUTION		ZORRO_ID(MACROSYSTEMS_GERMANY, 0x08, 0)
+#define  ZORRO_PROD_MACROSYSTEMS_TOCCATA			ZORRO_ID(MACROSYSTEMS_GERMANY, 0x0C, 0)
+#define  ZORRO_PROD_MACROSYSTEMS_RETINA_Z3			ZORRO_ID(MACROSYSTEMS_GERMANY, 0x10, 0)
+#define  ZORRO_PROD_MACROSYSTEMS_VLAB_MOTION			ZORRO_ID(MACROSYSTEMS_GERMANY, 0x12, 0)
+#define  ZORRO_PROD_MACROSYSTEMS_ALTAIS				ZORRO_ID(MACROSYSTEMS_GERMANY, 0x13, 0)
+#define  ZORRO_PROD_MACROSYSTEMS_FALCON_040			ZORRO_ID(MACROSYSTEMS_GERMANY, 0xFD, 0)
+
+#define ZORRO_MANUF_COMBITEC					0x6766
+
+#define ZORRO_MANUF_SKI_PERIPHERALS				0x8000
+#define  ZORRO_PROD_SKI_PERIPHERALS_MAST_FIREBALL		ZORRO_ID(SKI_PERIPHERALS, 0x08, 0)
+#define  ZORRO_PROD_SKI_PERIPHERALS_SCSI_DUAL_SERIAL		ZORRO_ID(SKI_PERIPHERALS, 0x80, 0)
+
+#define ZORRO_MANUF_REIS_WARE_2					0xA9AD
+#define  ZORRO_PROD_REIS_WARE_SCAN_KING				ZORRO_ID(REIS_WARE_2, 0x11, 0)
+
+#define ZORRO_MANUF_CAMERON					0xAA01
+#define  ZORRO_PROD_CAMERON_PERSONAL_A4				ZORRO_ID(CAMERON, 0x10, 0)
+
+#define ZORRO_MANUF_REIS_WARE					0xAA11
+#define  ZORRO_PROD_REIS_WARE_HANDYSCANNER			ZORRO_ID(REIS_WARE, 0x11, 0)
+
+#define ZORRO_MANUF_PHOENIX_2					0xB5A8
+#define  ZORRO_PROD_PHOENIX_ST506_2				ZORRO_ID(PHOENIX_2, 0x21, 0)
+#define  ZORRO_PROD_PHOENIX_SCSI_2				ZORRO_ID(PHOENIX_2, 0x22, 0)
+#define  ZORRO_PROD_PHOENIX_RAM_2				ZORRO_ID(PHOENIX_2, 0xBE, 0)
+
+#define ZORRO_MANUF_COMBITEC_2					0xC008
+#define  ZORRO_PROD_COMBITEC_HD					ZORRO_ID(COMBITEC_2, 0x2A, 0)
+#define  ZORRO_PROD_COMBITEC_SRAM				ZORRO_ID(COMBITEC_2, 0x2B, 0)
+
+
+    /*
+     *  Test and illegal Manufacturer IDs.
+     */
+
+#define ZORRO_MANUF_HACKER					0x07DB
+#define  ZORRO_PROD_GENERAL_PROTOTYPE				ZORRO_ID(HACKER, 0x00, 0)
+#define  ZORRO_PROD_HACKER_SCSI					ZORRO_ID(HACKER, 0x01, 0)
+#define  ZORRO_PROD_RESOURCE_MANAGEMENT_FORCE_QUICKNET_QN2000	ZORRO_ID(HACKER, 0x02, 0)
+#define  ZORRO_PROD_VECTOR_CONNECTION_2				ZORRO_ID(HACKER, 0xE0, 0)
+#define  ZORRO_PROD_VECTOR_CONNECTION_3				ZORRO_ID(HACKER, 0xE1, 0)
+#define  ZORRO_PROD_VECTOR_CONNECTION_4				ZORRO_ID(HACKER, 0xE2, 0)
+#define  ZORRO_PROD_VECTOR_CONNECTION_5				ZORRO_ID(HACKER, 0xE3, 0)
-- 
cgit v0.10.2


From bd9ba8f40ee30edf31cc0845d8838bc43d172ef3 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Fri, 4 Oct 2013 09:38:53 +0200
Subject: zorro/UAPI: Use proper types (endianness/size) in <linux/zorro.h>

Fix member definitions for non-native userspace handling:
  - All multi-byte values are big-endian, hence use __be*,
  - All pointers are 32-bit pointers under AmigaOS, but unused (except for
    cd_BoardAddr) under Linux, hence use __be32.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c
index acd9c16..65b5e93 100644
--- a/arch/m68k/amiga/config.c
+++ b/arch/m68k/amiga/config.c
@@ -28,6 +28,7 @@
 #include <linux/keyboard.h>
 
 #include <asm/bootinfo.h>
+#include <asm/byteorder.h>
 #include <asm/setup.h>
 #include <asm/pgtable.h>
 #include <asm/amigahw.h>
@@ -176,10 +177,10 @@ int __init amiga_parse_bootinfo(const struct bi_record *record)
 			const struct ConfigDev *cd = (struct ConfigDev *)data;
 			struct zorro_dev_init *dev = &zorro_autocon_init[zorro_num_autocon++];
 			dev->rom = cd->cd_Rom;
-			dev->slotaddr = cd->cd_SlotAddr;
-			dev->slotsize = cd->cd_SlotSize;
-			dev->boardaddr = (u32)cd->cd_BoardAddr;
-			dev->boardsize = cd->cd_BoardSize;
+			dev->slotaddr = be16_to_cpu(cd->cd_SlotAddr);
+			dev->slotsize = be16_to_cpu(cd->cd_SlotSize);
+			dev->boardaddr = be32_to_cpu(cd->cd_BoardAddr);
+			dev->boardsize = be32_to_cpu(cd->cd_BoardSize);
 		} else
 			printk("amiga_parse_bootinfo: too many AutoConfig devices\n");
 #endif /* CONFIG_ZORRO */
diff --git a/arch/m68k/amiga/platform.c b/arch/m68k/amiga/platform.c
index 7847b2b..d34029d 100644
--- a/arch/m68k/amiga/platform.c
+++ b/arch/m68k/amiga/platform.c
@@ -13,6 +13,7 @@
 
 #include <asm/amigahw.h>
 #include <asm/amigayle.h>
+#include <asm/byteorder.h>
 
 
 #ifdef CONFIG_ZORRO
@@ -66,10 +67,12 @@ static int __init z_dev_present(zorro_id id)
 {
 	unsigned int i;
 
-	for (i = 0; i < zorro_num_autocon; i++)
-		if (zorro_autocon_init[i].rom.er_Manufacturer == ZORRO_MANUF(id) &&
-		    zorro_autocon_init[i].rom.er_Product == ZORRO_PROD(id))
+	for (i = 0; i < zorro_num_autocon; i++) {
+		const struct ExpansionRom *rom = &zorro_autocon_init[i].rom;
+		if (be16_to_cpu(rom->er_Manufacturer) == ZORRO_MANUF(id) &&
+		    rom->er_Product == ZORRO_PROD(id))
 			return 1;
+	}
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/amd/a2065.c b/drivers/net/ethernet/amd/a2065.c
index f492a19..5613918 100644
--- a/drivers/net/ethernet/amd/a2065.c
+++ b/drivers/net/ethernet/amd/a2065.c
@@ -57,6 +57,7 @@
 #include <linux/zorro.h>
 #include <linux/bitops.h>
 
+#include <asm/byteorder.h>
 #include <asm/irq.h>
 #include <asm/amigaints.h>
 #include <asm/amigahw.h>
@@ -678,6 +679,7 @@ static int a2065_init_one(struct zorro_dev *z,
 	unsigned long base_addr = board + A2065_LANCE;
 	unsigned long mem_start = board + A2065_RAM;
 	struct resource *r1, *r2;
+	u32 serial;
 	int err;
 
 	r1 = request_mem_region(base_addr, sizeof(struct lance_regs),
@@ -702,6 +704,7 @@ static int a2065_init_one(struct zorro_dev *z,
 	r1->name = dev->name;
 	r2->name = dev->name;
 
+	serial = be32_to_cpu(z->rom.er_SerialNumber);
 	dev->dev_addr[0] = 0x00;
 	if (z->id != ZORRO_PROD_AMERISTAR_A2065) {	/* Commodore */
 		dev->dev_addr[1] = 0x80;
@@ -710,9 +713,9 @@ static int a2065_init_one(struct zorro_dev *z,
 		dev->dev_addr[1] = 0x00;
 		dev->dev_addr[2] = 0x9f;
 	}
-	dev->dev_addr[3] = (z->rom.er_SerialNumber >> 16) & 0xff;
-	dev->dev_addr[4] = (z->rom.er_SerialNumber >> 8) & 0xff;
-	dev->dev_addr[5] = z->rom.er_SerialNumber & 0xff;
+	dev->dev_addr[3] = (serial >> 16) & 0xff;
+	dev->dev_addr[4] = (serial >> 8) & 0xff;
+	dev->dev_addr[5] = serial & 0xff;
 	dev->base_addr = (unsigned long)ZTWO_VADDR(base_addr);
 	dev->mem_start = (unsigned long)ZTWO_VADDR(mem_start);
 	dev->mem_end = dev->mem_start + A2065_RAM_SIZE;
diff --git a/drivers/net/ethernet/amd/ariadne.c b/drivers/net/ethernet/amd/ariadne.c
index 33822cb..b08101b 100644
--- a/drivers/net/ethernet/amd/ariadne.c
+++ b/drivers/net/ethernet/amd/ariadne.c
@@ -51,6 +51,7 @@
 #include <linux/zorro.h>
 #include <linux/bitops.h>
 
+#include <asm/byteorder.h>
 #include <asm/amigaints.h>
 #include <asm/amigahw.h>
 #include <asm/irq.h>
@@ -718,6 +719,7 @@ static int ariadne_init_one(struct zorro_dev *z,
 	struct resource *r1, *r2;
 	struct net_device *dev;
 	struct ariadne_private *priv;
+	u32 serial;
 	int err;
 
 	r1 = request_mem_region(base_addr, sizeof(struct Am79C960), "Am79C960");
@@ -741,12 +743,13 @@ static int ariadne_init_one(struct zorro_dev *z,
 	r1->name = dev->name;
 	r2->name = dev->name;
 
+	serial = be32_to_cpu(z->rom.er_SerialNumber);
 	dev->dev_addr[0] = 0x00;
 	dev->dev_addr[1] = 0x60;
 	dev->dev_addr[2] = 0x30;
-	dev->dev_addr[3] = (z->rom.er_SerialNumber >> 16) & 0xff;
-	dev->dev_addr[4] = (z->rom.er_SerialNumber >> 8) & 0xff;
-	dev->dev_addr[5] = z->rom.er_SerialNumber & 0xff;
+	dev->dev_addr[3] = (serial >> 16) & 0xff;
+	dev->dev_addr[4] = (serial >> 8) & 0xff;
+	dev->dev_addr[5] = serial & 0xff;
 	dev->base_addr = (unsigned long)ZTWO_VADDR(base_addr);
 	dev->mem_start = (unsigned long)ZTWO_VADDR(mem_start);
 	dev->mem_end = dev->mem_start + ARIADNE_RAM_SIZE;
diff --git a/drivers/zorro/proc.c b/drivers/zorro/proc.c
index ea1ce82..6ac2579 100644
--- a/drivers/zorro/proc.c
+++ b/drivers/zorro/proc.c
@@ -14,6 +14,8 @@
 #include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/export.h>
+
+#include <asm/byteorder.h>
 #include <asm/uaccess.h>
 #include <asm/amigahw.h>
 #include <asm/setup.h>
@@ -41,10 +43,10 @@ proc_bus_zorro_read(struct file *file, char __user *buf, size_t nbytes, loff_t *
 	/* Construct a ConfigDev */
 	memset(&cd, 0, sizeof(cd));
 	cd.cd_Rom = z->rom;
-	cd.cd_SlotAddr = z->slotaddr;
-	cd.cd_SlotSize = z->slotsize;
-	cd.cd_BoardAddr = (void *)zorro_resource_start(z);
-	cd.cd_BoardSize = zorro_resource_len(z);
+	cd.cd_SlotAddr = cpu_to_be16(z->slotaddr);
+	cd.cd_SlotSize = cpu_to_be16(z->slotsize);
+	cd.cd_BoardAddr = cpu_to_be32(zorro_resource_start(z));
+	cd.cd_BoardSize = cpu_to_be32(zorro_resource_len(z));
 
 	if (copy_to_user(buf, (void *)&cd + pos, nbytes))
 		return -EFAULT;
diff --git a/drivers/zorro/zorro-sysfs.c b/drivers/zorro/zorro-sysfs.c
index 26f7184..36b210f 100644
--- a/drivers/zorro/zorro-sysfs.c
+++ b/drivers/zorro/zorro-sysfs.c
@@ -16,6 +16,8 @@
 #include <linux/stat.h>
 #include <linux/string.h>
 
+#include <asm/byteorder.h>
+
 #include "zorro.h"
 
 
@@ -33,10 +35,20 @@ static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL);
 
 zorro_config_attr(id, id, "0x%08x\n");
 zorro_config_attr(type, rom.er_Type, "0x%02x\n");
-zorro_config_attr(serial, rom.er_SerialNumber, "0x%08x\n");
 zorro_config_attr(slotaddr, slotaddr, "0x%04x\n");
 zorro_config_attr(slotsize, slotsize, "0x%04x\n");
 
+static ssize_t
+show_serial(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct zorro_dev *z;
+
+	z = to_zorro_dev(dev);
+	return sprintf(buf, "0x%08x\n", be32_to_cpu(z->rom.er_SerialNumber));
+}
+
+static DEVICE_ATTR(serial, S_IRUGO, show_serial, NULL);
+
 static ssize_t zorro_show_resource(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct zorro_dev *z = to_zorro_dev(dev);
@@ -60,10 +72,10 @@ static ssize_t zorro_read_config(struct file *filp, struct kobject *kobj,
 	/* Construct a ConfigDev */
 	memset(&cd, 0, sizeof(cd));
 	cd.cd_Rom = z->rom;
-	cd.cd_SlotAddr = z->slotaddr;
-	cd.cd_SlotSize = z->slotsize;
-	cd.cd_BoardAddr = (void *)zorro_resource_start(z);
-	cd.cd_BoardSize = zorro_resource_len(z);
+	cd.cd_SlotAddr = cpu_to_be16(z->slotaddr);
+	cd.cd_SlotSize = cpu_to_be16(z->slotsize);
+	cd.cd_BoardAddr = cpu_to_be32(zorro_resource_start(z));
+	cd.cd_BoardSize = cpu_to_be32(zorro_resource_len(z));
 
 	return memory_read_from_buffer(buf, count, &off, &cd, sizeof(cd));
 }
diff --git a/drivers/zorro/zorro.c b/drivers/zorro/zorro.c
index 450abf1..707c1a5 100644
--- a/drivers/zorro/zorro.c
+++ b/drivers/zorro/zorro.c
@@ -18,6 +18,7 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 
+#include <asm/byteorder.h>
 #include <asm/setup.h>
 #include <asm/amigahw.h>
 
@@ -161,7 +162,8 @@ static int __init amiga_zorro_probe(struct platform_device *pdev)
 		z = &zorro_autocon[i];
 
 		z->rom = zi->rom;
-		z->id = (z->rom.er_Manufacturer<<16) | (z->rom.er_Product<<8);
+		z->id = (be16_to_cpu(z->rom.er_Manufacturer) << 16) |
+			(z->rom.er_Product << 8);
 		if (z->id == ZORRO_PROD_GVP_EPC_BASE) {
 			/* GVP quirk */
 			unsigned long magic = zi->boardaddr + 0x8000;
diff --git a/include/uapi/linux/zorro.h b/include/uapi/linux/zorro.h
index 36a033e..59d021b 100644
--- a/include/uapi/linux/zorro.h
+++ b/include/uapi/linux/zorro.h
@@ -63,26 +63,26 @@ enum GVP_flags {
 
 
 struct Node {
-	struct  Node *ln_Succ;	/* Pointer to next (successor) */
-	struct  Node *ln_Pred;	/* Pointer to previous (predecessor) */
-	__u8    ln_Type;
-	__s8    ln_Pri;		/* Priority, for sorting */
-	__s8    *ln_Name;	/* ID string, null terminated */
+	__be32 ln_Succ;		/* Pointer to next (successor) */
+	__be32 ln_Pred;		/* Pointer to previous (predecessor) */
+	__u8   ln_Type;
+	__s8   ln_Pri;		/* Priority, for sorting */
+	__be32 ln_Name;		/* ID string, null terminated */
 } __packed;
 
 struct ExpansionRom {
 	/* -First 16 bytes of the expansion ROM */
-	__u8  er_Type;		/* Board type, size and flags */
-	__u8  er_Product;	/* Product number, assigned by manufacturer */
-	__u8  er_Flags;		/* Flags */
-	__u8  er_Reserved03;	/* Must be zero ($ff inverted) */
-	__u16 er_Manufacturer;	/* Unique ID, ASSIGNED BY COMMODORE-AMIGA! */
-	__u32 er_SerialNumber;	/* Available for use by manufacturer */
-	__u16 er_InitDiagVec;	/* Offset to optional "DiagArea" structure */
-	__u8  er_Reserved0c;
-	__u8  er_Reserved0d;
-	__u8  er_Reserved0e;
-	__u8  er_Reserved0f;
+	__u8   er_Type;		/* Board type, size and flags */
+	__u8   er_Product;	/* Product number, assigned by manufacturer */
+	__u8   er_Flags;		/* Flags */
+	__u8   er_Reserved03;	/* Must be zero ($ff inverted) */
+	__be16 er_Manufacturer;	/* Unique ID, ASSIGNED BY COMMODORE-AMIGA! */
+	__be32 er_SerialNumber;	/* Available for use by manufacturer */
+	__be16 er_InitDiagVec;	/* Offset to optional "DiagArea" structure */
+	__u8   er_Reserved0c;
+	__u8   er_Reserved0d;
+	__u8   er_Reserved0e;
+	__u8   er_Reserved0f;
 } __packed;
 
 /* er_Type board type bits */
@@ -99,13 +99,13 @@ struct ConfigDev {
 	__u8		cd_Flags;	/* (read/write) */
 	__u8		cd_Pad;		/* reserved */
 	struct ExpansionRom cd_Rom;	/* copy of board's expansion ROM */
-	void		*cd_BoardAddr;	/* where in memory the board was placed */
-	__u32		cd_BoardSize;	/* size of board in bytes */
-	__u16		cd_SlotAddr;	/* which slot number (PRIVATE) */
-	__u16		cd_SlotSize;	/* number of slots (PRIVATE) */
-	void		*cd_Driver;	/* pointer to node of driver */
-	struct ConfigDev *cd_NextCD;	/* linked list of drivers to config */
-	__u32		cd_Unused[4];	/* for whatever the driver wants */
+	__be32		cd_BoardAddr;	/* where in memory the board was placed */
+	__be32		cd_BoardSize;	/* size of board in bytes */
+	__be16		cd_SlotAddr;	/* which slot number (PRIVATE) */
+	__be16		cd_SlotSize;	/* number of slots (PRIVATE) */
+	__be32		cd_Driver;	/* pointer to node of driver */
+	__be32		cd_NextCD;	/* linked list of drivers to config */
+	__be32		cd_Unused[4];	/* for whatever the driver wants */
 } __packed;
 
 #define ZORRO_NUM_AUTO		16
-- 
cgit v0.10.2


From b3ce71720560a9125aa0343bdbf501d887dbfb74 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Fri, 4 Oct 2013 12:38:23 +0200
Subject: block/z2ram: Remove duplicate external declarations

Remove the external declarations for m68k_realnum_memory and m68k_memory,
which are already provided by <asm/setup.h>, to avoid conflicts later.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c
index 8b2a60c..27de5046 100644
--- a/drivers/block/z2ram.c
+++ b/drivers/block/z2ram.c
@@ -43,9 +43,6 @@
 #include <linux/zorro.h>
 
 
-extern int m68k_realnum_memory;
-extern struct mem_info m68k_memory[NUM_MEMINFO];
-
 #define Z2MINOR_COMBINED      (0)
 #define Z2MINOR_Z2ONLY        (1)
 #define Z2MINOR_CHIPONLY      (2)
-- 
cgit v0.10.2


From 29a202035753dd0e5810caaefe885ed8934bfd46 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Mon, 9 Sep 2013 09:00:50 +0200
Subject: m68k: The bootinfo is located right after the kernel

Since the introduction of init sections (which are located after BSS), the
bootinfo is no longer located right after the BSS, but after all kernel
sections.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/include/asm/bootinfo.h b/arch/m68k/include/asm/bootinfo.h
index 67e7a78..fbb6150 100644
--- a/arch/m68k/include/asm/bootinfo.h
+++ b/arch/m68k/include/asm/bootinfo.h
@@ -34,7 +34,7 @@
      *  This way I hope to keep all future changes back/forewards compatible.
      *  Thus, keep your fingers crossed...
      *
-     *  This structure is copied right after the kernel bss by the bootstrap
+     *  This structure is copied right after the kernel by the bootstrap
      *  routine.
      */
 
diff --git a/arch/m68k/kernel/head.S b/arch/m68k/kernel/head.S
index ac85f16..fb348ca 100644
--- a/arch/m68k/kernel/head.S
+++ b/arch/m68k/kernel/head.S
@@ -1532,7 +1532,7 @@ L(cache_done):
 
 /*
  * Find a tag record in the bootinfo structure
- * The bootinfo structure is located right after the kernel bss
+ * The bootinfo structure is located right after the kernel
  * Returns: d0: size (-1 if not found)
  *          a0: data pointer (end-of-records if not found)
  */
diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c
index 9f16a15..18423a8 100644
--- a/arch/m68k/kernel/setup_mm.c
+++ b/arch/m68k/kernel/setup_mm.c
@@ -220,7 +220,7 @@ void __init setup_arch(char **cmdline_p)
 	int i;
 #endif
 
-	/* The bootinfo is located right after the kernel bss */
+	/* The bootinfo is located right after the kernel */
 	if (!CPU_IS_COLDFIRE)
 		m68k_parse_bootinfo((const struct bi_record *)_end);
 
-- 
cgit v0.10.2


From 7ca1e52dc816e2c1f6663d9d114f25f0b22f98f1 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Mon, 14 Oct 2013 11:45:07 +0200
Subject: m68k: head.S - Correct date and spelling

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/kernel/head.S b/arch/m68k/kernel/head.S
index fb348ca..8d14b0f 100644
--- a/arch/m68k/kernel/head.S
+++ b/arch/m68k/kernel/head.S
@@ -23,7 +23,7 @@
 ** 98/04/25 Phil Blundell: added HP300 support
 ** 1998/08/30 David Kilzer: Added support for font_desc structures
 **            for linux-2.1.115
-** 9/02/11  Richard Zidlicky: added Q40 support (initial vesion 99/01/01)
+** 1999/02/11  Richard Zidlicky: added Q40 support (initial version 99/01/01)
 ** 2004/05/13 Kars de Jong: Finalised HP300 support
 **
 ** This file is subject to the terms and conditions of the GNU General Public
-- 
cgit v0.10.2


From 958903d6f08c977778bf5e1f18eb7fd27b30ca72 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Tue, 1 Oct 2013 20:42:32 +0200
Subject: m68k: Drop remainings and API of BOOTINFO_COMPAT_1_0

Drop remainings and API for backwards compatibility with bootinfo interface
version 1.0.  This was used when booting a 2.1.x or newer kernel on Amiga,
Atari, or Mac using a bootstrap for kernel 2.0.x.

Everybody upgraded his bootstrap a long time ago, so this can go.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/include/asm/bootinfo.h b/arch/m68k/include/asm/bootinfo.h
index fbb6150..44f97be 100644
--- a/arch/m68k/include/asm/bootinfo.h
+++ b/arch/m68k/include/asm/bootinfo.h
@@ -263,116 +263,4 @@ struct bootversion {
 #define Q40_BOOTI_VERSION      MK_BI_VERSION( 2, 0 )
 #define HP300_BOOTI_VERSION    MK_BI_VERSION( 2, 0 )
 
-#ifdef BOOTINFO_COMPAT_1_0
-
-    /*
-     *  Backwards compatibility with bootinfo interface version 1.0
-     */
-
-#define COMPAT_AMIGA_BOOTI_VERSION    MK_BI_VERSION( 1, 0 )
-#define COMPAT_ATARI_BOOTI_VERSION    MK_BI_VERSION( 1, 0 )
-#define COMPAT_MAC_BOOTI_VERSION      MK_BI_VERSION( 1, 0 )
-
-#include <linux/zorro.h>
-
-#define COMPAT_NUM_AUTO    16
-
-struct compat_bi_Amiga {
-    int model;
-    int num_autocon;
-    struct ConfigDev autocon[COMPAT_NUM_AUTO];
-    unsigned long chip_size;
-    unsigned char vblank;
-    unsigned char psfreq;
-    unsigned long eclock;
-    unsigned long chipset;
-    unsigned long hw_present;
-};
-
-struct compat_bi_Atari {
-    unsigned long hw_present;
-    unsigned long mch_cookie;
-};
-
-#ifndef __ASSEMBLY__
-
-struct compat_bi_Macintosh
-{
-	unsigned long videoaddr;
-	unsigned long videorow;
-	unsigned long videodepth;
-	unsigned long dimensions;
-	unsigned long args;
-	unsigned long boottime;
-	unsigned long gmtbias;
-	unsigned long bootver;
-	unsigned long videological;
-	unsigned long sccbase;
-	unsigned long id;
-	unsigned long memsize;
-	unsigned long serialmf;
-	unsigned long serialhsk;
-	unsigned long serialgpi;
-	unsigned long printmf;
-	unsigned long printhsk;
-	unsigned long printgpi;
-	unsigned long cpuid;
-	unsigned long rombase;
-	unsigned long adbdelay;
-	unsigned long timedbra;
-};
-
-#endif
-
-struct compat_mem_info {
-    unsigned long addr;
-    unsigned long size;
-};
-
-#define COMPAT_NUM_MEMINFO  4
-
-#define COMPAT_CPUB_68020 0
-#define COMPAT_CPUB_68030 1
-#define COMPAT_CPUB_68040 2
-#define COMPAT_CPUB_68060 3
-#define COMPAT_FPUB_68881 5
-#define COMPAT_FPUB_68882 6
-#define COMPAT_FPUB_68040 7
-#define COMPAT_FPUB_68060 8
-
-#define COMPAT_CPU_68020    (1<<COMPAT_CPUB_68020)
-#define COMPAT_CPU_68030    (1<<COMPAT_CPUB_68030)
-#define COMPAT_CPU_68040    (1<<COMPAT_CPUB_68040)
-#define COMPAT_CPU_68060    (1<<COMPAT_CPUB_68060)
-#define COMPAT_CPU_MASK     (31)
-#define COMPAT_FPU_68881    (1<<COMPAT_FPUB_68881)
-#define COMPAT_FPU_68882    (1<<COMPAT_FPUB_68882)
-#define COMPAT_FPU_68040    (1<<COMPAT_FPUB_68040)
-#define COMPAT_FPU_68060    (1<<COMPAT_FPUB_68060)
-#define COMPAT_FPU_MASK     (0xfe0)
-
-#define COMPAT_CL_SIZE      (256)
-
-struct compat_bootinfo {
-    unsigned long machtype;
-    unsigned long cputype;
-    struct compat_mem_info memory[COMPAT_NUM_MEMINFO];
-    int num_memory;
-    unsigned long ramdisk_size;
-    unsigned long ramdisk_addr;
-    char command_line[COMPAT_CL_SIZE];
-    union {
-	struct compat_bi_Amiga     bi_ami;
-	struct compat_bi_Atari     bi_ata;
-	struct compat_bi_Macintosh bi_mac;
-    } bi_un;
-};
-
-#define bi_amiga	bi_un.bi_ami
-#define bi_atari	bi_un.bi_ata
-#define bi_mac		bi_un.bi_mac
-
-#endif /* BOOTINFO_COMPAT_1_0 */
-
-
 #endif /* _M68K_BOOTINFO_H */
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index afb95d5..677244e 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -26,7 +26,6 @@
 #include <linux/adb.h>
 #include <linux/cuda.h>
 
-#define BOOTINFO_COMPAT_1_0
 #include <asm/setup.h>
 #include <asm/bootinfo.h>
 
diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c
index 5e08555..3d02a3c 100644
--- a/arch/m68k/mac/misc.c
+++ b/arch/m68k/mac/misc.c
@@ -25,7 +25,6 @@
 #include <asm/mac_via.h>
 #include <asm/mac_oss.h>
 
-#define BOOTINFO_COMPAT_1_0
 #include <asm/bootinfo.h>
 #include <asm/machdep.h>
 
-- 
cgit v0.10.2


From bdd47c9fc1d96d3319e938931c83b863b5331b57 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Wed, 2 Oct 2013 10:01:43 +0200
Subject: m68k/mac: Move struct mac_booter_data to <asm/macintosh.h>

struct mac_booter_data is no longer part of the bootinfo API, hence move it
from <asm/bootinfo.h> to <asm/macintosh.h>, dropping all unused fields in
the process.

Also remove the no longer used mac_booter_data pointer from head.S.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/include/asm/bootinfo.h b/arch/m68k/include/asm/bootinfo.h
index 44f97be..908c42f 100644
--- a/arch/m68k/include/asm/bootinfo.h
+++ b/arch/m68k/include/asm/bootinfo.h
@@ -167,45 +167,6 @@ struct bi_record {
 #define BI_MAC_IOP_SWIM		0x8020	/* Mac SWIM floppy IOP */
 #define BI_MAC_IOP_ADB		0x8021	/* Mac ADB IOP */
 
-    /*
-     * Mac: compatibility with old booter data format (temporarily)
-     * Fields unused with the new bootinfo can be deleted now; instead of
-     * adding new fields the struct might be splitted into a hardware address
-     * part and a hardware type part
-     */
-
-#ifndef __ASSEMBLY__
-
-struct mac_booter_data
-{
-	unsigned long videoaddr;
-	unsigned long videorow;
-	unsigned long videodepth;
-	unsigned long dimensions;
-	unsigned long args;
-	unsigned long boottime;
-	unsigned long gmtbias;
-	unsigned long bootver;
-	unsigned long videological;
-	unsigned long sccbase;
-	unsigned long id;
-	unsigned long memsize;
-	unsigned long serialmf;
-	unsigned long serialhsk;
-	unsigned long serialgpi;
-	unsigned long printmf;
-	unsigned long printhsk;
-	unsigned long printgpi;
-	unsigned long cpuid;
-	unsigned long rombase;
-	unsigned long adbdelay;
-	unsigned long timedbra;
-};
-
-extern struct mac_booter_data
-	mac_bi_data;
-
-#endif
 
     /*
      *  Apollo-specific tags
diff --git a/arch/m68k/include/asm/macintosh.h b/arch/m68k/include/asm/macintosh.h
index 682a1a2..6a633eb 100644
--- a/arch/m68k/include/asm/macintosh.h
+++ b/arch/m68k/include/asm/macintosh.h
@@ -135,4 +135,27 @@ struct mac_model
 
 extern struct mac_model *macintosh_config;
 
+
+    /*
+     * Internal representation of the Mac hardware, filled in from bootinfo
+     */
+
+struct mac_booter_data
+{
+	unsigned long videoaddr;
+	unsigned long videorow;
+	unsigned long videodepth;
+	unsigned long dimensions;
+	unsigned long boottime;
+	unsigned long gmtbias;
+	unsigned long videological;
+	unsigned long sccbase;
+	unsigned long id;
+	unsigned long memsize;
+	unsigned long cpuid;
+	unsigned long rombase;
+};
+
+extern struct mac_booter_data mac_bi_data;
+
 #endif
diff --git a/arch/m68k/kernel/head.S b/arch/m68k/kernel/head.S
index 8d14b0f..28f8174 100644
--- a/arch/m68k/kernel/head.S
+++ b/arch/m68k/kernel/head.S
@@ -3896,8 +3896,6 @@ BVME_SCC_DATA_A	= 0xffb0000f
 #endif
 
 #if defined(CONFIG_MAC)
-L(mac_booter_data):
-	.long	0
 L(mac_videobase):
 	.long	0
 L(mac_videodepth):
-- 
cgit v0.10.2


From 4edf07fd8f6520bea292384a3638088ccbfdcaa1 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Wed, 2 Oct 2013 22:28:08 +0200
Subject: m68k/vme: Remove unused mvme_bdid_ptr

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/include/asm/mvme16xhw.h b/arch/m68k/include/asm/mvme16xhw.h
index 6117f56..87fa84a 100644
--- a/arch/m68k/include/asm/mvme16xhw.h
+++ b/arch/m68k/include/asm/mvme16xhw.h
@@ -7,8 +7,6 @@
 
 /* Note, bytes 12 and 13 are board no in BCD (0162,0166,0167,0177,etc) */
 
-extern long mvme_bdid_ptr;
-
 typedef struct {
 	char	bdid[4];
 	u_char	rev, mth, day, yr;
-- 
cgit v0.10.2


From 4c3c522bcebe16a717d7a809fd14b11823794027 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Wed, 2 Oct 2013 11:37:33 +0200
Subject: m68k/UAPI: Disintegrate arch/m68k/include/asm/bootinfo.h

Export the bootinfo definitions that are used by bootstrap loaders, and
split them up in generic and platform-specific parts.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c
index 65b5e93..0c92c1b 100644
--- a/arch/m68k/amiga/config.c
+++ b/arch/m68k/amiga/config.c
@@ -28,6 +28,7 @@
 #include <linux/keyboard.h>
 
 #include <asm/bootinfo.h>
+#include <asm/bootinfo-amiga.h>
 #include <asm/byteorder.h>
 #include <asm/setup.h>
 #include <asm/pgtable.h>
diff --git a/arch/m68k/apollo/config.c b/arch/m68k/apollo/config.c
index 2bdde96..c90c19e 100644
--- a/arch/m68k/apollo/config.c
+++ b/arch/m68k/apollo/config.c
@@ -10,6 +10,7 @@
 
 #include <asm/setup.h>
 #include <asm/bootinfo.h>
+#include <asm/bootinfo-apollo.h>
 #include <asm/pgtable.h>
 #include <asm/apollohw.h>
 #include <asm/irq.h>
diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c
index fb2d0bd..9159195 100644
--- a/arch/m68k/atari/config.c
+++ b/arch/m68k/atari/config.c
@@ -37,6 +37,7 @@
 #include <linux/module.h>
 
 #include <asm/bootinfo.h>
+#include <asm/bootinfo-atari.h>
 #include <asm/setup.h>
 #include <asm/atarihw.h>
 #include <asm/atariints.h>
diff --git a/arch/m68k/bvme6000/config.c b/arch/m68k/bvme6000/config.c
index 1b9e31e..4d1b403 100644
--- a/arch/m68k/bvme6000/config.c
+++ b/arch/m68k/bvme6000/config.c
@@ -28,6 +28,7 @@
 #include <linux/bcd.h>
 
 #include <asm/bootinfo.h>
+#include <asm/bootinfo-vme.h>
 #include <asm/pgtable.h>
 #include <asm/setup.h>
 #include <asm/irq.h>
diff --git a/arch/m68k/hp300/config.c b/arch/m68k/hp300/config.c
index b7609f7..892d079 100644
--- a/arch/m68k/hp300/config.c
+++ b/arch/m68k/hp300/config.c
@@ -14,6 +14,7 @@
 #include <linux/console.h>
 
 #include <asm/bootinfo.h>
+#include <asm/bootinfo-hp300.h>
 #include <asm/machdep.h>
 #include <asm/blinken.h>
 #include <asm/io.h>                               /* readb() and writeb() */
diff --git a/arch/m68k/include/asm/atarihw.h b/arch/m68k/include/asm/atarihw.h
index d887050..972c8f3 100644
--- a/arch/m68k/include/asm/atarihw.h
+++ b/arch/m68k/include/asm/atarihw.h
@@ -21,7 +21,7 @@
 #define _LINUX_ATARIHW_H_
 
 #include <linux/types.h>
-#include <asm/bootinfo.h>
+#include <asm/bootinfo-atari.h>
 #include <asm/raw_io.h>
 
 extern u_long atari_mch_cookie;
diff --git a/arch/m68k/include/asm/bootinfo.h b/arch/m68k/include/asm/bootinfo.h
index 908c42f..9edc318 100644
--- a/arch/m68k/include/asm/bootinfo.h
+++ b/arch/m68k/include/asm/bootinfo.h
@@ -6,222 +6,11 @@
 ** This file is subject to the terms and conditions of the GNU General Public
 ** License.  See the file COPYING in the main directory of this archive
 ** for more details.
-**
-** Created 09/29/92 by Greg Harp
-**
-** 5/2/94 Roman Hodek:
-**   Added bi_atari part of the machine dependent union bi_un; for now it
-**   contains just a model field to distinguish between TT and Falcon.
-** 26/7/96 Roman Zippel:
-**   Renamed to setup.h; added some useful macros to allow gcc some
-**   optimizations if possible.
-** 5/10/96 Geert Uytterhoeven:
-**   Redesign of the boot information structure; renamed to bootinfo.h again
-** 27/11/96 Geert Uytterhoeven:
-**   Backwards compatibility with bootinfo interface version 1.0
 */
 
 #ifndef _M68K_BOOTINFO_H
 #define _M68K_BOOTINFO_H
 
-
-    /*
-     *  Bootinfo definitions
-     *
-     *  This is an easily parsable and extendable structure containing all
-     *  information to be passed from the bootstrap to the kernel.
-     *
-     *  This way I hope to keep all future changes back/forewards compatible.
-     *  Thus, keep your fingers crossed...
-     *
-     *  This structure is copied right after the kernel by the bootstrap
-     *  routine.
-     */
-
-#ifndef __ASSEMBLY__
-
-struct bi_record {
-    unsigned short tag;			/* tag ID */
-    unsigned short size;		/* size of record (in bytes) */
-    unsigned long data[0];		/* data */
-};
-
-#endif /* __ASSEMBLY__ */
-
-
-    /*
-     *  Tag Definitions
-     *
-     *  Machine independent tags start counting from 0x0000
-     *  Machine dependent tags start counting from 0x8000
-     */
-
-#define BI_LAST			0x0000	/* last record (sentinel) */
-#define BI_MACHTYPE		0x0001	/* machine type (u_long) */
-#define BI_CPUTYPE		0x0002	/* cpu type (u_long) */
-#define BI_FPUTYPE		0x0003	/* fpu type (u_long) */
-#define BI_MMUTYPE		0x0004	/* mmu type (u_long) */
-#define BI_MEMCHUNK		0x0005	/* memory chunk address and size */
-					/* (struct mem_info) */
-#define BI_RAMDISK		0x0006	/* ramdisk address and size */
-					/* (struct mem_info) */
-#define BI_COMMAND_LINE		0x0007	/* kernel command line parameters */
-					/* (string) */
-
-    /*
-     *  Amiga-specific tags
-     */
-
-#define BI_AMIGA_MODEL		0x8000	/* model (u_long) */
-#define BI_AMIGA_AUTOCON	0x8001	/* AutoConfig device */
-					/* (struct ConfigDev) */
-#define BI_AMIGA_CHIP_SIZE	0x8002	/* size of Chip RAM (u_long) */
-#define BI_AMIGA_VBLANK		0x8003	/* VBLANK frequency (u_char) */
-#define BI_AMIGA_PSFREQ		0x8004	/* power supply frequency (u_char) */
-#define BI_AMIGA_ECLOCK		0x8005	/* EClock frequency (u_long) */
-#define BI_AMIGA_CHIPSET	0x8006	/* native chipset present (u_long) */
-#define BI_AMIGA_SERPER		0x8007	/* serial port period (u_short) */
-
-    /*
-     *  Atari-specific tags
-     */
-
-#define BI_ATARI_MCH_COOKIE	0x8000	/* _MCH cookie from TOS (u_long) */
-#define BI_ATARI_MCH_TYPE	0x8001	/* special machine type (u_long) */
-					/* (values are ATARI_MACH_* defines */
-
-/* mch_cookie values (upper word) */
-#define ATARI_MCH_ST		0
-#define ATARI_MCH_STE		1
-#define ATARI_MCH_TT		2
-#define ATARI_MCH_FALCON	3
-
-/* mch_type values */
-#define ATARI_MACH_NORMAL	0	/* no special machine type */
-#define ATARI_MACH_MEDUSA	1	/* Medusa 040 */
-#define ATARI_MACH_HADES	2	/* Hades 040 or 060 */
-#define ATARI_MACH_AB40		3	/* Afterburner040 on Falcon */
-
-    /*
-     *  VME-specific tags
-     */
-
-#define BI_VME_TYPE		0x8000	/* VME sub-architecture (u_long) */
-#define BI_VME_BRDINFO		0x8001	/* VME board information (struct) */
-
-/* BI_VME_TYPE codes */
-#define	VME_TYPE_TP34V		0x0034	/* Tadpole TP34V */
-#define VME_TYPE_MVME147	0x0147	/* Motorola MVME147 */
-#define VME_TYPE_MVME162	0x0162	/* Motorola MVME162 */
-#define VME_TYPE_MVME166	0x0166	/* Motorola MVME166 */
-#define VME_TYPE_MVME167	0x0167	/* Motorola MVME167 */
-#define VME_TYPE_MVME172	0x0172	/* Motorola MVME172 */
-#define VME_TYPE_MVME177	0x0177	/* Motorola MVME177 */
-#define VME_TYPE_BVME4000	0x4000	/* BVM Ltd. BVME4000 */
-#define VME_TYPE_BVME6000	0x6000	/* BVM Ltd. BVME6000 */
-
-/* BI_VME_BRDINFO is a 32 byte struct as returned by the Bug code on
- * Motorola VME boards.  Contains board number, Bug version, board
- * configuration options, etc.  See include/asm/mvme16xhw.h for details.
- */
-
-
-    /*
-     *  Macintosh-specific tags (all u_long)
-     */
-
-#define BI_MAC_MODEL		0x8000	/* Mac Gestalt ID (model type) */
-#define BI_MAC_VADDR		0x8001	/* Mac video base address */
-#define BI_MAC_VDEPTH		0x8002	/* Mac video depth */
-#define BI_MAC_VROW		0x8003	/* Mac video rowbytes */
-#define BI_MAC_VDIM		0x8004	/* Mac video dimensions */
-#define BI_MAC_VLOGICAL		0x8005	/* Mac video logical base */
-#define BI_MAC_SCCBASE		0x8006	/* Mac SCC base address */
-#define BI_MAC_BTIME		0x8007	/* Mac boot time */
-#define BI_MAC_GMTBIAS		0x8008	/* Mac GMT timezone offset */
-#define BI_MAC_MEMSIZE		0x8009	/* Mac RAM size (sanity check) */
-#define BI_MAC_CPUID		0x800a	/* Mac CPU type (sanity check) */
-#define BI_MAC_ROMBASE		0x800b	/* Mac system ROM base address */
-
-    /*
-     *  Macintosh hardware profile data - unused, see macintosh.h for
-     *  reasonable type values
-     */
-
-#define BI_MAC_VIA1BASE		0x8010	/* Mac VIA1 base address (always present) */
-#define BI_MAC_VIA2BASE		0x8011	/* Mac VIA2 base address (type varies) */
-#define BI_MAC_VIA2TYPE		0x8012	/* Mac VIA2 type (VIA, RBV, OSS) */
-#define BI_MAC_ADBTYPE		0x8013	/* Mac ADB interface type */
-#define BI_MAC_ASCBASE		0x8014	/* Mac Apple Sound Chip base address */
-#define BI_MAC_SCSI5380		0x8015	/* Mac NCR 5380 SCSI (base address, multi) */
-#define BI_MAC_SCSIDMA		0x8016	/* Mac SCSI DMA (base address) */
-#define BI_MAC_SCSI5396		0x8017	/* Mac NCR 53C96 SCSI (base address, multi) */
-#define BI_MAC_IDETYPE		0x8018	/* Mac IDE interface type */
-#define BI_MAC_IDEBASE		0x8019	/* Mac IDE interface base address */
-#define BI_MAC_NUBUS		0x801a	/* Mac Nubus type (none, regular, pseudo) */
-#define BI_MAC_SLOTMASK		0x801b	/* Mac Nubus slots present */
-#define BI_MAC_SCCTYPE		0x801c	/* Mac SCC serial type (normal, IOP) */
-#define BI_MAC_ETHTYPE		0x801d	/* Mac builtin ethernet type (Sonic, MACE */
-#define BI_MAC_ETHBASE		0x801e	/* Mac builtin ethernet base address */
-#define BI_MAC_PMU		0x801f	/* Mac power management / poweroff hardware */
-#define BI_MAC_IOP_SWIM		0x8020	/* Mac SWIM floppy IOP */
-#define BI_MAC_IOP_ADB		0x8021	/* Mac ADB IOP */
-
-
-    /*
-     *  Apollo-specific tags
-     */
-
-#define BI_APOLLO_MODEL         0x8000  /* model (u_long) */
-
-    /*
-     *  HP300-specific tags
-     */
-
-#define BI_HP300_MODEL		0x8000	/* model (u_long) */
-#define BI_HP300_UART_SCODE	0x8001	/* UART select code (u_long) */
-#define BI_HP300_UART_ADDR	0x8002	/* phys. addr of UART (u_long) */
-
-    /*
-     * Stuff for bootinfo interface versioning
-     *
-     * At the start of kernel code, a 'struct bootversion' is located.
-     * bootstrap checks for a matching version of the interface before booting
-     * a kernel, to avoid user confusion if kernel and bootstrap don't work
-     * together :-)
-     *
-     * If incompatible changes are made to the bootinfo interface, the major
-     * number below should be stepped (and the minor reset to 0) for the
-     * appropriate machine. If a change is backward-compatible, the minor
-     * should be stepped. "Backwards-compatible" means that booting will work,
-     * but certain features may not.
-     */
-
-#define BOOTINFOV_MAGIC			0x4249561A	/* 'BIV^Z' */
-#define MK_BI_VERSION(major,minor)	(((major)<<16)+(minor))
-#define BI_VERSION_MAJOR(v)		(((v) >> 16) & 0xffff)
-#define BI_VERSION_MINOR(v)		((v) & 0xffff)
-
-#ifndef __ASSEMBLY__
-
-struct bootversion {
-    unsigned short branch;
-    unsigned long magic;
-    struct {
-	unsigned long machtype;
-	unsigned long version;
-    } machversions[0];
-};
-
-#endif /* __ASSEMBLY__ */
-
-#define AMIGA_BOOTI_VERSION    MK_BI_VERSION( 2, 0 )
-#define ATARI_BOOTI_VERSION    MK_BI_VERSION( 2, 1 )
-#define MAC_BOOTI_VERSION      MK_BI_VERSION( 2, 0 )
-#define MVME147_BOOTI_VERSION  MK_BI_VERSION( 2, 0 )
-#define MVME16x_BOOTI_VERSION  MK_BI_VERSION( 2, 0 )
-#define BVME6000_BOOTI_VERSION MK_BI_VERSION( 2, 0 )
-#define Q40_BOOTI_VERSION      MK_BI_VERSION( 2, 0 )
-#define HP300_BOOTI_VERSION    MK_BI_VERSION( 2, 0 )
+#include <uapi/asm/bootinfo.h>
 
 #endif /* _M68K_BOOTINFO_H */
diff --git a/arch/m68k/include/uapi/asm/Kbuild b/arch/m68k/include/uapi/asm/Kbuild
index 1fef45a..6a2d257 100644
--- a/arch/m68k/include/uapi/asm/Kbuild
+++ b/arch/m68k/include/uapi/asm/Kbuild
@@ -11,6 +11,14 @@ generic-y += termbits.h
 generic-y += termios.h
 
 header-y += a.out.h
+header-y += bootinfo.h
+header-y += bootinfo-amiga.h
+header-y += bootinfo-apollo.h
+header-y += bootinfo-atari.h
+header-y += bootinfo-hp300.h
+header-y += bootinfo-mac.h
+header-y += bootinfo-q40.h
+header-y += bootinfo-vme.h
 header-y += byteorder.h
 header-y += cachectl.h
 header-y += fcntl.h
diff --git a/arch/m68k/include/uapi/asm/bootinfo-amiga.h b/arch/m68k/include/uapi/asm/bootinfo-amiga.h
new file mode 100644
index 0000000..2c32d67
--- /dev/null
+++ b/arch/m68k/include/uapi/asm/bootinfo-amiga.h
@@ -0,0 +1,31 @@
+/*
+** asm/bootinfo-amiga.h -- Amiga-specific boot information definitions
+*/
+
+#ifndef _UAPI_ASM_M68K_BOOTINFO_AMIGA_H
+#define _UAPI_ASM_M68K_BOOTINFO_AMIGA_H
+
+
+    /*
+     *  Amiga-specific tags
+     */
+
+#define BI_AMIGA_MODEL		0x8000	/* model (u_long) */
+#define BI_AMIGA_AUTOCON	0x8001	/* AutoConfig device */
+					/* (AmigaOS struct ConfigDev) */
+#define BI_AMIGA_CHIP_SIZE	0x8002	/* size of Chip RAM (u_long) */
+#define BI_AMIGA_VBLANK		0x8003	/* VBLANK frequency (u_char) */
+#define BI_AMIGA_PSFREQ		0x8004	/* power supply frequency (u_char) */
+#define BI_AMIGA_ECLOCK		0x8005	/* EClock frequency (u_long) */
+#define BI_AMIGA_CHIPSET	0x8006	/* native chipset present (u_long) */
+#define BI_AMIGA_SERPER		0x8007	/* serial port period (u_short) */
+
+
+    /*
+     *  Latest Amiga bootinfo version
+     */
+
+#define AMIGA_BOOTI_VERSION	MK_BI_VERSION(2, 0)
+
+
+#endif /* _UAPI_ASM_M68K_BOOTINFO_AMIGA_H */
diff --git a/arch/m68k/include/uapi/asm/bootinfo-apollo.h b/arch/m68k/include/uapi/asm/bootinfo-apollo.h
new file mode 100644
index 0000000..3a2051e
--- /dev/null
+++ b/arch/m68k/include/uapi/asm/bootinfo-apollo.h
@@ -0,0 +1,16 @@
+/*
+** asm/bootinfo-apollo.h -- Apollo-specific boot information definitions
+*/
+
+#ifndef _UAPI_ASM_M68K_BOOTINFO_APOLLO_H
+#define _UAPI_ASM_M68K_BOOTINFO_APOLLO_H
+
+
+    /*
+     *  Apollo-specific tags
+     */
+
+#define BI_APOLLO_MODEL		0x8000	/* model (u_long) */
+
+
+#endif /* _UAPI_ASM_M68K_BOOTINFO_APOLLO_H */
diff --git a/arch/m68k/include/uapi/asm/bootinfo-atari.h b/arch/m68k/include/uapi/asm/bootinfo-atari.h
new file mode 100644
index 0000000..cca0a83
--- /dev/null
+++ b/arch/m68k/include/uapi/asm/bootinfo-atari.h
@@ -0,0 +1,44 @@
+/*
+** asm/bootinfo-atari.h -- Atari-specific boot information definitions
+*/
+
+#ifndef _UAPI_ASM_M68K_BOOTINFO_ATARI_H
+#define _UAPI_ASM_M68K_BOOTINFO_ATARI_H
+
+
+    /*
+     *  Atari-specific tags
+     */
+
+#define BI_ATARI_MCH_COOKIE	0x8000	/* _MCH cookie from TOS (u_long) */
+#define BI_ATARI_MCH_TYPE	0x8001	/* special machine type (u_long) */
+
+
+    /*
+     *  mch_cookie values (upper word of BI_ATARI_MCH_COOKIE)
+     */
+
+#define ATARI_MCH_ST		0
+#define ATARI_MCH_STE		1
+#define ATARI_MCH_TT		2
+#define ATARI_MCH_FALCON	3
+
+
+    /*
+     *  Atari machine types (BI_ATARI_MCH_TYPE)
+     */
+
+#define ATARI_MACH_NORMAL	0	/* no special machine type */
+#define ATARI_MACH_MEDUSA	1	/* Medusa 040 */
+#define ATARI_MACH_HADES	2	/* Hades 040 or 060 */
+#define ATARI_MACH_AB40		3	/* Afterburner040 on Falcon */
+
+
+    /*
+     *  Latest Atari bootinfo version
+     */
+
+#define ATARI_BOOTI_VERSION	MK_BI_VERSION(2, 1)
+
+
+#endif /* _UAPI_ASM_M68K_BOOTINFO_ATARI_H */
diff --git a/arch/m68k/include/uapi/asm/bootinfo-hp300.h b/arch/m68k/include/uapi/asm/bootinfo-hp300.h
new file mode 100644
index 0000000..e7ed19c
--- /dev/null
+++ b/arch/m68k/include/uapi/asm/bootinfo-hp300.h
@@ -0,0 +1,25 @@
+/*
+** asm/bootinfo-hp300.h -- HP9000/300-specific boot information definitions
+*/
+
+#ifndef _UAPI_ASM_M68K_BOOTINFO_HP300_H
+#define _UAPI_ASM_M68K_BOOTINFO_HP300_H
+
+
+    /*
+     *  HP9000/300-specific tags
+     */
+
+#define BI_HP300_MODEL		0x8000	/* model (u_long) */
+#define BI_HP300_UART_SCODE	0x8001	/* UART select code (u_long) */
+#define BI_HP300_UART_ADDR	0x8002	/* phys. addr of UART (u_long) */
+
+
+    /*
+     *  Latest HP9000/300 bootinfo version
+     */
+
+#define HP300_BOOTI_VERSION	MK_BI_VERSION(2, 0)
+
+
+#endif /* _UAPI_ASM_M68K_BOOTINFO_HP300_H */
diff --git a/arch/m68k/include/uapi/asm/bootinfo-mac.h b/arch/m68k/include/uapi/asm/bootinfo-mac.h
new file mode 100644
index 0000000..d4ef211
--- /dev/null
+++ b/arch/m68k/include/uapi/asm/bootinfo-mac.h
@@ -0,0 +1,59 @@
+/*
+** asm/bootinfo-mac.h -- Macintosh-specific boot information definitions
+*/
+
+#ifndef _UAPI_ASM_M68K_BOOTINFO_MAC_H
+#define _UAPI_ASM_M68K_BOOTINFO_MAC_H
+
+
+    /*
+     *  Macintosh-specific tags (all u_long)
+     */
+
+#define BI_MAC_MODEL		0x8000	/* Mac Gestalt ID (model type) */
+#define BI_MAC_VADDR		0x8001	/* Mac video base address */
+#define BI_MAC_VDEPTH		0x8002	/* Mac video depth */
+#define BI_MAC_VROW		0x8003	/* Mac video rowbytes */
+#define BI_MAC_VDIM		0x8004	/* Mac video dimensions */
+#define BI_MAC_VLOGICAL		0x8005	/* Mac video logical base */
+#define BI_MAC_SCCBASE		0x8006	/* Mac SCC base address */
+#define BI_MAC_BTIME		0x8007	/* Mac boot time */
+#define BI_MAC_GMTBIAS		0x8008	/* Mac GMT timezone offset */
+#define BI_MAC_MEMSIZE		0x8009	/* Mac RAM size (sanity check) */
+#define BI_MAC_CPUID		0x800a	/* Mac CPU type (sanity check) */
+#define BI_MAC_ROMBASE		0x800b	/* Mac system ROM base address */
+
+
+    /*
+     *  Macintosh hardware profile data - unused, see macintosh.h for
+     *  reasonable type values
+     */
+
+#define BI_MAC_VIA1BASE		0x8010	/* Mac VIA1 base address (always present) */
+#define BI_MAC_VIA2BASE		0x8011	/* Mac VIA2 base address (type varies) */
+#define BI_MAC_VIA2TYPE		0x8012	/* Mac VIA2 type (VIA, RBV, OSS) */
+#define BI_MAC_ADBTYPE		0x8013	/* Mac ADB interface type */
+#define BI_MAC_ASCBASE		0x8014	/* Mac Apple Sound Chip base address */
+#define BI_MAC_SCSI5380		0x8015	/* Mac NCR 5380 SCSI (base address, multi) */
+#define BI_MAC_SCSIDMA		0x8016	/* Mac SCSI DMA (base address) */
+#define BI_MAC_SCSI5396		0x8017	/* Mac NCR 53C96 SCSI (base address, multi) */
+#define BI_MAC_IDETYPE		0x8018	/* Mac IDE interface type */
+#define BI_MAC_IDEBASE		0x8019	/* Mac IDE interface base address */
+#define BI_MAC_NUBUS		0x801a	/* Mac Nubus type (none, regular, pseudo) */
+#define BI_MAC_SLOTMASK		0x801b	/* Mac Nubus slots present */
+#define BI_MAC_SCCTYPE		0x801c	/* Mac SCC serial type (normal, IOP) */
+#define BI_MAC_ETHTYPE		0x801d	/* Mac builtin ethernet type (Sonic, MACE */
+#define BI_MAC_ETHBASE		0x801e	/* Mac builtin ethernet base address */
+#define BI_MAC_PMU		0x801f	/* Mac power management / poweroff hardware */
+#define BI_MAC_IOP_SWIM		0x8020	/* Mac SWIM floppy IOP */
+#define BI_MAC_IOP_ADB		0x8021	/* Mac ADB IOP */
+
+
+    /*
+     *  Latest Macintosh bootinfo version
+     */
+
+#define MAC_BOOTI_VERSION	MK_BI_VERSION(2, 0)
+
+
+#endif /* _UAPI_ASM_M68K_BOOTINFO_MAC_H */
diff --git a/arch/m68k/include/uapi/asm/bootinfo-q40.h b/arch/m68k/include/uapi/asm/bootinfo-q40.h
new file mode 100644
index 0000000..c79fea7
--- /dev/null
+++ b/arch/m68k/include/uapi/asm/bootinfo-q40.h
@@ -0,0 +1,16 @@
+/*
+** asm/bootinfo-q40.h -- Q40-specific boot information definitions
+*/
+
+#ifndef _UAPI_ASM_M68K_BOOTINFO_Q40_H
+#define _UAPI_ASM_M68K_BOOTINFO_Q40_H
+
+
+    /*
+     *  Latest Q40 bootinfo version
+     */
+
+#define Q40_BOOTI_VERSION	MK_BI_VERSION(2, 0)
+
+
+#endif /* _UAPI_ASM_M68K_BOOTINFO_Q40_H */
diff --git a/arch/m68k/include/uapi/asm/bootinfo-vme.h b/arch/m68k/include/uapi/asm/bootinfo-vme.h
new file mode 100644
index 0000000..4643a55
--- /dev/null
+++ b/arch/m68k/include/uapi/asm/bootinfo-vme.h
@@ -0,0 +1,46 @@
+/*
+** asm/bootinfo-vme.h -- VME-specific boot information definitions
+*/
+
+#ifndef _UAPI_ASM_M68K_BOOTINFO_VME_H
+#define _UAPI_ASM_M68K_BOOTINFO_VME_H
+
+
+    /*
+     *  VME-specific tags
+     */
+
+#define BI_VME_TYPE		0x8000	/* VME sub-architecture (u_long) */
+#define BI_VME_BRDINFO		0x8001	/* VME board information (struct) */
+
+
+    /*
+     *  VME models (BI_VME_TYPE)
+     */
+
+#define VME_TYPE_TP34V		0x0034	/* Tadpole TP34V */
+#define VME_TYPE_MVME147	0x0147	/* Motorola MVME147 */
+#define VME_TYPE_MVME162	0x0162	/* Motorola MVME162 */
+#define VME_TYPE_MVME166	0x0166	/* Motorola MVME166 */
+#define VME_TYPE_MVME167	0x0167	/* Motorola MVME167 */
+#define VME_TYPE_MVME172	0x0172	/* Motorola MVME172 */
+#define VME_TYPE_MVME177	0x0177	/* Motorola MVME177 */
+#define VME_TYPE_BVME4000	0x4000	/* BVM Ltd. BVME4000 */
+#define VME_TYPE_BVME6000	0x6000	/* BVM Ltd. BVME6000 */
+
+/* BI_VME_BRDINFO is a 32 byte struct as returned by the Bug code on
+ * Motorola VME boards.  Contains board number, Bug version, board
+ * configuration options, etc.  See include/asm/mvme16xhw.h for details.
+ */
+
+
+    /*
+     *  Latest VME bootinfo versions
+     */
+
+#define MVME147_BOOTI_VERSION	MK_BI_VERSION(2, 0)
+#define MVME16x_BOOTI_VERSION	MK_BI_VERSION(2, 0)
+#define BVME6000_BOOTI_VERSION	MK_BI_VERSION(2, 0)
+
+
+#endif /* _UAPI_ASM_M68K_BOOTINFO_VME_H */
diff --git a/arch/m68k/include/uapi/asm/bootinfo.h b/arch/m68k/include/uapi/asm/bootinfo.h
new file mode 100644
index 0000000..74a6fae
--- /dev/null
+++ b/arch/m68k/include/uapi/asm/bootinfo.h
@@ -0,0 +1,95 @@
+/*
+ * asm/bootinfo.h -- Definition of the Linux/m68k boot information structure
+ *
+ * Copyright 1992 by Greg Harp
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file COPYING in the main directory of this archive
+ * for more details.
+ */
+
+#ifndef _UAPI_ASM_M68K_BOOTINFO_H
+#define _UAPI_ASM_M68K_BOOTINFO_H
+
+#include <linux/types.h>
+
+
+#ifndef __ASSEMBLY__
+
+    /*
+     *  Bootinfo definitions
+     *
+     *  This is an easily parsable and extendable structure containing all
+     *  information to be passed from the bootstrap to the kernel.
+     *
+     *  This way I hope to keep all future changes back/forewards compatible.
+     *  Thus, keep your fingers crossed...
+     *
+     *  This structure is copied right after the kernel by the bootstrap
+     *  routine.
+     */
+
+struct bi_record {
+	unsigned short tag;		/* tag ID */
+	unsigned short size;		/* size of record (in bytes) */
+	unsigned long data[0];		/* data */
+};
+
+#endif /* __ASSEMBLY__ */
+
+
+    /*
+     *  Tag Definitions
+     *
+     *  Machine independent tags start counting from 0x0000
+     *  Machine dependent tags start counting from 0x8000
+     */
+
+#define BI_LAST			0x0000	/* last record (sentinel) */
+#define BI_MACHTYPE		0x0001	/* machine type (u_long) */
+#define BI_CPUTYPE		0x0002	/* cpu type (u_long) */
+#define BI_FPUTYPE		0x0003	/* fpu type (u_long) */
+#define BI_MMUTYPE		0x0004	/* mmu type (u_long) */
+#define BI_MEMCHUNK		0x0005	/* memory chunk address and size */
+					/* (struct mem_info) */
+#define BI_RAMDISK		0x0006	/* ramdisk address and size */
+					/* (struct mem_info) */
+#define BI_COMMAND_LINE		0x0007	/* kernel command line parameters */
+					/* (string) */
+
+
+    /*
+     * Stuff for bootinfo interface versioning
+     *
+     * At the start of kernel code, a 'struct bootversion' is located.
+     * bootstrap checks for a matching version of the interface before booting
+     * a kernel, to avoid user confusion if kernel and bootstrap don't work
+     * together :-)
+     *
+     * If incompatible changes are made to the bootinfo interface, the major
+     * number below should be stepped (and the minor reset to 0) for the
+     * appropriate machine. If a change is backward-compatible, the minor
+     * should be stepped. "Backwards-compatible" means that booting will work,
+     * but certain features may not.
+     */
+
+#define BOOTINFOV_MAGIC			0x4249561A	/* 'BIV^Z' */
+#define MK_BI_VERSION(major, minor)	(((major) << 16) + (minor))
+#define BI_VERSION_MAJOR(v)		(((v) >> 16) & 0xffff)
+#define BI_VERSION_MINOR(v)		((v) & 0xffff)
+
+#ifndef __ASSEMBLY__
+
+struct bootversion {
+	unsigned short branch;
+	unsigned long magic;
+	struct {
+		unsigned long machtype;
+		unsigned long version;
+	} machversions[0];
+} __packed;
+
+#endif /* __ASSEMBLY__ */
+
+
+#endif /* _UAPI_ASM_M68K_BOOTINFO_H */
diff --git a/arch/m68k/kernel/head.S b/arch/m68k/kernel/head.S
index 28f8174..7d7913f 100644
--- a/arch/m68k/kernel/head.S
+++ b/arch/m68k/kernel/head.S
@@ -257,6 +257,12 @@
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <asm/bootinfo.h>
+#include <asm/bootinfo-amiga.h>
+#include <asm/bootinfo-atari.h>
+#include <asm/bootinfo-hp300.h>
+#include <asm/bootinfo-mac.h>
+#include <asm/bootinfo-q40.h>
+#include <asm/bootinfo-vme.h>
 #include <asm/setup.h>
 #include <asm/entry.h>
 #include <asm/pgtable.h>
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index 677244e..e48069d 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -28,6 +28,7 @@
 
 #include <asm/setup.h>
 #include <asm/bootinfo.h>
+#include <asm/bootinfo-mac.h>
 
 #include <asm/io.h>
 #include <asm/irq.h>
diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c
index 5c99154..3a1d475 100644
--- a/arch/m68k/mvme147/config.c
+++ b/arch/m68k/mvme147/config.c
@@ -26,6 +26,7 @@
 #include <linux/interrupt.h>
 
 #include <asm/bootinfo.h>
+#include <asm/bootinfo-vme.h>
 #include <asm/pgtable.h>
 #include <asm/setup.h>
 #include <asm/irq.h>
diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c
index 60d8a1b..e05994f 100644
--- a/arch/m68k/mvme16x/config.c
+++ b/arch/m68k/mvme16x/config.c
@@ -29,6 +29,7 @@
 #include <linux/module.h>
 
 #include <asm/bootinfo.h>
+#include <asm/bootinfo-vme.h>
 #include <asm/pgtable.h>
 #include <asm/setup.h>
 #include <asm/irq.h>
-- 
cgit v0.10.2


From 799300840c18e7fdc0a3dace70d9b56a189fd1ab Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Wed, 2 Oct 2013 21:50:56 +0200
Subject: m68k/UAPI: Move generic definitions to <asm/bootinfo.h>

Move generic definitions used by bootstraps to uapi/asm/bootinfo.h:
  - Machine types,
  - CPU, FPU, and MMU types,
  - struct mem_info.

Keep a copy of struct mem_info for in-kernel use, and rename it to struct
m68k_mem_info, as the exported one will be modified later.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/include/asm/setup.h b/arch/m68k/include/asm/setup.h
index 65e78a2d..8f2023f 100644
--- a/arch/m68k/include/asm/setup.h
+++ b/arch/m68k/include/asm/setup.h
@@ -22,6 +22,7 @@
 #ifndef _M68K_SETUP_H
 #define _M68K_SETUP_H
 
+#include <uapi/asm/bootinfo.h>
 #include <uapi/asm/setup.h>
 
 
@@ -297,14 +298,14 @@ extern int m68k_is040or060;
 #define NUM_MEMINFO	4
 
 #ifndef __ASSEMBLY__
-struct mem_info {
+struct m68k_mem_info {
 	unsigned long addr;		/* physical address of memory chunk */
 	unsigned long size;		/* length of memory chunk (in bytes) */
 };
 
 extern int m68k_num_memory;		/* # of memory blocks found (and used) */
 extern int m68k_realnum_memory;		/* real # of memory blocks found */
-extern struct mem_info m68k_memory[NUM_MEMINFO];/* memory description */
+extern struct m68k_mem_info m68k_memory[NUM_MEMINFO];/* memory description */
 #endif
 
 #endif /* _M68K_SETUP_H */
diff --git a/arch/m68k/include/uapi/asm/bootinfo.h b/arch/m68k/include/uapi/asm/bootinfo.h
index 74a6fae..9d64599 100644
--- a/arch/m68k/include/uapi/asm/bootinfo.h
+++ b/arch/m68k/include/uapi/asm/bootinfo.h
@@ -11,8 +11,6 @@
 #ifndef _UAPI_ASM_M68K_BOOTINFO_H
 #define _UAPI_ASM_M68K_BOOTINFO_H
 
-#include <linux/types.h>
-
 
 #ifndef __ASSEMBLY__
 
@@ -35,6 +33,12 @@ struct bi_record {
 	unsigned long data[0];		/* data */
 };
 
+
+struct mem_info {
+	unsigned long addr;		/* physical address of memory chunk */
+	unsigned long size;		/* length of memory chunk (in bytes) */
+};
+
 #endif /* __ASSEMBLY__ */
 
 
@@ -59,6 +63,78 @@ struct bi_record {
 
 
     /*
+     *  Linux/m68k Architectures (BI_MACHTYPE)
+     */
+
+#define MACH_AMIGA		1
+#define MACH_ATARI		2
+#define MACH_MAC		3
+#define MACH_APOLLO		4
+#define MACH_SUN3		5
+#define MACH_MVME147		6
+#define MACH_MVME16x		7
+#define MACH_BVME6000		8
+#define MACH_HP300		9
+#define MACH_Q40		10
+#define MACH_SUN3X		11
+#define MACH_M54XX		12
+
+
+    /*
+     *  CPU, FPU and MMU types (BI_CPUTYPE, BI_FPUTYPE, BI_MMUTYPE)
+     *
+     *  Note: we may rely on the following equalities:
+     *
+     *      CPU_68020 == MMU_68851
+     *      CPU_68030 == MMU_68030
+     *      CPU_68040 == FPU_68040 == MMU_68040
+     *      CPU_68060 == FPU_68060 == MMU_68060
+     */
+
+#define CPUB_68020		0
+#define CPUB_68030		1
+#define CPUB_68040		2
+#define CPUB_68060		3
+#define CPUB_COLDFIRE		4
+
+#define CPU_68020		(1 << CPUB_68020)
+#define CPU_68030		(1 << CPUB_68030)
+#define CPU_68040		(1 << CPUB_68040)
+#define CPU_68060		(1 << CPUB_68060)
+#define CPU_COLDFIRE		(1 << CPUB_COLDFIRE)
+
+#define FPUB_68881		0
+#define FPUB_68882		1
+#define FPUB_68040		2	/* Internal FPU */
+#define FPUB_68060		3	/* Internal FPU */
+#define FPUB_SUNFPA		4	/* Sun-3 FPA */
+#define FPUB_COLDFIRE		5	/* ColdFire FPU */
+
+#define FPU_68881		(1 << FPUB_68881)
+#define FPU_68882		(1 << FPUB_68882)
+#define FPU_68040		(1 << FPUB_68040)
+#define FPU_68060		(1 << FPUB_68060)
+#define FPU_SUNFPA		(1 << FPUB_SUNFPA)
+#define FPU_COLDFIRE		(1 << FPUB_COLDFIRE)
+
+#define MMUB_68851		0
+#define MMUB_68030		1	/* Internal MMU */
+#define MMUB_68040		2	/* Internal MMU */
+#define MMUB_68060		3	/* Internal MMU */
+#define MMUB_APOLLO		4	/* Custom Apollo */
+#define MMUB_SUN3		5	/* Custom Sun-3 */
+#define MMUB_COLDFIRE		6	/* Internal MMU */
+
+#define MMU_68851		(1 << MMUB_68851)
+#define MMU_68030		(1 << MMUB_68030)
+#define MMU_68040		(1 << MMUB_68040)
+#define MMU_68060		(1 << MMUB_68060)
+#define MMU_SUN3		(1 << MMUB_SUN3)
+#define MMU_APOLLO		(1 << MMUB_APOLLO)
+#define MMU_COLDFIRE		(1 << MMUB_COLDFIRE)
+
+
+    /*
      * Stuff for bootinfo interface versioning
      *
      * At the start of kernel code, a 'struct bootversion' is located.
diff --git a/arch/m68k/include/uapi/asm/setup.h b/arch/m68k/include/uapi/asm/setup.h
index 85579bf..6a6dc63 100644
--- a/arch/m68k/include/uapi/asm/setup.h
+++ b/arch/m68k/include/uapi/asm/setup.h
@@ -6,98 +6,11 @@
 ** This file is subject to the terms and conditions of the GNU General Public
 ** License.  See the file COPYING in the main directory of this archive
 ** for more details.
-**
-** Created 09/29/92 by Greg Harp
-**
-** 5/2/94 Roman Hodek:
-**   Added bi_atari part of the machine dependent union bi_un; for now it
-**   contains just a model field to distinguish between TT and Falcon.
-** 26/7/96 Roman Zippel:
-**   Renamed to setup.h; added some useful macros to allow gcc some
-**   optimizations if possible.
-** 5/10/96 Geert Uytterhoeven:
-**   Redesign of the boot information structure; moved boot information
-**   structure to bootinfo.h
 */
 
 #ifndef _UAPI_M68K_SETUP_H
 #define _UAPI_M68K_SETUP_H
 
-
-
-    /*
-     *  Linux/m68k Architectures
-     */
-
-#define MACH_AMIGA    1
-#define MACH_ATARI    2
-#define MACH_MAC      3
-#define MACH_APOLLO   4
-#define MACH_SUN3     5
-#define MACH_MVME147  6
-#define MACH_MVME16x  7
-#define MACH_BVME6000 8
-#define MACH_HP300    9
-#define MACH_Q40     10
-#define MACH_SUN3X   11
-#define MACH_M54XX   12
-
 #define COMMAND_LINE_SIZE 256
 
-
-
-    /*
-     *  CPU, FPU and MMU types
-     *
-     *  Note: we may rely on the following equalities:
-     *
-     *      CPU_68020 == MMU_68851
-     *      CPU_68030 == MMU_68030
-     *      CPU_68040 == FPU_68040 == MMU_68040
-     *      CPU_68060 == FPU_68060 == MMU_68060
-     */
-
-#define CPUB_68020     0
-#define CPUB_68030     1
-#define CPUB_68040     2
-#define CPUB_68060     3
-#define CPUB_COLDFIRE  4
-
-#define CPU_68020      (1<<CPUB_68020)
-#define CPU_68030      (1<<CPUB_68030)
-#define CPU_68040      (1<<CPUB_68040)
-#define CPU_68060      (1<<CPUB_68060)
-#define CPU_COLDFIRE   (1<<CPUB_COLDFIRE)
-
-#define FPUB_68881     0
-#define FPUB_68882     1
-#define FPUB_68040     2                       /* Internal FPU */
-#define FPUB_68060     3                       /* Internal FPU */
-#define FPUB_SUNFPA    4                       /* Sun-3 FPA */
-#define FPUB_COLDFIRE  5                       /* ColdFire FPU */
-
-#define FPU_68881      (1<<FPUB_68881)
-#define FPU_68882      (1<<FPUB_68882)
-#define FPU_68040      (1<<FPUB_68040)
-#define FPU_68060      (1<<FPUB_68060)
-#define FPU_SUNFPA     (1<<FPUB_SUNFPA)
-#define FPU_COLDFIRE   (1<<FPUB_COLDFIRE)
-
-#define MMUB_68851     0
-#define MMUB_68030     1                       /* Internal MMU */
-#define MMUB_68040     2                       /* Internal MMU */
-#define MMUB_68060     3                       /* Internal MMU */
-#define MMUB_APOLLO    4                       /* Custom Apollo */
-#define MMUB_SUN3      5                       /* Custom Sun-3 */
-#define MMUB_COLDFIRE  6                       /* Internal MMU */
-
-#define MMU_68851      (1<<MMUB_68851)
-#define MMU_68030      (1<<MMUB_68030)
-#define MMU_68040      (1<<MMUB_68040)
-#define MMU_68060      (1<<MMUB_68060)
-#define MMU_SUN3       (1<<MMUB_SUN3)
-#define MMU_APOLLO     (1<<MMUB_APOLLO)
-#define MMU_COLDFIRE   (1<<MMUB_COLDFIRE)
-
-
 #endif /* _UAPI_M68K_SETUP_H */
diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c
index 18423a8..cff9845 100644
--- a/arch/m68k/kernel/setup_mm.c
+++ b/arch/m68k/kernel/setup_mm.c
@@ -71,10 +71,10 @@ EXPORT_SYMBOL(m68k_num_memory);
 int m68k_realnum_memory;
 EXPORT_SYMBOL(m68k_realnum_memory);
 unsigned long m68k_memoffset;
-struct mem_info m68k_memory[NUM_MEMINFO];
+struct m68k_mem_info m68k_memory[NUM_MEMINFO];
 EXPORT_SYMBOL(m68k_memory);
 
-static struct mem_info m68k_ramdisk __initdata;
+static struct m68k_mem_info m68k_ramdisk __initdata;
 
 static char m68k_command_line[CL_SIZE] __initdata;
 
diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c
index 6b4baa6..acaff6a 100644
--- a/arch/m68k/mm/init.c
+++ b/arch/m68k/mm/init.c
@@ -59,7 +59,7 @@ EXPORT_SYMBOL(pg_data_table);
 void __init m68k_setup_node(int node)
 {
 #ifndef CONFIG_SINGLE_MEMORY_CHUNK
-	struct mem_info *info = m68k_memory + node;
+	struct m68k_mem_info *info = m68k_memory + node;
 	int i, end;
 
 	i = (unsigned long)phys_to_virt(info->addr) >> __virt_to_node_shift();
diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c
index 251c543..7d40244 100644
--- a/arch/m68k/mm/motorola.c
+++ b/arch/m68k/mm/motorola.c
@@ -233,7 +233,7 @@ void __init paging_init(void)
 			printk("Fix your bootloader or use a memfile to make use of this area!\n");
 			m68k_num_memory--;
 			memmove(m68k_memory + i, m68k_memory + i + 1,
-				(m68k_num_memory - i) * sizeof(struct mem_info));
+				(m68k_num_memory - i) * sizeof(struct m68k_mem_info));
 			continue;
 		}
 		addr = m68k_memory[i].addr + m68k_memory[i].size;
-- 
cgit v0.10.2


From 7bc449688bf73891625616f3f2e93e359603016b Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Thu, 3 Oct 2013 11:26:22 +0200
Subject: m68k/UAPI: Move Amiga model/chipset definitions to
 <asm/bootinfo-amiga.h>

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/include/asm/amigahw.h b/arch/m68k/include/asm/amigahw.h
index 3bef0b2..5ad5681 100644
--- a/arch/m68k/include/asm/amigahw.h
+++ b/arch/m68k/include/asm/amigahw.h
@@ -18,26 +18,7 @@
 
 #include <linux/ioport.h>
 
-    /*
-     *  Different Amiga models
-     */
-
-#define AMI_UNKNOWN	(0)
-#define AMI_500		(1)
-#define AMI_500PLUS	(2)
-#define AMI_600		(3)
-#define AMI_1000	(4)
-#define AMI_1200	(5)
-#define AMI_2000	(6)
-#define AMI_2500	(7)
-#define AMI_3000	(8)
-#define AMI_3000T	(9)
-#define AMI_3000PLUS	(10)
-#define AMI_4000	(11)
-#define AMI_4000T	(12)
-#define AMI_CDTV	(13)
-#define AMI_CD32	(14)
-#define AMI_DRACO	(15)
+#include <asm/bootinfo-amiga.h>
 
 
     /*
@@ -46,11 +27,6 @@
 
 extern unsigned long amiga_chipset;
 
-#define CS_STONEAGE	(0)
-#define CS_OCS		(1)
-#define CS_ECS		(2)
-#define CS_AGA		(3)
-
 
     /*
      *  Miscellaneous
diff --git a/arch/m68k/include/uapi/asm/bootinfo-amiga.h b/arch/m68k/include/uapi/asm/bootinfo-amiga.h
index 2c32d67..28b6da0 100644
--- a/arch/m68k/include/uapi/asm/bootinfo-amiga.h
+++ b/arch/m68k/include/uapi/asm/bootinfo-amiga.h
@@ -22,6 +22,38 @@
 
 
     /*
+     *  Amiga models (BI_AMIGA_MODEL)
+     */
+
+#define AMI_UNKNOWN		0
+#define AMI_500			1
+#define AMI_500PLUS		2
+#define AMI_600			3
+#define AMI_1000		4
+#define AMI_1200		5
+#define AMI_2000		6
+#define AMI_2500		7
+#define AMI_3000		8
+#define AMI_3000T		9
+#define AMI_3000PLUS		10
+#define AMI_4000		11
+#define AMI_4000T		12
+#define AMI_CDTV		13
+#define AMI_CD32		14
+#define AMI_DRACO		15
+
+
+    /*
+     *  Amiga chipsets (BI_AMIGA_CHIPSET)
+     */
+
+#define CS_STONEAGE		0
+#define CS_OCS			1
+#define CS_ECS			2
+#define CS_AGA			3
+
+
+    /*
      *  Latest Amiga bootinfo version
      */
 
-- 
cgit v0.10.2


From 7678e77d2a2fb2dd74a27b8283e030c580294a62 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Thu, 3 Oct 2013 11:31:08 +0200
Subject: m68k/UAPI: Move Apollo model definitions to <asm/bootinfo-apollo.h>

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/include/asm/apollohw.h b/arch/m68k/include/asm/apollohw.h
index 6c19e0c..87fc899 100644
--- a/arch/m68k/include/asm/apollohw.h
+++ b/arch/m68k/include/asm/apollohw.h
@@ -5,18 +5,11 @@
 
 #include <linux/types.h>
 
-/*
-   apollo models
-*/
+#include <asm/bootinfo-apollo.h>
+
 
 extern u_long apollo_model;
 
-#define APOLLO_UNKNOWN (0)
-#define APOLLO_DN3000 (1)
-#define APOLLO_DN3010 (2)
-#define APOLLO_DN3500 (3)
-#define APOLLO_DN4000 (4)
-#define APOLLO_DN4500 (5)
 
 /*
    see scn2681 data sheet for more info.
diff --git a/arch/m68k/include/uapi/asm/bootinfo-apollo.h b/arch/m68k/include/uapi/asm/bootinfo-apollo.h
index 3a2051e..6992369 100644
--- a/arch/m68k/include/uapi/asm/bootinfo-apollo.h
+++ b/arch/m68k/include/uapi/asm/bootinfo-apollo.h
@@ -13,4 +13,16 @@
 #define BI_APOLLO_MODEL		0x8000	/* model (u_long) */
 
 
+    /*
+     *  Apollo models (BI_APOLLO_MODEL)
+     */
+
+#define APOLLO_UNKNOWN		0
+#define APOLLO_DN3000		1
+#define APOLLO_DN3010		2
+#define APOLLO_DN3500		3
+#define APOLLO_DN4000		4
+#define APOLLO_DN4500		5
+
+
 #endif /* _UAPI_ASM_M68K_BOOTINFO_APOLLO_H */
-- 
cgit v0.10.2


From f3bd09e3dba76e76bec7e79a442f37b0762f4fa1 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Thu, 3 Oct 2013 11:36:52 +0200
Subject: m68k/UAPI: Move HP300 model definitions to <asm/bootinfo-hp300.h>

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/include/asm/hp300hw.h b/arch/m68k/include/asm/hp300hw.h
index d998ea6..64f5271 100644
--- a/arch/m68k/include/asm/hp300hw.h
+++ b/arch/m68k/include/asm/hp300hw.h
@@ -1,25 +1,9 @@
 #ifndef _M68K_HP300HW_H
 #define _M68K_HP300HW_H
 
-extern unsigned long hp300_model;
+#include <asm/bootinfo-hp300.h>
 
-/* This information was taken from NetBSD */
-#define	HP_320		(0)	/* 16MHz 68020+HP MMU+16K external cache */
-#define	HP_330		(1)	/* 16MHz 68020+68851 MMU */
-#define	HP_340		(2)	/* 16MHz 68030 */
-#define	HP_345		(3)	/* 50MHz 68030+32K external cache */
-#define	HP_350		(4)	/* 25MHz 68020+HP MMU+32K external cache */
-#define	HP_360		(5)	/* 25MHz 68030 */
-#define	HP_370		(6)	/* 33MHz 68030+64K external cache */
-#define	HP_375		(7)	/* 50MHz 68030+32K external cache */
-#define	HP_380		(8)	/* 25MHz 68040 */
-#define	HP_385		(9)	/* 33MHz 68040 */
 
-#define	HP_400		(10)	/* 50MHz 68030+32K external cache */
-#define	HP_425T		(11)	/* 25MHz 68040 - model 425t */
-#define	HP_425S		(12)	/* 25MHz 68040 - model 425s */
-#define HP_425E		(13)	/* 25MHz 68040 - model 425e */
-#define HP_433T		(14)	/* 33MHz 68040 - model 433t */
-#define HP_433S		(15)	/* 33MHz 68040 - model 433s */
+extern unsigned long hp300_model;
 
 #endif /* _M68K_HP300HW_H */
diff --git a/arch/m68k/include/uapi/asm/bootinfo-hp300.h b/arch/m68k/include/uapi/asm/bootinfo-hp300.h
index e7ed19c..08530e1 100644
--- a/arch/m68k/include/uapi/asm/bootinfo-hp300.h
+++ b/arch/m68k/include/uapi/asm/bootinfo-hp300.h
@@ -16,6 +16,31 @@
 
 
     /*
+     *  HP9000/300 and /400 models (BI_HP300_MODEL)
+     *
+     * This information was taken from NetBSD
+     */
+
+#define HP_320		0	/* 16MHz 68020+HP MMU+16K external cache */
+#define HP_330		1	/* 16MHz 68020+68851 MMU */
+#define HP_340		2	/* 16MHz 68030 */
+#define HP_345		3	/* 50MHz 68030+32K external cache */
+#define HP_350		4	/* 25MHz 68020+HP MMU+32K external cache */
+#define HP_360		5	/* 25MHz 68030 */
+#define HP_370		6	/* 33MHz 68030+64K external cache */
+#define HP_375		7	/* 50MHz 68030+32K external cache */
+#define HP_380		8	/* 25MHz 68040 */
+#define HP_385		9	/* 33MHz 68040 */
+
+#define HP_400		10	/* 50MHz 68030+32K external cache */
+#define HP_425T		11	/* 25MHz 68040 - model 425t */
+#define HP_425S		12	/* 25MHz 68040 - model 425s */
+#define HP_425E		13	/* 25MHz 68040 - model 425e */
+#define HP_433T		14	/* 33MHz 68040 - model 433t */
+#define HP_433S		15	/* 33MHz 68040 - model 433s */
+
+
+    /*
      *  Latest HP9000/300 bootinfo version
      */
 
-- 
cgit v0.10.2


From 8693d6167e16baab1ee900d94b16af586a26a916 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Thu, 3 Oct 2013 11:40:00 +0200
Subject: m68k/UAPI: Move Macintosh model definitions to <asm/bootinfo-mac.h>

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/include/asm/macintosh.h b/arch/m68k/include/asm/macintosh.h
index 6a633eb..d323b2c 100644
--- a/arch/m68k/include/asm/macintosh.h
+++ b/arch/m68k/include/asm/macintosh.h
@@ -4,6 +4,9 @@
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
 
+#include <asm/bootinfo-mac.h>
+
+
 /*
  *	Apple Macintoshisms
  */
@@ -74,65 +77,6 @@ struct mac_model
 #define MAC_FLOPPY_SWIM_IOP	3
 #define MAC_FLOPPY_AV		4
 
-/*
- *	Gestalt numbers
- */
-
-#define MAC_MODEL_II		6
-#define MAC_MODEL_IIX		7
-#define MAC_MODEL_IICX		8
-#define MAC_MODEL_SE30		9
-#define MAC_MODEL_IICI		11
-#define MAC_MODEL_IIFX		13	/* And well numbered it is too */
-#define MAC_MODEL_IISI		18
-#define MAC_MODEL_LC		19
-#define MAC_MODEL_Q900		20
-#define MAC_MODEL_PB170		21
-#define MAC_MODEL_Q700		22
-#define MAC_MODEL_CLII		23	/* aka: P200 */
-#define MAC_MODEL_PB140		25
-#define MAC_MODEL_Q950		26	/* aka: WGS95 */
-#define MAC_MODEL_LCIII		27	/* aka: P450 */
-#define MAC_MODEL_PB210		29
-#define MAC_MODEL_C650		30
-#define MAC_MODEL_PB230		32
-#define MAC_MODEL_PB180		33
-#define MAC_MODEL_PB160		34
-#define MAC_MODEL_Q800		35	/* aka: WGS80 */
-#define MAC_MODEL_Q650		36
-#define MAC_MODEL_LCII		37	/* aka: P400/405/410/430 */
-#define MAC_MODEL_PB250		38
-#define MAC_MODEL_IIVI		44
-#define MAC_MODEL_P600		45	/* aka: P600CD */
-#define MAC_MODEL_IIVX		48
-#define MAC_MODEL_CCL		49	/* aka: P250 */
-#define MAC_MODEL_PB165C	50
-#define MAC_MODEL_C610		52	/* aka: WGS60 */
-#define MAC_MODEL_Q610		53
-#define MAC_MODEL_PB145		54	/* aka: PB145B */
-#define MAC_MODEL_P520		56	/* aka: LC520 */
-#define MAC_MODEL_C660		60
-#define MAC_MODEL_P460		62	/* aka: LCIII+, P466/P467 */
-#define MAC_MODEL_PB180C	71
-#define MAC_MODEL_PB520		72	/* aka: PB520C, PB540, PB540C, PB550C */
-#define MAC_MODEL_PB270C	77
-#define MAC_MODEL_Q840		78
-#define MAC_MODEL_P550		80	/* aka: LC550, P560 */
-#define MAC_MODEL_CCLII		83	/* aka: P275 */
-#define MAC_MODEL_PB165		84
-#define MAC_MODEL_PB190		85	/* aka: PB190CS */
-#define MAC_MODEL_TV		88
-#define MAC_MODEL_P475		89	/* aka: LC475, P476 */
-#define MAC_MODEL_P475F		90	/* aka: P475 w/ FPU (no LC040) */
-#define MAC_MODEL_P575		92	/* aka: LC575, P577/P578 */
-#define MAC_MODEL_Q605		94
-#define MAC_MODEL_Q605_ACC	95	/* Q605 accelerated to 33 MHz */
-#define MAC_MODEL_Q630		98	/* aka: LC630, P630/631/635/636/637/638/640 */
-#define MAC_MODEL_P588		99	/* aka: LC580, P580 */
-#define MAC_MODEL_PB280		102
-#define MAC_MODEL_PB280C	103
-#define MAC_MODEL_PB150		115
-
 extern struct mac_model *macintosh_config;
 
 
diff --git a/arch/m68k/include/uapi/asm/bootinfo-mac.h b/arch/m68k/include/uapi/asm/bootinfo-mac.h
index d4ef211..971046f 100644
--- a/arch/m68k/include/uapi/asm/bootinfo-mac.h
+++ b/arch/m68k/include/uapi/asm/bootinfo-mac.h
@@ -50,6 +50,66 @@
 
 
     /*
+     * Macintosh Gestalt numbers (BI_MAC_MODEL)
+     */
+
+#define MAC_MODEL_II		6
+#define MAC_MODEL_IIX		7
+#define MAC_MODEL_IICX		8
+#define MAC_MODEL_SE30		9
+#define MAC_MODEL_IICI		11
+#define MAC_MODEL_IIFX		13	/* And well numbered it is too */
+#define MAC_MODEL_IISI		18
+#define MAC_MODEL_LC		19
+#define MAC_MODEL_Q900		20
+#define MAC_MODEL_PB170		21
+#define MAC_MODEL_Q700		22
+#define MAC_MODEL_CLII		23	/* aka: P200 */
+#define MAC_MODEL_PB140		25
+#define MAC_MODEL_Q950		26	/* aka: WGS95 */
+#define MAC_MODEL_LCIII		27	/* aka: P450 */
+#define MAC_MODEL_PB210		29
+#define MAC_MODEL_C650		30
+#define MAC_MODEL_PB230		32
+#define MAC_MODEL_PB180		33
+#define MAC_MODEL_PB160		34
+#define MAC_MODEL_Q800		35	/* aka: WGS80 */
+#define MAC_MODEL_Q650		36
+#define MAC_MODEL_LCII		37	/* aka: P400/405/410/430 */
+#define MAC_MODEL_PB250		38
+#define MAC_MODEL_IIVI		44
+#define MAC_MODEL_P600		45	/* aka: P600CD */
+#define MAC_MODEL_IIVX		48
+#define MAC_MODEL_CCL		49	/* aka: P250 */
+#define MAC_MODEL_PB165C	50
+#define MAC_MODEL_C610		52	/* aka: WGS60 */
+#define MAC_MODEL_Q610		53
+#define MAC_MODEL_PB145		54	/* aka: PB145B */
+#define MAC_MODEL_P520		56	/* aka: LC520 */
+#define MAC_MODEL_C660		60
+#define MAC_MODEL_P460		62	/* aka: LCIII+, P466/P467 */
+#define MAC_MODEL_PB180C	71
+#define MAC_MODEL_PB520		72	/* aka: PB520C, PB540, PB540C, PB550C */
+#define MAC_MODEL_PB270C	77
+#define MAC_MODEL_Q840		78
+#define MAC_MODEL_P550		80	/* aka: LC550, P560 */
+#define MAC_MODEL_CCLII		83	/* aka: P275 */
+#define MAC_MODEL_PB165		84
+#define MAC_MODEL_PB190		85	/* aka: PB190CS */
+#define MAC_MODEL_TV		88
+#define MAC_MODEL_P475		89	/* aka: LC475, P476 */
+#define MAC_MODEL_P475F		90	/* aka: P475 w/ FPU (no LC040) */
+#define MAC_MODEL_P575		92	/* aka: LC575, P577/P578 */
+#define MAC_MODEL_Q605		94
+#define MAC_MODEL_Q605_ACC	95	/* Q605 accelerated to 33 MHz */
+#define MAC_MODEL_Q630		98	/* aka: LC630, P630/631/635/636/637/638/640 */
+#define MAC_MODEL_P588		99	/* aka: LC580, P580 */
+#define MAC_MODEL_PB280		102
+#define MAC_MODEL_PB280C	103
+#define MAC_MODEL_PB150		115
+
+
+    /*
      *  Latest Macintosh bootinfo version
      */
 
-- 
cgit v0.10.2


From cf288bd5b122d12476fd7d9825c292daef5dba58 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Wed, 2 Oct 2013 22:40:44 +0200
Subject: m68k/UAPI: Move VME Board ID definition to <asm/bootinfo-vme.h>

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/include/asm/mvme16xhw.h b/arch/m68k/include/asm/mvme16xhw.h
index 87fa84a..1eb89de 100644
--- a/arch/m68k/include/asm/mvme16xhw.h
+++ b/arch/m68k/include/asm/mvme16xhw.h
@@ -3,21 +3,6 @@
 
 #include <asm/irq.h>
 
-/* Board ID data structure - pointer to this retrieved from Bug by head.S */
-
-/* Note, bytes 12 and 13 are board no in BCD (0162,0166,0167,0177,etc) */
-
-typedef struct {
-	char	bdid[4];
-	u_char	rev, mth, day, yr;
-	u_short	size, reserved;
-	u_short	brdno;
-	char brdsuffix[2];
-	u_long	options;
-	u_short	clun, dlun, ctype, dnum;
-	u_long	option2;
-} t_bdid, *p_bdid;
-
 
 typedef struct {
 	u_char	ack_icr,
diff --git a/arch/m68k/include/uapi/asm/bootinfo-vme.h b/arch/m68k/include/uapi/asm/bootinfo-vme.h
index 4643a55..13ba5e1 100644
--- a/arch/m68k/include/uapi/asm/bootinfo-vme.h
+++ b/arch/m68k/include/uapi/asm/bootinfo-vme.h
@@ -28,11 +28,32 @@
 #define VME_TYPE_BVME4000	0x4000	/* BVM Ltd. BVME4000 */
 #define VME_TYPE_BVME6000	0x6000	/* BVM Ltd. BVME6000 */
 
-/* BI_VME_BRDINFO is a 32 byte struct as returned by the Bug code on
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Board ID data structure - pointer to this retrieved from Bug by head.S
+ *
+ * BI_VME_BRDINFO is a 32 byte struct as returned by the Bug code on
  * Motorola VME boards.  Contains board number, Bug version, board
- * configuration options, etc.  See include/asm/mvme16xhw.h for details.
+ * configuration options, etc.
+ *
+ * Note, bytes 12 and 13 are board no in BCD (0162,0166,0167,0177,etc)
  */
 
+typedef struct {
+	char	bdid[4];
+	u_char	rev, mth, day, yr;
+	u_short	size, reserved;
+	u_short	brdno;
+	char	brdsuffix[2];
+	u_long	options;
+	u_short	clun, dlun, ctype, dnum;
+	u_long	option2;
+} t_bdid, *p_bdid;
+
+#endif /* __ASSEMBLY__ */
+
 
     /*
      *  Latest VME bootinfo versions
-- 
cgit v0.10.2


From abe48101c17eaf1b5d85270272392e6111562626 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Fri, 4 Oct 2013 11:41:24 +0200
Subject: m68k/UAPI: Use proper types (endianness/size) in <asm/bootinfo*.h>

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c
index 0c92c1b..06920e8 100644
--- a/arch/m68k/amiga/config.c
+++ b/arch/m68k/amiga/config.c
@@ -145,37 +145,37 @@ static struct resource ram_resource[NUM_MEMINFO];
 int __init amiga_parse_bootinfo(const struct bi_record *record)
 {
 	int unknown = 0;
-	const unsigned long *data = record->data;
+	const void *data = record->data;
 
-	switch (record->tag) {
+	switch (be16_to_cpu(record->tag)) {
 	case BI_AMIGA_MODEL:
-		amiga_model = *data;
+		amiga_model = be32_to_cpup(data);
 		break;
 
 	case BI_AMIGA_ECLOCK:
-		amiga_eclock = *data;
+		amiga_eclock = be32_to_cpup(data);
 		break;
 
 	case BI_AMIGA_CHIPSET:
-		amiga_chipset = *data;
+		amiga_chipset = be32_to_cpup(data);
 		break;
 
 	case BI_AMIGA_CHIP_SIZE:
-		amiga_chip_size = *(const int *)data;
+		amiga_chip_size = be32_to_cpup(data);
 		break;
 
 	case BI_AMIGA_VBLANK:
-		amiga_vblank = *(const unsigned char *)data;
+		amiga_vblank = *(const __u8 *)data;
 		break;
 
 	case BI_AMIGA_PSFREQ:
-		amiga_psfreq = *(const unsigned char *)data;
+		amiga_psfreq = *(const __u8 *)data;
 		break;
 
 	case BI_AMIGA_AUTOCON:
 #ifdef CONFIG_ZORRO
 		if (zorro_num_autocon < ZORRO_NUM_AUTO) {
-			const struct ConfigDev *cd = (struct ConfigDev *)data;
+			const struct ConfigDev *cd = data;
 			struct zorro_dev_init *dev = &zorro_autocon_init[zorro_num_autocon++];
 			dev->rom = cd->cd_Rom;
 			dev->slotaddr = be16_to_cpu(cd->cd_SlotAddr);
diff --git a/arch/m68k/apollo/config.c b/arch/m68k/apollo/config.c
index c90c19e..9268c0f9 100644
--- a/arch/m68k/apollo/config.c
+++ b/arch/m68k/apollo/config.c
@@ -11,6 +11,7 @@
 #include <asm/setup.h>
 #include <asm/bootinfo.h>
 #include <asm/bootinfo-apollo.h>
+#include <asm/byteorder.h>
 #include <asm/pgtable.h>
 #include <asm/apollohw.h>
 #include <asm/irq.h>
@@ -48,15 +49,15 @@ static const char *apollo_models[] = {
 int __init apollo_parse_bootinfo(const struct bi_record *record)
 {
 	int unknown = 0;
-	const unsigned long *data = record->data;
+	const void *data = record->data;
 
-	switch(record->tag) {
-		case BI_APOLLO_MODEL:
-			apollo_model=*data;
-			break;
+	switch (be16_to_cpu(record->tag)) {
+	case BI_APOLLO_MODEL:
+		apollo_model = be32_to_cpup(data);
+		break;
 
-		default:
-			 unknown=1;
+	default:
+		 unknown=1;
 	}
 
 	return unknown;
diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c
index 9159195..01a6216 100644
--- a/arch/m68k/atari/config.c
+++ b/arch/m68k/atari/config.c
@@ -38,6 +38,7 @@
 
 #include <asm/bootinfo.h>
 #include <asm/bootinfo-atari.h>
+#include <asm/byteorder.h>
 #include <asm/setup.h>
 #include <asm/atarihw.h>
 #include <asm/atariints.h>
@@ -130,14 +131,14 @@ static int __init scc_test(volatile char *ctla)
 int __init atari_parse_bootinfo(const struct bi_record *record)
 {
 	int unknown = 0;
-	const u_long *data = record->data;
+	const void *data = record->data;
 
-	switch (record->tag) {
+	switch (be16_to_cpu(record->tag)) {
 	case BI_ATARI_MCH_COOKIE:
-		atari_mch_cookie = *data;
+		atari_mch_cookie = be32_to_cpup(data);
 		break;
 	case BI_ATARI_MCH_TYPE:
-		atari_mch_type = *data;
+		atari_mch_type = be32_to_cpup(data);
 		break;
 	default:
 		unknown = 1;
diff --git a/arch/m68k/bvme6000/config.c b/arch/m68k/bvme6000/config.c
index 4d1b403..478623d 100644
--- a/arch/m68k/bvme6000/config.c
+++ b/arch/m68k/bvme6000/config.c
@@ -29,6 +29,7 @@
 
 #include <asm/bootinfo.h>
 #include <asm/bootinfo-vme.h>
+#include <asm/byteorder.h>
 #include <asm/pgtable.h>
 #include <asm/setup.h>
 #include <asm/irq.h>
@@ -53,7 +54,7 @@ static irq_handler_t tick_handler;
 
 int __init bvme6000_parse_bootinfo(const struct bi_record *bi)
 {
-	if (bi->tag == BI_VME_TYPE)
+	if (be16_to_cpu(bi->tag) == BI_VME_TYPE)
 		return 0;
 	else
 		return 1;
diff --git a/arch/m68k/hp300/config.c b/arch/m68k/hp300/config.c
index 892d079..2e5a787 100644
--- a/arch/m68k/hp300/config.c
+++ b/arch/m68k/hp300/config.c
@@ -15,6 +15,7 @@
 
 #include <asm/bootinfo.h>
 #include <asm/bootinfo-hp300.h>
+#include <asm/byteorder.h>
 #include <asm/machdep.h>
 #include <asm/blinken.h>
 #include <asm/io.h>                               /* readb() and writeb() */
@@ -71,15 +72,15 @@ extern int hp300_setup_serial_console(void) __init;
 int __init hp300_parse_bootinfo(const struct bi_record *record)
 {
 	int unknown = 0;
-	const unsigned long *data = record->data;
+	const void *data = record->data;
 
-	switch (record->tag) {
+	switch (be16_to_cpu(record->tag)) {
 	case BI_HP300_MODEL:
-		hp300_model = *data;
+		hp300_model = be32_to_cpup(data);
 		break;
 
 	case BI_HP300_UART_SCODE:
-		hp300_uart_scode = *data;
+		hp300_uart_scode = be32_to_cpup(data);
 		break;
 
 	case BI_HP300_UART_ADDR:
diff --git a/arch/m68k/include/uapi/asm/bootinfo-amiga.h b/arch/m68k/include/uapi/asm/bootinfo-amiga.h
index 28b6da0..daad3c5 100644
--- a/arch/m68k/include/uapi/asm/bootinfo-amiga.h
+++ b/arch/m68k/include/uapi/asm/bootinfo-amiga.h
@@ -10,15 +10,15 @@
      *  Amiga-specific tags
      */
 
-#define BI_AMIGA_MODEL		0x8000	/* model (u_long) */
+#define BI_AMIGA_MODEL		0x8000	/* model (__be32) */
 #define BI_AMIGA_AUTOCON	0x8001	/* AutoConfig device */
 					/* (AmigaOS struct ConfigDev) */
-#define BI_AMIGA_CHIP_SIZE	0x8002	/* size of Chip RAM (u_long) */
-#define BI_AMIGA_VBLANK		0x8003	/* VBLANK frequency (u_char) */
-#define BI_AMIGA_PSFREQ		0x8004	/* power supply frequency (u_char) */
-#define BI_AMIGA_ECLOCK		0x8005	/* EClock frequency (u_long) */
-#define BI_AMIGA_CHIPSET	0x8006	/* native chipset present (u_long) */
-#define BI_AMIGA_SERPER		0x8007	/* serial port period (u_short) */
+#define BI_AMIGA_CHIP_SIZE	0x8002	/* size of Chip RAM (__be32) */
+#define BI_AMIGA_VBLANK		0x8003	/* VBLANK frequency (__u8) */
+#define BI_AMIGA_PSFREQ		0x8004	/* power supply frequency (__u8) */
+#define BI_AMIGA_ECLOCK		0x8005	/* EClock frequency (__be32) */
+#define BI_AMIGA_CHIPSET	0x8006	/* native chipset present (__be32) */
+#define BI_AMIGA_SERPER		0x8007	/* serial port period (__be16) */
 
 
     /*
diff --git a/arch/m68k/include/uapi/asm/bootinfo-apollo.h b/arch/m68k/include/uapi/asm/bootinfo-apollo.h
index 6992369..a93e0af 100644
--- a/arch/m68k/include/uapi/asm/bootinfo-apollo.h
+++ b/arch/m68k/include/uapi/asm/bootinfo-apollo.h
@@ -10,7 +10,7 @@
      *  Apollo-specific tags
      */
 
-#define BI_APOLLO_MODEL		0x8000	/* model (u_long) */
+#define BI_APOLLO_MODEL		0x8000	/* model (__be32) */
 
 
     /*
diff --git a/arch/m68k/include/uapi/asm/bootinfo-atari.h b/arch/m68k/include/uapi/asm/bootinfo-atari.h
index cca0a83..a817854 100644
--- a/arch/m68k/include/uapi/asm/bootinfo-atari.h
+++ b/arch/m68k/include/uapi/asm/bootinfo-atari.h
@@ -10,8 +10,8 @@
      *  Atari-specific tags
      */
 
-#define BI_ATARI_MCH_COOKIE	0x8000	/* _MCH cookie from TOS (u_long) */
-#define BI_ATARI_MCH_TYPE	0x8001	/* special machine type (u_long) */
+#define BI_ATARI_MCH_COOKIE	0x8000	/* _MCH cookie from TOS (__be32) */
+#define BI_ATARI_MCH_TYPE	0x8001	/* special machine type (__be32) */
 
 
     /*
diff --git a/arch/m68k/include/uapi/asm/bootinfo-hp300.h b/arch/m68k/include/uapi/asm/bootinfo-hp300.h
index 08530e1..c90cb71 100644
--- a/arch/m68k/include/uapi/asm/bootinfo-hp300.h
+++ b/arch/m68k/include/uapi/asm/bootinfo-hp300.h
@@ -10,9 +10,9 @@
      *  HP9000/300-specific tags
      */
 
-#define BI_HP300_MODEL		0x8000	/* model (u_long) */
-#define BI_HP300_UART_SCODE	0x8001	/* UART select code (u_long) */
-#define BI_HP300_UART_ADDR	0x8002	/* phys. addr of UART (u_long) */
+#define BI_HP300_MODEL		0x8000	/* model (__be32) */
+#define BI_HP300_UART_SCODE	0x8001	/* UART select code (__be32) */
+#define BI_HP300_UART_ADDR	0x8002	/* phys. addr of UART (__be32) */
 
 
     /*
diff --git a/arch/m68k/include/uapi/asm/bootinfo-mac.h b/arch/m68k/include/uapi/asm/bootinfo-mac.h
index 971046f..b44ff73 100644
--- a/arch/m68k/include/uapi/asm/bootinfo-mac.h
+++ b/arch/m68k/include/uapi/asm/bootinfo-mac.h
@@ -7,7 +7,7 @@
 
 
     /*
-     *  Macintosh-specific tags (all u_long)
+     *  Macintosh-specific tags (all __be32)
      */
 
 #define BI_MAC_MODEL		0x8000	/* Mac Gestalt ID (model type) */
diff --git a/arch/m68k/include/uapi/asm/bootinfo-vme.h b/arch/m68k/include/uapi/asm/bootinfo-vme.h
index 13ba5e1..a135eb4 100644
--- a/arch/m68k/include/uapi/asm/bootinfo-vme.h
+++ b/arch/m68k/include/uapi/asm/bootinfo-vme.h
@@ -6,11 +6,14 @@
 #define _UAPI_ASM_M68K_BOOTINFO_VME_H
 
 
+#include <linux/types.h>
+
+
     /*
      *  VME-specific tags
      */
 
-#define BI_VME_TYPE		0x8000	/* VME sub-architecture (u_long) */
+#define BI_VME_TYPE		0x8000	/* VME sub-architecture (__be32) */
 #define BI_VME_BRDINFO		0x8001	/* VME board information (struct) */
 
 
@@ -43,13 +46,13 @@
 
 typedef struct {
 	char	bdid[4];
-	u_char	rev, mth, day, yr;
-	u_short	size, reserved;
-	u_short	brdno;
+	__u8	rev, mth, day, yr;
+	__be16	size, reserved;
+	__be16	brdno;
 	char	brdsuffix[2];
-	u_long	options;
-	u_short	clun, dlun, ctype, dnum;
-	u_long	option2;
+	__be32	options;
+	__be16	clun, dlun, ctype, dnum;
+	__be32	option2;
 } t_bdid, *p_bdid;
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/m68k/include/uapi/asm/bootinfo.h b/arch/m68k/include/uapi/asm/bootinfo.h
index 9d64599..cdeb26a0 100644
--- a/arch/m68k/include/uapi/asm/bootinfo.h
+++ b/arch/m68k/include/uapi/asm/bootinfo.h
@@ -12,6 +12,9 @@
 #define _UAPI_ASM_M68K_BOOTINFO_H
 
 
+#include <linux/types.h>
+
+
 #ifndef __ASSEMBLY__
 
     /*
@@ -28,15 +31,15 @@
      */
 
 struct bi_record {
-	unsigned short tag;		/* tag ID */
-	unsigned short size;		/* size of record (in bytes) */
-	unsigned long data[0];		/* data */
+	__be16 tag;			/* tag ID */
+	__be16 size;			/* size of record (in bytes) */
+	__be32 data[0];			/* data */
 };
 
 
 struct mem_info {
-	unsigned long addr;		/* physical address of memory chunk */
-	unsigned long size;		/* length of memory chunk (in bytes) */
+	__be32 addr;			/* physical address of memory chunk */
+	__be32 size;			/* length of memory chunk (in bytes) */
 };
 
 #endif /* __ASSEMBLY__ */
@@ -50,10 +53,10 @@ struct mem_info {
      */
 
 #define BI_LAST			0x0000	/* last record (sentinel) */
-#define BI_MACHTYPE		0x0001	/* machine type (u_long) */
-#define BI_CPUTYPE		0x0002	/* cpu type (u_long) */
-#define BI_FPUTYPE		0x0003	/* fpu type (u_long) */
-#define BI_MMUTYPE		0x0004	/* mmu type (u_long) */
+#define BI_MACHTYPE		0x0001	/* machine type (__be32) */
+#define BI_CPUTYPE		0x0002	/* cpu type (__be32) */
+#define BI_FPUTYPE		0x0003	/* fpu type (__be32) */
+#define BI_MMUTYPE		0x0004	/* mmu type (__be32) */
 #define BI_MEMCHUNK		0x0005	/* memory chunk address and size */
 					/* (struct mem_info) */
 #define BI_RAMDISK		0x0006	/* ramdisk address and size */
@@ -157,11 +160,11 @@ struct mem_info {
 #ifndef __ASSEMBLY__
 
 struct bootversion {
-	unsigned short branch;
-	unsigned long magic;
+	__be16 branch;
+	__be32 magic;
 	struct {
-		unsigned long machtype;
-		unsigned long version;
+		__be32 machtype;
+		__be32 version;
 	} machversions[0];
 } __packed;
 
diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c
index cff9845..0191485 100644
--- a/arch/m68k/kernel/setup_mm.c
+++ b/arch/m68k/kernel/setup_mm.c
@@ -26,6 +26,7 @@
 #include <linux/initrd.h>
 
 #include <asm/bootinfo.h>
+#include <asm/byteorder.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/fpu.h>
@@ -143,11 +144,14 @@ extern void paging_init(void);
 
 static void __init m68k_parse_bootinfo(const struct bi_record *record)
 {
-	while (record->tag != BI_LAST) {
+	uint16_t tag;
+
+	while ((tag = be16_to_cpu(record->tag)) != BI_LAST) {
 		int unknown = 0;
-		const unsigned long *data = record->data;
+		const void *data = record->data;
+		uint16_t size = be16_to_cpu(record->size);
 
-		switch (record->tag) {
+		switch (tag) {
 		case BI_MACHTYPE:
 		case BI_CPUTYPE:
 		case BI_FPUTYPE:
@@ -157,8 +161,11 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record)
 
 		case BI_MEMCHUNK:
 			if (m68k_num_memory < NUM_MEMINFO) {
-				m68k_memory[m68k_num_memory].addr = data[0];
-				m68k_memory[m68k_num_memory].size = data[1];
+				const struct mem_info *m = data;
+				m68k_memory[m68k_num_memory].addr =
+					be32_to_cpu(m->addr);
+				m68k_memory[m68k_num_memory].size =
+					be32_to_cpu(m->size);
 				m68k_num_memory++;
 			} else
 				pr_warn("%s: too many memory chunks\n",
@@ -166,12 +173,15 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record)
 			break;
 
 		case BI_RAMDISK:
-			m68k_ramdisk.addr = data[0];
-			m68k_ramdisk.size = data[1];
+			{
+				const struct mem_info *m = data;
+				m68k_ramdisk.addr = be32_to_cpu(m->addr);
+				m68k_ramdisk.size = be32_to_cpu(m->size);
+			}
 			break;
 
 		case BI_COMMAND_LINE:
-			strlcpy(m68k_command_line, (const char *)data,
+			strlcpy(m68k_command_line, data,
 				sizeof(m68k_command_line));
 			break;
 
@@ -199,9 +209,8 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record)
 		}
 		if (unknown)
 			pr_warn("%s: unknown tag 0x%04x ignored\n", __func__,
-				   record->tag);
-		record = (struct bi_record *)((unsigned long)record +
-					      record->size);
+				tag);
+		record = (struct bi_record *)((unsigned long)record + size);
 	}
 
 	m68k_realnum_memory = m68k_num_memory;
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index e48069d..982c3fe 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -29,6 +29,7 @@
 #include <asm/setup.h>
 #include <asm/bootinfo.h>
 #include <asm/bootinfo-mac.h>
+#include <asm/byteorder.h>
 
 #include <asm/io.h>
 #include <asm/irq.h>
@@ -107,45 +108,46 @@ static void __init mac_sched_init(irq_handler_t vector)
 int __init mac_parse_bootinfo(const struct bi_record *record)
 {
 	int unknown = 0;
-	const u_long *data = record->data;
+	const void *data = record->data;
 
-	switch (record->tag) {
+	switch (be16_to_cpu(record->tag)) {
 	case BI_MAC_MODEL:
-		mac_bi_data.id = *data;
+		mac_bi_data.id = be32_to_cpup(data);
 		break;
 	case BI_MAC_VADDR:
-		mac_bi_data.videoaddr = *data;
+		mac_bi_data.videoaddr = be32_to_cpup(data);
 		break;
 	case BI_MAC_VDEPTH:
-		mac_bi_data.videodepth = *data;
+		mac_bi_data.videodepth = be32_to_cpup(data);
 		break;
 	case BI_MAC_VROW:
-		mac_bi_data.videorow = *data;
+		mac_bi_data.videorow = be32_to_cpup(data);
 		break;
 	case BI_MAC_VDIM:
-		mac_bi_data.dimensions = *data;
+		mac_bi_data.dimensions = be32_to_cpup(data);
 		break;
 	case BI_MAC_VLOGICAL:
-		mac_bi_data.videological = VIDEOMEMBASE + (*data & ~VIDEOMEMMASK);
-		mac_orig_videoaddr = *data;
+		mac_orig_videoaddr = be32_to_cpup(data);
+		mac_bi_data.videological =
+			VIDEOMEMBASE + (mac_orig_videoaddr & ~VIDEOMEMMASK);
 		break;
 	case BI_MAC_SCCBASE:
-		mac_bi_data.sccbase = *data;
+		mac_bi_data.sccbase = be32_to_cpup(data);
 		break;
 	case BI_MAC_BTIME:
-		mac_bi_data.boottime = *data;
+		mac_bi_data.boottime = be32_to_cpup(data);
 		break;
 	case BI_MAC_GMTBIAS:
-		mac_bi_data.gmtbias = *data;
+		mac_bi_data.gmtbias = be32_to_cpup(data);
 		break;
 	case BI_MAC_MEMSIZE:
-		mac_bi_data.memsize = *data;
+		mac_bi_data.memsize = be32_to_cpup(data);
 		break;
 	case BI_MAC_CPUID:
-		mac_bi_data.cpuid = *data;
+		mac_bi_data.cpuid = be32_to_cpup(data);
 		break;
 	case BI_MAC_ROMBASE:
-		mac_bi_data.rombase = *data;
+		mac_bi_data.rombase = be32_to_cpup(data);
 		break;
 	default:
 		unknown = 1;
diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c
index 3a1d475..1bb3ce6 100644
--- a/arch/m68k/mvme147/config.c
+++ b/arch/m68k/mvme147/config.c
@@ -27,6 +27,7 @@
 
 #include <asm/bootinfo.h>
 #include <asm/bootinfo-vme.h>
+#include <asm/byteorder.h>
 #include <asm/pgtable.h>
 #include <asm/setup.h>
 #include <asm/irq.h>
@@ -54,7 +55,8 @@ irq_handler_t tick_handler;
 
 int __init mvme147_parse_bootinfo(const struct bi_record *bi)
 {
-	if (bi->tag == BI_VME_TYPE || bi->tag == BI_VME_BRDINFO)
+	uint16_t tag = be16_to_cpu(bi->tag);
+	if (tag == BI_VME_TYPE || tag == BI_VME_BRDINFO)
 		return 0;
 	else
 		return 1;
diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c
index e05994f..eab7d34 100644
--- a/arch/m68k/mvme16x/config.c
+++ b/arch/m68k/mvme16x/config.c
@@ -30,6 +30,7 @@
 
 #include <asm/bootinfo.h>
 #include <asm/bootinfo-vme.h>
+#include <asm/byteorder.h>
 #include <asm/pgtable.h>
 #include <asm/setup.h>
 #include <asm/irq.h>
@@ -63,7 +64,8 @@ EXPORT_SYMBOL(mvme16x_config);
 
 int __init mvme16x_parse_bootinfo(const struct bi_record *bi)
 {
-	if (bi->tag == BI_VME_TYPE || bi->tag == BI_VME_BRDINFO)
+	uint16_t tag = be16_to_cpu(bi->tag);
+	if (tag == BI_VME_TYPE || tag == BI_VME_BRDINFO)
 		return 0;
 	else
 		return 1;
@@ -88,15 +90,15 @@ static void mvme16x_get_model(char *model)
     suf[3] = '\0';
     suf[0] = suf[1] ? '-' : '\0';
 
-    sprintf(model, "Motorola MVME%x%s", p->brdno, suf);
+    sprintf(model, "Motorola MVME%x%s", be16_to_cpu(p->brdno), suf);
 }
 
 
 static void mvme16x_get_hardware_list(struct seq_file *m)
 {
-    p_bdid p = &mvme_bdid;
+    uint16_t brdno = be16_to_cpu(mvme_bdid.brdno);
 
-    if (p->brdno == 0x0162 || p->brdno == 0x0172)
+    if (brdno == 0x0162 || brdno == 0x0172)
     {
 	unsigned char rev = *(unsigned char *)MVME162_VERSION_REG;
 
@@ -286,6 +288,7 @@ void __init config_mvme16x(void)
 {
     p_bdid p = &mvme_bdid;
     char id[40];
+    uint16_t brdno = be16_to_cpu(p->brdno);
 
     mach_max_dma_address = 0xffffffff;
     mach_sched_init      = mvme16x_sched_init;
@@ -307,18 +310,18 @@ void __init config_mvme16x(void)
     }
     /* Board type is only set by newer versions of vmelilo/tftplilo */
     if (vme_brdtype == 0)
-	vme_brdtype = p->brdno;
+	vme_brdtype = brdno;
 
     mvme16x_get_model(id);
     printk ("\nBRD_ID: %s   BUG %x.%x %02x/%02x/%02x\n", id, p->rev>>4,
 					p->rev&0xf, p->yr, p->mth, p->day);
-    if (p->brdno == 0x0162 || p->brdno == 0x172)
+    if (brdno == 0x0162 || brdno == 0x172)
     {
 	unsigned char rev = *(unsigned char *)MVME162_VERSION_REG;
 
 	mvme16x_config = rev | MVME16x_CONFIG_GOT_SCCA;
 
-	printk ("MVME%x Hardware status:\n", p->brdno);
+	printk ("MVME%x Hardware status:\n", brdno);
 	printk ("    CPU Type           68%s040\n",
 			rev & MVME16x_CONFIG_GOT_FPU ? "" : "LC");
 	printk ("    CPU clock          %dMHz\n",
@@ -348,12 +351,12 @@ void __init config_mvme16x(void)
 
 static irqreturn_t mvme16x_abort_int (int irq, void *dev_id)
 {
-	p_bdid p = &mvme_bdid;
 	unsigned long *new = (unsigned long *)vectors;
 	unsigned long *old = (unsigned long *)0xffe00000;
 	volatile unsigned char uc, *ucp;
+	uint16_t brdno = be16_to_cpu(mvme_bdid.brdno);
 
-	if (p->brdno == 0x0162 || p->brdno == 0x172)
+	if (brdno == 0x0162 || brdno == 0x172)
 	{
 		ucp = (volatile unsigned char *)0xfff42043;
 		uc = *ucp | 8;
@@ -367,7 +370,7 @@ static irqreturn_t mvme16x_abort_int (int irq, void *dev_id)
 	*(new+9) = *(old+9);		/* Trace */
 	*(new+47) = *(old+47);		/* Trap #15 */
 
-	if (p->brdno == 0x0162 || p->brdno == 0x172)
+	if (brdno == 0x0162 || brdno == 0x172)
 		*(new+0x5e) = *(old+0x5e);	/* ABORT switch */
 	else
 		*(new+0x6e) = *(old+0x6e);	/* ABORT switch */
@@ -382,7 +385,7 @@ static irqreturn_t mvme16x_timer_int (int irq, void *dev_id)
 
 void mvme16x_sched_init (irq_handler_t timer_routine)
 {
-    p_bdid p = &mvme_bdid;
+    uint16_t brdno = be16_to_cpu(mvme_bdid.brdno);
     int irq;
 
     tick_handler = timer_routine;
@@ -395,7 +398,7 @@ void mvme16x_sched_init (irq_handler_t timer_routine)
 				"timer", mvme16x_timer_int))
 	panic ("Couldn't register timer int");
 
-    if (p->brdno == 0x0162 || p->brdno == 0x172)
+    if (brdno == 0x0162 || brdno == 0x172)
 	irq = MVME162_IRQ_ABORT;
     else
         irq = MVME167_IRQ_ABORT;
-- 
cgit v0.10.2


From 371001e502e8cd3543f7b9907d398a112939dff7 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Sat, 5 Oct 2013 21:14:22 +0200
Subject: m68k: Remove superfluous inclusions of <asm/bootinfo.h>

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/mac/iop.c b/arch/m68k/mac/iop.c
index ed0d9b0..4d2adfb 100644
--- a/arch/m68k/mac/iop.c
+++ b/arch/m68k/mac/iop.c
@@ -111,7 +111,6 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 
-#include <asm/bootinfo.h>
 #include <asm/macintosh.h>
 #include <asm/macints.h>
 #include <asm/mac_iop.h>
diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c
index 3d02a3c..707b61a 100644
--- a/arch/m68k/mac/misc.c
+++ b/arch/m68k/mac/misc.c
@@ -25,7 +25,6 @@
 #include <asm/mac_via.h>
 #include <asm/mac_oss.h>
 
-#include <asm/bootinfo.h>
 #include <asm/machdep.h>
 
 /* Offset between Unix time (1970-based) and Mac time (1904-based) */
diff --git a/arch/m68k/mac/oss.c b/arch/m68k/mac/oss.c
index 6c4c882..5403712 100644
--- a/arch/m68k/mac/oss.c
+++ b/arch/m68k/mac/oss.c
@@ -21,7 +21,6 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 
-#include <asm/bootinfo.h>
 #include <asm/macintosh.h>
 #include <asm/macints.h>
 #include <asm/mac_via.h>
diff --git a/arch/m68k/mac/psc.c b/arch/m68k/mac/psc.c
index cc9f3f0..835fa04 100644
--- a/arch/m68k/mac/psc.c
+++ b/arch/m68k/mac/psc.c
@@ -21,7 +21,6 @@
 #include <linux/irq.h>
 
 #include <asm/traps.h>
-#include <asm/bootinfo.h>
 #include <asm/macintosh.h>
 #include <asm/macints.h>
 #include <asm/mac_psc.h>
diff --git a/arch/m68k/mac/via.c b/arch/m68k/mac/via.c
index 5d1458b..e198dec 100644
--- a/arch/m68k/mac/via.c
+++ b/arch/m68k/mac/via.c
@@ -30,7 +30,6 @@
 #include <linux/module.h>
 #include <linux/irq.h>
 
-#include <asm/bootinfo.h>
 #include <asm/macintosh.h>
 #include <asm/macints.h>
 #include <asm/mac_via.h>
diff --git a/arch/m68k/sun3x/prom.c b/arch/m68k/sun3x/prom.c
index a7b7e81..0898c3f 100644
--- a/arch/m68k/sun3x/prom.c
+++ b/arch/m68k/sun3x/prom.c
@@ -10,7 +10,6 @@
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/bootinfo.h>
 #include <asm/setup.h>
 #include <asm/traps.h>
 #include <asm/sun3xprom.h>
diff --git a/drivers/net/ethernet/natsemi/macsonic.c b/drivers/net/ethernet/natsemi/macsonic.c
index 346a4e0..04b3ec1 100644
--- a/drivers/net/ethernet/natsemi/macsonic.c
+++ b/drivers/net/ethernet/natsemi/macsonic.c
@@ -52,7 +52,6 @@
 #include <linux/bitrev.h>
 #include <linux/slab.h>
 
-#include <asm/bootinfo.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
 #include <asm/hwtest.h>
diff --git a/drivers/video/macfb.c b/drivers/video/macfb.c
index 5bd2eb8..cda7587 100644
--- a/drivers/video/macfb.c
+++ b/drivers/video/macfb.c
@@ -34,7 +34,6 @@
 #include <linux/fb.h>
 
 #include <asm/setup.h>
-#include <asm/bootinfo.h>
 #include <asm/macintosh.h>
 #include <asm/io.h>
 
diff --git a/drivers/video/valkyriefb.c b/drivers/video/valkyriefb.c
index e287ebc..97cb9bd 100644
--- a/drivers/video/valkyriefb.c
+++ b/drivers/video/valkyriefb.c
@@ -56,7 +56,6 @@
 #include <linux/cuda.h>
 #include <asm/io.h>
 #ifdef CONFIG_MAC
-#include <asm/bootinfo.h>
 #include <asm/macintosh.h>
 #else
 #include <asm/prom.h>
-- 
cgit v0.10.2


From 7a15dd5c4b9d916cb1734dfd79dbdd5773772abb Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Fri, 18 Oct 2013 09:05:22 +0200
Subject: m68k/atari: Call paging_init() before nf_init()

nf_init() uses virt_to_phys(), which depends on m68k_memoffset being set and
module_fixup() having been called, but this is only done in paging_init().
Hence call paging_init() before nf_init().

This went unnoticed, as virt_to_phys() is a no-op on Atari, unless you start
fiddling with the memory blocks in the bootinfo manually.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c
index 0191485..28abca4 100644
--- a/arch/m68k/kernel/setup_mm.c
+++ b/arch/m68k/kernel/setup_mm.c
@@ -346,12 +346,12 @@ void __init setup_arch(char **cmdline_p)
 		panic("No configuration setup");
 	}
 
+	paging_init();
+
 #ifdef CONFIG_NATFEAT
 	nf_init();
 #endif
 
-	paging_init();
-
 #ifndef CONFIG_SUN3
 	for (i = 1; i < m68k_num_memory; i++)
 		free_bootmem_node(NODE_DATA(i), m68k_memory[i].addr,
-- 
cgit v0.10.2


From 017cecee99d897ae426f3948e7b970eb4f95e1f4 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Fri, 18 Oct 2013 13:10:08 +0200
Subject: m68k: Add infrastructure for machine-specific random_get_entropy()

On m68k, get_cycles() (the default implementation for random_get_entropy())
always returns zero, providing no entropy for the random driver.

Add a hook where platforms can provide their own implementation, and wire
it up in the infrastructure provided by commit
61875f30daf60305712e25b209ef41ced2635bad ("random: allow architectures to
optionally define random_get_entropy()").

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/include/asm/timex.h b/arch/m68k/include/asm/timex.h
index 6759dad..efc1f48 100644
--- a/arch/m68k/include/asm/timex.h
+++ b/arch/m68k/include/asm/timex.h
@@ -28,4 +28,14 @@ static inline cycles_t get_cycles(void)
 	return 0;
 }
 
+extern unsigned long (*mach_random_get_entropy)(void);
+
+static inline unsigned long random_get_entropy(void)
+{
+	if (mach_random_get_entropy)
+		return mach_random_get_entropy();
+	return 0;
+}
+#define random_get_entropy	random_get_entropy
+
 #endif
diff --git a/arch/m68k/kernel/time.c b/arch/m68k/kernel/time.c
index 7eb9792..958f1ad 100644
--- a/arch/m68k/kernel/time.c
+++ b/arch/m68k/kernel/time.c
@@ -28,6 +28,10 @@
 #include <linux/timex.h>
 #include <linux/profile.h>
 
+
+unsigned long (*mach_random_get_entropy)(void);
+
+
 /*
  * timer_interrupt() needs to keep up the real-time clock,
  * as well as call the "xtime_update()" routine every clocktick
-- 
cgit v0.10.2


From 50190edb2a56bb9efa3e2f8ca32482dbd3e42412 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Fri, 18 Oct 2013 13:16:06 +0200
Subject: m68k/amiga: Provide mach_random_get_entropy()

Use the beam position registers, which provide at least 17 bits of data
changing at 1.79 MHz.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c
index 06920e8..c425fa6 100644
--- a/arch/m68k/amiga/config.c
+++ b/arch/m68k/amiga/config.c
@@ -360,6 +360,14 @@ static void __init amiga_identify(void)
 #undef AMIGAHW_ANNOUNCE
 }
 
+
+static unsigned long amiga_random_get_entropy(void)
+{
+	/* VPOSR/VHPOSR provide at least 17 bits of data changing at 1.79 MHz */
+	return *(unsigned long *)&amiga_custom.vposr;
+}
+
+
     /*
      *  Setup the Amiga configuration info
      */
@@ -397,6 +405,8 @@ void __init config_amiga(void)
 	mach_heartbeat = amiga_heartbeat;
 #endif
 
+	mach_random_get_entropy = amiga_random_get_entropy;
+
 	/* Fill in the clock value (based on the 700 kHz E-Clock) */
 	amiga_colorclock = 5*amiga_eclock;	/* 3.5 MHz */
 
-- 
cgit v0.10.2


From 5800dc3cff87c3a1548382298bb16e1fb4ec7e32 Mon Sep 17 00:00:00 2001
From: Jason Baron <jbaron@akamai.com>
Date: Mon, 25 Nov 2013 23:23:04 +0000
Subject: panic: Make panic_timeout configurable

The panic_timeout value can be set via the command line option
'panic=x', or via /proc/sys/kernel/panic, however that is not
sufficient when the panic occurs before we are able to set up
these values. Thus, add a CONFIG_PANIC_TIMEOUT so that we can
set the desired value from the .config.

The default panic_timeout value continues to be 0 - wait
forever. Also adds set_arch_panic_timeout(new_timeout,
arch_default_timeout), which is intended to be used by arches in
arch_setup(). The idea being that the new_timeout is only set if
the user hasn't changed from the arch_default_timeout.

Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: benh@kernel.crashing.org
Cc: paulus@samba.org
Cc: ralf@linux-mips.org
Cc: mpe@ellerman.id.au
Cc: felipe.contreras@gmail.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1a1674daec27c534df409697025ac568ebcee91e.1385418410.git.jbaron@akamai.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index d4e98d1..2ac0277 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -393,6 +393,15 @@ extern int panic_on_oops;
 extern int panic_on_unrecovered_nmi;
 extern int panic_on_io_nmi;
 extern int sysctl_panic_on_stackoverflow;
+/*
+ * Only to be used by arch init code. If the user over-wrote the default
+ * CONFIG_PANIC_TIMEOUT, honor it.
+ */
+static inline void set_arch_panic_timeout(int timeout, int arch_default_timeout)
+{
+	if (panic_timeout == arch_default_timeout)
+		panic_timeout = timeout;
+}
 extern const char *print_tainted(void);
 enum lockdep_ok {
 	LOCKDEP_STILL_OK,
diff --git a/kernel/panic.c b/kernel/panic.c
index c00b4ce..6d63003 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -33,7 +33,7 @@ static int pause_on_oops;
 static int pause_on_oops_flag;
 static DEFINE_SPINLOCK(pause_on_oops_lock);
 
-int panic_timeout;
+int panic_timeout = CONFIG_PANIC_TIMEOUT;
 EXPORT_SYMBOL_GPL(panic_timeout);
 
 ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index db25707..6982094 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -761,6 +761,15 @@ config PANIC_ON_OOPS_VALUE
 	default 0 if !PANIC_ON_OOPS
 	default 1 if PANIC_ON_OOPS
 
+config PANIC_TIMEOUT
+	int "panic timeout"
+	default 0
+	help
+	  Set the timeout value (in seconds) until a reboot occurs when the
+	  the kernel panics. If n = 0, then we wait forever. A timeout
+	  value n > 0 will wait n seconds before rebooting, while a timeout
+	  value n < 0 will reboot immediately.
+
 config SCHED_DEBUG
 	bool "Collect scheduler debugging info"
 	depends on DEBUG_KERNEL && PROC_FS
-- 
cgit v0.10.2


From 7972e966b032939afe63d8db22975240879dfd2a Mon Sep 17 00:00:00 2001
From: Ralf Baechle <ralf@linux-mips.org>
Date: Mon, 25 Nov 2013 23:23:07 +0000
Subject: MIPS: Remove panic_timeout settings

Now that we have a CONFIG_PANIC_TIMEOUT=x setting, remove the
mips settings. The default is 0, which means don't reboot on
panic.

Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Acked-by: Shinya Kuribayashi <skuribay@pobox.com>
Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: benh@kernel.crashing.org
Cc: paulus@samba.org
Cc: mpe@ellerman.id.au
Cc: felipe.contreras@gmail.com
Cc: linux-mips@linux-mips.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/d19dc75fca343ec5d9ada75a1400f57330021976.1385418410.git.jbaron@akamai.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/mips/ar7/setup.c b/arch/mips/ar7/setup.c
index 9a357ff..820b7a3 100644
--- a/arch/mips/ar7/setup.c
+++ b/arch/mips/ar7/setup.c
@@ -92,7 +92,6 @@ void __init plat_mem_setup(void)
 	_machine_restart = ar7_machine_restart;
 	_machine_halt = ar7_machine_halt;
 	pm_power_off = ar7_machine_power_off;
-	panic_timeout = 3;
 
 	io_base = (unsigned long)ioremap(AR7_REGS_BASE, 0x10000);
 	if (!io_base)
diff --git a/arch/mips/emma/markeins/setup.c b/arch/mips/emma/markeins/setup.c
index d710058..9100122 100644
--- a/arch/mips/emma/markeins/setup.c
+++ b/arch/mips/emma/markeins/setup.c
@@ -111,9 +111,6 @@ void __init plat_mem_setup(void)
 	iomem_resource.start = EMMA2RH_IO_BASE;
 	iomem_resource.end = EMMA2RH_ROM_BASE - 1;
 
-	/* Reboot on panic */
-	panic_timeout = 180;
-
 	markeins_sio_setup();
 }
 
diff --git a/arch/mips/netlogic/xlp/setup.c b/arch/mips/netlogic/xlp/setup.c
index 6d981bb..54e75c7 100644
--- a/arch/mips/netlogic/xlp/setup.c
+++ b/arch/mips/netlogic/xlp/setup.c
@@ -92,7 +92,6 @@ static void __init xlp_init_mem_from_bars(void)
 
 void __init plat_mem_setup(void)
 {
-	panic_timeout	= 5;
 	_machine_restart = (void (*)(char *))nlm_linux_exit;
 	_machine_halt	= nlm_linux_exit;
 	pm_power_off	= nlm_linux_exit;
diff --git a/arch/mips/netlogic/xlr/setup.c b/arch/mips/netlogic/xlr/setup.c
index 214d123..921be5f 100644
--- a/arch/mips/netlogic/xlr/setup.c
+++ b/arch/mips/netlogic/xlr/setup.c
@@ -92,7 +92,6 @@ static void nlm_linux_exit(void)
 
 void __init plat_mem_setup(void)
 {
-	panic_timeout	= 5;
 	_machine_restart = (void (*)(char *))nlm_linux_exit;
 	_machine_halt	= nlm_linux_exit;
 	pm_power_off	= nlm_linux_exit;
diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c
index 41707a2..3462c83 100644
--- a/arch/mips/sibyte/swarm/setup.c
+++ b/arch/mips/sibyte/swarm/setup.c
@@ -134,8 +134,6 @@ void __init plat_mem_setup(void)
 #error invalid SiByte board configuration
 #endif
 
-	panic_timeout = 5;  /* For debug.  */
-
 	board_be_handler = swarm_be_handler;
 
 	if (xicor_probe())
-- 
cgit v0.10.2


From b71d47c14fba6270c0b5a0d56639bf042017025b Mon Sep 17 00:00:00 2001
From: Jason Baron <jbaron@akamai.com>
Date: Mon, 25 Nov 2013 23:23:11 +0000
Subject: powerpc: Clean up panic_timeout usage

Default CONFIG_PANIC_TIMEOUT to 180 seconds on powerpc. The
pSeries continue to set the timeout to 10 seconds at run-time.

Thus, there's a small window where we don't have the correct
value on pSeries, but if this is only run-time discoverable we
don't have a better option. In any case, if the user changes the
default setting of 180 seconds, we honor that user setting.

Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: benh@kernel.crashing.org
Cc: paulus@samba.org
Cc: ralf@linux-mips.org
Cc: mpe@ellerman.id.au
Cc: felipe.contreras@gmail.com
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/705bbe0f70fb20759151642ba0176a6414ec9f7a.1385418410.git.jbaron@akamai.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index b44b52c..b2be8e8 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -147,6 +147,10 @@ config EARLY_PRINTK
 	bool
 	default y
 
+config PANIC_TIMEOUT
+	int
+	default 180
+
 config COMPAT
 	bool
 	default y if PPC64
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index 703a841..11ba86e 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -26,6 +26,7 @@ extern void reloc_got2(unsigned long);
 void check_for_initrd(void);
 void do_init_bootmem(void);
 void setup_panic(void);
+#define ARCH_PANIC_TIMEOUT 180
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index b903dc5..2b0da27 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -296,9 +296,6 @@ void __init setup_arch(char **cmdline_p)
 	if (cpu_has_feature(CPU_FTR_UNIFIED_ID_CACHE))
 		ucache_bsize = icache_bsize = dcache_bsize;
 
-	/* reboot on panic */
-	panic_timeout = 180;
-
 	if (ppc_md.panic)
 		setup_panic();
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 4085aaa..856dd4e 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -588,9 +588,6 @@ void __init setup_arch(char **cmdline_p)
 	dcache_bsize = ppc64_caches.dline_size;
 	icache_bsize = ppc64_caches.iline_size;
 
-	/* reboot on panic */
-	panic_timeout = 180;
-
 	if (ppc_md.panic)
 		setup_panic();
 
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index c1f1908..6f76ae4 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -470,7 +470,7 @@ static long pseries_little_endian_exceptions(void)
 
 static void __init pSeries_setup_arch(void)
 {
-	panic_timeout = 10;
+	set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT);
 
 	/* Discover PIC type and setup ppc_md accordingly */
 	pseries_discover_pic();
-- 
cgit v0.10.2


From 39e24d8ffbb6aa90222527dbd5991ec49fbbf323 Mon Sep 17 00:00:00 2001
From: Shigeru Yoshida <shigeru.yoshida@gmail.com>
Date: Sat, 23 Nov 2013 18:38:01 +0900
Subject: sched: Fix a trivial syntax misuse

Use if statement instead of while loop.

Signed-off-by: Shigeru Yoshida <shigeru.yoshida@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Jiri Kosina <trivial@kernel.org>
Link: http://lkml.kernel.org/r/20131123.183801.769652906919404319.shigeru.yoshida@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c180860..687985b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3654,7 +3654,7 @@ again:
 	}
 
 	double_rq_lock(rq, p_rq);
-	while (task_rq(p) != p_rq) {
+	if (task_rq(p) != p_rq) {
 		double_rq_unlock(rq, p_rq);
 		goto again;
 	}
-- 
cgit v0.10.2


From f48cfddc6729ef133933062320039808bafa6f45 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 8 Nov 2013 16:31:29 -0800
Subject: vfs: In d_path don't call d_dname on a mount point

Aditya Kali (adityakali@google.com) wrote:
> Commit bf056bfa80596a5d14b26b17276a56a0dcb080e5:
> "proc: Fix the namespace inode permission checks." converted
> the namespace files into symlinks. The same commit changed
> the way namespace bind mounts appear in /proc/mounts:
>   $ mount --bind /proc/self/ns/ipc /mnt/ipc
> Originally:
>   $ cat /proc/mounts | grep ipc
>   proc /mnt/ipc proc rw,nosuid,nodev,noexec 0 0
>
> After commit bf056bfa80596a5d14b26b17276a56a0dcb080e5:
>   $ cat /proc/mounts | grep ipc
>   proc ipc:[4026531839] proc rw,nosuid,nodev,noexec 0 0
>
> This breaks userspace which expects the 2nd field in
> /proc/mounts to be a valid path.

The symlink /proc/<pid>/ns/{ipc,mnt,net,pid,user,uts} point to
dentries allocated with d_alloc_pseudo that we can mount, and
that have interesting names printed out with d_dname.

When these files are bind mounted /proc/mounts is not currently
displaying the mount point correctly because d_dname is called instead
of just displaying the path where the file is mounted.

Solve this by adding an explicit check to distinguish mounted pseudo
inodes and unmounted pseudo inodes.  Unmounted pseudo inodes always
use mount of their filesstem as the mnt_root  in their path making
these two cases easy to distinguish.

CC: stable@vger.kernel.org
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Reported-by: Aditya Kali <adityakali@google.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

diff --git a/fs/dcache.c b/fs/dcache.c
index 4bdb300..f7282eb 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -3061,8 +3061,13 @@ char *d_path(const struct path *path, char *buf, int buflen)
 	 * thus don't need to be hashed.  They also don't need a name until a
 	 * user wants to identify the object in /proc/pid/fd/.  The little hack
 	 * below allows us to generate a name for these objects on demand:
+	 *
+	 * Some pseudo inodes are mountable.  When they are mounted
+	 * path->dentry == path->mnt->mnt_root.  In that case don't call d_dname
+	 * and instead have d_path return the mounted path.
 	 */
-	if (path->dentry->d_op && path->dentry->d_op->d_dname)
+	if (path->dentry->d_op && path->dentry->d_op->d_dname &&
+	    (!IS_ROOT(path->dentry) || path->dentry != path->mnt->mnt_root))
 		return path->dentry->d_op->d_dname(path->dentry, buf, buflen);
 
 	rcu_read_lock();
-- 
cgit v0.10.2


From 1f7f4dde5c945f41a7abc2285be43d918029ecc5 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 14 Nov 2013 21:10:16 -0800
Subject: fork:  Allow CLONE_PARENT after setns(CLONE_NEWPID)

Serge Hallyn <serge.hallyn@ubuntu.com> writes:
> Hi Oleg,
>
> commit 40a0d32d1eaffe6aac7324ca92604b6b3977eb0e :
> "fork: unify and tighten up CLONE_NEWUSER/CLONE_NEWPID checks"
> breaks lxc-attach in 3.12.  That code forks a child which does
> setns() and then does a clone(CLONE_PARENT).  That way the
> grandchild can be in the right namespaces (which the child was
> not) and be a child of the original task, which is the monitor.
>
> lxc-attach in 3.11 was working fine with no side effects that I
> could see.  Is there a real danger in allowing CLONE_PARENT
> when current->nsproxy->pidns_for_children is not our pidns,
> or was this done out of an "over-abundance of caution"?  Can we
> safely revert that new extra check?

The two fundamental things I know we can not allow are:
- A shared signal queue aka CLONE_THREAD.  Because we compute the pid
  and uid of the signal when we place it in the queue.

- Changing the pid and by extention pid_namespace of an existing
  process.

From a parents perspective there is nothing special about the pid
namespace, to deny CLONE_PARENT, because the parent simply won't know or
care.

From the childs perspective all that is special really are shared signal
queues.

User mode threading with CLONE_PARENT|CLONE_VM|CLONE_SIGHAND and tasks
in different pid namespaces is almost certainly going to break because
it is complicated.  But shared signal handlers can look at per thread
information to know which pid namespace a process is in, so I don't know
of any reason not to support CLONE_PARENT|CLONE_VM|CLONE_SIGHAND threads
at the kernel level.  It would be absolutely stupid to implement but
that is a different thing.

So hmm.

Because it can do no harm, and because it is a regression let's remove
the CLONE_PARENT check and send it stable.

Cc: stable@vger.kernel.org
Acked-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Andy Lutomirski <luto@amacapital.net>
Acked-by: Serge E. Hallyn <serge.hallyn@ubuntu.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

diff --git a/kernel/fork.c b/kernel/fork.c
index 728d5be..f82fa2e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1171,7 +1171,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	 * do not allow it to share a thread group or signal handlers or
 	 * parent with the forking task.
 	 */
-	if (clone_flags & (CLONE_SIGHAND | CLONE_PARENT)) {
+	if (clone_flags & CLONE_SIGHAND) {
 		if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) ||
 		    (task_active_pid_ns(current) !=
 				current->nsproxy->pid_ns_for_children))
-- 
cgit v0.10.2


From 41301ae78a99ead04ea42672a1ab72c6f44cc81d Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 14 Nov 2013 21:22:25 -0800
Subject: vfs: Fix a regression in mounting proc

Gao feng <gaofeng@cn.fujitsu.com> reported that commit
e51db73532955dc5eaba4235e62b74b460709d5b
userns: Better restrictions on when proc and sysfs can be mounted
caused a regression on mounting a new instance of proc in a mount
namespace created with user namespace privileges, when binfmt_misc
is mounted on /proc/sys/fs/binfmt_misc.

This is an unintended regression caused by the absolutely bogus empty
directory check in fs_fully_visible.  The check fs_fully_visible replaced
didn't even bother to attempt to verify proc was fully visible and
hiding proc files with any kind of mount is rare.  So for now fix
the userspace regression by allowing directory with nlink == 1
as /proc/sys/fs/binfmt_misc has.

I will have a better patch but it is not stable material, or
last minute kernel material.  So it will have to wait.

Cc: stable@vger.kernel.org
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Acked-by: Gao feng <gaofeng@cn.fujitsu.com>
Tested-by: Gao feng <gaofeng@cn.fujitsu.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

diff --git a/fs/namespace.c b/fs/namespace.c
index ac2ce8a..be32ebc 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2886,7 +2886,7 @@ bool fs_fully_visible(struct file_system_type *type)
 			struct inode *inode = child->mnt_mountpoint->d_inode;
 			if (!S_ISDIR(inode->i_mode))
 				goto next;
-			if (inode->i_nlink != 2)
+			if (inode->i_nlink > 2)
 				goto next;
 		}
 		visible = true;
-- 
cgit v0.10.2


From 5c4853b60ca8ec3d989ce05a5e995d15c3ed52c0 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Wed, 20 Nov 2013 01:07:34 +0100
Subject: lockdep: Simplify a bit hardirq <-> softirq transitions

Instead of saving the hardirq state on a per CPU variable, which require
an explicit call before the softirq handling and some complication,
just save and restore the hardirq tracing state through functions
return values and parameters.

It simplifies a bit the black magic that works around the fact that
softirqs can be called from hardirqs while hardirqs can nest on softirqs
but those two cases have very different semantics and only the latter
case assume both states.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1384906054-30676-1-git-send-email-fweisbec@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/softirq.c b/kernel/softirq.c
index f84aa48..9a4500e 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -213,40 +213,35 @@ EXPORT_SYMBOL(local_bh_enable_ip);
 
 #ifdef CONFIG_TRACE_IRQFLAGS
 /*
- * Convoluted means of passing __do_softirq() a message through the various
- * architecture execute_on_stack() bits.
- *
  * When we run softirqs from irq_exit() and thus on the hardirq stack we need
  * to keep the lockdep irq context tracking as tight as possible in order to
  * not miss-qualify lock contexts and miss possible deadlocks.
  */
-static DEFINE_PER_CPU(int, softirq_from_hardirq);
 
-static inline void lockdep_softirq_from_hardirq(void)
+static inline bool lockdep_softirq_start(void)
 {
-	this_cpu_write(softirq_from_hardirq, 1);
-}
+	bool in_hardirq = false;
 
-static inline void lockdep_softirq_start(void)
-{
-	if (this_cpu_read(softirq_from_hardirq))
+	if (trace_hardirq_context(current)) {
+		in_hardirq = true;
 		trace_hardirq_exit();
+	}
+
 	lockdep_softirq_enter();
+
+	return in_hardirq;
 }
 
-static inline void lockdep_softirq_end(void)
+static inline void lockdep_softirq_end(bool in_hardirq)
 {
 	lockdep_softirq_exit();
-	if (this_cpu_read(softirq_from_hardirq)) {
-		this_cpu_write(softirq_from_hardirq, 0);
+
+	if (in_hardirq)
 		trace_hardirq_enter();
-	}
 }
-
 #else
-static inline void lockdep_softirq_from_hardirq(void) { }
-static inline void lockdep_softirq_start(void) { }
-static inline void lockdep_softirq_end(void) { }
+static inline bool lockdep_softirq_start(void) { return false; }
+static inline void lockdep_softirq_end(bool in_hardirq) { }
 #endif
 
 asmlinkage void __do_softirq(void)
@@ -255,6 +250,7 @@ asmlinkage void __do_softirq(void)
 	unsigned long old_flags = current->flags;
 	int max_restart = MAX_SOFTIRQ_RESTART;
 	struct softirq_action *h;
+	bool in_hardirq;
 	__u32 pending;
 	int cpu;
 
@@ -269,7 +265,7 @@ asmlinkage void __do_softirq(void)
 	account_irq_enter_time(current);
 
 	__local_bh_disable(_RET_IP_, SOFTIRQ_OFFSET);
-	lockdep_softirq_start();
+	in_hardirq = lockdep_softirq_start();
 
 	cpu = smp_processor_id();
 restart:
@@ -316,7 +312,7 @@ restart:
 		wakeup_softirqd();
 	}
 
-	lockdep_softirq_end();
+	lockdep_softirq_end(in_hardirq);
 	account_irq_exit_time(current);
 	__local_bh_enable(SOFTIRQ_OFFSET);
 	WARN_ON_ONCE(in_interrupt());
@@ -365,7 +361,6 @@ void irq_enter(void)
 static inline void invoke_softirq(void)
 {
 	if (!force_irqthreads) {
-		lockdep_softirq_from_hardirq();
 #ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK
 		/*
 		 * We can safely execute softirq on the current stack if
-- 
cgit v0.10.2


From 71ad88efebbcde374bddf904b96f3a7fc82d45d4 Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Tue, 12 Nov 2013 17:58:48 +0100
Subject: perf: Add active_entry list head to struct perf_event

This patch adds a new field to the struct perf_event.
It is intended to be used to chain events which are
active (enabled). It helps in the hardware layer
for PMUs which do not have actual counter restrictions, i.e.,
free running read-only counters. Active events are chained
as opposed to being tracked via the counter they use.

To save space we use a union with hlist_entry as both
are mutually exclusive (suggested by Jiri Olsa).

Signed-off-by: Stephane Eranian <eranian@google.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: acme@redhat.com
Cc: jolsa@redhat.com
Cc: zheng.z.yan@intel.com
Cc: bp@alien8.de
Cc: maria.n.dimakopoulou@gmail.com
Link: http://lkml.kernel.org/r/1384275531-10892-2-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2e069d1..8f4a70f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -319,7 +319,10 @@ struct perf_event {
 	 */
 	struct list_head		migrate_entry;
 
-	struct hlist_node		hlist_entry;
+	union {
+		struct hlist_node	hlist_entry;
+		struct list_head	active_entry;
+	};
 	int				nr_siblings;
 	int				group_flags;
 	struct perf_event		*group_leader;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 72348dc..403b781 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6655,6 +6655,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	INIT_LIST_HEAD(&event->event_entry);
 	INIT_LIST_HEAD(&event->sibling_list);
 	INIT_LIST_HEAD(&event->rb_entry);
+	INIT_LIST_HEAD(&event->active_entry);
 
 	init_waitqueue_head(&event->waitq);
 	init_irq_work(&event->pending, perf_pending_event);
-- 
cgit v0.10.2


From 410136f5dd96b6013fe6d1011b523b1c247e1ccb Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Tue, 12 Nov 2013 17:58:49 +0100
Subject: tools/perf/stat: Add event unit and scale support

This patch adds perf stat support for handling event units and
scales as exported by the kernel.

The kernel can export PMU events actual unit and scaling factor
via sysfs:

  $ ls -1 /sys/devices/power/events/energy-*
  /sys/devices/power/events/energy-cores
  /sys/devices/power/events/energy-cores.scale
  /sys/devices/power/events/energy-cores.unit
  /sys/devices/power/events/energy-pkg
  /sys/devices/power/events/energy-pkg.scale
  /sys/devices/power/events/energy-pkg.unit
  $ cat /sys/devices/power/events/energy-cores.scale
  2.3283064365386962890625e-10
  $ cat cat /sys/devices/power/events/energy-cores.unit
  Joules

This patch modifies the pmu event alias code to check
for the presence of the .unit and .scale files to load
the corresponding values. They are then used by perf stat
transparently:

   # perf stat -a -e power/energy-pkg/,power/energy-cores/,cycles -I 1000 sleep 1000
   #          time             counts   unit events
       1.000214717               3.07 Joules power/energy-pkg/         [100.00%]
       1.000214717               0.53 Joules power/energy-cores/
       1.000214717           12965028        cycles                    [100.00%]
       2.000749289               3.01 Joules power/energy-pkg/
       2.000749289               0.52 Joules power/energy-cores/
       2.000749289           15817043        cycles

When the event does not have an explicit unit exported by
the kernel, nothing is printed. In csv output mode, there
will be an empty field.

Special thanks to Jiri for providing the supporting code
in the parser to trigger reading of the scale and unit files.

Signed-off-by: Stephane Eranian <eranian@google.com>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: zheng.z.yan@intel.com
Cc: bp@alien8.de
Cc: maria.n.dimakopoulou@gmail.com
Cc: acme@redhat.com
Link: http://lkml.kernel.org/r/1384275531-10892-3-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index ee0d565..dab98b5 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -138,6 +138,7 @@ static const char		*post_cmd			= NULL;
 static bool			sync_run			= false;
 static unsigned int		interval			= 0;
 static unsigned int		initial_delay			= 0;
+static unsigned int		unit_width			= 4; /* strlen("unit") */
 static bool			forever				= false;
 static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
@@ -461,17 +462,17 @@ static void print_interval(void)
 	if (num_print_interval == 0 && !csv_output) {
 		switch (aggr_mode) {
 		case AGGR_SOCKET:
-			fprintf(output, "#           time socket cpus             counts events\n");
+			fprintf(output, "#           time socket cpus             counts %*s events\n", unit_width, "unit");
 			break;
 		case AGGR_CORE:
-			fprintf(output, "#           time core         cpus             counts events\n");
+			fprintf(output, "#           time core         cpus             counts %*s events\n", unit_width, "unit");
 			break;
 		case AGGR_NONE:
-			fprintf(output, "#           time CPU                 counts events\n");
+			fprintf(output, "#           time CPU                counts %*s events\n", unit_width, "unit");
 			break;
 		case AGGR_GLOBAL:
 		default:
-			fprintf(output, "#           time             counts events\n");
+			fprintf(output, "#           time             counts %*s events\n", unit_width, "unit");
 		}
 	}
 
@@ -516,6 +517,7 @@ static int __run_perf_stat(int argc, const char **argv)
 	unsigned long long t0, t1;
 	struct perf_evsel *counter;
 	struct timespec ts;
+	size_t l;
 	int status = 0;
 	const bool forks = (argc > 0);
 
@@ -565,6 +567,10 @@ static int __run_perf_stat(int argc, const char **argv)
 			return -1;
 		}
 		counter->supported = true;
+
+		l = strlen(counter->unit);
+		if (l > unit_width)
+			unit_width = l;
 	}
 
 	if (perf_evlist__apply_filters(evsel_list)) {
@@ -704,14 +710,25 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 {
 	double msecs = avg / 1e6;
-	const char *fmt = csv_output ? "%.6f%s%s" : "%18.6f%s%-25s";
+	const char *fmt_v, *fmt_n;
 	char name[25];
 
+	fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
+	fmt_n = csv_output ? "%s" : "%-25s";
+
 	aggr_printout(evsel, cpu, nr);
 
 	scnprintf(name, sizeof(name), "%s%s",
 		  perf_evsel__name(evsel), csv_output ? "" : " (msec)");
-	fprintf(output, fmt, msecs, csv_sep, name);
+
+	fprintf(output, fmt_v, msecs, csv_sep);
+
+	if (csv_output)
+		fprintf(output, "%s%s", evsel->unit, csv_sep);
+	else
+		fprintf(output, "%-*s%s", unit_width, evsel->unit, csv_sep);
+
+	fprintf(output, fmt_n, name);
 
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
@@ -908,21 +925,31 @@ static void print_ll_cache_misses(int cpu,
 static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 {
 	double total, ratio = 0.0, total2;
+	double sc =  evsel->scale;
 	const char *fmt;
 
-	if (csv_output)
-		fmt = "%.0f%s%s";
-	else if (big_num)
-		fmt = "%'18.0f%s%-25s";
-	else
-		fmt = "%18.0f%s%-25s";
+	if (csv_output) {
+		fmt = sc != 1.0 ?  "%.2f%s" : "%.0f%s";
+	} else {
+		if (big_num)
+			fmt = sc != 1.0 ? "%'18.2f%s" : "%'18.0f%s";
+		else
+			fmt = sc != 1.0 ? "%18.2f%s" : "%18.0f%s";
+	}
 
 	aggr_printout(evsel, cpu, nr);
 
 	if (aggr_mode == AGGR_GLOBAL)
 		cpu = 0;
 
-	fprintf(output, fmt, avg, csv_sep, perf_evsel__name(evsel));
+	fprintf(output, fmt, avg, csv_sep);
+
+	if (evsel->unit)
+		fprintf(output, "%-*s%s",
+			csv_output ? 0 : unit_width,
+			evsel->unit, csv_sep);
+
+	fprintf(output, "%-*s", csv_output ? 0 : 25, perf_evsel__name(evsel));
 
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
@@ -941,7 +968,10 @@ static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 
 		if (total && avg) {
 			ratio = total / avg;
-			fprintf(output, "\n                                             #   %5.2f  stalled cycles per insn", ratio);
+			fprintf(output, "\n");
+			if (aggr_mode == AGGR_NONE)
+				fprintf(output, "        ");
+			fprintf(output, "                                                  #   %5.2f  stalled cycles per insn", ratio);
 		}
 
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
@@ -1061,6 +1091,7 @@ static void print_aggr(char *prefix)
 {
 	struct perf_evsel *counter;
 	int cpu, cpu2, s, s2, id, nr;
+	double uval;
 	u64 ena, run, val;
 
 	if (!(aggr_map || aggr_get_id))
@@ -1087,11 +1118,17 @@ static void print_aggr(char *prefix)
 			if (run == 0 || ena == 0) {
 				aggr_printout(counter, id, nr);
 
-				fprintf(output, "%*s%s%*s",
+				fprintf(output, "%*s%s",
 					csv_output ? 0 : 18,
 					counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-					csv_sep,
-					csv_output ? 0 : -24,
+					csv_sep);
+
+				fprintf(output, "%-*s%s",
+					csv_output ? 0 : unit_width,
+					counter->unit, csv_sep);
+
+				fprintf(output, "%*s",
+					csv_output ? 0 : -25,
 					perf_evsel__name(counter));
 
 				if (counter->cgrp)
@@ -1101,11 +1138,12 @@ static void print_aggr(char *prefix)
 				fputc('\n', output);
 				continue;
 			}
+			uval = val * counter->scale;
 
 			if (nsec_counter(counter))
-				nsec_printout(id, nr, counter, val);
+				nsec_printout(id, nr, counter, uval);
 			else
-				abs_printout(id, nr, counter, val);
+				abs_printout(id, nr, counter, uval);
 
 			if (!csv_output) {
 				print_noise(counter, 1.0);
@@ -1128,16 +1166,21 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 	struct perf_stat *ps = counter->priv;
 	double avg = avg_stats(&ps->res_stats[0]);
 	int scaled = counter->counts->scaled;
+	double uval;
 
 	if (prefix)
 		fprintf(output, "%s", prefix);
 
 	if (scaled == -1) {
-		fprintf(output, "%*s%s%*s",
+		fprintf(output, "%*s%s",
 			csv_output ? 0 : 18,
 			counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-			csv_sep,
-			csv_output ? 0 : -24,
+			csv_sep);
+		fprintf(output, "%-*s%s",
+			csv_output ? 0 : unit_width,
+			counter->unit, csv_sep);
+		fprintf(output, "%*s",
+			csv_output ? 0 : -25,
 			perf_evsel__name(counter));
 
 		if (counter->cgrp)
@@ -1147,10 +1190,12 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 		return;
 	}
 
+	uval = avg * counter->scale;
+
 	if (nsec_counter(counter))
-		nsec_printout(-1, 0, counter, avg);
+		nsec_printout(-1, 0, counter, uval);
 	else
-		abs_printout(-1, 0, counter, avg);
+		abs_printout(-1, 0, counter, uval);
 
 	print_noise(counter, avg);
 
@@ -1177,6 +1222,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 static void print_counter(struct perf_evsel *counter, char *prefix)
 {
 	u64 ena, run, val;
+	double uval;
 	int cpu;
 
 	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
@@ -1188,14 +1234,20 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 			fprintf(output, "%s", prefix);
 
 		if (run == 0 || ena == 0) {
-			fprintf(output, "CPU%*d%s%*s%s%*s",
+			fprintf(output, "CPU%*d%s%*s%s",
 				csv_output ? 0 : -4,
 				perf_evsel__cpus(counter)->map[cpu], csv_sep,
 				csv_output ? 0 : 18,
 				counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-				csv_sep,
-				csv_output ? 0 : -24,
-				perf_evsel__name(counter));
+				csv_sep);
+
+				fprintf(output, "%-*s%s",
+					csv_output ? 0 : unit_width,
+					counter->unit, csv_sep);
+
+				fprintf(output, "%*s",
+					csv_output ? 0 : -25,
+					perf_evsel__name(counter));
 
 			if (counter->cgrp)
 				fprintf(output, "%s%s",
@@ -1205,10 +1257,12 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 			continue;
 		}
 
+		uval = val * counter->scale;
+
 		if (nsec_counter(counter))
-			nsec_printout(cpu, 0, counter, val);
+			nsec_printout(cpu, 0, counter, uval);
 		else
-			abs_printout(cpu, 0, counter, val);
+			abs_printout(cpu, 0, counter, uval);
 
 		if (!csv_output) {
 			print_noise(counter, 1.0);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 46dd4c2..dad6492 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -162,6 +162,8 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->idx	   = idx;
 	evsel->attr	   = *attr;
 	evsel->leader	   = evsel;
+	evsel->unit	   = "";
+	evsel->scale	   = 1.0;
 	INIT_LIST_HEAD(&evsel->node);
 	hists__init(&evsel->hists);
 	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 1ea7c92..8120eeb 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -68,6 +68,8 @@ struct perf_evsel {
 	u32			ids;
 	struct hists		hists;
 	char			*name;
+	double			scale;
+	const char		*unit;
 	struct event_format	*tp_format;
 	union {
 		void		*priv;
@@ -138,6 +140,7 @@ extern const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX];
 int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
 					    char *bf, size_t size);
 const char *perf_evsel__name(struct perf_evsel *evsel);
+
 const char *perf_evsel__group_name(struct perf_evsel *evsel);
 int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 6de6f89..969cb8f 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -269,9 +269,10 @@ const char *event_type(int type)
 
 
 
-static int __add_event(struct list_head *list, int *idx,
-		       struct perf_event_attr *attr,
-		       char *name, struct cpu_map *cpus)
+static struct perf_evsel *
+__add_event(struct list_head *list, int *idx,
+	    struct perf_event_attr *attr,
+	    char *name, struct cpu_map *cpus)
 {
 	struct perf_evsel *evsel;
 
@@ -279,19 +280,19 @@ static int __add_event(struct list_head *list, int *idx,
 
 	evsel = perf_evsel__new_idx(attr, (*idx)++);
 	if (!evsel)
-		return -ENOMEM;
+		return NULL;
 
 	evsel->cpus = cpus;
 	if (name)
 		evsel->name = strdup(name);
 	list_add_tail(&evsel->node, list);
-	return 0;
+	return evsel;
 }
 
 static int add_event(struct list_head *list, int *idx,
 		     struct perf_event_attr *attr, char *name)
 {
-	return __add_event(list, idx, attr, name, NULL);
+	return __add_event(list, idx, attr, name, NULL) ? 0 : -ENOMEM;
 }
 
 static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size)
@@ -633,6 +634,9 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 {
 	struct perf_event_attr attr;
 	struct perf_pmu *pmu;
+	struct perf_evsel *evsel;
+	char *unit;
+	double scale;
 
 	pmu = perf_pmu__find(name);
 	if (!pmu)
@@ -640,7 +644,7 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 
 	memset(&attr, 0, sizeof(attr));
 
-	if (perf_pmu__check_alias(pmu, head_config))
+	if (perf_pmu__check_alias(pmu, head_config, &unit, &scale))
 		return -EINVAL;
 
 	/*
@@ -652,8 +656,14 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 	if (perf_pmu__config(pmu, &attr, head_config))
 		return -EINVAL;
 
-	return __add_event(list, idx, &attr, pmu_event_name(head_config),
-			   pmu->cpus);
+	evsel = __add_event(list, idx, &attr, pmu_event_name(head_config),
+			    pmu->cpus);
+	if (evsel) {
+		evsel->unit = unit;
+		evsel->scale = scale;
+	}
+
+	return evsel ? 0 : -ENOMEM;
 }
 
 int parse_events__modifier_group(struct list_head *list,
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index c232d8d..56fc10a 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1,19 +1,23 @@
 #include <linux/list.h>
 #include <sys/types.h>
-#include <sys/stat.h>
 #include <unistd.h>
 #include <stdio.h>
 #include <dirent.h>
 #include "fs.h"
+#include <locale.h>
 #include "util.h"
 #include "pmu.h"
 #include "parse-events.h"
 #include "cpumap.h"
 
+#define UNIT_MAX_LEN	31 /* max length for event unit name */
+
 struct perf_pmu_alias {
 	char *name;
 	struct list_head terms;
 	struct list_head list;
+	char unit[UNIT_MAX_LEN+1];
+	double scale;
 };
 
 struct perf_pmu_format {
@@ -94,7 +98,80 @@ static int pmu_format(const char *name, struct list_head *format)
 	return 0;
 }
 
-static int perf_pmu__new_alias(struct list_head *list, char *name, FILE *file)
+static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name)
+{
+	struct stat st;
+	ssize_t sret;
+	char scale[128];
+	int fd, ret = -1;
+	char path[PATH_MAX];
+	char *lc;
+
+	snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
+
+	fd = open(path, O_RDONLY);
+	if (fd == -1)
+		return -1;
+
+	if (fstat(fd, &st) < 0)
+		goto error;
+
+	sret = read(fd, scale, sizeof(scale)-1);
+	if (sret < 0)
+		goto error;
+
+	scale[sret] = '\0';
+	/*
+	 * save current locale
+	 */
+	lc = setlocale(LC_NUMERIC, NULL);
+
+	/*
+	 * force to C locale to ensure kernel
+	 * scale string is converted correctly.
+	 * kernel uses default C locale.
+	 */
+	setlocale(LC_NUMERIC, "C");
+
+	alias->scale = strtod(scale, NULL);
+
+	/* restore locale */
+	setlocale(LC_NUMERIC, lc);
+
+	ret = 0;
+error:
+	close(fd);
+	return ret;
+}
+
+static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *name)
+{
+	char path[PATH_MAX];
+	ssize_t sret;
+	int fd;
+
+	snprintf(path, PATH_MAX, "%s/%s.unit", dir, name);
+
+	fd = open(path, O_RDONLY);
+	if (fd == -1)
+		return -1;
+
+		sret = read(fd, alias->unit, UNIT_MAX_LEN);
+	if (sret < 0)
+		goto error;
+
+	close(fd);
+
+	alias->unit[sret] = '\0';
+
+	return 0;
+error:
+	close(fd);
+	alias->unit[0] = '\0';
+	return -1;
+}
+
+static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file)
 {
 	struct perf_pmu_alias *alias;
 	char buf[256];
@@ -110,6 +187,9 @@ static int perf_pmu__new_alias(struct list_head *list, char *name, FILE *file)
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&alias->terms);
+	alias->scale = 1.0;
+	alias->unit[0] = '\0';
+
 	ret = parse_events_terms(&alias->terms, buf);
 	if (ret) {
 		free(alias);
@@ -117,7 +197,14 @@ static int perf_pmu__new_alias(struct list_head *list, char *name, FILE *file)
 	}
 
 	alias->name = strdup(name);
+	/*
+	 * load unit name and scale if available
+	 */
+	perf_pmu__parse_unit(alias, dir, name);
+	perf_pmu__parse_scale(alias, dir, name);
+
 	list_add_tail(&alias->list, list);
+
 	return 0;
 }
 
@@ -129,6 +216,7 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 {
 	struct dirent *evt_ent;
 	DIR *event_dir;
+	size_t len;
 	int ret = 0;
 
 	event_dir = opendir(dir);
@@ -143,13 +231,24 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 		if (!strcmp(name, ".") || !strcmp(name, ".."))
 			continue;
 
+		/*
+		 * skip .unit and .scale info files
+		 * parsed in perf_pmu__new_alias()
+		 */
+		len = strlen(name);
+		if (len > 5 && !strcmp(name + len - 5, ".unit"))
+			continue;
+		if (len > 6 && !strcmp(name + len - 6, ".scale"))
+			continue;
+
 		snprintf(path, PATH_MAX, "%s/%s", dir, name);
 
 		ret = -EINVAL;
 		file = fopen(path, "r");
 		if (!file)
 			break;
-		ret = perf_pmu__new_alias(head, name, file);
+
+		ret = perf_pmu__new_alias(head, dir, name, file);
 		fclose(file);
 	}
 
@@ -508,16 +607,42 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 	return NULL;
 }
 
+
+static int check_unit_scale(struct perf_pmu_alias *alias,
+			    char **unit, double *scale)
+{
+	/*
+	 * Only one term in event definition can
+	 * define unit and scale, fail if there's
+	 * more than one.
+	 */
+	if ((*unit && alias->unit) ||
+	    (*scale && alias->scale))
+		return -EINVAL;
+
+	if (alias->unit)
+		*unit = alias->unit;
+
+	if (alias->scale)
+		*scale = alias->scale;
+
+	return 0;
+}
+
 /*
  * Find alias in the terms list and replace it with the terms
  * defined for the alias
  */
-int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms)
+int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
+			  char **unit, double *scale)
 {
 	struct parse_events_term *term, *h;
 	struct perf_pmu_alias *alias;
 	int ret;
 
+	*unit   = NULL;
+	*scale  = 0;
+
 	list_for_each_entry_safe(term, h, head_terms, list) {
 		alias = pmu_find_alias(pmu, term);
 		if (!alias)
@@ -525,6 +650,11 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms)
 		ret = pmu_alias_terms(alias, &term->list);
 		if (ret)
 			return ret;
+
+		ret = check_unit_scale(alias, unit, scale);
+		if (ret)
+			return ret;
+
 		list_del(&term->list);
 		free(term);
 	}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 1179b26..9183380 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -28,7 +28,8 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
 int perf_pmu__config_terms(struct list_head *formats,
 			   struct perf_event_attr *attr,
 			   struct list_head *head_terms);
-int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms);
+int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
+			  char **unit, double *scale);
 struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
 				  struct list_head *head_terms);
 int perf_pmu_wrap(void);
-- 
cgit v0.10.2


From 4788e5b4b2338f85fa42a712a182d8afd65d7c58 Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Tue, 12 Nov 2013 17:58:50 +0100
Subject: perf/x86: Add Intel RAPL PMU support

This patch adds a new uncore PMU to expose the Intel
RAPL energy consumption counters. Up to 3 counters,
each counting a particular RAPL event are exposed.

The RAPL counters are available on Intel SandyBridge,
IvyBridge, Haswell. The server skus add a 3rd counter.

The following events are available and exposed in sysfs:

  - power/energy-cores: power consumption of all cores on socket
  - power/energy-pkg: power consumption of all cores + LLc cache
  - power/energy-dram: power consumption of DRAM (servers only)

For each event both the unit (Joules) and scale (2^-32 J)
is exposed in sysfs for use by perf stat and other tools.
The files are:

	/sys/devices/power/events/energy-*.unit
	/sys/devices/power/events/energy-*.scale

The RAPL PMU is uncore by nature and is implemented such
that it only works in system-wide mode. Measuring only
one CPU per socket is sufficient. The /sys/devices/power/cpumask
file can be used by tools to figure out which CPUs to monitor
by default. For instance, on a 2-socket system, 2 CPUs
(one on each socket) will be shown.

All the counters measure in the same unit (exposed via sysfs).
The perf_events API exposes all RAPL counters as 64-bit integers
counting in unit of 1/2^32 Joules (about 0.23 nJ). User level tools
must convert the counts by multiplying them by 2^-32 to obtain
Joules. The reason for this is that the kernel avoids
doing floating point math whenever possible because it is
expensive (user floating-point state must be saved). The method
used avoids kernel floating-point usage. There is no loss of
precision. Thanks to PeterZ for suggesting this approach.

To convert the raw count in Watt:
   W = C * 2.3 / (1e10 * time)
or ldexp(C, -32).

RAPL PMU is a new standalone PMU which registers with the
perf_event core subsystem. The PMU type (attr->type) is
dynamically allocated and is available from /sys/device/power/type.

Sampling is not supported by the RAPL PMU. There is no
privilege level filtering either.

Signed-off-by: Stephane Eranian <eranian@google.com>
Reviewed-by: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: acme@redhat.com
Cc: jolsa@redhat.com
Cc: zheng.z.yan@intel.com
Cc: bp@alien8.de
Link: http://lkml.kernel.org/r/1384275531-10892-4-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 47b56a7..6359506 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -36,7 +36,7 @@ obj-$(CONFIG_CPU_SUP_AMD)		+= perf_event_amd_iommu.o
 endif
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_p6.o perf_event_knc.o perf_event_p4.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
-obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_uncore.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_uncore.o perf_event_intel_rapl.o
 endif
 
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
new file mode 100644
index 0000000..cfcd386
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -0,0 +1,591 @@
+/*
+ * perf_event_intel_rapl.c: support Intel RAPL energy consumption counters
+ * Copyright (C) 2013 Google, Inc., Stephane Eranian
+ *
+ * Intel RAPL interface is specified in the IA-32 Manual Vol3b
+ * section 14.7.1 (September 2013)
+ *
+ * RAPL provides more controls than just reporting energy consumption
+ * however here we only expose the 3 energy consumption free running
+ * counters (pp0, pkg, dram).
+ *
+ * Each of those counters increments in a power unit defined by the
+ * RAPL_POWER_UNIT MSR. On SandyBridge, this unit is 1/(2^16) Joules
+ * but it can vary.
+ *
+ * Counter to rapl events mappings:
+ *
+ *  pp0 counter: consumption of all physical cores (power plane 0)
+ * 	  event: rapl_energy_cores
+ *    perf code: 0x1
+ *
+ *  pkg counter: consumption of the whole processor package
+ *	  event: rapl_energy_pkg
+ *    perf code: 0x2
+ *
+ * dram counter: consumption of the dram domain (servers only)
+ *	  event: rapl_energy_dram
+ *    perf code: 0x3
+ *
+ * We manage those counters as free running (read-only). They may be
+ * use simultaneously by other tools, such as turbostat.
+ *
+ * The events only support system-wide mode counting. There is no
+ * sampling support because it does not make sense and is not
+ * supported by the RAPL hardware.
+ *
+ * Because we want to avoid floating-point operations in the kernel,
+ * the events are all reported in fixed point arithmetic (32.32).
+ * Tools must adjust the counts to convert them to Watts using
+ * the duration of the measurement. Tools may use a function such as
+ * ldexp(raw_count, -32);
+ */
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/perf_event.h>
+#include <asm/cpu_device_id.h>
+#include "perf_event.h"
+
+/*
+ * RAPL energy status counters
+ */
+#define RAPL_IDX_PP0_NRG_STAT	0	/* all cores */
+#define INTEL_RAPL_PP0		0x1	/* pseudo-encoding */
+#define RAPL_IDX_PKG_NRG_STAT	1	/* entire package */
+#define INTEL_RAPL_PKG		0x2	/* pseudo-encoding */
+#define RAPL_IDX_RAM_NRG_STAT	2	/* DRAM */
+#define INTEL_RAPL_RAM		0x3	/* pseudo-encoding */
+
+/* Clients have PP0, PKG */
+#define RAPL_IDX_CLN	(1<<RAPL_IDX_PP0_NRG_STAT|\
+			 1<<RAPL_IDX_PKG_NRG_STAT)
+
+/* Servers have PP0, PKG, RAM */
+#define RAPL_IDX_SRV	(1<<RAPL_IDX_PP0_NRG_STAT|\
+			 1<<RAPL_IDX_PKG_NRG_STAT|\
+			 1<<RAPL_IDX_RAM_NRG_STAT)
+
+/*
+ * event code: LSB 8 bits, passed in attr->config
+ * any other bit is reserved
+ */
+#define RAPL_EVENT_MASK	0xFFULL
+
+#define DEFINE_RAPL_FORMAT_ATTR(_var, _name, _format)		\
+static ssize_t __rapl_##_var##_show(struct kobject *kobj,	\
+				struct kobj_attribute *attr,	\
+				char *page)			\
+{								\
+	BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE);		\
+	return sprintf(page, _format "\n");			\
+}								\
+static struct kobj_attribute format_attr_##_var =		\
+	__ATTR(_name, 0444, __rapl_##_var##_show, NULL)
+
+#define RAPL_EVENT_DESC(_name, _config)				\
+{								\
+	.attr	= __ATTR(_name, 0444, rapl_event_show, NULL),	\
+	.config	= _config,					\
+}
+
+#define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */
+
+struct rapl_pmu {
+	spinlock_t	 lock;
+	int		 hw_unit;  /* 1/2^hw_unit Joule */
+	int		 n_active; /* number of active events */
+	struct list_head active_list;
+	struct pmu	 *pmu; /* pointer to rapl_pmu_class */
+};
+
+static struct pmu rapl_pmu_class;
+static cpumask_t rapl_cpu_mask;
+static int rapl_cntr_mask;
+
+static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu);
+static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu_to_free);
+
+static inline u64 rapl_read_counter(struct perf_event *event)
+{
+	u64 raw;
+	rdmsrl(event->hw.event_base, raw);
+	return raw;
+}
+
+static inline u64 rapl_scale(u64 v)
+{
+	/*
+	 * scale delta to smallest unit (1/2^32)
+	 * users must then scale back: count * 1/(1e9*2^32) to get Joules
+	 * or use ldexp(count, -32).
+	 * Watts = Joules/Time delta
+	 */
+	return v << (32 - __get_cpu_var(rapl_pmu)->hw_unit);
+}
+
+static u64 rapl_event_update(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	u64 prev_raw_count, new_raw_count;
+	s64 delta, sdelta;
+	int shift = RAPL_CNTR_WIDTH;
+
+again:
+	prev_raw_count = local64_read(&hwc->prev_count);
+	rdmsrl(event->hw.event_base, new_raw_count);
+
+	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
+			    new_raw_count) != prev_raw_count) {
+		cpu_relax();
+		goto again;
+	}
+
+	/*
+	 * Now we have the new raw value and have updated the prev
+	 * timestamp already. We can now calculate the elapsed delta
+	 * (event-)time and add that to the generic event.
+	 *
+	 * Careful, not all hw sign-extends above the physical width
+	 * of the count.
+	 */
+	delta = (new_raw_count << shift) - (prev_raw_count << shift);
+	delta >>= shift;
+
+	sdelta = rapl_scale(delta);
+
+	local64_add(sdelta, &event->count);
+
+	return new_raw_count;
+}
+
+static void __rapl_pmu_event_start(struct rapl_pmu *pmu,
+				   struct perf_event *event)
+{
+	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+		return;
+
+	event->hw.state = 0;
+
+	list_add_tail(&event->active_entry, &pmu->active_list);
+
+	local64_set(&event->hw.prev_count, rapl_read_counter(event));
+
+	pmu->n_active++;
+}
+
+static void rapl_pmu_event_start(struct perf_event *event, int mode)
+{
+	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	unsigned long flags;
+
+	spin_lock_irqsave(&pmu->lock, flags);
+	__rapl_pmu_event_start(pmu, event);
+	spin_unlock_irqrestore(&pmu->lock, flags);
+}
+
+static void rapl_pmu_event_stop(struct perf_event *event, int mode)
+{
+	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pmu->lock, flags);
+
+	/* mark event as deactivated and stopped */
+	if (!(hwc->state & PERF_HES_STOPPED)) {
+		WARN_ON_ONCE(pmu->n_active <= 0);
+		pmu->n_active--;
+
+		list_del(&event->active_entry);
+
+		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+		hwc->state |= PERF_HES_STOPPED;
+	}
+
+	/* check if update of sw counter is necessary */
+	if ((mode & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+		/*
+		 * Drain the remaining delta count out of a event
+		 * that we are disabling:
+		 */
+		rapl_event_update(event);
+		hwc->state |= PERF_HES_UPTODATE;
+	}
+
+	spin_unlock_irqrestore(&pmu->lock, flags);
+}
+
+static int rapl_pmu_event_add(struct perf_event *event, int mode)
+{
+	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pmu->lock, flags);
+
+	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+	if (mode & PERF_EF_START)
+		__rapl_pmu_event_start(pmu, event);
+
+	spin_unlock_irqrestore(&pmu->lock, flags);
+
+	return 0;
+}
+
+static void rapl_pmu_event_del(struct perf_event *event, int flags)
+{
+	rapl_pmu_event_stop(event, PERF_EF_UPDATE);
+}
+
+static int rapl_pmu_event_init(struct perf_event *event)
+{
+	u64 cfg = event->attr.config & RAPL_EVENT_MASK;
+	int bit, msr, ret = 0;
+
+	/* only look at RAPL events */
+	if (event->attr.type != rapl_pmu_class.type)
+		return -ENOENT;
+
+	/* check only supported bits are set */
+	if (event->attr.config & ~RAPL_EVENT_MASK)
+		return -EINVAL;
+
+	/*
+	 * check event is known (determines counter)
+	 */
+	switch (cfg) {
+	case INTEL_RAPL_PP0:
+		bit = RAPL_IDX_PP0_NRG_STAT;
+		msr = MSR_PP0_ENERGY_STATUS;
+		break;
+	case INTEL_RAPL_PKG:
+		bit = RAPL_IDX_PKG_NRG_STAT;
+		msr = MSR_PKG_ENERGY_STATUS;
+		break;
+	case INTEL_RAPL_RAM:
+		bit = RAPL_IDX_RAM_NRG_STAT;
+		msr = MSR_DRAM_ENERGY_STATUS;
+		break;
+	default:
+		return -EINVAL;
+	}
+	/* check event supported */
+	if (!(rapl_cntr_mask & (1 << bit)))
+		return -EINVAL;
+
+	/* unsupported modes and filters */
+	if (event->attr.exclude_user   ||
+	    event->attr.exclude_kernel ||
+	    event->attr.exclude_hv     ||
+	    event->attr.exclude_idle   ||
+	    event->attr.exclude_host   ||
+	    event->attr.exclude_guest  ||
+	    event->attr.sample_period) /* no sampling */
+		return -EINVAL;
+
+	/* must be done before validate_group */
+	event->hw.event_base = msr;
+	event->hw.config = cfg;
+	event->hw.idx = bit;
+
+	return ret;
+}
+
+static void rapl_pmu_event_read(struct perf_event *event)
+{
+	rapl_event_update(event);
+}
+
+static ssize_t rapl_get_attr_cpumask(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &rapl_cpu_mask);
+
+	buf[n++] = '\n';
+	buf[n] = '\0';
+	return n;
+}
+
+static DEVICE_ATTR(cpumask, S_IRUGO, rapl_get_attr_cpumask, NULL);
+
+static struct attribute *rapl_pmu_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL,
+};
+
+static struct attribute_group rapl_pmu_attr_group = {
+	.attrs = rapl_pmu_attrs,
+};
+
+EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
+EVENT_ATTR_STR(energy-pkg  , rapl_pkg, "event=0x02");
+EVENT_ATTR_STR(energy-ram  , rapl_ram, "event=0x03");
+
+EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules");
+EVENT_ATTR_STR(energy-pkg.unit  , rapl_pkg_unit, "Joules");
+EVENT_ATTR_STR(energy-ram.unit  , rapl_ram_unit, "Joules");
+
+/*
+ * we compute in 0.23 nJ increments regardless of MSR
+ */
+EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10");
+EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10");
+EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10");
+
+static struct attribute *rapl_events_srv_attr[] = {
+	EVENT_PTR(rapl_cores),
+	EVENT_PTR(rapl_pkg),
+	EVENT_PTR(rapl_ram),
+
+	EVENT_PTR(rapl_cores_unit),
+	EVENT_PTR(rapl_pkg_unit),
+	EVENT_PTR(rapl_ram_unit),
+
+	EVENT_PTR(rapl_cores_scale),
+	EVENT_PTR(rapl_pkg_scale),
+	EVENT_PTR(rapl_ram_scale),
+	NULL,
+};
+
+static struct attribute *rapl_events_cln_attr[] = {
+	EVENT_PTR(rapl_cores),
+	EVENT_PTR(rapl_pkg),
+
+	EVENT_PTR(rapl_cores_unit),
+	EVENT_PTR(rapl_pkg_unit),
+
+	EVENT_PTR(rapl_cores_scale),
+	EVENT_PTR(rapl_pkg_scale),
+	NULL,
+};
+
+static struct attribute_group rapl_pmu_events_group = {
+	.name = "events",
+	.attrs = NULL, /* patched at runtime */
+};
+
+DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7");
+static struct attribute *rapl_formats_attr[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group rapl_pmu_format_group = {
+	.name = "format",
+	.attrs = rapl_formats_attr,
+};
+
+const struct attribute_group *rapl_attr_groups[] = {
+	&rapl_pmu_attr_group,
+	&rapl_pmu_format_group,
+	&rapl_pmu_events_group,
+	NULL,
+};
+
+static struct pmu rapl_pmu_class = {
+	.attr_groups	= rapl_attr_groups,
+	.task_ctx_nr	= perf_invalid_context, /* system-wide only */
+	.event_init	= rapl_pmu_event_init,
+	.add		= rapl_pmu_event_add, /* must have */
+	.del		= rapl_pmu_event_del, /* must have */
+	.start		= rapl_pmu_event_start,
+	.stop		= rapl_pmu_event_stop,
+	.read		= rapl_pmu_event_read,
+};
+
+static void rapl_cpu_exit(int cpu)
+{
+	struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
+	int i, phys_id = topology_physical_package_id(cpu);
+	int target = -1;
+
+	/* find a new cpu on same package */
+	for_each_online_cpu(i) {
+		if (i == cpu)
+			continue;
+		if (phys_id == topology_physical_package_id(i)) {
+			target = i;
+			break;
+		}
+	}
+	/*
+	 * clear cpu from cpumask
+	 * if was set in cpumask and still some cpu on package,
+	 * then move to new cpu
+	 */
+	if (cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask) && target >= 0)
+		cpumask_set_cpu(target, &rapl_cpu_mask);
+
+	WARN_ON(cpumask_empty(&rapl_cpu_mask));
+	/*
+	 * migrate events and context to new cpu
+	 */
+	if (target >= 0)
+		perf_pmu_migrate_context(pmu->pmu, cpu, target);
+}
+
+static void rapl_cpu_init(int cpu)
+{
+	int i, phys_id = topology_physical_package_id(cpu);
+
+	/* check if phys_is is already covered */
+	for_each_cpu(i, &rapl_cpu_mask) {
+		if (phys_id == topology_physical_package_id(i))
+			return;
+	}
+	/* was not found, so add it */
+	cpumask_set_cpu(cpu, &rapl_cpu_mask);
+}
+
+static int rapl_cpu_prepare(int cpu)
+{
+	struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
+	int phys_id = topology_physical_package_id(cpu);
+
+	if (pmu)
+		return 0;
+
+	if (phys_id < 0)
+		return -1;
+
+	pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
+	if (!pmu)
+		return -1;
+
+	spin_lock_init(&pmu->lock);
+
+	INIT_LIST_HEAD(&pmu->active_list);
+
+	/*
+	 * grab power unit as: 1/2^unit Joules
+	 *
+	 * we cache in local PMU instance
+	 */
+	rdmsrl(MSR_RAPL_POWER_UNIT, pmu->hw_unit);
+	pmu->hw_unit = (pmu->hw_unit >> 8) & 0x1FULL;
+	pmu->pmu = &rapl_pmu_class;
+
+	/* set RAPL pmu for this cpu for now */
+	per_cpu(rapl_pmu, cpu) = pmu;
+	per_cpu(rapl_pmu_to_free, cpu) = NULL;
+
+	return 0;
+}
+
+static void rapl_cpu_kfree(int cpu)
+{
+	struct rapl_pmu *pmu = per_cpu(rapl_pmu_to_free, cpu);
+
+	kfree(pmu);
+
+	per_cpu(rapl_pmu_to_free, cpu) = NULL;
+}
+
+static int rapl_cpu_dying(int cpu)
+{
+	struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
+
+	if (!pmu)
+		return 0;
+
+	per_cpu(rapl_pmu, cpu) = NULL;
+
+	per_cpu(rapl_pmu_to_free, cpu) = pmu;
+
+	return 0;
+}
+
+static int rapl_cpu_notifier(struct notifier_block *self,
+			     unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (long)hcpu;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_UP_PREPARE:
+		rapl_cpu_prepare(cpu);
+		break;
+	case CPU_STARTING:
+		rapl_cpu_init(cpu);
+		break;
+	case CPU_UP_CANCELED:
+	case CPU_DYING:
+		rapl_cpu_dying(cpu);
+		break;
+	case CPU_ONLINE:
+	case CPU_DEAD:
+		rapl_cpu_kfree(cpu);
+		break;
+	case CPU_DOWN_PREPARE:
+		rapl_cpu_exit(cpu);
+		break;
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static const struct x86_cpu_id rapl_cpu_match[] = {
+	[0] = { .vendor = X86_VENDOR_INTEL, .family = 6 },
+	[1] = {},
+};
+
+static int __init rapl_pmu_init(void)
+{
+	struct rapl_pmu *pmu;
+	int cpu, ret;
+
+	/*
+	 * check for Intel processor family 6
+	 */
+	if (!x86_match_cpu(rapl_cpu_match))
+		return 0;
+
+	/* check supported CPU */
+	switch (boot_cpu_data.x86_model) {
+	case 42: /* Sandy Bridge */
+	case 58: /* Ivy Bridge */
+	case 60: /* Haswell */
+		rapl_cntr_mask = RAPL_IDX_CLN;
+		rapl_pmu_events_group.attrs = rapl_events_cln_attr;
+		break;
+	case 45: /* Sandy Bridge-EP */
+	case 62: /* IvyTown */
+		rapl_cntr_mask = RAPL_IDX_SRV;
+		rapl_pmu_events_group.attrs = rapl_events_srv_attr;
+		break;
+
+	default:
+		/* unsupported */
+		return 0;
+	}
+	get_online_cpus();
+
+	for_each_online_cpu(cpu) {
+		rapl_cpu_prepare(cpu);
+		rapl_cpu_init(cpu);
+	}
+
+	perf_cpu_notifier(rapl_cpu_notifier);
+
+	ret = perf_pmu_register(&rapl_pmu_class, "power", -1);
+	if (WARN_ON(ret)) {
+		pr_info("RAPL PMU detected, registration failed (%d), RAPL PMU disabled\n", ret);
+		put_online_cpus();
+		return -1;
+	}
+
+	pmu = __get_cpu_var(rapl_pmu);
+
+	pr_info("RAPL PMU detected, hw unit 2^-%d Joules,"
+		" API unit is 2^-32 Joules,"
+		" %d fixed counters\n",
+		pmu->hw_unit,
+		hweight32(rapl_cntr_mask));
+
+	put_online_cpus();
+
+	return 0;
+}
+device_initcall(rapl_pmu_init);
-- 
cgit v0.10.2


From 8dce7a9a6f4ca7163161a80a4603b66c88c5de8e Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Thu, 13 Jun 2013 18:41:16 -0400
Subject: lockdep: Be nice about building from userspace

Lockdep is an awesome piece of code which detects locking issues
which are relevant both to userspace and kernelspace. We can
easily make lockdep work in userspace since there is really no
kernel spacific magic going on in the code.

All we need is to wrap two functions which are used by lockdep
and are very kernel specific.

Doing that will allow tools located in tools/ to easily utilize
lockdep's code for their own use.

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: penberg@kernel.org
Cc: torvalds@linux-foundation.org
Link: http://lkml.kernel.org/r/1352753446-24109-1-git-send-email-sasha.levin@oracle.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 576ba75..eb8a547 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -590,6 +590,7 @@ static int very_verbose(struct lock_class *class)
 /*
  * Is this the address of a static object:
  */
+#ifdef __KERNEL__
 static int static_obj(void *obj)
 {
 	unsigned long start = (unsigned long) &_stext,
@@ -616,6 +617,7 @@ static int static_obj(void *obj)
 	 */
 	return is_module_address(addr) || is_module_percpu_address(addr);
 }
+#endif
 
 /*
  * To make lock name printouts unique, we calculate a unique
@@ -4115,6 +4117,7 @@ void debug_check_no_locks_held(void)
 }
 EXPORT_SYMBOL_GPL(debug_check_no_locks_held);
 
+#ifdef __KERNEL__
 void debug_show_all_locks(void)
 {
 	struct task_struct *g, *p;
@@ -4172,6 +4175,7 @@ retry:
 		read_unlock(&tasklist_lock);
 }
 EXPORT_SYMBOL_GPL(debug_show_all_locks);
+#endif
 
 /*
  * Careful: only use this function if you are sure that
-- 
cgit v0.10.2


From 5634bd7d2ab14fbf736b62b0788fb68e2cb0fde2 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Thu, 13 Jun 2013 18:41:17 -0400
Subject: liblockdep: Wrap kernel/locking/lockdep.c to allow usage from
 userspace

kernel/locking/lockdep.c deals with validating locking scenarios for
various architectures supported by the kernel. There isn't
anything kernel specific going on in lockdep, and when we
compare userspace to other architectures that don't have to deal
with irqs such as s390, they become all too similar.

We wrap kernel/locking/lockdep.c and include/linux/lockdep.h with
several headers which allow us to build and use lockdep from
userspace. We don't touch the kernel code itself which means
that any work done on lockdep in the kernel will automatically
benefit userspace lockdep as well!

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: torvalds@linux-foundation.org
Link: http://lkml.kernel.org/r/1371163284-6346-3-git-send-email-sasha.levin@oracle.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile
new file mode 100644
index 0000000..da8b7aa
--- /dev/null
+++ b/tools/lib/lockdep/Makefile
@@ -0,0 +1,251 @@
+# liblockdep version
+LL_VERSION = 0
+LL_PATCHLEVEL = 0
+LL_EXTRAVERSION = 1
+
+# file format version
+FILE_VERSION = 1
+
+MAKEFLAGS += --no-print-directory
+
+
+# Makefiles suck: This macro sets a default value of $(2) for the
+# variable named by $(1), unless the variable has been set by
+# environment or command line. This is necessary for CC and AR
+# because make sets default values, so the simpler ?= approach
+# won't work as expected.
+define allow-override
+  $(if $(or $(findstring environment,$(origin $(1))),\
+            $(findstring command line,$(origin $(1)))),,\
+    $(eval $(1) = $(2)))
+endef
+
+# Allow setting CC and AR, or setting CROSS_COMPILE as a prefix.
+$(call allow-override,CC,$(CROSS_COMPILE)gcc)
+$(call allow-override,AR,$(CROSS_COMPILE)ar)
+
+INSTALL = install
+
+# Use DESTDIR for installing into a different root directory.
+# This is useful for building a package. The program will be
+# installed in this directory as if it was the root directory.
+# Then the build tool can move it later.
+DESTDIR ?=
+DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
+
+prefix ?= /usr/local
+libdir_relative = lib
+libdir = $(prefix)/$(libdir_relative)
+bindir_relative = bin
+bindir = $(prefix)/$(bindir_relative)
+
+export DESTDIR DESTDIR_SQ INSTALL
+
+# copy a bit from Linux kbuild
+
+ifeq ("$(origin V)", "command line")
+  VERBOSE = $(V)
+endif
+ifndef VERBOSE
+  VERBOSE = 0
+endif
+
+ifeq ("$(origin O)", "command line")
+  BUILD_OUTPUT := $(O)
+endif
+
+ifeq ($(BUILD_SRC),)
+ifneq ($(BUILD_OUTPUT),)
+
+define build_output
+	$(if $(VERBOSE:1=),@)$(MAKE) -C $(BUILD_OUTPUT)	\
+	BUILD_SRC=$(CURDIR) -f $(CURDIR)/Makefile $1
+endef
+
+saved-output := $(BUILD_OUTPUT)
+BUILD_OUTPUT := $(shell cd $(BUILD_OUTPUT) && /bin/pwd)
+$(if $(BUILD_OUTPUT),, \
+     $(error output directory "$(saved-output)" does not exist))
+
+all: sub-make
+
+gui: force
+	$(call build_output, all_cmd)
+
+$(filter-out gui,$(MAKECMDGOALS)): sub-make
+
+sub-make: force
+	$(call build_output, $(MAKECMDGOALS))
+
+
+# Leave processing to above invocation of make
+skip-makefile := 1
+
+endif # BUILD_OUTPUT
+endif # BUILD_SRC
+
+# We process the rest of the Makefile if this is the final invocation of make
+ifeq ($(skip-makefile),)
+
+srctree		:= $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR))
+objtree		:= $(CURDIR)
+src		:= $(srctree)
+obj		:= $(objtree)
+
+export prefix libdir bindir src obj
+
+# Shell quotes
+libdir_SQ = $(subst ','\'',$(libdir))
+bindir_SQ = $(subst ','\'',$(bindir))
+
+LIB_FILE = liblockdep.a liblockdep.so
+BIN_FILE = lockdep
+
+CONFIG_INCLUDES =
+CONFIG_LIBS	=
+CONFIG_FLAGS	=
+
+OBJ		= $@
+N		=
+
+export Q VERBOSE
+
+LIBLOCKDEP_VERSION = $(LL_VERSION).$(LL_PATCHLEVEL).$(LL_EXTRAVERSION)
+
+INCLUDES = -I. -I/usr/local/include -I./uinclude $(CONFIG_INCLUDES)
+
+# Set compile option CFLAGS if not set elsewhere
+CFLAGS ?= -g -DCONFIG_LOCKDEP -DCONFIG_STACKTRACE -DCONFIG_PROVE_LOCKING -DBITS_PER_LONG=__WORDSIZE -DLIBLOCKDEP_VERSION='"$(LIBLOCKDEP_VERSION)"' -rdynamic -O0 -g
+
+override CFLAGS += $(CONFIG_FLAGS) $(INCLUDES) $(PLUGIN_DIR_SQ)
+
+ifeq ($(VERBOSE),1)
+  Q =
+  print_compile =
+  print_app_build =
+  print_fpic_compile =
+  print_shared_lib_compile =
+  print_install =
+else
+  Q = @
+  print_compile =		echo '  CC                 '$(OBJ);
+  print_app_build =		echo '  BUILD              '$(OBJ);
+  print_fpic_compile =		echo '  CC FPIC            '$(OBJ);
+  print_shared_lib_compile =	echo '  BUILD SHARED LIB   '$(OBJ);
+  print_static_lib_build =	echo '  BUILD STATIC LIB   '$(OBJ);
+  print_install =		echo '  INSTALL     '$1'	to	$(DESTDIR_SQ)$2';
+endif
+
+do_fpic_compile =					\
+	($(print_fpic_compile)				\
+	$(CC) -c $(CFLAGS) $(EXT) -fPIC $< -o $@)
+
+do_app_build =						\
+	($(print_app_build)				\
+	$(CC) $^ -rdynamic -o $@ $(CONFIG_LIBS) $(LIBS))
+
+do_compile_shared_library =			\
+	($(print_shared_lib_compile)		\
+	$(CC) --shared $^ -o $@ -lpthread -ldl)
+
+do_build_static_lib =				\
+	($(print_static_lib_build)		\
+	$(RM) $@;  $(AR) rcs $@ $^)
+
+
+define do_compile
+	$(print_compile)						\
+	$(CC) -c $(CFLAGS) $(EXT) $< -o $(obj)/$@;
+endef
+
+$(obj)/%.o: $(src)/%.c
+	$(Q)$(call do_compile)
+
+%.o: $(src)/%.c
+	$(Q)$(call do_compile)
+
+PEVENT_LIB_OBJS = common.o lockdep.o preload.o rbtree.o
+
+ALL_OBJS = $(PEVENT_LIB_OBJS)
+
+CMD_TARGETS = $(LIB_FILE)
+
+TARGETS = $(CMD_TARGETS)
+
+
+all: all_cmd
+
+all_cmd: $(CMD_TARGETS)
+
+liblockdep.so: $(PEVENT_LIB_OBJS)
+	$(Q)$(do_compile_shared_library)
+
+liblockdep.a: $(PEVENT_LIB_OBJS)
+	$(Q)$(do_build_static_lib)
+
+$(PEVENT_LIB_OBJS): %.o: $(src)/%.c
+	$(Q)$(do_fpic_compile)
+
+## make deps
+
+all_objs := $(sort $(ALL_OBJS))
+all_deps := $(all_objs:%.o=.%.d)
+
+# let .d file also depends on the source and header files
+define check_deps
+		@set -e; $(RM) $@; \
+		$(CC) -MM $(CFLAGS) $< > $@.$$$$; \
+		sed 's,\($*\)\.o[ :]*,\1.o $@ : ,g' < $@.$$$$ > $@; \
+		$(RM) $@.$$$$
+endef
+
+$(all_deps): .%.d: $(src)/%.c
+	$(Q)$(call check_deps)
+
+$(all_objs) : %.o : .%.d
+
+dep_includes := $(wildcard $(all_deps))
+
+ifneq ($(dep_includes),)
+ include $(dep_includes)
+endif
+
+### Detect environment changes
+TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):$(ARCH):$(CROSS_COMPILE)
+
+tags:	force
+	$(RM) tags
+	find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \
+	--regex-c++='/_PE\(([^,)]*).*/PEVENT_ERRNO__\1/'
+
+TAGS:	force
+	$(RM) TAGS
+	find . -name '*.[ch]' | xargs etags \
+	--regex='/_PE(\([^,)]*\).*/PEVENT_ERRNO__\1/'
+
+define do_install
+	$(print_install)				\
+	if [ ! -d '$(DESTDIR_SQ)$2' ]; then		\
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2';	\
+	fi;						\
+	$(INSTALL) $1 '$(DESTDIR_SQ)$2'
+endef
+
+install_lib: all_cmd
+	$(Q)$(call do_install,$(LIB_FILE),$(libdir_SQ))
+	$(Q)$(call do_install,$(BIN_FILE),$(bindir_SQ))
+
+install: install_lib
+
+clean:
+	$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d
+	$(RM) tags TAGS
+
+endif # skip-makefile
+
+PHONY += force
+force:
+
+# Declare the contents of the .PHONY variable as phony.  We keep that
+# information in a variable so we can use it in if_changed and friends.
+.PHONY: $(PHONY)
diff --git a/tools/lib/lockdep/common.c b/tools/lib/lockdep/common.c
new file mode 100644
index 0000000..8ef602f
--- /dev/null
+++ b/tools/lib/lockdep/common.c
@@ -0,0 +1,33 @@
+#include <stddef.h>
+#include <stdbool.h>
+#include <linux/compiler.h>
+#include <linux/lockdep.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+
+static __thread struct task_struct current_obj;
+
+/* lockdep wants these */
+bool debug_locks = true;
+bool debug_locks_silent;
+
+__attribute__((constructor)) static void liblockdep_init(void)
+{
+	lockdep_init();
+}
+
+__attribute__((destructor)) static void liblockdep_exit(void)
+{
+	debug_check_no_locks_held(&current_obj);
+}
+
+struct task_struct *__curr(void)
+{
+	if (current_obj.pid == 0) {
+		/* Makes lockdep output pretty */
+		prctl(PR_GET_NAME, current_obj.comm);
+		current_obj.pid = syscall(__NR_gettid);
+	}
+
+	return &current_obj;
+}
diff --git a/tools/lib/lockdep/lockdep.c b/tools/lib/lockdep/lockdep.c
new file mode 100644
index 0000000..f42b7e9
--- /dev/null
+++ b/tools/lib/lockdep/lockdep.c
@@ -0,0 +1,2 @@
+#include <linux/lockdep.h>
+#include "../../../kernel/locking/lockdep.c"
diff --git a/tools/lib/lockdep/lockdep_internals.h b/tools/lib/lockdep/lockdep_internals.h
new file mode 100644
index 0000000..29d0c95
--- /dev/null
+++ b/tools/lib/lockdep/lockdep_internals.h
@@ -0,0 +1 @@
+#include "../../../kernel/locking/lockdep_internals.h"
diff --git a/tools/lib/lockdep/lockdep_states.h b/tools/lib/lockdep/lockdep_states.h
new file mode 100644
index 0000000..248d235
--- /dev/null
+++ b/tools/lib/lockdep/lockdep_states.h
@@ -0,0 +1 @@
+#include "../../../kernel/locking/lockdep_states.h"
diff --git a/tools/lib/lockdep/rbtree.c b/tools/lib/lockdep/rbtree.c
new file mode 100644
index 0000000..f7f4303
--- /dev/null
+++ b/tools/lib/lockdep/rbtree.c
@@ -0,0 +1 @@
+#include "../../../lib/rbtree.c"
diff --git a/tools/lib/lockdep/uinclude/asm/hweight.h b/tools/lib/lockdep/uinclude/asm/hweight.h
new file mode 100644
index 0000000..fab00ff
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/asm/hweight.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/asm/sections.h b/tools/lib/lockdep/uinclude/asm/sections.h
new file mode 100644
index 0000000..fab00ff
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/asm/sections.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/bitops.h b/tools/lib/lockdep/uinclude/linux/bitops.h
new file mode 100644
index 0000000..fab00ff
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/bitops.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/compiler.h b/tools/lib/lockdep/uinclude/linux/compiler.h
new file mode 100644
index 0000000..7ac838a
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/compiler.h
@@ -0,0 +1,7 @@
+#ifndef _LIBLOCKDEP_LINUX_COMPILER_H_
+#define _LIBLOCKDEP_LINUX_COMPILER_H_
+
+#define __used		__attribute__((__unused__))
+#define unlikely
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/debug_locks.h b/tools/lib/lockdep/uinclude/linux/debug_locks.h
new file mode 100644
index 0000000..f38eb64
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/debug_locks.h
@@ -0,0 +1,12 @@
+#ifndef _LIBLOCKDEP_DEBUG_LOCKS_H_
+#define _LIBLOCKDEP_DEBUG_LOCKS_H_
+
+#include <stddef.h>
+#include <linux/compiler.h>
+
+#define DEBUG_LOCKS_WARN_ON(x) (x)
+
+extern bool debug_locks;
+extern bool debug_locks_silent;
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/delay.h b/tools/lib/lockdep/uinclude/linux/delay.h
new file mode 100644
index 0000000..fab00ff
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/delay.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/export.h b/tools/lib/lockdep/uinclude/linux/export.h
new file mode 100644
index 0000000..6bdf349
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/export.h
@@ -0,0 +1,7 @@
+#ifndef _LIBLOCKDEP_LINUX_EXPORT_H_
+#define _LIBLOCKDEP_LINUX_EXPORT_H_
+
+#define EXPORT_SYMBOL(sym)
+#define EXPORT_SYMBOL_GPL(sym)
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/ftrace.h b/tools/lib/lockdep/uinclude/linux/ftrace.h
new file mode 100644
index 0000000..fab00ff
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/ftrace.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/gfp.h b/tools/lib/lockdep/uinclude/linux/gfp.h
new file mode 100644
index 0000000..fab00ff
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/gfp.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/hardirq.h b/tools/lib/lockdep/uinclude/linux/hardirq.h
new file mode 100644
index 0000000..c8f3f8f
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/hardirq.h
@@ -0,0 +1,11 @@
+#ifndef _LIBLOCKDEP_LINUX_HARDIRQ_H_
+#define _LIBLOCKDEP_LINUX_HARDIRQ_H_
+
+#define SOFTIRQ_BITS	0UL
+#define HARDIRQ_BITS	0UL
+#define SOFTIRQ_SHIFT	0UL
+#define HARDIRQ_SHIFT	0UL
+#define hardirq_count()	0UL
+#define softirq_count()	0UL
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/hash.h b/tools/lib/lockdep/uinclude/linux/hash.h
new file mode 100644
index 0000000..0f84798
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/hash.h
@@ -0,0 +1 @@
+#include "../../../include/linux/hash.h"
diff --git a/tools/lib/lockdep/uinclude/linux/interrupt.h b/tools/lib/lockdep/uinclude/linux/interrupt.h
new file mode 100644
index 0000000..fab00ff
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/interrupt.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/irqflags.h b/tools/lib/lockdep/uinclude/linux/irqflags.h
new file mode 100644
index 0000000..6cc296f
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/irqflags.h
@@ -0,0 +1,38 @@
+#ifndef _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_
+#define _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_
+
+# define trace_hardirq_context(p)	0
+# define trace_softirq_context(p)	0
+# define trace_hardirqs_enabled(p)	0
+# define trace_softirqs_enabled(p)	0
+# define trace_hardirq_enter()		do { } while (0)
+# define trace_hardirq_exit()		do { } while (0)
+# define lockdep_softirq_enter()	do { } while (0)
+# define lockdep_softirq_exit()		do { } while (0)
+# define INIT_TRACE_IRQFLAGS
+
+# define stop_critical_timings() do { } while (0)
+# define start_critical_timings() do { } while (0)
+
+#define raw_local_irq_disable() do { } while (0)
+#define raw_local_irq_enable() do { } while (0)
+#define raw_local_irq_save(flags) ((flags) = 0)
+#define raw_local_irq_restore(flags) do { } while (0)
+#define raw_local_save_flags(flags) ((flags) = 0)
+#define raw_irqs_disabled_flags(flags) do { } while (0)
+#define raw_irqs_disabled() 0
+#define raw_safe_halt()
+
+#define local_irq_enable() do { } while (0)
+#define local_irq_disable() do { } while (0)
+#define local_irq_save(flags) ((flags) = 0)
+#define local_irq_restore(flags) do { } while (0)
+#define local_save_flags(flags)	((flags) = 0)
+#define irqs_disabled() (1)
+#define irqs_disabled_flags(flags) (0)
+#define safe_halt() do { } while (0)
+
+#define trace_lock_release(x, y)
+#define trace_lock_acquire(a, b, c, d, e, f, g)
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/kallsyms.h b/tools/lib/lockdep/uinclude/linux/kallsyms.h
new file mode 100644
index 0000000..b0f2dbd
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/kallsyms.h
@@ -0,0 +1,32 @@
+#ifndef _LIBLOCKDEP_LINUX_KALLSYMS_H_
+#define _LIBLOCKDEP_LINUX_KALLSYMS_H_
+
+#include <linux/kernel.h>
+#include <stdio.h>
+
+#define KSYM_NAME_LEN 128
+
+struct module;
+
+static inline const char *kallsyms_lookup(unsigned long addr,
+					  unsigned long *symbolsize,
+					  unsigned long *offset,
+					  char **modname, char *namebuf)
+{
+	return NULL;
+}
+
+#include <execinfo.h>
+#include <stdlib.h>
+static inline void print_ip_sym(unsigned long ip)
+{
+	char **name;
+
+	name = backtrace_symbols((void **)&ip, 1);
+
+	printf("%s\n", *name);
+
+	free(name);
+}
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/kern_levels.h b/tools/lib/lockdep/uinclude/linux/kern_levels.h
new file mode 100644
index 0000000..3b9bade
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/kern_levels.h
@@ -0,0 +1,25 @@
+#ifndef __KERN_LEVELS_H__
+#define __KERN_LEVELS_H__
+
+#define KERN_SOH	""		/* ASCII Start Of Header */
+#define KERN_SOH_ASCII	''
+
+#define KERN_EMERG	KERN_SOH ""	/* system is unusable */
+#define KERN_ALERT	KERN_SOH ""	/* action must be taken immediately */
+#define KERN_CRIT	KERN_SOH ""	/* critical conditions */
+#define KERN_ERR	KERN_SOH ""	/* error conditions */
+#define KERN_WARNING	KERN_SOH ""	/* warning conditions */
+#define KERN_NOTICE	KERN_SOH ""	/* normal but significant condition */
+#define KERN_INFO	KERN_SOH ""	/* informational */
+#define KERN_DEBUG	KERN_SOH ""	/* debug-level messages */
+
+#define KERN_DEFAULT	KERN_SOH ""	/* the default kernel loglevel */
+
+/*
+ * Annotation for a "continued" line of log printout (only done after a
+ * line that had no enclosing \n). Only to be used by core/arch code
+ * during early bootup (a continued line is not SMP-safe otherwise).
+ */
+#define KERN_CONT	""
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/kernel.h b/tools/lib/lockdep/uinclude/linux/kernel.h
new file mode 100644
index 0000000..a11e3c3
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/kernel.h
@@ -0,0 +1,44 @@
+#ifndef _LIBLOCKDEP_LINUX_KERNEL_H_
+#define _LIBLOCKDEP_LINUX_KERNEL_H_
+
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/rcu.h>
+#include <linux/hardirq.h>
+#include <linux/kern_levels.h>
+
+#ifndef container_of
+#define container_of(ptr, type, member) ({			\
+	const typeof(((type *)0)->member) * __mptr = (ptr);	\
+	(type *)((char *)__mptr - offsetof(type, member)); })
+#endif
+
+#define max(x, y) ({				\
+	typeof(x) _max1 = (x);			\
+	typeof(y) _max2 = (y);			\
+	(void) (&_max1 == &_max2);		\
+	_max1 > _max2 ? _max1 : _max2; })
+
+#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
+#define WARN_ON(x) (x)
+#define WARN_ON_ONCE(x) (x)
+#define likely(x) (x)
+#define WARN(x, y, z) (x)
+#define uninitialized_var(x) x
+#define __init
+#define noinline
+#define list_add_tail_rcu list_add_tail
+
+#ifndef CALLER_ADDR0
+#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
+#endif
+
+#ifndef _RET_IP_
+#define _RET_IP_ CALLER_ADDR0
+#endif
+
+#ifndef _THIS_IP_
+#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; })
+#endif
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/kmemcheck.h b/tools/lib/lockdep/uinclude/linux/kmemcheck.h
new file mode 100644
index 0000000..94d598b
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/kmemcheck.h
@@ -0,0 +1,8 @@
+#ifndef _LIBLOCKDEP_LINUX_KMEMCHECK_H_
+#define _LIBLOCKDEP_LINUX_KMEMCHECK_H_
+
+static inline void kmemcheck_mark_initialized(void *address, unsigned int n)
+{
+}
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/linkage.h b/tools/lib/lockdep/uinclude/linux/linkage.h
new file mode 100644
index 0000000..fab00ff
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/linkage.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/list.h b/tools/lib/lockdep/uinclude/linux/list.h
new file mode 100644
index 0000000..6e9ef31
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/list.h
@@ -0,0 +1 @@
+#include "../../../include/linux/list.h"
diff --git a/tools/lib/lockdep/uinclude/linux/lockdep.h b/tools/lib/lockdep/uinclude/linux/lockdep.h
new file mode 100644
index 0000000..d0f5d6e
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/lockdep.h
@@ -0,0 +1,55 @@
+#ifndef _LIBLOCKDEP_LOCKDEP_H_
+#define _LIBLOCKDEP_LOCKDEP_H_
+
+#include <sys/prctl.h>
+#include <sys/syscall.h>
+#include <string.h>
+#include <limits.h>
+#include <linux/utsname.h>
+
+
+#define MAX_LOCK_DEPTH 2000UL
+
+#include "../../../include/linux/lockdep.h"
+
+struct task_struct {
+	u64 curr_chain_key;
+	int lockdep_depth;
+	unsigned int lockdep_recursion;
+	struct held_lock held_locks[MAX_LOCK_DEPTH];
+	gfp_t lockdep_reclaim_gfp;
+	int pid;
+	char comm[17];
+};
+
+extern struct task_struct *__curr(void);
+
+#define current (__curr())
+
+#define debug_locks_off() 1
+#define task_pid_nr(tsk) ((tsk)->pid)
+
+#define KSYM_NAME_LEN 128
+#define printk printf
+
+#define list_del_rcu list_del
+
+#define atomic_t unsigned long
+#define atomic_inc(x) ((*(x))++)
+
+static struct new_utsname *init_utsname(void)
+{
+	static struct new_utsname n = (struct new_utsname) {
+		.release = "liblockdep",
+		.version = LIBLOCKDEP_VERSION,
+	};
+
+	return &n;
+}
+
+#define print_tainted() ""
+#define static_obj(x) 1
+
+#define debug_show_all_locks()
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/module.h b/tools/lib/lockdep/uinclude/linux/module.h
new file mode 100644
index 0000000..09c7a7b
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/module.h
@@ -0,0 +1,6 @@
+#ifndef _LIBLOCKDEP_LINUX_MODULE_H_
+#define _LIBLOCKDEP_LINUX_MODULE_H_
+
+#define module_param(name, type, perm)
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/mutex.h b/tools/lib/lockdep/uinclude/linux/mutex.h
new file mode 100644
index 0000000..fab00ff
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/mutex.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/poison.h b/tools/lib/lockdep/uinclude/linux/poison.h
new file mode 100644
index 0000000..0c27bdf
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/poison.h
@@ -0,0 +1 @@
+#include "../../../include/linux/poison.h"
diff --git a/tools/lib/lockdep/uinclude/linux/prefetch.h b/tools/lib/lockdep/uinclude/linux/prefetch.h
new file mode 100644
index 0000000..d73fe6f
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/prefetch.h
@@ -0,0 +1,6 @@
+#ifndef _LIBLOCKDEP_LINUX_PREFETCH_H_
+#define _LIBLOCKDEP_LINUX_PREFETCH_H
+
+static inline void prefetch(void *a __attribute__((unused))) { }
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/proc_fs.h b/tools/lib/lockdep/uinclude/linux/proc_fs.h
new file mode 100644
index 0000000..fab00ff
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/proc_fs.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/rbtree.h b/tools/lib/lockdep/uinclude/linux/rbtree.h
new file mode 100644
index 0000000..965901d
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/rbtree.h
@@ -0,0 +1 @@
+#include "../../../include/linux/rbtree.h"
diff --git a/tools/lib/lockdep/uinclude/linux/rbtree_augmented.h b/tools/lib/lockdep/uinclude/linux/rbtree_augmented.h
new file mode 100644
index 0000000..c375947
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/rbtree_augmented.h
@@ -0,0 +1,2 @@
+#define __always_inline
+#include "../../../include/linux/rbtree_augmented.h"
diff --git a/tools/lib/lockdep/uinclude/linux/rcu.h b/tools/lib/lockdep/uinclude/linux/rcu.h
new file mode 100644
index 0000000..4c99fcb
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/rcu.h
@@ -0,0 +1,16 @@
+#ifndef _LIBLOCKDEP_RCU_H_
+#define _LIBLOCKDEP_RCU_H_
+
+int rcu_scheduler_active;
+
+static inline int rcu_lockdep_current_cpu_online(void)
+{
+	return 1;
+}
+
+static inline int rcu_is_cpu_idle(void)
+{
+	return 1;
+}
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/seq_file.h b/tools/lib/lockdep/uinclude/linux/seq_file.h
new file mode 100644
index 0000000..fab00ff
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/seq_file.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
diff --git a/tools/lib/lockdep/uinclude/linux/spinlock.h b/tools/lib/lockdep/uinclude/linux/spinlock.h
new file mode 100644
index 0000000..68c1aa2
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/spinlock.h
@@ -0,0 +1,25 @@
+#ifndef _LIBLOCKDEP_SPINLOCK_H_
+#define _LIBLOCKDEP_SPINLOCK_H_
+
+#include <pthread.h>
+#include <stdbool.h>
+
+#define arch_spinlock_t pthread_mutex_t
+#define __ARCH_SPIN_LOCK_UNLOCKED PTHREAD_MUTEX_INITIALIZER
+
+static inline void arch_spin_lock(arch_spinlock_t *mutex)
+{
+	pthread_mutex_lock(mutex);
+}
+
+static inline void arch_spin_unlock(arch_spinlock_t *mutex)
+{
+	pthread_mutex_unlock(mutex);
+}
+
+static inline bool arch_spin_is_locked(arch_spinlock_t *mutex)
+{
+	return true;
+}
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/stacktrace.h b/tools/lib/lockdep/uinclude/linux/stacktrace.h
new file mode 100644
index 0000000..39aecc6
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/stacktrace.h
@@ -0,0 +1,32 @@
+#ifndef _LIBLOCKDEP_LINUX_STACKTRACE_H_
+#define _LIBLOCKDEP_LINUX_STACKTRACE_H_
+
+#include <execinfo.h>
+
+struct stack_trace {
+	unsigned int nr_entries, max_entries;
+	unsigned long *entries;
+	int skip;
+};
+
+static inline void print_stack_trace(struct stack_trace *trace, int spaces)
+{
+	backtrace_symbols_fd((void **)trace->entries, trace->nr_entries, 1);
+}
+
+#define save_stack_trace(trace)	\
+	((trace)->nr_entries =	\
+		backtrace((void **)(trace)->entries, (trace)->max_entries))
+
+static inline int dump_stack(void)
+{
+	void *array[64];
+	size_t size;
+
+	size = backtrace(array, 64);
+	backtrace_symbols_fd(array, size, 1);
+
+	return 0;
+}
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/stringify.h b/tools/lib/lockdep/uinclude/linux/stringify.h
new file mode 100644
index 0000000..05dfcd1
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/stringify.h
@@ -0,0 +1,7 @@
+#ifndef _LIBLOCKDEP_LINUX_STRINGIFY_H_
+#define _LIBLOCKDEP_LINUX_STRINGIFY_H_
+
+#define __stringify_1(x...)	#x
+#define __stringify(x...)	__stringify_1(x)
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/linux/types.h b/tools/lib/lockdep/uinclude/linux/types.h
new file mode 100644
index 0000000..929938f
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/linux/types.h
@@ -0,0 +1,58 @@
+#ifndef _LIBLOCKDEP_LINUX_TYPES_H_
+#define _LIBLOCKDEP_LINUX_TYPES_H_
+
+#include <stdbool.h>
+#include <stddef.h>
+
+#define __SANE_USERSPACE_TYPES__	/* For PPC64, to get LL64 types */
+#include <asm/types.h>
+
+struct page;
+struct kmem_cache;
+
+typedef unsigned gfp_t;
+
+typedef __u64 u64;
+typedef __s64 s64;
+
+typedef __u32 u32;
+typedef __s32 s32;
+
+typedef __u16 u16;
+typedef __s16 s16;
+
+typedef __u8  u8;
+typedef __s8  s8;
+
+#ifdef __CHECKER__
+#define __bitwise__ __attribute__((bitwise))
+#else
+#define __bitwise__
+#endif
+#ifdef __CHECK_ENDIAN__
+#define __bitwise __bitwise__
+#else
+#define __bitwise
+#endif
+
+
+typedef __u16 __bitwise __le16;
+typedef __u16 __bitwise __be16;
+typedef __u32 __bitwise __le32;
+typedef __u32 __bitwise __be32;
+typedef __u64 __bitwise __le64;
+typedef __u64 __bitwise __be64;
+
+struct list_head {
+	struct list_head *next, *prev;
+};
+
+struct hlist_head {
+	struct hlist_node *first;
+};
+
+struct hlist_node {
+	struct hlist_node *next, **pprev;
+};
+
+#endif
diff --git a/tools/lib/lockdep/uinclude/trace/events/lock.h b/tools/lib/lockdep/uinclude/trace/events/lock.h
new file mode 100644
index 0000000..fab00ff
--- /dev/null
+++ b/tools/lib/lockdep/uinclude/trace/events/lock.h
@@ -0,0 +1,3 @@
+
+/* empty file */
+
-- 
cgit v0.10.2


From 45e6207464b59dca63c8a9a79a7befbbf6a68fdb Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Thu, 13 Jun 2013 18:41:18 -0400
Subject: liblockdep: Add public headers for pthread_mutex_t implementation

These headers provide the same API as their pthread mutex
counterparts.

The design here is to allow to easily switch to liblockdep lock
validation just by adding a "liblockdep_" to pthread_mutex_*()
calls, which means that it's easy to integrate liblockdep into
existing codebases.

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: torvalds@linux-foundation.org
Link: http://lkml.kernel.org/r/1371163284-6346-4-git-send-email-sasha.levin@oracle.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/tools/lib/lockdep/include/liblockdep/common.h b/tools/lib/lockdep/include/liblockdep/common.h
new file mode 100644
index 0000000..0bda630
--- /dev/null
+++ b/tools/lib/lockdep/include/liblockdep/common.h
@@ -0,0 +1,50 @@
+#ifndef _LIBLOCKDEP_COMMON_H
+#define _LIBLOCKDEP_COMMON_H
+
+#include <pthread.h>
+
+#define NR_LOCKDEP_CACHING_CLASSES 2
+#define MAX_LOCKDEP_SUBCLASSES 8UL
+
+#ifndef CALLER_ADDR0
+#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
+#endif
+
+#ifndef _RET_IP_
+#define _RET_IP_ CALLER_ADDR0
+#endif
+
+#ifndef _THIS_IP_
+#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; })
+#endif
+
+struct lockdep_subclass_key {
+	char __one_byte;
+};
+
+struct lock_class_key {
+	struct lockdep_subclass_key subkeys[MAX_LOCKDEP_SUBCLASSES];
+};
+
+struct lockdep_map {
+	struct lock_class_key	*key;
+	struct lock_class	*class_cache[NR_LOCKDEP_CACHING_CLASSES];
+	const char		*name;
+#ifdef CONFIG_LOCK_STAT
+	int			cpu;
+	unsigned long		ip;
+#endif
+};
+
+void lockdep_init_map(struct lockdep_map *lock, const char *name,
+			struct lock_class_key *key, int subclass);
+void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
+			int trylock, int read, int check,
+			struct lockdep_map *nest_lock, unsigned long ip);
+void lock_release(struct lockdep_map *lock, int nested,
+			unsigned long ip);
+
+#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \
+	{ .name = (_name), .key = (void *)(_key), }
+
+#endif
diff --git a/tools/lib/lockdep/include/liblockdep/mutex.h b/tools/lib/lockdep/include/liblockdep/mutex.h
new file mode 100644
index 0000000..c342f70
--- /dev/null
+++ b/tools/lib/lockdep/include/liblockdep/mutex.h
@@ -0,0 +1,70 @@
+#ifndef _LIBLOCKDEP_MUTEX_H
+#define _LIBLOCKDEP_MUTEX_H
+
+#include <pthread.h>
+#include "common.h"
+
+struct liblockdep_pthread_mutex {
+	pthread_mutex_t mutex;
+	struct lockdep_map dep_map;
+};
+
+typedef struct liblockdep_pthread_mutex liblockdep_pthread_mutex_t;
+
+#define LIBLOCKDEP_PTHREAD_MUTEX_INITIALIZER(mtx)			\
+		(const struct liblockdep_pthread_mutex) {		\
+	.mutex = PTHREAD_MUTEX_INITIALIZER,				\
+	.dep_map = STATIC_LOCKDEP_MAP_INIT(#mtx, &((&(mtx))->dep_map)),	\
+}
+
+static inline int __mutex_init(liblockdep_pthread_mutex_t *lock,
+				const char *name,
+				struct lock_class_key *key,
+				const pthread_mutexattr_t *__mutexattr)
+{
+	lockdep_init_map(&lock->dep_map, name, key, 0);
+	return pthread_mutex_init(&lock->mutex, __mutexattr);
+}
+
+#define liblockdep_pthread_mutex_init(mutex, mutexattr)		\
+({								\
+	static struct lock_class_key __key;			\
+								\
+	__mutex_init((mutex), #mutex, &__key, (mutexattr));	\
+})
+
+static inline int liblockdep_pthread_mutex_lock(liblockdep_pthread_mutex_t *lock)
+{
+	lock_acquire(&lock->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+	return pthread_mutex_lock(&lock->mutex);
+}
+
+static inline int liblockdep_pthread_mutex_unlock(liblockdep_pthread_mutex_t *lock)
+{
+	lock_release(&lock->dep_map, 0, (unsigned long)_RET_IP_);
+	return pthread_mutex_unlock(&lock->mutex);
+}
+
+static inline int liblockdep_pthread_mutex_trylock(liblockdep_pthread_mutex_t *lock)
+{
+	lock_acquire(&lock->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_);
+	return pthread_mutex_trylock(&lock->mutex) == 0 ? 1 : 0;
+}
+
+static inline int liblockdep_pthread_mutex_destroy(liblockdep_pthread_mutex_t *lock)
+{
+	return pthread_mutex_destroy(&lock->mutex);
+}
+
+#ifdef __USE_LIBLOCKDEP
+
+#define pthread_mutex_t         liblockdep_pthread_mutex_t
+#define pthread_mutex_init      liblockdep_pthread_mutex_init
+#define pthread_mutex_lock      liblockdep_pthread_mutex_lock
+#define pthread_mutex_unlock    liblockdep_pthread_mutex_unlock
+#define pthread_mutex_trylock   liblockdep_pthread_mutex_trylock
+#define pthread_mutex_destroy   liblockdep_pthread_mutex_destroy
+
+#endif
+
+#endif
-- 
cgit v0.10.2


From 878f968eeb852383ff79dc3f181db24e5b52fd75 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Thu, 13 Jun 2013 18:41:19 -0400
Subject: liblockdep: Add pthread_mutex_t test suite

This is a rather simple and basic test suite to test common
locking issues.

Beyond tests, it also shows how to use the library.

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: torvalds@linux-foundation.org
Link: http://lkml.kernel.org/r/1371163284-6346-5-git-send-email-sasha.levin@oracle.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/tools/lib/lockdep/run_tests.sh b/tools/lib/lockdep/run_tests.sh
new file mode 100644
index 0000000..5334ad9
--- /dev/null
+++ b/tools/lib/lockdep/run_tests.sh
@@ -0,0 +1,27 @@
+#! /bin/bash
+
+make &> /dev/null
+
+for i in `ls tests/*.c`; do
+	testname=$(basename -s .c "$i")
+	gcc -o tests/$testname -pthread -lpthread $i liblockdep.a -Iinclude -D__USE_LIBLOCKDEP &> /dev/null
+	echo -ne "$testname... "
+	if [ $(timeout 1 ./tests/$testname | wc -l) -gt 0 ]; then
+		echo "PASSED!"
+	else
+		echo "FAILED!"
+	fi
+	rm tests/$testname
+done
+
+for i in `ls tests/*.c`; do
+	testname=$(basename -s .c "$i")
+	gcc -o tests/$testname -pthread -lpthread -Iinclude $i &> /dev/null
+	echo -ne "(PRELOAD) $testname... "
+	if [ $(timeout 1 ./lockdep ./tests/$testname | wc -l) -gt 0 ]; then
+		echo "PASSED!"
+	else
+		echo "FAILED!"
+	fi
+	rm tests/$testname
+done
diff --git a/tools/lib/lockdep/tests/AA.c b/tools/lib/lockdep/tests/AA.c
new file mode 100644
index 0000000..0f782ff
--- /dev/null
+++ b/tools/lib/lockdep/tests/AA.c
@@ -0,0 +1,13 @@
+#include <liblockdep/mutex.h>
+
+void main(void)
+{
+	pthread_mutex_t a, b;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+
+	pthread_mutex_lock(&a);
+	pthread_mutex_lock(&b);
+	pthread_mutex_lock(&a);
+}
diff --git a/tools/lib/lockdep/tests/ABBA.c b/tools/lib/lockdep/tests/ABBA.c
new file mode 100644
index 0000000..07f0e29
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABBA.c
@@ -0,0 +1,13 @@
+#include <liblockdep/mutex.h>
+#include "common.h"
+
+void main(void)
+{
+	pthread_mutex_t a, b;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+
+	LOCK_UNLOCK_2(a, b);
+	LOCK_UNLOCK_2(b, a);
+}
diff --git a/tools/lib/lockdep/tests/ABBCCA.c b/tools/lib/lockdep/tests/ABBCCA.c
new file mode 100644
index 0000000..843db09
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABBCCA.c
@@ -0,0 +1,15 @@
+#include <liblockdep/mutex.h>
+#include "common.h"
+
+void main(void)
+{
+	pthread_mutex_t a, b, c;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+	pthread_mutex_init(&c, NULL);
+
+	LOCK_UNLOCK_2(a, b);
+	LOCK_UNLOCK_2(b, c);
+	LOCK_UNLOCK_2(c, a);
+}
diff --git a/tools/lib/lockdep/tests/ABBCCDDA.c b/tools/lib/lockdep/tests/ABBCCDDA.c
new file mode 100644
index 0000000..33620e2
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABBCCDDA.c
@@ -0,0 +1,17 @@
+#include <liblockdep/mutex.h>
+#include "common.h"
+
+void main(void)
+{
+	pthread_mutex_t a, b, c, d;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+	pthread_mutex_init(&c, NULL);
+	pthread_mutex_init(&d, NULL);
+
+	LOCK_UNLOCK_2(a, b);
+	LOCK_UNLOCK_2(b, c);
+	LOCK_UNLOCK_2(c, d);
+	LOCK_UNLOCK_2(d, a);
+}
diff --git a/tools/lib/lockdep/tests/ABCABC.c b/tools/lib/lockdep/tests/ABCABC.c
new file mode 100644
index 0000000..3fee51e
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABCABC.c
@@ -0,0 +1,15 @@
+#include <liblockdep/mutex.h>
+#include "common.h"
+
+void main(void)
+{
+	pthread_mutex_t a, b, c;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+	pthread_mutex_init(&c, NULL);
+
+	LOCK_UNLOCK_2(a, b);
+	LOCK_UNLOCK_2(c, a);
+	LOCK_UNLOCK_2(b, c);
+}
diff --git a/tools/lib/lockdep/tests/ABCDBCDA.c b/tools/lib/lockdep/tests/ABCDBCDA.c
new file mode 100644
index 0000000..427ba56
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABCDBCDA.c
@@ -0,0 +1,17 @@
+#include <liblockdep/mutex.h>
+#include "common.h"
+
+void main(void)
+{
+	pthread_mutex_t a, b, c, d;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+	pthread_mutex_init(&c, NULL);
+	pthread_mutex_init(&d, NULL);
+
+	LOCK_UNLOCK_2(a, b);
+	LOCK_UNLOCK_2(c, d);
+	LOCK_UNLOCK_2(b, c);
+	LOCK_UNLOCK_2(d, a);
+}
diff --git a/tools/lib/lockdep/tests/ABCDBDDA.c b/tools/lib/lockdep/tests/ABCDBDDA.c
new file mode 100644
index 0000000..680c6cf
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABCDBDDA.c
@@ -0,0 +1,17 @@
+#include <liblockdep/mutex.h>
+#include "common.h"
+
+void main(void)
+{
+	pthread_mutex_t a, b, c, d;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+	pthread_mutex_init(&c, NULL);
+	pthread_mutex_init(&d, NULL);
+
+	LOCK_UNLOCK_2(a, b);
+	LOCK_UNLOCK_2(c, d);
+	LOCK_UNLOCK_2(b, d);
+	LOCK_UNLOCK_2(d, a);
+}
diff --git a/tools/lib/lockdep/tests/common.h b/tools/lib/lockdep/tests/common.h
new file mode 100644
index 0000000..d89e94d
--- /dev/null
+++ b/tools/lib/lockdep/tests/common.h
@@ -0,0 +1,12 @@
+#ifndef _LIBLOCKDEP_TEST_COMMON_H
+#define _LIBLOCKDEP_TEST_COMMON_H
+
+#define LOCK_UNLOCK_2(a, b)			\
+	do {					\
+		pthread_mutex_lock(&(a));	\
+		pthread_mutex_lock(&(b));	\
+		pthread_mutex_unlock(&(b));	\
+		pthread_mutex_unlock(&(a));	\
+	} while(0)
+
+#endif
diff --git a/tools/lib/lockdep/tests/unlock_balance.c b/tools/lib/lockdep/tests/unlock_balance.c
new file mode 100644
index 0000000..0bc62de
--- /dev/null
+++ b/tools/lib/lockdep/tests/unlock_balance.c
@@ -0,0 +1,12 @@
+#include <liblockdep/mutex.h>
+
+void main(void)
+{
+	pthread_mutex_t a;
+
+	pthread_mutex_init(&a, NULL);
+
+	pthread_mutex_lock(&a);
+	pthread_mutex_unlock(&a);
+	pthread_mutex_unlock(&a);
+}
-- 
cgit v0.10.2


From 5a52c9b480e09a782618dbf08de57f9ca54c8b49 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Thu, 13 Jun 2013 18:41:20 -0400
Subject: liblockdep: Add public headers for pthread_rwlock_t implementation

Both pthreads and lockdep support dealing with rwlocks, so
here's the liblockdep implementation for those.

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: torvalds@linux-foundation.org
Link: http://lkml.kernel.org/r/1371163284-6346-6-git-send-email-sasha.levin@oracle.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/tools/lib/lockdep/include/liblockdep/rwlock.h b/tools/lib/lockdep/include/liblockdep/rwlock.h
new file mode 100644
index 0000000..a680ab8
--- /dev/null
+++ b/tools/lib/lockdep/include/liblockdep/rwlock.h
@@ -0,0 +1,86 @@
+#ifndef _LIBLOCKDEP_RWLOCK_H
+#define _LIBLOCKDEP_RWLOCK_H
+
+#include <pthread.h>
+#include "common.h"
+
+struct liblockdep_pthread_rwlock {
+	pthread_rwlock_t rwlock;
+	struct lockdep_map dep_map;
+};
+
+typedef struct liblockdep_pthread_rwlock liblockdep_pthread_rwlock_t;
+
+#define LIBLOCKDEP_PTHREAD_RWLOCK_INITIALIZER(rwl)			\
+		(struct liblockdep_pthread_rwlock) {			\
+	.rwlock = PTHREAD_RWLOCK_INITIALIZER,				\
+	.dep_map = STATIC_LOCKDEP_MAP_INIT(#rwl, &((&(rwl))->dep_map)),	\
+}
+
+static inline int __rwlock_init(liblockdep_pthread_rwlock_t *lock,
+				const char *name,
+				struct lock_class_key *key,
+				const pthread_rwlockattr_t *attr)
+{
+	lockdep_init_map(&lock->dep_map, name, key, 0);
+
+	return pthread_rwlock_init(&lock->rwlock, attr);
+}
+
+#define liblockdep_pthread_rwlock_init(lock, attr)		\
+({							\
+	static struct lock_class_key __key;		\
+							\
+	__rwlock_init((lock), #lock, &__key, (attr));	\
+})
+
+static inline int liblockdep_pthread_rwlock_rdlock(liblockdep_pthread_rwlock_t *lock)
+{
+	lock_acquire(&lock->dep_map, 0, 0, 2, 2, NULL, (unsigned long)_RET_IP_);
+	return pthread_rwlock_rdlock(&lock->rwlock);
+
+}
+
+static inline int liblockdep_pthread_rwlock_unlock(liblockdep_pthread_rwlock_t *lock)
+{
+	lock_release(&lock->dep_map, 0, (unsigned long)_RET_IP_);
+	return pthread_rwlock_unlock(&lock->rwlock);
+}
+
+static inline int liblockdep_pthread_rwlock_wrlock(liblockdep_pthread_rwlock_t *lock)
+{
+	lock_acquire(&lock->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+	return pthread_rwlock_wrlock(&lock->rwlock);
+}
+
+static inline int liblockdep_pthread_rwlock_tryrdlock(liblockdep_pthread_rwlock_t *lock)
+{
+	lock_acquire(&lock->dep_map, 0, 1, 2, 2, NULL, (unsigned long)_RET_IP_);
+	return pthread_rwlock_tryrdlock(&lock->rwlock) == 0 ? 1 : 0;
+}
+
+static inline int liblockdep_pthread_rwlock_trywlock(liblockdep_pthread_rwlock_t *lock)
+{
+	lock_acquire(&lock->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_);
+	return pthread_rwlock_trywlock(&lock->rwlock) == 0 ? 1 : 0;
+}
+
+static inline int liblockdep_rwlock_destroy(liblockdep_pthread_rwlock_t *lock)
+{
+	return pthread_rwlock_destroy(&lock->rwlock);
+}
+
+#ifdef __USE_LIBLOCKDEP
+
+#define pthread_rwlock_t		liblockdep_pthread_rwlock_t
+#define pthread_rwlock_init		liblockdep_pthread_rwlock_init
+#define pthread_rwlock_rdlock		liblockdep_pthread_rwlock_rdlock
+#define pthread_rwlock_unlock		liblockdep_pthread_rwlock_unlock
+#define pthread_rwlock_wrlock		liblockdep_pthread_rwlock_wrlock
+#define pthread_rwlock_tryrdlock	liblockdep_pthread_rwlock_tryrdlock
+#define pthread_rwlock_trywlock		liblockdep_pthread_rwlock_trywlock
+#define pthread_rwlock_destroy		liblockdep_rwlock_destroy
+
+#endif
+
+#endif
-- 
cgit v0.10.2


From dbe941827eab53194eda5cd350a4e1414f192658 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Thu, 13 Jun 2013 18:41:21 -0400
Subject: liblockdep: Add pthread_rwlock_t test suite

A simple test to make sure we handle rwlocks correctly.

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: torvalds@linux-foundation.org
Link: http://lkml.kernel.org/r/1371163284-6346-7-git-send-email-sasha.levin@oracle.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/tools/lib/lockdep/tests/WW.c b/tools/lib/lockdep/tests/WW.c
new file mode 100644
index 0000000..d44f77d
--- /dev/null
+++ b/tools/lib/lockdep/tests/WW.c
@@ -0,0 +1,13 @@
+#include <liblockdep/rwlock.h>
+
+void main(void)
+{
+	pthread_rwlock_t a, b;
+
+	pthread_rwlock_init(&a, NULL);
+	pthread_rwlock_init(&b, NULL);
+
+	pthread_rwlock_wrlock(&a);
+	pthread_rwlock_rdlock(&b);
+	pthread_rwlock_wrlock(&a);
+}
-- 
cgit v0.10.2


From 231941eec8aeee4f0ac210a28e484200b20f74d8 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Thu, 13 Jun 2013 18:41:22 -0400
Subject: liblockdep: Support using LD_PRELOAD

This allows lockdep to be used without being compiled in the
original program.

Usage is quite simple:

	LD_PRELOAD=/path/to/liblockdep.so /path/to/my/program

And magically, you'll have lockdep checking in your program!

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: torvalds@linux-foundation.org
Link: http://lkml.kernel.org/r/1371163284-6346-8-git-send-email-sasha.levin@oracle.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c
new file mode 100644
index 0000000..f8465a8
--- /dev/null
+++ b/tools/lib/lockdep/preload.c
@@ -0,0 +1,447 @@
+#define _GNU_SOURCE
+#include <pthread.h>
+#include <stdio.h>
+#include <dlfcn.h>
+#include <stdlib.h>
+#include <sysexits.h>
+#include "include/liblockdep/mutex.h"
+#include "../../../include/linux/rbtree.h"
+
+/**
+ * struct lock_lookup - liblockdep's view of a single unique lock
+ * @orig: pointer to the original pthread lock, used for lookups
+ * @dep_map: lockdep's dep_map structure
+ * @key: lockdep's key structure
+ * @node: rb-tree node used to store the lock in a global tree
+ * @name: a unique name for the lock
+ */
+struct lock_lookup {
+	void *orig; /* Original pthread lock, used for lookups */
+	struct lockdep_map dep_map; /* Since all locks are dynamic, we need
+				     * a dep_map and a key for each lock */
+	/*
+	 * Wait, there's no support for key classes? Yup :(
+	 * Most big projects wrap the pthread api with their own calls to
+	 * be compatible with different locking methods. This means that
+	 * "classes" will be brokes since the function that creates all
+	 * locks will point to a generic locking function instead of the
+	 * actual code that wants to do the locking.
+	 */
+	struct lock_class_key key;
+	struct rb_node node;
+#define LIBLOCKDEP_MAX_LOCK_NAME 22
+	char name[LIBLOCKDEP_MAX_LOCK_NAME];
+};
+
+/* This is where we store our locks */
+static struct rb_root locks = RB_ROOT;
+static pthread_rwlock_t locks_rwlock = PTHREAD_RWLOCK_INITIALIZER;
+
+/* pthread mutex API */
+
+#ifdef __GLIBC__
+extern int __pthread_mutex_init(pthread_mutex_t *mutex, const pthread_mutexattr_t *attr);
+extern int __pthread_mutex_lock(pthread_mutex_t *mutex);
+extern int __pthread_mutex_trylock(pthread_mutex_t *mutex);
+extern int __pthread_mutex_unlock(pthread_mutex_t *mutex);
+extern int __pthread_mutex_destroy(pthread_mutex_t *mutex);
+#else
+#define __pthread_mutex_init	NULL
+#define __pthread_mutex_lock	NULL
+#define __pthread_mutex_trylock	NULL
+#define __pthread_mutex_unlock	NULL
+#define __pthread_mutex_destroy	NULL
+#endif
+static int (*ll_pthread_mutex_init)(pthread_mutex_t *mutex,
+			const pthread_mutexattr_t *attr)	= __pthread_mutex_init;
+static int (*ll_pthread_mutex_lock)(pthread_mutex_t *mutex)	= __pthread_mutex_lock;
+static int (*ll_pthread_mutex_trylock)(pthread_mutex_t *mutex)	= __pthread_mutex_trylock;
+static int (*ll_pthread_mutex_unlock)(pthread_mutex_t *mutex)	= __pthread_mutex_unlock;
+static int (*ll_pthread_mutex_destroy)(pthread_mutex_t *mutex)	= __pthread_mutex_destroy;
+
+/* pthread rwlock API */
+
+#ifdef __GLIBC__
+extern int __pthread_rwlock_init(pthread_rwlock_t *rwlock, const pthread_rwlockattr_t *attr);
+extern int __pthread_rwlock_destroy(pthread_rwlock_t *rwlock);
+extern int __pthread_rwlock_wrlock(pthread_rwlock_t *rwlock);
+extern int __pthread_rwlock_trywrlock(pthread_rwlock_t *rwlock);
+extern int __pthread_rwlock_rdlock(pthread_rwlock_t *rwlock);
+extern int __pthread_rwlock_tryrdlock(pthread_rwlock_t *rwlock);
+extern int __pthread_rwlock_unlock(pthread_rwlock_t *rwlock);
+#else
+#define __pthread_rwlock_init		NULL
+#define __pthread_rwlock_destroy	NULL
+#define __pthread_rwlock_wrlock		NULL
+#define __pthread_rwlock_trywrlock	NULL
+#define __pthread_rwlock_rdlock		NULL
+#define __pthread_rwlock_tryrdlock	NULL
+#define __pthread_rwlock_unlock		NULL
+#endif
+
+static int (*ll_pthread_rwlock_init)(pthread_rwlock_t *rwlock,
+			const pthread_rwlockattr_t *attr)		= __pthread_rwlock_init;
+static int (*ll_pthread_rwlock_destroy)(pthread_rwlock_t *rwlock)	= __pthread_rwlock_destroy;
+static int (*ll_pthread_rwlock_rdlock)(pthread_rwlock_t *rwlock)	= __pthread_rwlock_rdlock;
+static int (*ll_pthread_rwlock_tryrdlock)(pthread_rwlock_t *rwlock)	= __pthread_rwlock_tryrdlock;
+static int (*ll_pthread_rwlock_trywrlock)(pthread_rwlock_t *rwlock)	= __pthread_rwlock_trywrlock;
+static int (*ll_pthread_rwlock_wrlock)(pthread_rwlock_t *rwlock)	= __pthread_rwlock_wrlock;
+static int (*ll_pthread_rwlock_unlock)(pthread_rwlock_t *rwlock)	= __pthread_rwlock_unlock;
+
+enum { none, prepare, done, } __init_state;
+static void init_preload(void);
+static void try_init_preload(void)
+{
+	if (!__init_state != done)
+		init_preload();
+}
+
+static struct rb_node **__get_lock_node(void *lock, struct rb_node **parent)
+{
+	struct rb_node **node = &locks.rb_node;
+	struct lock_lookup *l;
+
+	*parent = NULL;
+
+	while (*node) {
+		l = rb_entry(*node, struct lock_lookup, node);
+
+		*parent = *node;
+		if (lock < l->orig)
+			node = &l->node.rb_left;
+		else if (lock > l->orig)
+			node = &l->node.rb_right;
+		else
+			return node;
+	}
+
+	return node;
+}
+
+#ifndef LIBLOCKDEP_STATIC_ENTRIES
+#define LIBLOCKDEP_STATIC_ENTRIES	1024
+#endif
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+static struct lock_lookup __locks[LIBLOCKDEP_STATIC_ENTRIES];
+static int __locks_nr;
+
+static inline bool is_static_lock(struct lock_lookup *lock)
+{
+	return lock >= __locks && lock < __locks + ARRAY_SIZE(__locks);
+}
+
+static struct lock_lookup *alloc_lock(void)
+{
+	if (__init_state != done) {
+		/*
+		 * Some programs attempt to initialize and use locks in their
+		 * allocation path. This means that a call to malloc() would
+		 * result in locks being initialized and locked.
+		 *
+		 * Why is it an issue for us? dlsym() below will try allocating
+		 * to give us the original function. Since this allocation will
+		 * result in a locking operations, we have to let pthread deal
+		 * with it, but we can't! we don't have the pointer to the
+		 * original API since we're inside dlsym() trying to get it
+		 */
+
+		int idx = __locks_nr++;
+		if (idx >= ARRAY_SIZE(__locks)) {
+			fprintf(stderr,
+		"LOCKDEP error: insufficient LIBLOCKDEP_STATIC_ENTRIES\n");
+			exit(EX_UNAVAILABLE);
+		}
+		return __locks + idx;
+	}
+
+	return malloc(sizeof(struct lock_lookup));
+}
+
+static inline void free_lock(struct lock_lookup *lock)
+{
+	if (likely(!is_static_lock(lock)))
+		free(lock);
+}
+
+/**
+ * __get_lock - find or create a lock instance
+ * @lock: pointer to a pthread lock function
+ *
+ * Try to find an existing lock in the rbtree using the provided pointer. If
+ * one wasn't found - create it.
+ */
+static struct lock_lookup *__get_lock(void *lock)
+{
+	struct rb_node **node, *parent;
+	struct lock_lookup *l;
+
+	ll_pthread_rwlock_rdlock(&locks_rwlock);
+	node = __get_lock_node(lock, &parent);
+	ll_pthread_rwlock_unlock(&locks_rwlock);
+	if (*node) {
+		return rb_entry(*node, struct lock_lookup, node);
+	}
+
+	/* We didn't find the lock, let's create it */
+	l = alloc_lock();
+	if (l == NULL)
+		return NULL;
+
+	l->orig = lock;
+	/*
+	 * Currently the name of the lock is the ptr value of the pthread lock,
+	 * while not optimal, it makes debugging a bit easier.
+	 *
+	 * TODO: Get the real name of the lock using libdwarf
+	 */
+	sprintf(l->name, "%p", lock);
+	lockdep_init_map(&l->dep_map, l->name, &l->key, 0);
+
+	ll_pthread_rwlock_wrlock(&locks_rwlock);
+	/* This might have changed since the last time we fetched it */
+	node = __get_lock_node(lock, &parent);
+	rb_link_node(&l->node, parent, node);
+	rb_insert_color(&l->node, &locks);
+	ll_pthread_rwlock_unlock(&locks_rwlock);
+
+	return l;
+}
+
+static void __del_lock(struct lock_lookup *lock)
+{
+	ll_pthread_rwlock_wrlock(&locks_rwlock);
+	rb_erase(&lock->node, &locks);
+	ll_pthread_rwlock_unlock(&locks_rwlock);
+	free_lock(lock);
+}
+
+int pthread_mutex_init(pthread_mutex_t *mutex,
+			const pthread_mutexattr_t *attr)
+{
+	int r;
+
+	/*
+	 * We keep trying to init our preload module because there might be
+	 * code in init sections that tries to touch locks before we are
+	 * initialized, in that case we'll need to manually call preload
+	 * to get us going.
+	 *
+	 * Funny enough, kernel's lockdep had the same issue, and used
+	 * (almost) the same solution. See look_up_lock_class() in
+	 * kernel/locking/lockdep.c for details.
+	 */
+	try_init_preload();
+
+	r = ll_pthread_mutex_init(mutex, attr);
+	if (r == 0)
+		/*
+		 * We do a dummy initialization here so that lockdep could
+		 * warn us if something fishy is going on - such as
+		 * initializing a held lock.
+		 */
+		__get_lock(mutex);
+
+	return r;
+}
+
+int pthread_mutex_lock(pthread_mutex_t *mutex)
+{
+	int r;
+
+	try_init_preload();
+
+	lock_acquire(&__get_lock(mutex)->dep_map, 0, 0, 0, 2, NULL,
+			(unsigned long)_RET_IP_);
+	/*
+	 * Here's the thing with pthread mutexes: unlike the kernel variant,
+	 * they can fail.
+	 *
+	 * This means that the behaviour here is a bit different from what's
+	 * going on in the kernel: there we just tell lockdep that we took the
+	 * lock before actually taking it, but here we must deal with the case
+	 * that locking failed.
+	 *
+	 * To do that we'll "release" the lock if locking failed - this way
+	 * we'll get lockdep doing the correct checks when we try to take
+	 * the lock, and if that fails - we'll be back to the correct
+	 * state by releasing it.
+	 */
+	r = ll_pthread_mutex_lock(mutex);
+	if (r)
+		lock_release(&__get_lock(mutex)->dep_map, 0, (unsigned long)_RET_IP_);
+
+	return r;
+}
+
+int pthread_mutex_trylock(pthread_mutex_t *mutex)
+{
+	int r;
+
+	try_init_preload();
+
+	lock_acquire(&__get_lock(mutex)->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_);
+	r = ll_pthread_mutex_trylock(mutex);
+	if (r)
+		lock_release(&__get_lock(mutex)->dep_map, 0, (unsigned long)_RET_IP_);
+
+	return r;
+}
+
+int pthread_mutex_unlock(pthread_mutex_t *mutex)
+{
+	int r;
+
+	try_init_preload();
+
+	lock_release(&__get_lock(mutex)->dep_map, 0, (unsigned long)_RET_IP_);
+	/*
+	 * Just like taking a lock, only in reverse!
+	 *
+	 * If we fail releasing the lock, tell lockdep we're holding it again.
+	 */
+	r = ll_pthread_mutex_unlock(mutex);
+	if (r)
+		lock_acquire(&__get_lock(mutex)->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+
+	return r;
+}
+
+int pthread_mutex_destroy(pthread_mutex_t *mutex)
+{
+	try_init_preload();
+
+	/*
+	 * Let's see if we're releasing a lock that's held.
+	 *
+	 * TODO: Hook into free() and add that check there as well.
+	 */
+	debug_check_no_locks_freed(mutex, mutex + sizeof(*mutex));
+	__del_lock(__get_lock(mutex));
+	return ll_pthread_mutex_destroy(mutex);
+}
+
+/* This is the rwlock part, very similar to what happened with mutex above */
+int pthread_rwlock_init(pthread_rwlock_t *rwlock,
+			const pthread_rwlockattr_t *attr)
+{
+	int r;
+
+	try_init_preload();
+
+	r = ll_pthread_rwlock_init(rwlock, attr);
+	if (r == 0)
+		__get_lock(rwlock);
+
+	return r;
+}
+
+int pthread_rwlock_destroy(pthread_rwlock_t *rwlock)
+{
+	try_init_preload();
+
+	debug_check_no_locks_freed(rwlock, rwlock + sizeof(*rwlock));
+	__del_lock(__get_lock(rwlock));
+	return ll_pthread_rwlock_destroy(rwlock);
+}
+
+int pthread_rwlock_rdlock(pthread_rwlock_t *rwlock)
+{
+	int r;
+
+        init_preload();
+
+	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 2, 2, NULL, (unsigned long)_RET_IP_);
+	r = ll_pthread_rwlock_rdlock(rwlock);
+	if (r)
+		lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
+
+	return r;
+}
+
+int pthread_rwlock_tryrdlock(pthread_rwlock_t *rwlock)
+{
+	int r;
+
+        init_preload();
+
+	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 2, 2, NULL, (unsigned long)_RET_IP_);
+	r = ll_pthread_rwlock_tryrdlock(rwlock);
+	if (r)
+		lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
+
+	return r;
+}
+
+int pthread_rwlock_trywrlock(pthread_rwlock_t *rwlock)
+{
+	int r;
+
+        init_preload();
+
+	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_);
+	r = ll_pthread_rwlock_trywrlock(rwlock);
+	if (r)
+                lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
+
+	return r;
+}
+
+int pthread_rwlock_wrlock(pthread_rwlock_t *rwlock)
+{
+	int r;
+
+        init_preload();
+
+	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+	r = ll_pthread_rwlock_wrlock(rwlock);
+	if (r)
+		lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
+
+	return r;
+}
+
+int pthread_rwlock_unlock(pthread_rwlock_t *rwlock)
+{
+	int r;
+
+        init_preload();
+
+	lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
+	r = ll_pthread_rwlock_unlock(rwlock);
+	if (r)
+		lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+
+	return r;
+}
+
+__attribute__((constructor)) static void init_preload(void)
+{
+	if (__init_state != done)
+		return;
+
+#ifndef __GLIBC__
+	__init_state = prepare;
+
+	ll_pthread_mutex_init = dlsym(RTLD_NEXT, "pthread_mutex_init");
+	ll_pthread_mutex_lock = dlsym(RTLD_NEXT, "pthread_mutex_lock");
+	ll_pthread_mutex_trylock = dlsym(RTLD_NEXT, "pthread_mutex_trylock");
+	ll_pthread_mutex_unlock = dlsym(RTLD_NEXT, "pthread_mutex_unlock");
+	ll_pthread_mutex_destroy = dlsym(RTLD_NEXT, "pthread_mutex_destroy");
+
+	ll_pthread_rwlock_init = dlsym(RTLD_NEXT, "pthread_rwlock_init");
+	ll_pthread_rwlock_destroy = dlsym(RTLD_NEXT, "pthread_rwlock_destroy");
+	ll_pthread_rwlock_rdlock = dlsym(RTLD_NEXT, "pthread_rwlock_rdlock");
+	ll_pthread_rwlock_tryrdlock = dlsym(RTLD_NEXT, "pthread_rwlock_tryrdlock");
+	ll_pthread_rwlock_wrlock = dlsym(RTLD_NEXT, "pthread_rwlock_wrlock");
+	ll_pthread_rwlock_trywrlock = dlsym(RTLD_NEXT, "pthread_rwlock_trywrlock");
+	ll_pthread_rwlock_unlock = dlsym(RTLD_NEXT, "pthread_rwlock_unlock");
+#endif
+
+	printf("%p\n", ll_pthread_mutex_trylock);fflush(stdout);
+
+	lockdep_init();
+
+	__init_state = done;
+}
-- 
cgit v0.10.2


From f612ac05b7ce66919507d25f4c81e4272f7a8705 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Thu, 13 Jun 2013 18:41:23 -0400
Subject: liblockdep: Add the 'lockdep' user-space utility

This is a simple wrapper to make using liblockdep on existing
applications much easier.

After running 'make && make install', it becomes quite simple to
test things with liblockdep. For example, to try it on perf:

	lockdep perf

No other integration required.

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: torvalds@linux-foundation.org
Link: http://lkml.kernel.org/r/1371163284-6346-9-git-send-email-sasha.levin@oracle.com
[ Changed it to load ./liblockdep.so, so it can be tested in situ. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/tools/lib/lockdep/lockdep b/tools/lib/lockdep/lockdep
new file mode 100755
index 0000000..49af9fe
--- /dev/null
+++ b/tools/lib/lockdep/lockdep
@@ -0,0 +1,3 @@
+#!/bin/bash
+
+LD_PRELOAD="./liblockdep.so $LD_PRELOAD" "$@"
-- 
cgit v0.10.2


From 1acd437c59c7dd78d8f1e5f07bea6a18b7b5cd77 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Thu, 13 Jun 2013 18:41:24 -0400
Subject: liblockdep: Add a MAINTAINERS entry

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: torvalds@linux-foundation.org
Link: http://lkml.kernel.org/r/1371163284-6346-10-git-send-email-sasha.levin@oracle.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/MAINTAINERS b/MAINTAINERS
index 63f3048..9e62574 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5111,6 +5111,11 @@ F:	drivers/lguest/
 F:	include/linux/lguest*.h
 F:	tools/lguest/
 
+LIBLOCKDEP
+M:	Sasha Levin <sasha.levin@oracle.com>
+S:	Maintained
+F:	tools/lib/lockdep/
+
 LINUX FOR IBM pSERIES (RS/6000)
 M:	Paul Mackerras <paulus@au.ibm.com>
 W:	http://www.ibm.com/linux/ltc/projects/ppc
-- 
cgit v0.10.2


From bb8cbbfee68518796df4050868e5b0f5ad078f9f Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Wed, 13 Nov 2013 15:36:12 +0100
Subject: tasks/fork: Remove unnecessary child->exit_state

A zombie task obviously can't fork(), remove the unnecessary
initialization of child->exit_state. It is zero anyway after
dup_task_struct().

Note: copy_process() is huge and it has a lot of chaotic
initializations, probably it makes sense to move them into the
new helper called by dup_task_struct().

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: David Laight <David.Laight@ACULAB.COM>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131113143612.GA10540@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/fork.c b/kernel/fork.c
index 728d5be..b308082 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1402,13 +1402,11 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		p->tgid = p->pid;
 	}
 
-	p->pdeath_signal = 0;
-	p->exit_state = 0;
-
 	p->nr_dirtied = 0;
 	p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
 	p->dirty_paused_when = 0;
 
+	p->pdeath_signal = 0;
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
 
-- 
cgit v0.10.2


From 86506a99a62400e9f7b7d1344bcc9ea235faf98f Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Wed, 13 Nov 2013 15:36:14 +0100
Subject: tasks/exit: Remove unused task_is_dead() method

task_is_dead() has no users since commit 43e13cc107cf
("cred: remove task_is_dead() from __task_cred() validation"), and
nobody except exit.c should rely on ->exit_state (we still have
the users which should be changed).

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: David Laight <David.Laight@ACULAB.COM>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20131113143614.GA10547@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7e35d4b..cda8d63 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -168,7 +168,6 @@ extern char ___assert_task_state[1 - 2*!!(
 
 #define task_is_traced(task)	((task->state & __TASK_TRACED) != 0)
 #define task_is_stopped(task)	((task->state & __TASK_STOPPED) != 0)
-#define task_is_dead(task)	((task)->exit_state != 0)
 #define task_is_stopped_or_traced(task)	\
 			((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
 #define task_contributes_to_load(task)	\
-- 
cgit v0.10.2


From 192301e70af3f6803c6354a464ebfa742da738ae Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Wed, 13 Nov 2013 16:45:38 +0100
Subject: sched: Check TASK_DEAD rather than EXIT_DEAD in schedule_debug()

schedule_debug() ignores in_atomic() if prev->exit_state != 0.
This is not what we want, ->exit_state is set by exit_notify()
but we should complain until the task does the last schedule()
in TASK_DEAD.

See also 7407251a0e2e "PF_DEAD cleanup", I think this ancient
commit explains why schedule() had to rely on ->exit_state,
until that commit exit_notify() disabled preemption and set
PF_DEAD which was used to detect the exiting task.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: David Laight <David.Laight@ACULAB.COM>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20131113154538.GB15810@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 687985b..19db8f3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2414,10 +2414,10 @@ static inline void schedule_debug(struct task_struct *prev)
 {
 	/*
 	 * Test if we are atomic. Since do_exit() needs to call into
-	 * schedule() atomically, we ignore that path for now.
-	 * Otherwise, whine if we are scheduling when we should not be.
+	 * schedule() atomically, we ignore that path. Otherwise whine
+	 * if we are scheduling when we should not.
 	 */
-	if (unlikely(in_atomic_preempt_off() && !prev->exit_state))
+	if (unlikely(in_atomic_preempt_off() && prev->state != TASK_DEAD))
 		__schedule_bug(prev);
 	rcu_sleep_check();
 
-- 
cgit v0.10.2


From c44f2a020072d75d6b0cbf9f139a09719cda9367 Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Fri, 18 Oct 2013 13:52:21 +0200
Subject: sched/fair: Move load idx selection in find_idlest_group

load_idx is used in find_idlest_group but initialized in select_task_rq_fair
even when not used. The load_idx initialisation is moved in find_idlest_group
and the sd_flag replaces it in the function's args.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Cc: len.brown@intel.com
Cc: amit.kucheria@linaro.org
Cc: pjt@google.com
Cc: l.majewski@samsung.com
Cc: Morten.Rasmussen@arm.com
Cc: cmetcalf@tilera.com
Cc: tony.luck@intel.com
Cc: alex.shi@intel.com
Cc: preeti@linux.vnet.ibm.com
Cc: linaro-kernel@lists.linaro.org
Cc: rjw@sisk.pl
Cc: paulmck@linux.vnet.ibm.com
Cc: corbet@lwn.net
Cc: arjan@linux.intel.com
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1382097147-30088-8-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e8b652e..6cb36c7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4110,12 +4110,16 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
  */
 static struct sched_group *
 find_idlest_group(struct sched_domain *sd, struct task_struct *p,
-		  int this_cpu, int load_idx)
+		  int this_cpu, int sd_flag)
 {
 	struct sched_group *idlest = NULL, *group = sd->groups;
 	unsigned long min_load = ULONG_MAX, this_load = 0;
+	int load_idx = sd->forkexec_idx;
 	int imbalance = 100 + (sd->imbalance_pct-100)/2;
 
+	if (sd_flag & SD_BALANCE_WAKE)
+		load_idx = sd->wake_idx;
+
 	do {
 		unsigned long load, avg_load;
 		int local_group;
@@ -4283,7 +4287,6 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 	}
 
 	while (sd) {
-		int load_idx = sd->forkexec_idx;
 		struct sched_group *group;
 		int weight;
 
@@ -4292,10 +4295,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 			continue;
 		}
 
-		if (sd_flag & SD_BALANCE_WAKE)
-			load_idx = sd->wake_idx;
-
-		group = find_idlest_group(sd, p, cpu, load_idx);
+		group = find_idlest_group(sd, p, cpu, sd_flag);
 		if (!group) {
 			sd = sd->child;
 			continue;
-- 
cgit v0.10.2


From 380c9077b38df2962a22f00f21f6cd0db62d3390 Mon Sep 17 00:00:00 2001
From: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Date: Fri, 15 Nov 2013 15:06:52 +0530
Subject: sched/fair: Clean up update_sg_lb_stats() a bit

Add rq->nr_running to sgs->sum_nr_running directly instead of
assigning it through an intermediate variable nr_running.

Signed-off-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1384508212-25032-1-git-send-email-kamalesh@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6cb36c7..a566c07 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5500,7 +5500,6 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			struct sched_group *group, int load_idx,
 			int local_group, struct sg_lb_stats *sgs)
 {
-	unsigned long nr_running;
 	unsigned long load;
 	int i;
 
@@ -5509,8 +5508,6 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 	for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
 		struct rq *rq = cpu_rq(i);
 
-		nr_running = rq->nr_running;
-
 		/* Bias balancing toward cpus of our domain */
 		if (local_group)
 			load = target_load(i, load_idx);
@@ -5518,7 +5515,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			load = source_load(i, load_idx);
 
 		sgs->group_load += load;
-		sgs->sum_nr_running += nr_running;
+		sgs->sum_nr_running += rq->nr_running;
 #ifdef CONFIG_NUMA_BALANCING
 		sgs->nr_numa_running += rq->nr_numa_running;
 		sgs->nr_preferred_running += rq->nr_preferred_running;
-- 
cgit v0.10.2


From e6c390f2dfd04c165ce45b0032f73fba85b1f282 Mon Sep 17 00:00:00 2001
From: Dario Faggioli <raistlin@linux.it>
Date: Thu, 7 Nov 2013 14:43:35 +0100
Subject: sched: Add sched_class->task_dead() method

Add a new function to the scheduling class interface. It is called
at the end of a context switch, if the prev task is in TASK_DEAD state.

It will be useful for the scheduling classes that want to be notified
when one of their tasks dies, e.g. to perform some cleanup actions,
such as SCHED_DEADLINE.

Signed-off-by: Dario Faggioli <raistlin@linux.it>
Reviewed-by: Paul Turner <pjt@google.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Cc: bruce.ashfield@windriver.com
Cc: claudio@evidence.eu.com
Cc: darren@dvhart.com
Cc: dhaval.giani@gmail.com
Cc: fchecconi@gmail.com
Cc: fweisbec@gmail.com
Cc: harald.gustafsson@ericsson.com
Cc: hgu1972@gmail.com
Cc: insop.song@gmail.com
Cc: jkacur@redhat.com
Cc: johan.eker@ericsson.com
Cc: liming.wang@windriver.com
Cc: luca.abeni@unitn.it
Cc: michael@amarulasolutions.com
Cc: nicola.manica@disi.unitn.it
Cc: oleg@redhat.com
Cc: paulmck@linux.vnet.ibm.com
Cc: p.faure@akatech.ch
Cc: rostedt@goodmis.org
Cc: tommaso.cucinotta@sssup.it
Cc: vincent.guittot@linaro.org
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-2-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 19db8f3..25b3779 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2003,6 +2003,9 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	if (unlikely(prev_state == TASK_DEAD)) {
 		task_numa_free(prev);
 
+		if (prev->sched_class->task_dead)
+			prev->sched_class->task_dead(prev);
+
 		/*
 		 * Remove function-return probe instances associated with this
 		 * task and put them back on the free list.
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 88c85b2..b3b4a49 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1023,6 +1023,7 @@ struct sched_class {
 	void (*set_curr_task) (struct rq *rq);
 	void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
 	void (*task_fork) (struct task_struct *p);
+	void (*task_dead) (struct task_struct *p);
 
 	void (*switched_from) (struct rq *this_rq, struct task_struct *task);
 	void (*switched_to) (struct rq *this_rq, struct task_struct *task);
-- 
cgit v0.10.2


From 65661f96d3b32f4b28fef26d21be81d7e173b965 Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Tue, 12 Nov 2013 17:58:51 +0100
Subject: perf/x86: Add RAPL hrtimer support

The RAPL PMU counters do not interrupt on overflow.
Therefore, the kernel needs to poll the counters
to avoid missing an overflow. This patch adds
the hrtimer code to do this.

The timer interval is calculated at boot time
based on the power unit used by the HW.

There is one hrtimer per-cpu to handle the case
of multiple simultaneous use across cores on
the same package + hotplug CPU.

Thanks to Maria Dimakopoulou for her contributions
to this patch especially on the math aspects.

Signed-off-by: Stephane Eranian <eranian@google.com>
Reviewed-by: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
[ Applied 32-bit build fix. ]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: acme@redhat.com
Cc: jolsa@redhat.com
Cc: zheng.z.yan@intel.com
Cc: bp@alien8.de
Cc: maria.n.dimakopoulou@gmail.com
Link: http://lkml.kernel.org/r/1384275531-10892-5-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index cfcd386..bf8e4a7 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -96,6 +96,8 @@ struct rapl_pmu {
 	int		 n_active; /* number of active events */
 	struct list_head active_list;
 	struct pmu	 *pmu; /* pointer to rapl_pmu_class */
+	ktime_t		 timer_interval; /* in ktime_t unit */
+	struct hrtimer   hrtimer;
 };
 
 static struct pmu rapl_pmu_class;
@@ -158,6 +160,48 @@ again:
 	return new_raw_count;
 }
 
+static void rapl_start_hrtimer(struct rapl_pmu *pmu)
+{
+	__hrtimer_start_range_ns(&pmu->hrtimer,
+			pmu->timer_interval, 0,
+			HRTIMER_MODE_REL_PINNED, 0);
+}
+
+static void rapl_stop_hrtimer(struct rapl_pmu *pmu)
+{
+	hrtimer_cancel(&pmu->hrtimer);
+}
+
+static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer)
+{
+	struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+	struct perf_event *event;
+	unsigned long flags;
+
+	if (!pmu->n_active)
+		return HRTIMER_NORESTART;
+
+	spin_lock_irqsave(&pmu->lock, flags);
+
+	list_for_each_entry(event, &pmu->active_list, active_entry) {
+		rapl_event_update(event);
+	}
+
+	spin_unlock_irqrestore(&pmu->lock, flags);
+
+	hrtimer_forward_now(hrtimer, pmu->timer_interval);
+
+	return HRTIMER_RESTART;
+}
+
+static void rapl_hrtimer_init(struct rapl_pmu *pmu)
+{
+	struct hrtimer *hr = &pmu->hrtimer;
+
+	hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hr->function = rapl_hrtimer_handle;
+}
+
 static void __rapl_pmu_event_start(struct rapl_pmu *pmu,
 				   struct perf_event *event)
 {
@@ -171,6 +215,8 @@ static void __rapl_pmu_event_start(struct rapl_pmu *pmu,
 	local64_set(&event->hw.prev_count, rapl_read_counter(event));
 
 	pmu->n_active++;
+	if (pmu->n_active == 1)
+		rapl_start_hrtimer(pmu);
 }
 
 static void rapl_pmu_event_start(struct perf_event *event, int mode)
@@ -195,6 +241,8 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode)
 	if (!(hwc->state & PERF_HES_STOPPED)) {
 		WARN_ON_ONCE(pmu->n_active <= 0);
 		pmu->n_active--;
+		if (pmu->n_active == 0)
+			rapl_stop_hrtimer(pmu);
 
 		list_del(&event->active_entry);
 
@@ -423,6 +471,9 @@ static void rapl_cpu_exit(int cpu)
 	 */
 	if (target >= 0)
 		perf_pmu_migrate_context(pmu->pmu, cpu, target);
+
+	/* cancel overflow polling timer for CPU */
+	rapl_stop_hrtimer(pmu);
 }
 
 static void rapl_cpu_init(int cpu)
@@ -442,6 +493,7 @@ static int rapl_cpu_prepare(int cpu)
 {
 	struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
 	int phys_id = topology_physical_package_id(cpu);
+	u64 ms;
 
 	if (pmu)
 		return 0;
@@ -466,6 +518,22 @@ static int rapl_cpu_prepare(int cpu)
 	pmu->hw_unit = (pmu->hw_unit >> 8) & 0x1FULL;
 	pmu->pmu = &rapl_pmu_class;
 
+	/*
+	 * use reference of 200W for scaling the timeout
+	 * to avoid missing counter overflows.
+	 * 200W = 200 Joules/sec
+	 * divide interval by 2 to avoid lockstep (2 * 100)
+	 * if hw unit is 32, then we use 2 ms 1/200/2
+	 */
+	if (pmu->hw_unit < 32)
+		ms = (1000 / (2 * 100)) * (1ULL << (32 - pmu->hw_unit - 1));
+	else
+		ms = 2;
+
+	pmu->timer_interval = ms_to_ktime(ms);
+
+	rapl_hrtimer_init(pmu);
+
 	/* set RAPL pmu for this cpu for now */
 	per_cpu(rapl_pmu, cpu) = pmu;
 	per_cpu(rapl_pmu_to_free, cpu) = NULL;
@@ -580,9 +648,11 @@ static int __init rapl_pmu_init(void)
 
 	pr_info("RAPL PMU detected, hw unit 2^-%d Joules,"
 		" API unit is 2^-32 Joules,"
-		" %d fixed counters\n",
+		" %d fixed counters"
+		" %llu ms ovfl timer\n",
 		pmu->hw_unit,
-		hweight32(rapl_cntr_mask));
+		hweight32(rapl_cntr_mask),
+		ktime_to_ms(pmu->timer_interval));
 
 	put_online_cpus();
 
-- 
cgit v0.10.2


From 12e55569a244996a23cb401e8116e5a060b664f0 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Tue, 19 Nov 2013 18:29:37 -0500
Subject: tools lib traceevent: Use helper trace-seq in print functions like
 kernel does

Jiri Olsa reported that his plugin for scsi was chopping off part of the
output. Investigating this, I found that Jiri used the same functions as
what is in the kernel, which adds the following:

	trace_seq_putc(p, 0);

This adds a '\0' to the output string. The reason this works in the
kernel is that the "p" that is passed to the function helper is a
temporary trace_seq. But in the libtraceevent library, it's the pointer
to the trace_seq used to output. By adding the '\0', it truncates the
line and nothing added after that will be printed.

We can solve this in two ways. One is to have the helper functions for
the library not add the unnecessary '\0'. The other is to change the
library to also use a helper trace_seq structure that gets copied to the
main trace_seq just like the kernel does.

The latter allows the helper functions in the plugins to be the same as
the kernel, which is the better solution.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Reported-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Jiri Olsa <jolsa@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/20131119182937.401668e3@gandalf.local.home
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 217c82ee..900fca0 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -4099,6 +4099,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 	unsigned long long val;
 	struct func_map *func;
 	const char *saveptr;
+	struct trace_seq p;
 	char *bprint_fmt = NULL;
 	char format[32];
 	int show_func;
@@ -4306,8 +4307,12 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 				format[len] = 0;
 				if (!len_as_arg)
 					len_arg = -1;
-				print_str_arg(s, data, size, event,
+				/* Use helper trace_seq */
+				trace_seq_init(&p);
+				print_str_arg(&p, data, size, event,
 					      format, len_arg, arg);
+				trace_seq_terminate(&p);
+				trace_seq_puts(s, p.buffer);
 				arg = arg->next;
 				break;
 			default:
-- 
cgit v0.10.2


From 15e65c693d7de4c83d1e97fd89f87d47f2219782 Mon Sep 17 00:00:00 2001
From: Pekka Enberg <penberg@kernel.org>
Date: Thu, 14 Nov 2013 18:43:30 +0200
Subject: perf trace: Remove thread summary coloring

Thread summary line coloring looks ugly.  It doesn't add much value so
remove coloring completely.

Signed-off-by: Pekka Enberg <penberg@kernel.org>
Acked-by: David Ahern <dsahern@gmail.com>
Link: http://lkml.kernel.org/r/1384447410-1771-1-git-send-email-penberg@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 8be17fc..e9f345e2 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2158,7 +2158,6 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv)
 	size_t printed = data->printed;
 	struct trace *trace = data->trace;
 	struct thread_trace *ttrace = thread->priv;
-	const char *color;
 	double ratio;
 
 	if (ttrace == NULL)
@@ -2166,17 +2165,9 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv)
 
 	ratio = (double)ttrace->nr_events / trace->nr_events * 100.0;
 
-	color = PERF_COLOR_NORMAL;
-	if (ratio > 50.0)
-		color = PERF_COLOR_RED;
-	else if (ratio > 25.0)
-		color = PERF_COLOR_GREEN;
-	else if (ratio > 5.0)
-		color = PERF_COLOR_YELLOW;
-
-	printed += color_fprintf(fp, color, " %s (%d), ", thread__comm_str(thread), thread->tid);
+	printed += fprintf(fp, " %s (%d), ", thread__comm_str(thread), thread->tid);
 	printed += fprintf(fp, "%lu events, ", ttrace->nr_events);
-	printed += color_fprintf(fp, color, "%.1f%%", ratio);
+	printed += fprintf(fp, "%.1f%%", ratio);
 	printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
 	printed += thread__dump_stats(ttrace, trace, fp);
 
-- 
cgit v0.10.2


From bf80669e4f689f181f23a54dfe2a0f264147ad67 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Thu, 14 Nov 2013 20:51:30 -0700
Subject: perf top: Make -g refer to callchains

In most commands -g is used for callchains. Make perf-top follow suit.
Move group to just --group with no short cut making it similar to
perf-record.

Signed-off-by: David Ahern <dsahern@gmail.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1384487490-6865-1-git-send-email-dsahern@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 7de01dd..cdd8d49 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -50,7 +50,6 @@ Default is to monitor all CPUS.
 --count-filter=<count>::
 	Only display functions with more events than this.
 
--g::
 --group::
         Put the counters into a counter group.
 
@@ -143,12 +142,12 @@ Default is to monitor all CPUS.
 --asm-raw::
 	Show raw instruction encoding of assembly instructions.
 
--G::
+-g::
 	Enables call-graph (stack chain/backtrace) recording.
 
 --call-graph::
 	Setup and enable call-graph (stack chain/backtrace) recording,
-	implies -G.
+	implies -g.
 
 --max-stack::
 	Set the stack depth limit when parsing the callchain, anything
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 71e6402..531522d 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1084,7 +1084,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 			    "dump the symbol table used for profiling"),
 	OPT_INTEGER('f', "count-filter", &top.count_filter,
 		    "only display functions with more events than this"),
-	OPT_BOOLEAN('g', "group", &opts->group,
+	OPT_BOOLEAN(0, "group", &opts->group,
 			    "put the counters into a counter group"),
 	OPT_BOOLEAN('i', "no-inherit", &opts->no_inherit,
 		    "child tasks do not inherit counters"),
@@ -1105,7 +1105,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		   " abort, in_tx, transaction"),
 	OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
 		    "Show a column with the number of samples"),
-	OPT_CALLBACK_NOOPT('G', NULL, &top.record_opts,
+	OPT_CALLBACK_NOOPT('g', NULL, &top.record_opts,
 			   NULL, "enables call-graph recording",
 			   &callchain_opt),
 	OPT_CALLBACK(0, "call-graph", &top.record_opts,
-- 
cgit v0.10.2


From 2cf025e69543f5f4aa68e8549d60680515fef5ad Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <artagnon@gmail.com>
Date: Sun, 17 Nov 2013 21:43:23 +0530
Subject: perf completion: Introduce a layer of indirection

Define the variables cur, words, cword, and prev outside the main
completion function so that we have a chance to override it when we
introduce zsh support.

Signed-off-by: Ramkumar Ramachandra <artagnon@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Link: http://lkml.kernel.org/r/1384704807-15779-2-git-send-email-artagnon@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/bash_completion b/tools/perf/bash_completion
index 62e157db..3efdc84 100644
--- a/tools/perf/bash_completion
+++ b/tools/perf/bash_completion
@@ -89,15 +89,12 @@ __ltrim_colon_completions()
 	fi
 }
 
-type perf &>/dev/null &&
-_perf()
+__perf_main ()
 {
-	local cur words cword prev cmd
-
-	COMPREPLY=()
-	_get_comp_words_by_ref -n =: cur words cword prev
+	local cmd
 
 	cmd=${words[0]}
+	COMPREPLY=()
 
 	# List perf subcommands or long options
 	if [ $cword -eq 1 ]; then
@@ -120,6 +117,14 @@ _perf()
 		opts=$($cmd $subcmd --list-opts)
 		COMPREPLY=( $( compgen -W '$opts' -- "$cur" ) )
 	fi
+}
+
+type perf &>/dev/null &&
+_perf()
+{
+	local cur words cword prev
+	_get_comp_words_by_ref -n =: cur words cword prev
+	__perf_main
 } &&
 
 complete -o bashdefault -o default -o nospace -F _perf perf 2>/dev/null \
-- 
cgit v0.10.2


From 12f9dd5042483698c74a133d9004ff1d1a6474f9 Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <artagnon@gmail.com>
Date: Sun, 17 Nov 2013 21:43:24 +0530
Subject: perf completion: Factor out compgen stuff

compgen is a bash-builtin; factor out the invocations into a separate
function to give us a chance to override it with a zsh equivalent in
future patches.

Signed-off-by: Ramkumar Ramachandra <artagnon@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Link: http://lkml.kernel.org/r/1384704807-15779-3-git-send-email-artagnon@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/bash_completion b/tools/perf/bash_completion
index 3efdc84..82431268 100644
--- a/tools/perf/bash_completion
+++ b/tools/perf/bash_completion
@@ -89,6 +89,11 @@ __ltrim_colon_completions()
 	fi
 }
 
+__perfcomp ()
+{
+	COMPREPLY=( $( compgen -W "$1" -- "$2" ) )
+}
+
 __perf_main ()
 {
 	local cmd
@@ -99,23 +104,23 @@ __perf_main ()
 	# List perf subcommands or long options
 	if [ $cword -eq 1 ]; then
 		if [[ $cur == --* ]]; then
-			COMPREPLY=( $( compgen -W '--help --version \
+			__perfcomp '--help --version \
 			--exec-path --html-path --paginate --no-pager \
-			--perf-dir --work-tree --debugfs-dir' -- "$cur" ) )
+			--perf-dir --work-tree --debugfs-dir' -- "$cur"
 		else
 			cmds=$($cmd --list-cmds)
-			COMPREPLY=( $( compgen -W '$cmds' -- "$cur" ) )
+			__perfcomp "$cmds" "$cur"
 		fi
 	# List possible events for -e option
 	elif [[ $prev == "-e" && "${words[1]}" == @(record|stat|top) ]]; then
 		evts=$($cmd list --raw-dump)
-		COMPREPLY=( $( compgen -W '$evts' -- "$cur" ) )
+		__perfcomp "$evts" "$cur"
 		__ltrim_colon_completions $cur
 	# List long option names
 	elif [[ $cur == --* ]];  then
 		subcmd=${words[1]}
 		opts=$($cmd $subcmd --list-opts)
-		COMPREPLY=( $( compgen -W '$opts' -- "$cur" ) )
+		__perfcomp "$opts" "$cur"
 	fi
 }
 
-- 
cgit v0.10.2


From 37e72c31061521d6f0e4b7fe47cd5748280ed691 Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <artagnon@gmail.com>
Date: Sun, 17 Nov 2013 21:43:25 +0530
Subject: perf completion: Factor out call to __ltrim_colon_completions

In our sole callsite, __ltrim_colon_completions is called after
__perfcomp, to modify the COMPREPLY set by the invocation.

This is problematic, because in the zsh equivalent (using compset/
compadd), we'll have to generate completions in one-shot.

So factor out this entire callsite into a special override'able
__perfcomp_colon function; we will override it when introducing zsh
support.

Signed-off-by: Ramkumar Ramachandra <artagnon@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Link: http://lkml.kernel.org/r/1384704807-15779-4-git-send-email-artagnon@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/bash_completion b/tools/perf/bash_completion
index 82431268..573599b 100644
--- a/tools/perf/bash_completion
+++ b/tools/perf/bash_completion
@@ -94,6 +94,12 @@ __perfcomp ()
 	COMPREPLY=( $( compgen -W "$1" -- "$2" ) )
 }
 
+__perfcomp_colon ()
+{
+	__perfcomp "$1" "$2"
+	__ltrim_colon_completions $cur
+}
+
 __perf_main ()
 {
 	local cmd
@@ -114,8 +120,7 @@ __perf_main ()
 	# List possible events for -e option
 	elif [[ $prev == "-e" && "${words[1]}" == @(record|stat|top) ]]; then
 		evts=$($cmd list --raw-dump)
-		__perfcomp "$evts" "$cur"
-		__ltrim_colon_completions $cur
+		__perfcomp_colon "$evts" "$cur"
 	# List long option names
 	elif [[ $cur == --* ]];  then
 		subcmd=${words[1]}
-- 
cgit v0.10.2


From f38ab8af794c184c15f5e001d0eaa16f4a120978 Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <artagnon@gmail.com>
Date: Sun, 17 Nov 2013 21:43:26 +0530
Subject: perf completion: Introduce zsh support

__perfcomp(), __perfcomp_colon(), and _perf() have to be overridden.
Inspired by the way the git.git completion system is structured.

Signed-off-by: Ramkumar Ramachandra <artagnon@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1384704807-15779-5-git-send-email-artagnon@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/bash_completion b/tools/perf/bash_completion
index 573599b..4949488 100644
--- a/tools/perf/bash_completion
+++ b/tools/perf/bash_completion
@@ -1,4 +1,4 @@
-# perf completion
+# perf bash and zsh completion
 
 # Taken from git.git's completion script.
 __my_reassemble_comp_words_by_ref()
@@ -129,6 +129,67 @@ __perf_main ()
 	fi
 }
 
+if [[ -n ${ZSH_VERSION-} ]]; then
+	autoload -U +X compinit && compinit
+
+	__perfcomp ()
+	{
+		emulate -L zsh
+
+		local c IFS=$' \t\n'
+		local -a array
+
+		for c in ${=1}; do
+			case $c in
+			--*=*|*.) ;;
+			*) c="$c " ;;
+			esac
+			array[${#array[@]}+1]="$c"
+		done
+
+		compset -P '*[=:]'
+		compadd -Q -S '' -a -- array && _ret=0
+	}
+
+	__perfcomp_colon ()
+	{
+		emulate -L zsh
+
+		local cur_="${2-$cur}"
+		local c IFS=$' \t\n'
+		local -a array
+
+		if [[ "$cur_" == *:* ]]; then
+			local colon_word=${cur_%"${cur_##*:}"}
+		fi
+
+		for c in ${=1}; do
+			case $c in
+			--*=*|*.) ;;
+			*) c="$c " ;;
+			esac
+			array[$#array+1]=${c#"$colon_word"}
+		done
+
+		compset -P '*[=:]'
+		compadd -Q -S '' -a -- array && _ret=0
+	}
+
+	_perf ()
+	{
+		local _ret=1 cur cword prev
+		cur=${words[CURRENT]}
+		prev=${words[CURRENT-1]}
+		let cword=CURRENT-1
+		emulate ksh -c __perf_main
+		let _ret && _default && _ret=0
+		return _ret
+	}
+
+	compdef _perf perf
+	return
+fi
+
 type perf &>/dev/null &&
 _perf()
 {
-- 
cgit v0.10.2


From a8b4c7014cadfdacd4e1f4c963128593be6f20de Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <artagnon@gmail.com>
Date: Sun, 17 Nov 2013 21:43:27 +0530
Subject: perf completion: Rename file to reflect zsh support

Signed-off-by: Ramkumar Ramachandra <artagnon@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Link: http://lkml.kernel.org/r/1384704807-15779-6-git-send-email-artagnon@gmail.com
[ Fix 'make install' target ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 7fc8f17..e416ccc 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -840,9 +840,9 @@ ifndef NO_LIBPYTHON
 		$(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'; \
 		$(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
 endif
-	$(call QUIET_INSTALL, bash_completion-script) \
+	$(call QUIET_INSTALL, perf_completion-script) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \
-		$(INSTALL) bash_completion '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
+		$(INSTALL) perf-completion.sh '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
 	$(call QUIET_INSTALL, tests) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
 		$(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
diff --git a/tools/perf/bash_completion b/tools/perf/bash_completion
deleted file mode 100644
index 4949488..0000000
--- a/tools/perf/bash_completion
+++ /dev/null
@@ -1,202 +0,0 @@
-# perf bash and zsh completion
-
-# Taken from git.git's completion script.
-__my_reassemble_comp_words_by_ref()
-{
-	local exclude i j first
-	# Which word separators to exclude?
-	exclude="${1//[^$COMP_WORDBREAKS]}"
-	cword_=$COMP_CWORD
-	if [ -z "$exclude" ]; then
-		words_=("${COMP_WORDS[@]}")
-		return
-	fi
-	# List of word completion separators has shrunk;
-	# re-assemble words to complete.
-	for ((i=0, j=0; i < ${#COMP_WORDS[@]}; i++, j++)); do
-		# Append each nonempty word consisting of just
-		# word separator characters to the current word.
-		first=t
-		while
-			[ $i -gt 0 ] &&
-			[ -n "${COMP_WORDS[$i]}" ] &&
-			# word consists of excluded word separators
-			[ "${COMP_WORDS[$i]//[^$exclude]}" = "${COMP_WORDS[$i]}" ]
-		do
-			# Attach to the previous token,
-			# unless the previous token is the command name.
-			if [ $j -ge 2 ] && [ -n "$first" ]; then
-				((j--))
-			fi
-			first=
-			words_[$j]=${words_[j]}${COMP_WORDS[i]}
-			if [ $i = $COMP_CWORD ]; then
-				cword_=$j
-			fi
-			if (($i < ${#COMP_WORDS[@]} - 1)); then
-				((i++))
-			else
-				# Done.
-				return
-			fi
-		done
-		words_[$j]=${words_[j]}${COMP_WORDS[i]}
-		if [ $i = $COMP_CWORD ]; then
-			cword_=$j
-		fi
-	done
-}
-
-type _get_comp_words_by_ref &>/dev/null ||
-_get_comp_words_by_ref()
-{
-	local exclude cur_ words_ cword_
-	if [ "$1" = "-n" ]; then
-		exclude=$2
-		shift 2
-	fi
-	__my_reassemble_comp_words_by_ref "$exclude"
-	cur_=${words_[cword_]}
-	while [ $# -gt 0 ]; do
-		case "$1" in
-		cur)
-			cur=$cur_
-			;;
-		prev)
-			prev=${words_[$cword_-1]}
-			;;
-		words)
-			words=("${words_[@]}")
-			;;
-		cword)
-			cword=$cword_
-			;;
-		esac
-		shift
-	done
-}
-
-type __ltrim_colon_completions &>/dev/null ||
-__ltrim_colon_completions()
-{
-	if [[ "$1" == *:* && "$COMP_WORDBREAKS" == *:* ]]; then
-		# Remove colon-word prefix from COMPREPLY items
-		local colon_word=${1%"${1##*:}"}
-		local i=${#COMPREPLY[*]}
-		while [[ $((--i)) -ge 0 ]]; do
-			COMPREPLY[$i]=${COMPREPLY[$i]#"$colon_word"}
-		done
-	fi
-}
-
-__perfcomp ()
-{
-	COMPREPLY=( $( compgen -W "$1" -- "$2" ) )
-}
-
-__perfcomp_colon ()
-{
-	__perfcomp "$1" "$2"
-	__ltrim_colon_completions $cur
-}
-
-__perf_main ()
-{
-	local cmd
-
-	cmd=${words[0]}
-	COMPREPLY=()
-
-	# List perf subcommands or long options
-	if [ $cword -eq 1 ]; then
-		if [[ $cur == --* ]]; then
-			__perfcomp '--help --version \
-			--exec-path --html-path --paginate --no-pager \
-			--perf-dir --work-tree --debugfs-dir' -- "$cur"
-		else
-			cmds=$($cmd --list-cmds)
-			__perfcomp "$cmds" "$cur"
-		fi
-	# List possible events for -e option
-	elif [[ $prev == "-e" && "${words[1]}" == @(record|stat|top) ]]; then
-		evts=$($cmd list --raw-dump)
-		__perfcomp_colon "$evts" "$cur"
-	# List long option names
-	elif [[ $cur == --* ]];  then
-		subcmd=${words[1]}
-		opts=$($cmd $subcmd --list-opts)
-		__perfcomp "$opts" "$cur"
-	fi
-}
-
-if [[ -n ${ZSH_VERSION-} ]]; then
-	autoload -U +X compinit && compinit
-
-	__perfcomp ()
-	{
-		emulate -L zsh
-
-		local c IFS=$' \t\n'
-		local -a array
-
-		for c in ${=1}; do
-			case $c in
-			--*=*|*.) ;;
-			*) c="$c " ;;
-			esac
-			array[${#array[@]}+1]="$c"
-		done
-
-		compset -P '*[=:]'
-		compadd -Q -S '' -a -- array && _ret=0
-	}
-
-	__perfcomp_colon ()
-	{
-		emulate -L zsh
-
-		local cur_="${2-$cur}"
-		local c IFS=$' \t\n'
-		local -a array
-
-		if [[ "$cur_" == *:* ]]; then
-			local colon_word=${cur_%"${cur_##*:}"}
-		fi
-
-		for c in ${=1}; do
-			case $c in
-			--*=*|*.) ;;
-			*) c="$c " ;;
-			esac
-			array[$#array+1]=${c#"$colon_word"}
-		done
-
-		compset -P '*[=:]'
-		compadd -Q -S '' -a -- array && _ret=0
-	}
-
-	_perf ()
-	{
-		local _ret=1 cur cword prev
-		cur=${words[CURRENT]}
-		prev=${words[CURRENT-1]}
-		let cword=CURRENT-1
-		emulate ksh -c __perf_main
-		let _ret && _default && _ret=0
-		return _ret
-	}
-
-	compdef _perf perf
-	return
-fi
-
-type perf &>/dev/null &&
-_perf()
-{
-	local cur words cword prev
-	_get_comp_words_by_ref -n =: cur words cword prev
-	__perf_main
-} &&
-
-complete -o bashdefault -o default -o nospace -F _perf perf 2>/dev/null \
-	|| complete -o default -o nospace -F _perf perf
diff --git a/tools/perf/perf-completion.sh b/tools/perf/perf-completion.sh
new file mode 100644
index 0000000..4949488
--- /dev/null
+++ b/tools/perf/perf-completion.sh
@@ -0,0 +1,202 @@
+# perf bash and zsh completion
+
+# Taken from git.git's completion script.
+__my_reassemble_comp_words_by_ref()
+{
+	local exclude i j first
+	# Which word separators to exclude?
+	exclude="${1//[^$COMP_WORDBREAKS]}"
+	cword_=$COMP_CWORD
+	if [ -z "$exclude" ]; then
+		words_=("${COMP_WORDS[@]}")
+		return
+	fi
+	# List of word completion separators has shrunk;
+	# re-assemble words to complete.
+	for ((i=0, j=0; i < ${#COMP_WORDS[@]}; i++, j++)); do
+		# Append each nonempty word consisting of just
+		# word separator characters to the current word.
+		first=t
+		while
+			[ $i -gt 0 ] &&
+			[ -n "${COMP_WORDS[$i]}" ] &&
+			# word consists of excluded word separators
+			[ "${COMP_WORDS[$i]//[^$exclude]}" = "${COMP_WORDS[$i]}" ]
+		do
+			# Attach to the previous token,
+			# unless the previous token is the command name.
+			if [ $j -ge 2 ] && [ -n "$first" ]; then
+				((j--))
+			fi
+			first=
+			words_[$j]=${words_[j]}${COMP_WORDS[i]}
+			if [ $i = $COMP_CWORD ]; then
+				cword_=$j
+			fi
+			if (($i < ${#COMP_WORDS[@]} - 1)); then
+				((i++))
+			else
+				# Done.
+				return
+			fi
+		done
+		words_[$j]=${words_[j]}${COMP_WORDS[i]}
+		if [ $i = $COMP_CWORD ]; then
+			cword_=$j
+		fi
+	done
+}
+
+type _get_comp_words_by_ref &>/dev/null ||
+_get_comp_words_by_ref()
+{
+	local exclude cur_ words_ cword_
+	if [ "$1" = "-n" ]; then
+		exclude=$2
+		shift 2
+	fi
+	__my_reassemble_comp_words_by_ref "$exclude"
+	cur_=${words_[cword_]}
+	while [ $# -gt 0 ]; do
+		case "$1" in
+		cur)
+			cur=$cur_
+			;;
+		prev)
+			prev=${words_[$cword_-1]}
+			;;
+		words)
+			words=("${words_[@]}")
+			;;
+		cword)
+			cword=$cword_
+			;;
+		esac
+		shift
+	done
+}
+
+type __ltrim_colon_completions &>/dev/null ||
+__ltrim_colon_completions()
+{
+	if [[ "$1" == *:* && "$COMP_WORDBREAKS" == *:* ]]; then
+		# Remove colon-word prefix from COMPREPLY items
+		local colon_word=${1%"${1##*:}"}
+		local i=${#COMPREPLY[*]}
+		while [[ $((--i)) -ge 0 ]]; do
+			COMPREPLY[$i]=${COMPREPLY[$i]#"$colon_word"}
+		done
+	fi
+}
+
+__perfcomp ()
+{
+	COMPREPLY=( $( compgen -W "$1" -- "$2" ) )
+}
+
+__perfcomp_colon ()
+{
+	__perfcomp "$1" "$2"
+	__ltrim_colon_completions $cur
+}
+
+__perf_main ()
+{
+	local cmd
+
+	cmd=${words[0]}
+	COMPREPLY=()
+
+	# List perf subcommands or long options
+	if [ $cword -eq 1 ]; then
+		if [[ $cur == --* ]]; then
+			__perfcomp '--help --version \
+			--exec-path --html-path --paginate --no-pager \
+			--perf-dir --work-tree --debugfs-dir' -- "$cur"
+		else
+			cmds=$($cmd --list-cmds)
+			__perfcomp "$cmds" "$cur"
+		fi
+	# List possible events for -e option
+	elif [[ $prev == "-e" && "${words[1]}" == @(record|stat|top) ]]; then
+		evts=$($cmd list --raw-dump)
+		__perfcomp_colon "$evts" "$cur"
+	# List long option names
+	elif [[ $cur == --* ]];  then
+		subcmd=${words[1]}
+		opts=$($cmd $subcmd --list-opts)
+		__perfcomp "$opts" "$cur"
+	fi
+}
+
+if [[ -n ${ZSH_VERSION-} ]]; then
+	autoload -U +X compinit && compinit
+
+	__perfcomp ()
+	{
+		emulate -L zsh
+
+		local c IFS=$' \t\n'
+		local -a array
+
+		for c in ${=1}; do
+			case $c in
+			--*=*|*.) ;;
+			*) c="$c " ;;
+			esac
+			array[${#array[@]}+1]="$c"
+		done
+
+		compset -P '*[=:]'
+		compadd -Q -S '' -a -- array && _ret=0
+	}
+
+	__perfcomp_colon ()
+	{
+		emulate -L zsh
+
+		local cur_="${2-$cur}"
+		local c IFS=$' \t\n'
+		local -a array
+
+		if [[ "$cur_" == *:* ]]; then
+			local colon_word=${cur_%"${cur_##*:}"}
+		fi
+
+		for c in ${=1}; do
+			case $c in
+			--*=*|*.) ;;
+			*) c="$c " ;;
+			esac
+			array[$#array+1]=${c#"$colon_word"}
+		done
+
+		compset -P '*[=:]'
+		compadd -Q -S '' -a -- array && _ret=0
+	}
+
+	_perf ()
+	{
+		local _ret=1 cur cword prev
+		cur=${words[CURRENT]}
+		prev=${words[CURRENT-1]}
+		let cword=CURRENT-1
+		emulate ksh -c __perf_main
+		let _ret && _default && _ret=0
+		return _ret
+	}
+
+	compdef _perf perf
+	return
+fi
+
+type perf &>/dev/null &&
+_perf()
+{
+	local cur words cword prev
+	_get_comp_words_by_ref -n =: cur words cword prev
+	__perf_main
+} &&
+
+complete -o bashdefault -o default -o nospace -F _perf perf 2>/dev/null \
+	|| complete -o default -o nospace -F _perf perf
-- 
cgit v0.10.2


From e944d3d7d151eea149c62310eaff7b92c7732f58 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 18 Nov 2013 14:34:52 +0900
Subject: perf script: Move evname print code to process_event()

The print_sample_start() will be reused by other printing routine for
internal events like COMM, FORK and EXIT from next patch.  And because
they're not tied to a specific event, move the evname print code to its
caller.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: David Ahern <dsahern@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1384752894-10974-1-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index baf1798..b392770 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -288,7 +288,6 @@ static void print_sample_start(struct perf_sample *sample,
 			       struct perf_evsel *evsel)
 {
 	struct perf_event_attr *attr = &evsel->attr;
-	const char *evname = NULL;
 	unsigned long secs;
 	unsigned long usecs;
 	unsigned long long nsecs;
@@ -323,11 +322,6 @@ static void print_sample_start(struct perf_sample *sample,
 		usecs = nsecs / NSECS_PER_USEC;
 		printf("%5lu.%06lu: ", secs, usecs);
 	}
-
-	if (PRINT_FIELD(EVNAME)) {
-		evname = perf_evsel__name(evsel);
-		printf("%s: ", evname ? evname : "[unknown]");
-	}
 }
 
 static bool is_bts_event(struct perf_event_attr *attr)
@@ -434,6 +428,11 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 
 	print_sample_start(sample, thread, evsel);
 
+	if (PRINT_FIELD(EVNAME)) {
+		const char *evname = perf_evsel__name(evsel);
+		printf("%s: ", evname ? evname : "[unknown]");
+	}
+
 	if (is_bts_event(attr)) {
 		print_sample_bts(event, sample, evsel, machine, thread);
 		return;
-- 
cgit v0.10.2


From 3aa5939d71fa22a947808ba9c798b8537c35097a Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 15 Nov 2013 15:52:29 +0200
Subject: perf record: Make per-cpu mmaps the default.

This affects the -p, -t and -u options that previously defaulted to
per-thread mmaps.

Consequently add an option to select per-thread mmaps to support the old
behaviour.

Note that per-thread can be used with a workload-only (i.e. none of -p,
-t, -u, -a or -C is selected) to get a per-thread mmap with no
inheritance.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/5286271D.3020808@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 43b42c4..6ac867e 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -201,11 +201,11 @@ abort events and some memory events in precise mode on modern Intel CPUs.
 --transaction::
 Record transaction flags for transaction related events.
 
---force-per-cpu::
-Force the use of per-cpu mmaps.  By default, when tasks are specified (i.e. -p,
--t or -u options) per-thread mmaps are created.  This option overrides that and
-forces per-cpu mmaps.  A side-effect of that is that inheritance is
-automatically enabled.  Add the -i option also to disable inheritance.
+--per-thread::
+Use per-thread mmaps.  By default per-cpu mmaps are created.  This option
+overrides that and uses per-thread mmaps.  A side-effect of that is that
+inheritance is automatically disabled.  --per-thread is ignored with a warning
+if combined with -a or -C options.
 
 SEE ALSO
 --------
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 7c8020a..f5b18b8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -800,6 +800,7 @@ static struct perf_record record = {
 		.freq		     = 4000,
 		.target		     = {
 			.uses_mmap   = true,
+			.default_per_cpu = true,
 		},
 	},
 };
@@ -888,8 +889,8 @@ const struct option record_options[] = {
 		    "sample by weight (on special events only)"),
 	OPT_BOOLEAN(0, "transaction", &record.opts.sample_transaction,
 		    "sample transaction flags (special events only)"),
-	OPT_BOOLEAN(0, "force-per-cpu", &record.opts.target.force_per_cpu,
-		    "force the use of per-cpu mmaps"),
+	OPT_BOOLEAN(0, "per-thread", &record.opts.target.per_thread,
+		    "use per-thread mmaps"),
 	OPT_END()
 };
 
diff --git a/tools/perf/tests/attr/test-record-no-inherit b/tools/perf/tests/attr/test-record-no-inherit
index 9079a25..44edcb2 100644
--- a/tools/perf/tests/attr/test-record-no-inherit
+++ b/tools/perf/tests/attr/test-record-no-inherit
@@ -3,5 +3,5 @@ command = record
 args    = -i kill >/dev/null 2>&1
 
 [event:base-record]
-sample_type=259
+sample_type=263
 inherit=0
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index bbc746a..76fa764 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -819,8 +819,10 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 	if (evlist->threads == NULL)
 		return -1;
 
-	if (target->force_per_cpu)
-		evlist->cpus = cpu_map__new(target->cpu_list);
+	if (target->default_per_cpu)
+		evlist->cpus = target->per_thread ?
+					cpu_map__dummy_new() :
+					cpu_map__new(target->cpu_list);
 	else if (target__has_task(target))
 		evlist->cpus = cpu_map__dummy_new();
 	else if (!target__has_cpu(target) && !target->uses_mmap)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index dad6492..b5fe7f9 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -574,6 +574,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 	struct perf_evsel *leader = evsel->leader;
 	struct perf_event_attr *attr = &evsel->attr;
 	int track = !evsel->idx; /* only the first counter needs these */
+	bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread;
 
 	attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
 	attr->inherit	    = !opts->no_inherit;
@@ -647,7 +648,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 		}
 	}
 
-	if (target__has_cpu(&opts->target) || opts->target.force_per_cpu)
+	if (target__has_cpu(&opts->target))
 		perf_evsel__set_sample_bit(evsel, CPU);
 
 	if (opts->period)
@@ -655,7 +656,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 
 	if (!perf_missing_features.sample_id_all &&
 	    (opts->sample_time || !opts->no_inherit ||
-	     target__has_cpu(&opts->target) || opts->target.force_per_cpu))
+	     target__has_cpu(&opts->target) || per_cpu))
 		perf_evsel__set_sample_bit(evsel, TIME);
 
 	if (opts->raw_samples) {
diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
index 3c778a0..e74c596 100644
--- a/tools/perf/util/target.c
+++ b/tools/perf/util/target.c
@@ -55,6 +55,13 @@ enum target_errno target__validate(struct target *target)
 			ret = TARGET_ERRNO__UID_OVERRIDE_SYSTEM;
 	}
 
+	/* THREAD and SYSTEM/CPU are mutually exclusive */
+	if (target->per_thread && (target->system_wide || target->cpu_list)) {
+		target->per_thread = false;
+		if (ret == TARGET_ERRNO__SUCCESS)
+			ret = TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD;
+	}
+
 	return ret;
 }
 
@@ -100,6 +107,7 @@ static const char *target__error_str[] = {
 	"UID switch overriding CPU",
 	"PID/TID switch overriding SYSTEM",
 	"UID switch overriding SYSTEM",
+	"SYSTEM/CPU switch overriding PER-THREAD",
 	"Invalid User: %s",
 	"Problems obtaining information for user %s",
 };
@@ -131,7 +139,8 @@ int target__strerror(struct target *target, int errnum,
 	msg = target__error_str[idx];
 
 	switch (errnum) {
-	case TARGET_ERRNO__PID_OVERRIDE_CPU ... TARGET_ERRNO__UID_OVERRIDE_SYSTEM:
+	case TARGET_ERRNO__PID_OVERRIDE_CPU ...
+	     TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD:
 		snprintf(buf, buflen, "%s", msg);
 		break;
 
diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h
index 2d0c506..31dd2e9 100644
--- a/tools/perf/util/target.h
+++ b/tools/perf/util/target.h
@@ -12,7 +12,8 @@ struct target {
 	uid_t	     uid;
 	bool	     system_wide;
 	bool	     uses_mmap;
-	bool	     force_per_cpu;
+	bool	     default_per_cpu;
+	bool	     per_thread;
 };
 
 enum target_errno {
@@ -33,6 +34,7 @@ enum target_errno {
 	TARGET_ERRNO__UID_OVERRIDE_CPU,
 	TARGET_ERRNO__PID_OVERRIDE_SYSTEM,
 	TARGET_ERRNO__UID_OVERRIDE_SYSTEM,
+	TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD,
 
 	/* for target__parse_uid() */
 	TARGET_ERRNO__INVALID_UID,
-- 
cgit v0.10.2


From 4bc437964ef540462bd15af4a713da62961809aa Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 18 Nov 2013 11:55:55 +0200
Subject: perf tools: Allow '--inherit' as the negation of '--no-inherit'

Long options can be negated by prefixing them with 'no-'.  However
options that already start with 'no-', such as '--no-inherit' result in
ugly double 'no's.

Avoid that by accepting that the removal of 'no-' also negates the long
option.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1384768557-23331-3-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index 31f404a..b6b39ff 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -224,6 +224,24 @@ static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg,
 			return 0;
 		}
 		if (!rest) {
+			if (!prefixcmp(options->long_name, "no-")) {
+				/*
+				 * The long name itself starts with "no-", so
+				 * accept the option without "no-" so that users
+				 * do not have to enter "no-no-" to get the
+				 * negation.
+				 */
+				rest = skip_prefix(arg, options->long_name + 3);
+				if (rest) {
+					flags |= OPT_UNSET;
+					goto match;
+				}
+				/* Abbreviated case */
+				if (!prefixcmp(options->long_name + 3, arg)) {
+					flags |= OPT_UNSET;
+					goto is_abbreviated;
+				}
+			}
 			/* abbreviated? */
 			if (!strncmp(options->long_name, arg, arg_end - arg)) {
 is_abbreviated:
@@ -259,6 +277,7 @@ is_abbreviated:
 			if (!rest)
 				continue;
 		}
+match:
 		if (*rest) {
 			if (*rest != '=')
 				continue;
-- 
cgit v0.10.2


From 167faf32b07fc47637048fbcbdfcf4a89481686d Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 18 Nov 2013 11:55:56 +0200
Subject: perf tools: Add option macro OPT_BOOLEAN_SET

OPT_BOOLEAN_SET records whether a boolean option was set by the user.

That information can be used to change the default value for the option
after the options have been parsed.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1384768557-23331-4-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index b6b39ff..d22e3f80 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -78,6 +78,8 @@ static int get_value(struct parse_opt_ctx_t *p,
 
 	case OPTION_BOOLEAN:
 		*(bool *)opt->value = unset ? false : true;
+		if (opt->set)
+			*(bool *)opt->set = true;
 		return 0;
 
 	case OPTION_INCR:
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index b0241e2..cbf0149 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -82,6 +82,9 @@ typedef int parse_opt_cb(const struct option *, const char *arg, int unset);
  *   OPTION_{BIT,SET_UINT,SET_PTR} store the {mask,integer,pointer} to put in
  *   the value when met.
  *   CALLBACKS can use it like they want.
+ *
+ * `set`::
+ *   whether an option was set by the user
  */
 struct option {
 	enum parse_opt_type type;
@@ -94,6 +97,7 @@ struct option {
 	int flags;
 	parse_opt_cb *callback;
 	intptr_t defval;
+	bool *set;
 };
 
 #define check_vtype(v, type) ( BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v )
@@ -103,6 +107,10 @@ struct option {
 #define OPT_GROUP(h)                { .type = OPTION_GROUP, .help = (h) }
 #define OPT_BIT(s, l, v, h, b)      { .type = OPTION_BIT, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h), .defval = (b) }
 #define OPT_BOOLEAN(s, l, v, h)     { .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), .value = check_vtype(v, bool *), .help = (h) }
+#define OPT_BOOLEAN_SET(s, l, v, os, h) \
+	{ .type = OPTION_BOOLEAN, .short_name = (s), .long_name = (l), \
+	.value = check_vtype(v, bool *), .help = (h), \
+	.set = check_vtype(os, bool *)}
 #define OPT_INCR(s, l, v, h)        { .type = OPTION_INCR, .short_name = (s), .long_name = (l), .value = check_vtype(v, int *), .help = (h) }
 #define OPT_SET_UINT(s, l, v, h, i)  { .type = OPTION_SET_UINT, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h), .defval = (i) }
 #define OPT_SET_PTR(s, l, v, h, p)  { .type = OPTION_SET_PTR, .short_name = (s), .long_name = (l), .value = (v), .help = (h), .defval = (p) }
-- 
cgit v0.10.2


From 69e7e5b02bc6a9e5cf4a54911b27ca133cc1f99f Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 18 Nov 2013 11:55:57 +0200
Subject: perf record: Default -t option to no inheritance

The change to per-cpu mmaps causes the -p, -t and -u options now to have
inheritance enabled by default.  Change that back to no inheritance but
for the -t option only.

Requested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1384768557-23331-5-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 6ac867e..c407897 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -57,6 +57,8 @@ OPTIONS
 -t::
 --tid=::
         Record events on existing thread ID (comma separated list).
+        This option also disables inheritance by default.  Enable it by adding
+        --inherit.
 
 -u::
 --uid=::
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f5b18b8..65615a8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -843,8 +843,9 @@ const struct option record_options[] = {
 	OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
 	OPT_STRING('o', "output", &record.file.path, "file",
 		    "output file name"),
-	OPT_BOOLEAN('i', "no-inherit", &record.opts.no_inherit,
-		    "child tasks do not inherit counters"),
+	OPT_BOOLEAN_SET('i', "no-inherit", &record.opts.no_inherit,
+			&record.opts.no_inherit_set,
+			"child tasks do not inherit counters"),
 	OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
 	OPT_CALLBACK('m', "mmap-pages", &record.opts.mmap_pages, "pages",
 		     "number of mmap data pages",
@@ -939,6 +940,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto out_symbol_exit;
 	}
 
+	if (rec->opts.target.tid && !rec->opts.no_inherit_set)
+		rec->opts.no_inherit = true;
+
 	err = target__validate(&rec->opts.target);
 	if (err) {
 		target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index b079304..b23fed5 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -254,6 +254,7 @@ struct perf_record_opts {
 	bool	     inherit_stat;
 	bool	     no_delay;
 	bool	     no_inherit;
+	bool	     no_inherit_set;
 	bool	     no_samples;
 	bool	     raw_samples;
 	bool	     sample_address;
-- 
cgit v0.10.2


From 0a8eb275cbdb8462854d5f7e1168d86cee4cc9ea Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <stfomichev@yandex-team.ru>
Date: Fri, 1 Nov 2013 20:25:45 +0400
Subject: perf timechart: Always try to print at least 15 tasks

Always try to print at least 15 tasks no matter how long they run.

Signed-off-by: Stanislav Fomichev <stfomichev@yandex-team.ru>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1383323151-19810-2-git-send-email-stfomichev@yandex-team.ru
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 41c9bde2..bb21e57 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -945,15 +945,17 @@ static void write_svg_file(const char *filename)
 {
 	u64 i;
 	int count;
+	int thresh = TIME_THRESH;
 
 	numcpus++;
 
 
-	count = determine_display_tasks(TIME_THRESH);
-
-	/* We'd like to show at least 15 tasks; be less picky if we have fewer */
-	if (count < 15)
-		count = determine_display_tasks(TIME_THRESH / 10);
+	/* We'd like to show at least proc_num tasks;
+	 * be less picky if we have fewer */
+	do {
+		count = determine_display_tasks(thresh);
+		thresh /= 10;
+	} while (!process_filter && thresh && count < 15);
 
 	open_svg(filename, numcpus, count, first_time, last_time);
 
-- 
cgit v0.10.2


From 54874e3236b834064943c02a647823ab5d97be57 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <stfomichev@yandex-team.ru>
Date: Fri, 1 Nov 2013 20:25:46 +0400
Subject: perf timechart: Add option to limit number of tasks

Add -n option to specify min. number of tasks to print.

Signed-off-by: Stanislav Fomichev <stfomichev@yandex-team.ru>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1383323151-19810-3-git-send-email-stfomichev@yandex-team.ru
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index 3ff8bd4..4373144 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -54,6 +54,10 @@ $ perf timechart
 
   Written 10.2 seconds of trace to output.svg.
 
+-n::
+--proc-num::
+        Print task info for at least given number of tasks.
+
 SEE ALSO
 --------
 linkperf:perf-record[1]
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index bb21e57..c352be4 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -41,6 +41,7 @@
 #define SUPPORT_OLD_POWER_EVENTS 1
 #define PWR_EVENT_EXIT -1
 
+static int proc_num = 15;
 
 static unsigned int	numcpus;
 static u64		min_freq;	/* Lowest CPU frequency seen */
@@ -955,7 +956,7 @@ static void write_svg_file(const char *filename)
 	do {
 		count = determine_display_tasks(thresh);
 		thresh /= 10;
-	} while (!process_filter && thresh && count < 15);
+	} while (!process_filter && thresh && count < proc_num);
 
 	open_svg(filename, numcpus, count, first_time, last_time);
 
@@ -1102,6 +1103,8 @@ int cmd_timechart(int argc, const char **argv,
 		       parse_process),
 	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
 		    "Look for files with symbols relative to this directory"),
+	OPT_INTEGER('n', "proc-num", &proc_num,
+		    "min. number of tasks to print"),
 	OPT_END()
 	};
 	const char * const timechart_usage[] = {
-- 
cgit v0.10.2


From 753c505dc49a87a4421d452bda048e4b93e8e42b Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <stfomichev@yandex-team.ru>
Date: Fri, 1 Nov 2013 20:25:47 +0400
Subject: perf timechart: Use proc_num to implement --power-only

Don't use special flag to indicate power-only mode, just set proc_num to
0.

Signed-off-by: Stanislav Fomichev <stfomichev@yandex-team.ru>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1383323151-19810-4-git-send-email-stfomichev@yandex-team.ru
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index c352be4..6410c9e 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -912,7 +912,7 @@ static int determine_display_tasks(u64 threshold)
 		/* no exit marker, task kept running to the end */
 		if (p->end_time == 0)
 			p->end_time = last_time;
-		if (p->total_time >= threshold && !power_only)
+		if (p->total_time >= threshold)
 			p->display = 1;
 
 		c = p->all;
@@ -923,7 +923,7 @@ static int determine_display_tasks(u64 threshold)
 			if (c->start_time == 1)
 				c->start_time = first_time;
 
-			if (c->total_time >= threshold && !power_only) {
+			if (c->total_time >= threshold) {
 				c->display = 1;
 				count++;
 			}
@@ -950,6 +950,8 @@ static void write_svg_file(const char *filename)
 
 	numcpus++;
 
+	if (power_only)
+		proc_num = 0;
 
 	/* We'd like to show at least proc_num tasks;
 	 * be less picky if we have fewer */
@@ -967,9 +969,11 @@ static void write_svg_file(const char *filename)
 		svg_cpu_box(i, max_freq, turbo_frequency);
 
 	draw_cpu_usage();
-	draw_process_bars();
+	if (proc_num)
+		draw_process_bars();
 	draw_c_p_states();
-	draw_wakeups();
+	if (proc_num)
+		draw_wakeups();
 
 	svg_close();
 }
-- 
cgit v0.10.2


From c87097d39dae1c42a5068e00dd3b76a4162ee0fc Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <stfomichev@yandex-team.ru>
Date: Fri, 1 Nov 2013 20:25:48 +0400
Subject: perf timechart: Add support for displaying only tasks related data

In order to make SVG smaller and faster to browse add possibility to
switch off power related information with -T switch.

Signed-off-by: Stanislav Fomichev <stfomichev@yandex-team.ru>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1383323151-19810-5-git-send-email-stfomichev@yandex-team.ru
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index 4373144..d844189 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -35,6 +35,9 @@ OPTIONS
 -P::
 --power-only::
         Only output the CPU power section of the diagram
+-T::
+--tasks-only::
+        Don't output processor state transitions
 -p::
 --process::
         Select the processes to display, by name or PID
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 6410c9e..b3f175a 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -51,6 +51,7 @@ static u64		turbo_frequency;
 static u64		first_time, last_time;
 
 static bool		power_only;
+static bool		tasks_only;
 
 
 struct per_pid;
@@ -971,7 +972,8 @@ static void write_svg_file(const char *filename)
 	draw_cpu_usage();
 	if (proc_num)
 		draw_process_bars();
-	draw_c_p_states();
+	if (!tasks_only)
+		draw_c_p_states();
 	if (proc_num)
 		draw_wakeups();
 
@@ -1102,6 +1104,8 @@ int cmd_timechart(int argc, const char **argv,
 	OPT_STRING('o', "output", &output_name, "file", "output file name"),
 	OPT_INTEGER('w', "width", &svg_page_width, "page width"),
 	OPT_BOOLEAN('P', "power-only", &power_only, "output power data only"),
+	OPT_BOOLEAN('T', "tasks-only", &tasks_only,
+		    "output processes data only"),
 	OPT_CALLBACK('p', "process", NULL, "process",
 		      "process selector. Pass a pid or process name.",
 		       parse_process),
@@ -1119,6 +1123,11 @@ int cmd_timechart(int argc, const char **argv,
 	argc = parse_options(argc, argv, options, timechart_usage,
 			PARSE_OPT_STOP_AT_NON_OPTION);
 
+	if (power_only && tasks_only) {
+		pr_err("-P and -T options cannot be used at the same time.\n");
+		return -1;
+	}
+
 	symbol__init();
 
 	if (argc && !strncmp(argv[0], "rec", 3))
-- 
cgit v0.10.2


From cbb2e81e5232b1bca5cd2aa1d7a7eb1cd30f8304 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <stfomichev@yandex-team.ru>
Date: Fri, 1 Nov 2013 20:25:49 +0400
Subject: perf timechart: Group figures and add title with details

Add titles to figures so we can run SVG interactively in Firefox and
check event details in the tooltips.

This also aids exploring SVG with Inkscape because when user clicks on
one part of logical figure, all parts are selected.

It's also possible to read titles with Inkscape in the object details.

Signed-off-by: Stanislav Fomichev <stfomichev@yandex-team.ru>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1383323151-19810-6-git-send-email-stfomichev@yandex-team.ru
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index b3f175a..6a848b8 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -798,11 +798,11 @@ static void draw_process_bars(void)
 			sample = c->samples;
 			while (sample) {
 				if (sample->type == TYPE_RUNNING)
-					svg_sample(Y, sample->cpu, sample->start_time, sample->end_time);
+					svg_running(Y, sample->cpu, sample->start_time, sample->end_time);
 				if (sample->type == TYPE_BLOCKED)
-					svg_box(Y, sample->start_time, sample->end_time, "blocked");
+					svg_blocked(Y, sample->cpu, sample->start_time, sample->end_time);
 				if (sample->type == TYPE_WAITING)
-					svg_waiting(Y, sample->start_time, sample->end_time);
+					svg_waiting(Y, sample->cpu, sample->start_time, sample->end_time);
 				sample = sample->next;
 			}
 
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 96c8660..9a5b413 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -95,6 +95,7 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end)
 
 	total_height = (1 + rows + cpu2slot(cpus)) * SLOT_MULT;
 	fprintf(svgfile, "<?xml version=\"1.0\" standalone=\"no\"?> \n");
+	fprintf(svgfile, "<!DOCTYPE svg SYSTEM \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n");
 	fprintf(svgfile, "<svg width=\"%i\" height=\"%" PRIu64 "\" version=\"1.1\" xmlns=\"http://www.w3.org/2000/svg\">\n", svg_page_width, total_height);
 
 	fprintf(svgfile, "<defs>\n  <style type=\"text/css\">\n    <![CDATA[\n");
@@ -128,12 +129,29 @@ void svg_box(int Yslot, u64 start, u64 end, const char *type)
 		time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT, type);
 }
 
-void svg_sample(int Yslot, int cpu, u64 start, u64 end)
+static char *time_to_string(u64 duration);
+void svg_blocked(int Yslot, int cpu, u64 start, u64 end)
+{
+	if (!svgfile)
+		return;
+
+	fprintf(svgfile, "<g>\n");
+	fprintf(svgfile, "<title>#%d blocked %s</title>\n", cpu,
+		time_to_string(end - start));
+	svg_box(Yslot, start, end, "blocked");
+	fprintf(svgfile, "</g>\n");
+}
+
+void svg_running(int Yslot, int cpu, u64 start, u64 end)
 {
 	double text_size;
 	if (!svgfile)
 		return;
 
+	fprintf(svgfile, "<g>\n");
+
+	fprintf(svgfile, "<title>#%d running %s</title>\n",
+		cpu, time_to_string(end - start));
 	fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"sample\"/>\n",
 		time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT);
 
@@ -148,6 +166,7 @@ void svg_sample(int Yslot, int cpu, u64 start, u64 end)
 		fprintf(svgfile, "<text x=\"%1.8f\" y=\"%1.8f\" font-size=\"%1.8fpt\">%i</text>\n",
 			time2pixels(start), Yslot *  SLOT_MULT + SLOT_HEIGHT - 1, text_size,  cpu + 1);
 
+	fprintf(svgfile, "</g>\n");
 }
 
 static char *time_to_string(u64 duration)
@@ -168,7 +187,7 @@ static char *time_to_string(u64 duration)
 	return text;
 }
 
-void svg_waiting(int Yslot, u64 start, u64 end)
+void svg_waiting(int Yslot, int cpu, u64 start, u64 end)
 {
 	char *text;
 	const char *style;
@@ -192,6 +211,7 @@ void svg_waiting(int Yslot, u64 start, u64 end)
 	font_size = round_text_size(font_size);
 
 	fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT);
+	fprintf(svgfile, "<title>#%d waiting %s</title>\n", cpu, time_to_string(end - start));
 	fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
 		time2pixels(end)-time2pixels(start), SLOT_HEIGHT, style);
 	if (font_size > MIN_TEXT_SIZE)
@@ -242,6 +262,8 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq)
 	max_freq = __max_freq;
 	turbo_frequency = __turbo_freq;
 
+	fprintf(svgfile, "<g>\n");
+
 	fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"cpu\"/>\n",
 		time2pixels(first_time),
 		time2pixels(last_time)-time2pixels(first_time),
@@ -253,6 +275,8 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq)
 
 	fprintf(svgfile, "<text transform=\"translate(%4.8f,%4.8f)\" font-size=\"1.25pt\">%s</text>\n",
 		10+time2pixels(first_time), cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - 4, cpu_model());
+
+	fprintf(svgfile, "</g>\n");
 }
 
 void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name)
@@ -264,6 +288,7 @@ void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name
 
 
 	fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), cpu2y(cpu));
+	fprintf(svgfile, "<title>%s %s</title>\n", name, time_to_string(end - start));
 	fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
 		time2pixels(end)-time2pixels(start), SLOT_MULT+SLOT_HEIGHT, type);
 	width = time2pixels(end)-time2pixels(start);
@@ -288,6 +313,8 @@ void svg_cstate(int cpu, u64 start, u64 end, int type)
 		return;
 
 
+	fprintf(svgfile, "<g>\n");
+
 	if (type > 6)
 		type = 6;
 	sprintf(style, "c%i", type);
@@ -306,6 +333,8 @@ void svg_cstate(int cpu, u64 start, u64 end, int type)
 	if (width > MIN_TEXT_SIZE)
 		fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"%3.8fpt\">C%i</text>\n",
 			time2pixels(start), cpu2y(cpu)+width, width, type);
+
+	fprintf(svgfile, "</g>\n");
 }
 
 static char *HzToHuman(unsigned long hz)
@@ -339,6 +368,8 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq)
 	if (!svgfile)
 		return;
 
+	fprintf(svgfile, "<g>\n");
+
 	if (max_freq)
 		height = freq * 1.0 / max_freq * (SLOT_HEIGHT + SLOT_MULT);
 	height = 1 + cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - height;
@@ -347,6 +378,7 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq)
 	fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"0.25pt\">%s</text>\n",
 		time2pixels(start), height+0.9, HzToHuman(freq));
 
+	fprintf(svgfile, "</g>\n");
 }
 
 
@@ -358,6 +390,12 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
 		return;
 
 
+	fprintf(svgfile, "<g>\n");
+
+	fprintf(svgfile, "<title>%s wakes up %s</title>\n",
+		desc1 ? desc1 : "?",
+		desc2 ? desc2 : "?");
+
 	if (row1 < row2) {
 		if (row1) {
 			fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
@@ -395,6 +433,8 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
 	if (row1)
 		fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(32,255,32)\"/>\n",
 			time2pixels(start), height);
+
+	fprintf(svgfile, "</g>\n");
 }
 
 void svg_wakeline(u64 start, int row1, int row2)
@@ -405,6 +445,8 @@ void svg_wakeline(u64 start, int row1, int row2)
 		return;
 
 
+	fprintf(svgfile, "<g>\n");
+
 	if (row1 < row2)
 		fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
 			time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT,  time2pixels(start), row2 * SLOT_MULT);
@@ -417,6 +459,8 @@ void svg_wakeline(u64 start, int row1, int row2)
 		height += SLOT_HEIGHT;
 	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(32,255,32)\"/>\n",
 			time2pixels(start), height);
+
+	fprintf(svgfile, "</g>\n");
 }
 
 void svg_interrupt(u64 start, int row)
@@ -424,10 +468,16 @@ void svg_interrupt(u64 start, int row)
 	if (!svgfile)
 		return;
 
+	fprintf(svgfile, "<g>\n");
+
+	fprintf(svgfile, "<title>Wakeup from interrupt</title>\n");
+
 	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
 			time2pixels(start), row * SLOT_MULT);
 	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
 			time2pixels(start), row * SLOT_MULT + SLOT_HEIGHT);
+
+	fprintf(svgfile, "</g>\n");
 }
 
 void svg_text(int Yslot, u64 start, const char *text)
@@ -455,6 +505,7 @@ void svg_legenda(void)
 	if (!svgfile)
 		return;
 
+	fprintf(svgfile, "<g>\n");
 	svg_legenda_box(0,	"Running", "sample");
 	svg_legenda_box(100,	"Idle","c1");
 	svg_legenda_box(200,	"Deeper Idle", "c3");
@@ -462,6 +513,7 @@ void svg_legenda(void)
 	svg_legenda_box(550,	"Sleeping", "process2");
 	svg_legenda_box(650,	"Waiting for cpu", "waiting");
 	svg_legenda_box(800,	"Blocked on IO", "blocked");
+	fprintf(svgfile, "</g>\n");
 }
 
 void svg_time_grid(void)
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index e078198..aa53345 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -5,8 +5,9 @@
 
 extern void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end);
 extern void svg_box(int Yslot, u64 start, u64 end, const char *type);
-extern void svg_sample(int Yslot, int cpu, u64 start, u64 end);
-extern void svg_waiting(int Yslot, u64 start, u64 end);
+extern void svg_blocked(int Yslot, int cpu, u64 start, u64 end);
+extern void svg_running(int Yslot, int cpu, u64 start, u64 end);
+extern void svg_waiting(int Yslot, int cpu, u64 start, u64 end);
 extern void svg_cpu_box(int cpu, u64 max_frequency, u64 turbo_frequency);
 
 
-- 
cgit v0.10.2


From 367b3152d72c20d789b07650bd1189ce0fe266b8 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <stfomichev@yandex-team.ru>
Date: Fri, 1 Nov 2013 20:25:50 +0400
Subject: perf timechart: Add support for -P and -T in timechart recording

If we don't want either power or task events we may use -T or -P with
the `perf timechart record` command to filter out events while recording
to keep perf.data small.

Signed-off-by: Stanislav Fomichev <stfomichev@yandex-team.ru>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1383323151-19810-7-git-send-email-stfomichev@yandex-team.ru
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index d844189..8359cfa 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -8,8 +8,7 @@ perf-timechart - Tool to visualize total system behavior during a workload
 SYNOPSIS
 --------
 [verse]
-'perf timechart' record <command>
-'perf timechart' [<options>]
+'perf timechart' [<timechart options>] {record} [<record options>]
 
 DESCRIPTION
 -----------
@@ -21,8 +20,8 @@ There are two variants of perf timechart:
   'perf timechart' to turn a trace into a Scalable Vector Graphics file,
   that can be viewed with popular SVG viewers such as 'Inkscape'.
 
-OPTIONS
--------
+TIMECHART OPTIONS
+-----------------
 -o::
 --output=::
         Select the output file (default: output.svg)
@@ -61,6 +60,15 @@ $ perf timechart
 --proc-num::
         Print task info for at least given number of tasks.
 
+RECORD OPTIONS
+--------------
+-P::
+--power-only::
+        Record only power-related events
+-T::
+--tasks-only::
+        Record only tasks-related events
+
 SEE ALSO
 --------
 linkperf:perf-record[1]
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 6a848b8..1c60ed3 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -1040,50 +1040,81 @@ out_delete:
 
 static int __cmd_record(int argc, const char **argv)
 {
-#ifdef SUPPORT_OLD_POWER_EVENTS
-	const char * const record_old_args[] = {
+	unsigned int rec_argc, i, j;
+	const char **rec_argv;
+	const char **p;
+	unsigned int record_elems;
+
+	const char * const common_args[] = {
 		"record", "-a", "-R", "-c", "1",
+	};
+	unsigned int common_args_nr = ARRAY_SIZE(common_args);
+
+	const char * const power_args[] = {
+		"-e", "power:cpu_frequency",
+		"-e", "power:cpu_idle",
+	};
+	unsigned int power_args_nr = ARRAY_SIZE(power_args);
+
+	const char * const old_power_args[] = {
+#ifdef SUPPORT_OLD_POWER_EVENTS
 		"-e", "power:power_start",
 		"-e", "power:power_end",
 		"-e", "power:power_frequency",
-		"-e", "sched:sched_wakeup",
-		"-e", "sched:sched_switch",
-	};
 #endif
-	const char * const record_new_args[] = {
-		"record", "-a", "-R", "-c", "1",
-		"-e", "power:cpu_frequency",
-		"-e", "power:cpu_idle",
+	};
+	unsigned int old_power_args_nr = ARRAY_SIZE(old_power_args);
+
+	const char * const tasks_args[] = {
 		"-e", "sched:sched_wakeup",
 		"-e", "sched:sched_switch",
 	};
-	unsigned int rec_argc, i, j;
-	const char **rec_argv;
-	const char * const *record_args = record_new_args;
-	unsigned int record_elems = ARRAY_SIZE(record_new_args);
+	unsigned int tasks_args_nr = ARRAY_SIZE(tasks_args);
 
 #ifdef SUPPORT_OLD_POWER_EVENTS
 	if (!is_valid_tracepoint("power:cpu_idle") &&
 	    is_valid_tracepoint("power:power_start")) {
 		use_old_power_events = 1;
-		record_args = record_old_args;
-		record_elems = ARRAY_SIZE(record_old_args);
+		power_args_nr = 0;
+	} else {
+		old_power_args_nr = 0;
 	}
 #endif
 
-	rec_argc = record_elems + argc - 1;
+	if (power_only)
+		tasks_args_nr = 0;
+
+	if (tasks_only) {
+		power_args_nr = 0;
+		old_power_args_nr = 0;
+	}
+
+	record_elems = common_args_nr + tasks_args_nr +
+		power_args_nr + old_power_args_nr;
+
+	rec_argc = record_elems + argc;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
 	if (rec_argv == NULL)
 		return -ENOMEM;
 
-	for (i = 0; i < record_elems; i++)
-		rec_argv[i] = strdup(record_args[i]);
+	p = rec_argv;
+	for (i = 0; i < common_args_nr; i++)
+		*p++ = strdup(common_args[i]);
+
+	for (i = 0; i < tasks_args_nr; i++)
+		*p++ = strdup(tasks_args[i]);
+
+	for (i = 0; i < power_args_nr; i++)
+		*p++ = strdup(power_args[i]);
 
-	for (j = 1; j < (unsigned int)argc; j++, i++)
-		rec_argv[i] = argv[j];
+	for (i = 0; i < old_power_args_nr; i++)
+		*p++ = strdup(old_power_args[i]);
 
-	return cmd_record(i, rec_argv, NULL);
+	for (j = 1; j < (unsigned int)argc; j++)
+		*p++ = argv[j];
+
+	return cmd_record(rec_argc, rec_argv, NULL);
 }
 
 static int
@@ -1099,7 +1130,7 @@ int cmd_timechart(int argc, const char **argv,
 		  const char *prefix __maybe_unused)
 {
 	const char *output_name = "output.svg";
-	const struct option options[] = {
+	const struct option timechart_options[] = {
 	OPT_STRING('i', "input", &input_name, "file", "input file name"),
 	OPT_STRING('o', "output", &output_name, "file", "output file name"),
 	OPT_INTEGER('w', "width", &svg_page_width, "page width"),
@@ -1120,7 +1151,17 @@ int cmd_timechart(int argc, const char **argv,
 		NULL
 	};
 
-	argc = parse_options(argc, argv, options, timechart_usage,
+	const struct option record_options[] = {
+	OPT_BOOLEAN('P', "power-only", &power_only, "output power data only"),
+	OPT_BOOLEAN('T', "tasks-only", &tasks_only,
+		    "output processes data only"),
+	OPT_END()
+	};
+	const char * const record_usage[] = {
+		"perf timechart record [<options>]",
+		NULL
+	};
+	argc = parse_options(argc, argv, timechart_options, timechart_usage,
 			PARSE_OPT_STOP_AT_NON_OPTION);
 
 	if (power_only && tasks_only) {
@@ -1130,10 +1171,18 @@ int cmd_timechart(int argc, const char **argv,
 
 	symbol__init();
 
-	if (argc && !strncmp(argv[0], "rec", 3))
+	if (argc && !strncmp(argv[0], "rec", 3)) {
+		argc = parse_options(argc, argv, record_options, record_usage,
+				     PARSE_OPT_STOP_AT_NON_OPTION);
+
+		if (power_only && tasks_only) {
+			pr_err("-P and -T options cannot be used at the same time.\n");
+			return -1;
+		}
+
 		return __cmd_record(argc, argv);
-	else if (argc)
-		usage_with_options(timechart_usage, options);
+	} else if (argc)
+		usage_with_options(timechart_usage, timechart_options);
 
 	setup_pager();
 
-- 
cgit v0.10.2


From 6f8d67fa0c6bdca535ecab137c44b095023cc1b4 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <stfomichev@yandex-team.ru>
Date: Fri, 1 Nov 2013 20:25:51 +0400
Subject: perf timechart: Add backtrace support

Add -g flag to `perf timechart record` which saves callchain info in the
perf.data.

When generating SVG, add backtrace information to the figure details, so
now it's possible to see which code path woke up the task and why some
task went to sleep.

Signed-off-by: Stanislav Fomichev <stfomichev@yandex-team.ru>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1383323151-19810-8-git-send-email-stfomichev@yandex-team.ru
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index 8359cfa..271dd4e 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -68,6 +68,9 @@ RECORD OPTIONS
 -T::
 --tasks-only::
         Record only tasks-related events
+-g::
+--callchain::
+        Do call-graph (stack chain/backtrace) recording
 
 SEE ALSO
 --------
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 1c60ed3..491662b 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -52,6 +52,7 @@ static u64		first_time, last_time;
 
 static bool		power_only;
 static bool		tasks_only;
+static bool		with_backtrace;
 
 
 struct per_pid;
@@ -126,6 +127,7 @@ struct cpu_sample {
 	u64 end_time;
 	int type;
 	int cpu;
+	const char *backtrace;
 };
 
 static struct per_pid *all_data;
@@ -147,6 +149,7 @@ struct wake_event {
 	int waker;
 	int wakee;
 	u64 time;
+	const char *backtrace;
 };
 
 static struct power_event    *power_events;
@@ -231,7 +234,8 @@ static void pid_exit(int pid, u64 timestamp)
 }
 
 static void
-pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end)
+pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end,
+	       const char *backtrace)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
@@ -254,6 +258,7 @@ pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end)
 	sample->type = type;
 	sample->next = c->samples;
 	sample->cpu = cpu;
+	sample->backtrace = backtrace;
 	c->samples = sample;
 
 	if (sample->type == TYPE_RUNNING && end > start && start > 0) {
@@ -405,7 +410,8 @@ static void p_state_change(int cpu, u64 timestamp, u64 new_freq)
 }
 
 static void
-sched_wakeup(int cpu, u64 timestamp, int pid, struct trace_entry *te)
+sched_wakeup(int cpu, u64 timestamp, int pid, struct trace_entry *te,
+	     const char *backtrace)
 {
 	struct per_pid *p;
 	struct wakeup_entry *wake = (void *)te;
@@ -416,6 +422,7 @@ sched_wakeup(int cpu, u64 timestamp, int pid, struct trace_entry *te)
 
 	we->time = timestamp;
 	we->waker = pid;
+	we->backtrace = backtrace;
 
 	if ((te->flags & TRACE_FLAG_HARDIRQ) || (te->flags & TRACE_FLAG_SOFTIRQ))
 		we->waker = -1;
@@ -430,13 +437,15 @@ sched_wakeup(int cpu, u64 timestamp, int pid, struct trace_entry *te)
 		p->current->state = TYPE_WAITING;
 	}
 	if (p && p->current && p->current->state == TYPE_BLOCKED) {
-		pid_put_sample(p->pid, p->current->state, cpu, p->current->state_since, timestamp);
+		pid_put_sample(p->pid, p->current->state, cpu,
+			       p->current->state_since, timestamp, NULL);
 		p->current->state_since = timestamp;
 		p->current->state = TYPE_WAITING;
 	}
 }
 
-static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te)
+static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te,
+			 const char *backtrace)
 {
 	struct per_pid *p = NULL, *prev_p;
 	struct sched_switch *sw = (void *)te;
@@ -447,10 +456,14 @@ static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te)
 	p = find_create_pid(sw->next_pid);
 
 	if (prev_p->current && prev_p->current->state != TYPE_NONE)
-		pid_put_sample(sw->prev_pid, TYPE_RUNNING, cpu, prev_p->current->state_since, timestamp);
+		pid_put_sample(sw->prev_pid, TYPE_RUNNING, cpu,
+			       prev_p->current->state_since, timestamp,
+			       backtrace);
 	if (p && p->current) {
 		if (p->current->state != TYPE_NONE)
-			pid_put_sample(sw->next_pid, p->current->state, cpu, p->current->state_since, timestamp);
+			pid_put_sample(sw->next_pid, p->current->state, cpu,
+				       p->current->state_since, timestamp,
+				       backtrace);
 
 		p->current->state_since = timestamp;
 		p->current->state = TYPE_RUNNING;
@@ -466,8 +479,87 @@ static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te)
 	}
 }
 
+static const char *cat_backtrace(union perf_event *event,
+				 struct perf_sample *sample,
+				 struct machine *machine)
+{
+	struct addr_location al;
+	unsigned int i;
+	char *p = NULL;
+	size_t p_len;
+	u8 cpumode = PERF_RECORD_MISC_USER;
+	struct addr_location tal;
+	struct ip_callchain *chain = sample->callchain;
+	FILE *f = open_memstream(&p, &p_len);
+
+	if (!f) {
+		perror("open_memstream error");
+		return NULL;
+	}
+
+	if (!chain)
+		goto exit;
+
+	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
+		fprintf(stderr, "problem processing %d event, skipping it.\n",
+			event->header.type);
+		goto exit;
+	}
+
+	for (i = 0; i < chain->nr; i++) {
+		u64 ip;
+
+		if (callchain_param.order == ORDER_CALLEE)
+			ip = chain->ips[i];
+		else
+			ip = chain->ips[chain->nr - i - 1];
+
+		if (ip >= PERF_CONTEXT_MAX) {
+			switch (ip) {
+			case PERF_CONTEXT_HV:
+				cpumode = PERF_RECORD_MISC_HYPERVISOR;
+				break;
+			case PERF_CONTEXT_KERNEL:
+				cpumode = PERF_RECORD_MISC_KERNEL;
+				break;
+			case PERF_CONTEXT_USER:
+				cpumode = PERF_RECORD_MISC_USER;
+				break;
+			default:
+				pr_debug("invalid callchain context: "
+					 "%"PRId64"\n", (s64) ip);
+
+				/*
+				 * It seems the callchain is corrupted.
+				 * Discard all.
+				 */
+				free(p);
+				p = NULL;
+				goto exit;
+			}
+			continue;
+		}
+
+		tal.filtered = false;
+		thread__find_addr_location(al.thread, machine, cpumode,
+					   MAP__FUNCTION, ip, &tal);
+
+		if (tal.sym)
+			fprintf(f, "..... %016" PRIx64 " %s\n", ip,
+				tal.sym->name);
+		else
+			fprintf(f, "..... %016" PRIx64 "\n", ip);
+	}
+
+exit:
+	fclose(f);
+
+	return p;
+}
+
 typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
-				  struct perf_sample *sample);
+				  struct perf_sample *sample,
+				  const char *backtrace);
 
 static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				union perf_event *event __maybe_unused,
@@ -487,7 +579,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 
 	if (evsel->handler != NULL) {
 		tracepoint_handler f = evsel->handler;
-		return f(evsel, sample);
+		return f(evsel, sample, cat_backtrace(event, sample, machine));
 	}
 
 	return 0;
@@ -495,7 +587,8 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 
 static int
 process_sample_cpu_idle(struct perf_evsel *evsel __maybe_unused,
-			struct perf_sample *sample)
+			struct perf_sample *sample,
+			const char *backtrace __maybe_unused)
 {
 	struct power_processor_entry *ppe = sample->raw_data;
 
@@ -508,7 +601,8 @@ process_sample_cpu_idle(struct perf_evsel *evsel __maybe_unused,
 
 static int
 process_sample_cpu_frequency(struct perf_evsel *evsel __maybe_unused,
-			     struct perf_sample *sample)
+			     struct perf_sample *sample,
+			     const char *backtrace __maybe_unused)
 {
 	struct power_processor_entry *ppe = sample->raw_data;
 
@@ -518,28 +612,31 @@ process_sample_cpu_frequency(struct perf_evsel *evsel __maybe_unused,
 
 static int
 process_sample_sched_wakeup(struct perf_evsel *evsel __maybe_unused,
-			    struct perf_sample *sample)
+			    struct perf_sample *sample,
+			    const char *backtrace)
 {
 	struct trace_entry *te = sample->raw_data;
 
-	sched_wakeup(sample->cpu, sample->time, sample->pid, te);
+	sched_wakeup(sample->cpu, sample->time, sample->pid, te, backtrace);
 	return 0;
 }
 
 static int
 process_sample_sched_switch(struct perf_evsel *evsel __maybe_unused,
-			    struct perf_sample *sample)
+			    struct perf_sample *sample,
+			    const char *backtrace)
 {
 	struct trace_entry *te = sample->raw_data;
 
-	sched_switch(sample->cpu, sample->time, te);
+	sched_switch(sample->cpu, sample->time, te, backtrace);
 	return 0;
 }
 
 #ifdef SUPPORT_OLD_POWER_EVENTS
 static int
 process_sample_power_start(struct perf_evsel *evsel __maybe_unused,
-			   struct perf_sample *sample)
+			   struct perf_sample *sample,
+			   const char *backtrace __maybe_unused)
 {
 	struct power_entry_old *peo = sample->raw_data;
 
@@ -549,7 +646,8 @@ process_sample_power_start(struct perf_evsel *evsel __maybe_unused,
 
 static int
 process_sample_power_end(struct perf_evsel *evsel __maybe_unused,
-			 struct perf_sample *sample)
+			 struct perf_sample *sample,
+			 const char *backtrace __maybe_unused)
 {
 	c_state_end(sample->cpu, sample->time);
 	return 0;
@@ -557,7 +655,8 @@ process_sample_power_end(struct perf_evsel *evsel __maybe_unused,
 
 static int
 process_sample_power_frequency(struct perf_evsel *evsel __maybe_unused,
-			       struct perf_sample *sample)
+			       struct perf_sample *sample,
+			       const char *backtrace __maybe_unused)
 {
 	struct power_entry_old *peo = sample->raw_data;
 
@@ -741,11 +840,12 @@ static void draw_wakeups(void)
 		}
 
 		if (we->waker == -1)
-			svg_interrupt(we->time, to);
+			svg_interrupt(we->time, to, we->backtrace);
 		else if (from && to && abs(from - to) == 1)
-			svg_wakeline(we->time, from, to);
+			svg_wakeline(we->time, from, to, we->backtrace);
 		else
-			svg_partial_wakeline(we->time, from, task_from, to, task_to);
+			svg_partial_wakeline(we->time, from, task_from, to,
+					     task_to, we->backtrace);
 		we = we->next;
 
 		free(task_from);
@@ -798,11 +898,20 @@ static void draw_process_bars(void)
 			sample = c->samples;
 			while (sample) {
 				if (sample->type == TYPE_RUNNING)
-					svg_running(Y, sample->cpu, sample->start_time, sample->end_time);
+					svg_running(Y, sample->cpu,
+						    sample->start_time,
+						    sample->end_time,
+						    sample->backtrace);
 				if (sample->type == TYPE_BLOCKED)
-					svg_blocked(Y, sample->cpu, sample->start_time, sample->end_time);
+					svg_blocked(Y, sample->cpu,
+						    sample->start_time,
+						    sample->end_time,
+						    sample->backtrace);
 				if (sample->type == TYPE_WAITING)
-					svg_waiting(Y, sample->cpu, sample->start_time, sample->end_time);
+					svg_waiting(Y, sample->cpu,
+						    sample->start_time,
+						    sample->end_time,
+						    sample->backtrace);
 				sample = sample->next;
 			}
 
@@ -1050,6 +1159,11 @@ static int __cmd_record(int argc, const char **argv)
 	};
 	unsigned int common_args_nr = ARRAY_SIZE(common_args);
 
+	const char * const backtrace_args[] = {
+		"-g",
+	};
+	unsigned int backtrace_args_no = ARRAY_SIZE(backtrace_args);
+
 	const char * const power_args[] = {
 		"-e", "power:cpu_frequency",
 		"-e", "power:cpu_idle",
@@ -1089,8 +1203,11 @@ static int __cmd_record(int argc, const char **argv)
 		old_power_args_nr = 0;
 	}
 
+	if (!with_backtrace)
+		backtrace_args_no = 0;
+
 	record_elems = common_args_nr + tasks_args_nr +
-		power_args_nr + old_power_args_nr;
+		power_args_nr + old_power_args_nr + backtrace_args_no;
 
 	rec_argc = record_elems + argc;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
@@ -1102,6 +1219,9 @@ static int __cmd_record(int argc, const char **argv)
 	for (i = 0; i < common_args_nr; i++)
 		*p++ = strdup(common_args[i]);
 
+	for (i = 0; i < backtrace_args_no; i++)
+		*p++ = strdup(backtrace_args[i]);
+
 	for (i = 0; i < tasks_args_nr; i++)
 		*p++ = strdup(tasks_args[i]);
 
@@ -1155,6 +1275,7 @@ int cmd_timechart(int argc, const char **argv,
 	OPT_BOOLEAN('P', "power-only", &power_only, "output power data only"),
 	OPT_BOOLEAN('T', "tasks-only", &tasks_only,
 		    "output processes data only"),
+	OPT_BOOLEAN('g', "callchain", &with_backtrace, "record callchain"),
 	OPT_END()
 	};
 	const char * const record_usage[] = {
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 9a5b413..8b79d3a 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -130,7 +130,7 @@ void svg_box(int Yslot, u64 start, u64 end, const char *type)
 }
 
 static char *time_to_string(u64 duration);
-void svg_blocked(int Yslot, int cpu, u64 start, u64 end)
+void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 {
 	if (!svgfile)
 		return;
@@ -138,11 +138,13 @@ void svg_blocked(int Yslot, int cpu, u64 start, u64 end)
 	fprintf(svgfile, "<g>\n");
 	fprintf(svgfile, "<title>#%d blocked %s</title>\n", cpu,
 		time_to_string(end - start));
+	if (backtrace)
+		fprintf(svgfile, "<desc>Blocked on:\n%s</desc>\n", backtrace);
 	svg_box(Yslot, start, end, "blocked");
 	fprintf(svgfile, "</g>\n");
 }
 
-void svg_running(int Yslot, int cpu, u64 start, u64 end)
+void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 {
 	double text_size;
 	if (!svgfile)
@@ -152,6 +154,8 @@ void svg_running(int Yslot, int cpu, u64 start, u64 end)
 
 	fprintf(svgfile, "<title>#%d running %s</title>\n",
 		cpu, time_to_string(end - start));
+	if (backtrace)
+		fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace);
 	fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"sample\"/>\n",
 		time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT);
 
@@ -187,7 +191,7 @@ static char *time_to_string(u64 duration)
 	return text;
 }
 
-void svg_waiting(int Yslot, int cpu, u64 start, u64 end)
+void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 {
 	char *text;
 	const char *style;
@@ -212,6 +216,8 @@ void svg_waiting(int Yslot, int cpu, u64 start, u64 end)
 
 	fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT);
 	fprintf(svgfile, "<title>#%d waiting %s</title>\n", cpu, time_to_string(end - start));
+	if (backtrace)
+		fprintf(svgfile, "<desc>Waiting on:\n%s</desc>\n", backtrace);
 	fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
 		time2pixels(end)-time2pixels(start), SLOT_HEIGHT, style);
 	if (font_size > MIN_TEXT_SIZE)
@@ -382,7 +388,7 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq)
 }
 
 
-void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2)
+void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace)
 {
 	double height;
 
@@ -396,6 +402,9 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
 		desc1 ? desc1 : "?",
 		desc2 ? desc2 : "?");
 
+	if (backtrace)
+		fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
+
 	if (row1 < row2) {
 		if (row1) {
 			fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
@@ -437,7 +446,7 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
 	fprintf(svgfile, "</g>\n");
 }
 
-void svg_wakeline(u64 start, int row1, int row2)
+void svg_wakeline(u64 start, int row1, int row2, const char *backtrace)
 {
 	double height;
 
@@ -447,6 +456,9 @@ void svg_wakeline(u64 start, int row1, int row2)
 
 	fprintf(svgfile, "<g>\n");
 
+	if (backtrace)
+		fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
+
 	if (row1 < row2)
 		fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
 			time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT,  time2pixels(start), row2 * SLOT_MULT);
@@ -463,7 +475,7 @@ void svg_wakeline(u64 start, int row1, int row2)
 	fprintf(svgfile, "</g>\n");
 }
 
-void svg_interrupt(u64 start, int row)
+void svg_interrupt(u64 start, int row, const char *backtrace)
 {
 	if (!svgfile)
 		return;
@@ -472,6 +484,9 @@ void svg_interrupt(u64 start, int row)
 
 	fprintf(svgfile, "<title>Wakeup from interrupt</title>\n");
 
+	if (backtrace)
+		fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
+
 	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
 			time2pixels(start), row * SLOT_MULT);
 	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index aa53345..fad79ce 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -5,9 +5,9 @@
 
 extern void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end);
 extern void svg_box(int Yslot, u64 start, u64 end, const char *type);
-extern void svg_blocked(int Yslot, int cpu, u64 start, u64 end);
-extern void svg_running(int Yslot, int cpu, u64 start, u64 end);
-extern void svg_waiting(int Yslot, int cpu, u64 start, u64 end);
+extern void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
+extern void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
+extern void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
 extern void svg_cpu_box(int cpu, u64 max_frequency, u64 turbo_frequency);
 
 
@@ -18,9 +18,9 @@ extern void svg_pstate(int cpu, u64 start, u64 end, u64 freq);
 
 extern void svg_time_grid(void);
 extern void svg_legenda(void);
-extern void svg_wakeline(u64 start, int row1, int row2);
-extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2);
-extern void svg_interrupt(u64 start, int row);
+extern void svg_wakeline(u64 start, int row1, int row2, const char *backtrace);
+extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace);
+extern void svg_interrupt(u64 start, int row, const char *backtrace);
 extern void svg_text(int Yslot, u64 start, const char *text);
 extern void svg_close(void);
 
-- 
cgit v0.10.2


From d2ff1b1499c8e0ad2fc79376a4215ba37771823f Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 18 Nov 2013 13:32:44 -0700
Subject: perf evsel: Skip ignored symbols while printing callchain

Allows a command to have a symbol_filter controlled by the user to skip
certain functions in a backtrace. One example is to allow the user to
reduce repeating patterns like:

    do_select  core_sys_select  sys_select

to just sys_select when dumping callchains, consuming less real estate
on the screen while still conveying the essential message - the process
is in a select call.

This option is leveraged by the upcoming timehist command.

Signed-off-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1384806771-2945-2-git-send-email-dsahern@gmail.com
[ Checked if al.sym is NULL before touching al.sym->ignored, as noted by Adrian Hunter ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f36d24a..b0b15e2 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1522,6 +1522,9 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 			if (!node)
 				break;
 
+			if (node->sym && node->sym->ignore)
+				goto next;
+
 			if (print_ip)
 				printf("%c%16" PRIx64, s, node->ip);
 
@@ -1544,12 +1547,15 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 			if (!print_oneline)
 				printf("\n");
 
-			callchain_cursor_advance(&callchain_cursor);
-
 			stack_depth--;
+next:
+			callchain_cursor_advance(&callchain_cursor);
 		}
 
 	} else {
+		if (al.sym && al.sym->ignore)
+			return;
+
 		if (print_ip)
 			printf("%16" PRIx64, sample->ip);
 
-- 
cgit v0.10.2


From 82d1deb0546a4af7a2ddbcfed99690b3a61776c5 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 18 Nov 2013 13:32:45 -0700
Subject: perf symbols: Move idle syms check from top to generic function

Allows list of idle symbols to be leveraged by other commands, such as
the upcoming timehist command.

Signed-off-by: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1384806771-2945-3-git-send-email-dsahern@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 531522d..03d37a7 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -634,26 +634,9 @@ repeat:
 	return NULL;
 }
 
-/* Tag samples to be skipped. */
-static const char *skip_symbols[] = {
-	"intel_idle",
-	"default_idle",
-	"native_safe_halt",
-	"cpu_idle",
-	"enter_idle",
-	"exit_idle",
-	"mwait_idle",
-	"mwait_idle_with_hints",
-	"poll_idle",
-	"ppc64_runlatch_off",
-	"pseries_dedicated_idle_sleep",
-	NULL
-};
-
 static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
 {
 	const char *name = sym->name;
-	int i;
 
 	/*
 	 * ppc64 uses function descriptors and appends a '.' to the
@@ -671,12 +654,8 @@ static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
 	    strstr(name, "_text_end"))
 		return 1;
 
-	for (i = 0; skip_symbols[i]; i++) {
-		if (!strcmp(skip_symbols[i], name)) {
-			sym->ignore = true;
-			break;
-		}
-	}
+	if (symbol__is_idle(sym))
+		sym->ignore = true;
 
 	return 0;
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index c0c3696..f55c18d 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -573,6 +573,36 @@ static u8 kallsyms2elf_type(char type)
 	return isupper(type) ? STB_GLOBAL : STB_LOCAL;
 }
 
+bool symbol__is_idle(struct symbol *sym)
+{
+	const char * const idle_symbols[] = {
+		"cpu_idle",
+		"intel_idle",
+		"default_idle",
+		"native_safe_halt",
+		"enter_idle",
+		"exit_idle",
+		"mwait_idle",
+		"mwait_idle_with_hints",
+		"poll_idle",
+		"ppc64_runlatch_off",
+		"pseries_dedicated_idle_sleep",
+		NULL
+	};
+
+	int i;
+
+	if (!sym)
+		return false;
+
+	for (i = 0; idle_symbols[i]; i++) {
+		if (!strcmp(idle_symbols[i], sym->name))
+			return true;
+	}
+
+	return false;
+}
+
 static int map__process_kallsym_symbol(void *arg, const char *name,
 				       char type, u64 start)
 {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 07de8fe..ad13c5d 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -240,6 +240,7 @@ size_t symbol__fprintf(struct symbol *sym, FILE *fp);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 bool symbol__restricted_filename(const char *filename,
 				 const char *restricted_filename);
+bool symbol__is_idle(struct symbol *sym);
 
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		  struct symsrc *runtime_ss, symbol_filter_t filter,
-- 
cgit v0.10.2


From 1f3878c11ca8c9f2d9545ec6e1e6bb5386e0565f Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 18 Nov 2013 13:32:47 -0700
Subject: perf thread: Move comm_list check into function

Signed-off-by: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1384806771-2945-5-git-send-email-dsahern@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index bb788c1..c77814b 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -732,8 +732,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
 	if (thread == NULL)
 		return -1;
 
-	if (symbol_conf.comm_list &&
-	    !strlist__has_entry(symbol_conf.comm_list, thread__comm_str(thread)))
+	if (thread__is_filtered(thread))
 		goto out_filtered;
 
 	dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 897c1b2..5b856bf 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -6,6 +6,7 @@
 #include <unistd.h>
 #include <sys/types.h>
 #include "symbol.h"
+#include <strlist.h>
 
 struct thread {
 	union {
@@ -66,4 +67,15 @@ static inline void thread__set_priv(struct thread *thread, void *p)
 {
 	thread->priv = p;
 }
+
+static inline bool thread__is_filtered(struct thread *thread)
+{
+	if (symbol_conf.comm_list &&
+	    !strlist__has_entry(symbol_conf.comm_list, thread__comm_str(thread))) {
+		return true;
+	}
+
+	return false;
+}
+
 #endif	/* __PERF_THREAD_H */
-- 
cgit v0.10.2


From 3bfe5f81fc8f87bf822f3da36927cfc549f3b3db Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 18 Nov 2013 13:32:48 -0700
Subject: perf tools: Export setup_list

Used in upcoming patches (perf sched timehist command).

Signed-off-by: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1384806771-2945-6-git-send-email-dsahern@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index f55c18d..ce9ce10 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1749,7 +1749,7 @@ out_fail:
 	return -1;
 }
 
-static int setup_list(struct strlist **list, const char *list_str,
+int setup_list(struct strlist **list, const char *list_str,
 		      const char *list_name)
 {
 	if (list_str == NULL)
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index ad13c5d..f1031a1 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -274,4 +274,7 @@ void kcore_extract__delete(struct kcore_extract *kce);
 int kcore_copy(const char *from_dir, const char *to_dir);
 int compare_proc_modules(const char *from, const char *to);
 
+int setup_list(struct strlist **list, const char *list_str,
+	       const char *list_name);
+
 #endif /* __PERF_SYMBOL */
-- 
cgit v0.10.2


From 80b8b496ec6edaff01f9ab74dbe8a517cd718de8 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 19 Nov 2013 21:07:37 -0700
Subject: perf script: Print callchains and symbols if they exist

The intent of perf-script is to dump the events and information in the
file. H/W, S/W and raw events all dump callchains if they are present;
might as well make that the default for tracepoints too.

v2: Only add options for sym, dso and ip if callchains are present

Signed-off-by: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/1384920457-5986-1-git-send-email-dsahern@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index b392770..9f3ba44 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -280,6 +280,30 @@ static int perf_session__check_output_opt(struct perf_session *session)
 		set_print_ip_opts(&evsel->attr);
 	}
 
+	/*
+	 * set default for tracepoints to print symbols only
+	 * if callchains are present
+	 */
+	if (symbol_conf.use_callchain &&
+	    !output[PERF_TYPE_TRACEPOINT].user_set) {
+		struct perf_event_attr *attr;
+
+		j = PERF_TYPE_TRACEPOINT;
+		evsel = perf_session__find_first_evtype(session, j);
+		if (evsel == NULL)
+			goto out;
+
+		attr = &evsel->attr;
+
+		if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) {
+			output[j].fields |= PERF_OUTPUT_IP;
+			output[j].fields |= PERF_OUTPUT_SYM;
+			output[j].fields |= PERF_OUTPUT_DSO;
+			set_print_ip_opts(attr);
+		}
+	}
+
+out:
 	return 0;
 }
 
-- 
cgit v0.10.2


From ad7ebb9a48f59bad2714b64725653a73d78b686e Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 26 Nov 2013 17:51:12 +0900
Subject: perf script: Print comm, fork and exit events also

If --show-task-events option is given, also print internal COMM, FORK
and EXIT events.  It would be helpful for debugging.

  $ perf script --show-task-events
  ...
         swapper     0 [009] 3350640.335261: sched:sched_switch: prev_comm=swapper/9
           sleep  9486 [009] 3350640.335509: PERF_RECORD_COMM: sleep:9486
           sleep  9486 [009] 3350640.335806: sched:sched_stat_runtime: comm=sleep pid=9486
         firefox  2635 [003] 3350641.275896: PERF_RECORD_FORK(2635:9487):(2635:2635)
         firefox  2635 [003] 3350641.275896: sched:sched_process_fork: comm=firefox pid=2635
           sleep  9486 [009] 3350641.336009: PERF_RECORD_EXIT(9486:9486):(9486:9486)

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Suggested-by: Frederic Weisbecker <fweisbec@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1385455873-25865-1-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index e9cbfcd..67af9b7 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -203,6 +203,9 @@ OPTIONS
 --show-kernel-path::
 	Try to resolve the path of [kernel.kallsyms]
 
+--show-task-events
+	Display task related events (e.g. FORK, COMM, EXIT).
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9f3ba44..e2b9aff 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -572,6 +572,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 struct perf_script {
 	struct perf_tool	tool;
 	struct perf_session	*session;
+	bool			show_task_events;
 };
 
 static int process_attr(struct perf_tool *tool, union perf_event *event,
@@ -602,6 +603,101 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	return perf_evsel__check_attr(evsel, scr->session);
 }
 
+static int process_comm_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+	int ret = -1;
+
+	thread = machine__findnew_thread(machine, event->comm.pid, event->comm.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing COMM event, skipping it.\n");
+		return -1;
+	}
+
+	if (perf_event__process_comm(tool, event, sample, machine) < 0)
+		goto out;
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+		sample->tid = event->comm.tid;
+		sample->pid = event->comm.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+	ret = 0;
+
+out:
+	return ret;
+}
+
+static int process_fork_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+	if (perf_event__process_fork(tool, event, sample, machine) < 0)
+		return -1;
+
+	thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing FORK event, skipping it.\n");
+		return -1;
+	}
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = event->fork.time;
+		sample->tid = event->fork.tid;
+		sample->pid = event->fork.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+
+	return 0;
+}
+static int process_exit_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+	thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing EXIT event, skipping it.\n");
+		return -1;
+	}
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+		sample->tid = event->comm.tid;
+		sample->pid = event->comm.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+
+	if (perf_event__process_exit(tool, event, sample, machine) < 0)
+		return -1;
+
+	return 0;
+}
+
 static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
@@ -613,6 +709,13 @@ static int __cmd_script(struct perf_script *script)
 
 	signal(SIGINT, sig_handler);
 
+	/* override event processing functions */
+	if (script->show_task_events) {
+		script->tool.comm = process_comm_event;
+		script->tool.fork = process_fork_event;
+		script->tool.exit = process_exit_event;
+	}
+
 	ret = perf_session__process_events(script->session, &script->tool);
 
 	if (debug_mode)
@@ -1375,6 +1478,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "display extended information from perf.data file"),
 	OPT_BOOLEAN('\0', "show-kernel-path", &symbol_conf.show_kernel_path,
 		    "Show the path of [kernel.kallsyms]"),
+	OPT_BOOLEAN('\0', "show-task-events", &script.show_task_events,
+		    "Show the fork/comm/exit events"),
 	OPT_END()
 	};
 	const char * const script_usage[] = {
-- 
cgit v0.10.2


From ba1ddf42f3c3af111d3adee277534f73c1ef6a9b Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 26 Nov 2013 17:54:26 +0900
Subject: perf script: Print mmap[2] events also

If --show-mmap-events option is given, also print internal MMAP and
MMAP2 events.  It would be helpful for debugging.

  $ perf script --show-mmap-events
  ...
           sleep  9486 [009] 3350640.335531: PERF_RECORD_MMAP 9486/9486: [0x400000(0x6000) @ 0]: x /usr/bin/sleep
           sleep  9486 [009] 3350640.335542: PERF_RECORD_MMAP 9486/9486: [0x3153a00000(0x223000) @ 0]: x /usr/lib64/ld-2.17.so
           sleep  9486 [009] 3350640.335553: PERF_RECORD_MMAP 9486/9486: [0x7fff8b5fe000(0x2000) @ 0x7fff8b5fe000]: x [vdso]
           sleep  9486 [009] 3350640.335643: PERF_RECORD_MMAP 9486/9486: [0x3153e00000(0x3c0000) @ 0]: x /usr/lib64/libc-2.17.so

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Suggested-by: Frederic Weisbecker <fweisbec@gmail.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1385456066-26592-1-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 67af9b7..cfdbb1e 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -206,6 +206,9 @@ OPTIONS
 --show-task-events
 	Display task related events (e.g. FORK, COMM, EXIT).
 
+--show-mmap-events
+	Display mmap related events (e.g. MMAP, MMAP2).
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index e2b9aff..952dce9 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -573,6 +573,7 @@ struct perf_script {
 	struct perf_tool	tool;
 	struct perf_session	*session;
 	bool			show_task_events;
+	bool			show_mmap_events;
 };
 
 static int process_attr(struct perf_tool *tool, union perf_event *event,
@@ -698,6 +699,68 @@ static int process_exit_event(struct perf_tool *tool,
 	return 0;
 }
 
+static int process_mmap_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+	if (perf_event__process_mmap(tool, event, sample, machine) < 0)
+		return -1;
+
+	thread = machine__findnew_thread(machine, event->mmap.pid, event->mmap.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing MMAP event, skipping it.\n");
+		return -1;
+	}
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+		sample->tid = event->mmap.tid;
+		sample->pid = event->mmap.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+
+	return 0;
+}
+
+static int process_mmap2_event(struct perf_tool *tool,
+			      union perf_event *event,
+			      struct perf_sample *sample,
+			      struct machine *machine)
+{
+	struct thread *thread;
+	struct perf_script *script = container_of(tool, struct perf_script, tool);
+	struct perf_session *session = script->session;
+	struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+
+	if (perf_event__process_mmap2(tool, event, sample, machine) < 0)
+		return -1;
+
+	thread = machine__findnew_thread(machine, event->mmap2.pid, event->mmap2.tid);
+	if (thread == NULL) {
+		pr_debug("problem processing MMAP2 event, skipping it.\n");
+		return -1;
+	}
+
+	if (!evsel->attr.sample_id_all) {
+		sample->cpu = 0;
+		sample->time = 0;
+		sample->tid = event->mmap2.tid;
+		sample->pid = event->mmap2.pid;
+	}
+	print_sample_start(sample, thread, evsel);
+	perf_event__fprintf(event, stdout);
+
+	return 0;
+}
+
 static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
@@ -715,6 +778,10 @@ static int __cmd_script(struct perf_script *script)
 		script->tool.fork = process_fork_event;
 		script->tool.exit = process_exit_event;
 	}
+	if (script->show_mmap_events) {
+		script->tool.mmap = process_mmap_event;
+		script->tool.mmap2 = process_mmap2_event;
+	}
 
 	ret = perf_session__process_events(script->session, &script->tool);
 
@@ -1480,6 +1547,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Show the path of [kernel.kallsyms]"),
 	OPT_BOOLEAN('\0', "show-task-events", &script.show_task_events,
 		    "Show the fork/comm/exit events"),
+	OPT_BOOLEAN('\0', "show-mmap-events", &script.show_mmap_events,
+		    "Show the mmap events"),
 	OPT_END()
 	};
 	const char * const script_usage[] = {
-- 
cgit v0.10.2


From 449867e346bfd52c5df6bba5b706a795c35e78d4 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 26 Nov 2013 15:19:24 +0200
Subject: perf symbols: Fix not finding kcore in buildid cache

The logic was not looking in the buildid cache for kcore if the host
kernel buildid did not match the recorded kernel buildid.

This affects the non-live case i.e. the kernel has changed and we are
looking at a special copy of kcore that we placed in the buildid cache
(using "perf buildid-cache -v -k /proc/kcore") when the data was
recorded.

After this fix kernel symbols get resolved/annotated correctly.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1385471964-4037-1-git-send-email-adrian.hunter@intel.com
[ Added further explanation extracted from conversation between Ingo & Adrian on lkml ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index ce9ce10..360eefe 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1526,14 +1526,15 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 
 	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
 
+	scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s", buildid_dir,
+		  sbuild_id);
+
 	/* Use /proc/kallsyms if possible */
 	if (is_host) {
 		DIR *d;
 		int fd;
 
 		/* If no cached kcore go with /proc/kallsyms */
-		scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s",
-			  buildid_dir, sbuild_id);
 		d = opendir(path);
 		if (!d)
 			goto proc_kallsyms;
@@ -1558,6 +1559,10 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 		goto proc_kallsyms;
 	}
 
+	/* Find kallsyms in build-id cache with kcore */
+	if (!find_matching_kcore(map, path, sizeof(path)))
+		return strdup(path);
+
 	scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s",
 		  buildid_dir, sbuild_id);
 
-- 
cgit v0.10.2


From 3ed0d21e1103787e21ca38bed2ff50c9f087bedb Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <stfomichev@yandex-team.ru>
Date: Wed, 27 Nov 2013 14:45:00 +0400
Subject: perf timechart: dynamically determine event fields offset

Since b000c8065a92 "tracing: Remove the extra 4 bytes of padding in
events" removed padding bytes, perf timechart got out of sync with the
kernel's trace_entry structure.

Convert perf timechart to use dynamic fields offsets (via
perf_evsel__intval) not relying on a hardcoded copy of fields layout
from the kernel.

Signed-off-by: Stanislav Fomichev <stfomichev@yandex-team.ru>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Chia-I Wu <olvaffe@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20131127104459.GB3309@stfomichev-desktop
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 491662b..436cb5f 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -306,50 +306,10 @@ static int process_exit_event(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-struct trace_entry {
-	unsigned short		type;
-	unsigned char		flags;
-	unsigned char		preempt_count;
-	int			pid;
-	int			lock_depth;
-};
-
 #ifdef SUPPORT_OLD_POWER_EVENTS
 static int use_old_power_events;
-struct power_entry_old {
-	struct trace_entry te;
-	u64	type;
-	u64	value;
-	u64	cpu_id;
-};
 #endif
 
-struct power_processor_entry {
-	struct trace_entry te;
-	u32	state;
-	u32	cpu_id;
-};
-
-#define TASK_COMM_LEN 16
-struct wakeup_entry {
-	struct trace_entry te;
-	char comm[TASK_COMM_LEN];
-	int   pid;
-	int   prio;
-	int   success;
-};
-
-struct sched_switch {
-	struct trace_entry te;
-	char prev_comm[TASK_COMM_LEN];
-	int  prev_pid;
-	int  prev_prio;
-	long prev_state; /* Arjan weeps. */
-	char next_comm[TASK_COMM_LEN];
-	int  next_pid;
-	int  next_prio;
-};
-
 static void c_state_start(int cpu, u64 timestamp, int state)
 {
 	cpus_cstate_start_times[cpu] = timestamp;
@@ -409,25 +369,23 @@ static void p_state_change(int cpu, u64 timestamp, u64 new_freq)
 			turbo_frequency = max_freq;
 }
 
-static void
-sched_wakeup(int cpu, u64 timestamp, int pid, struct trace_entry *te,
-	     const char *backtrace)
+static void sched_wakeup(int cpu, u64 timestamp, int waker, int wakee,
+			 u8 flags, const char *backtrace)
 {
 	struct per_pid *p;
-	struct wakeup_entry *wake = (void *)te;
 	struct wake_event *we = zalloc(sizeof(*we));
 
 	if (!we)
 		return;
 
 	we->time = timestamp;
-	we->waker = pid;
+	we->waker = waker;
 	we->backtrace = backtrace;
 
-	if ((te->flags & TRACE_FLAG_HARDIRQ) || (te->flags & TRACE_FLAG_SOFTIRQ))
+	if ((flags & TRACE_FLAG_HARDIRQ) || (flags & TRACE_FLAG_SOFTIRQ))
 		we->waker = -1;
 
-	we->wakee = wake->pid;
+	we->wakee = wakee;
 	we->next = wake_events;
 	wake_events = we;
 	p = find_create_pid(we->wakee);
@@ -444,24 +402,22 @@ sched_wakeup(int cpu, u64 timestamp, int pid, struct trace_entry *te,
 	}
 }
 
-static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te,
-			 const char *backtrace)
+static void sched_switch(int cpu, u64 timestamp, int prev_pid, int next_pid,
+			 u64 prev_state, const char *backtrace)
 {
 	struct per_pid *p = NULL, *prev_p;
-	struct sched_switch *sw = (void *)te;
-
 
-	prev_p = find_create_pid(sw->prev_pid);
+	prev_p = find_create_pid(prev_pid);
 
-	p = find_create_pid(sw->next_pid);
+	p = find_create_pid(next_pid);
 
 	if (prev_p->current && prev_p->current->state != TYPE_NONE)
-		pid_put_sample(sw->prev_pid, TYPE_RUNNING, cpu,
+		pid_put_sample(prev_pid, TYPE_RUNNING, cpu,
 			       prev_p->current->state_since, timestamp,
 			       backtrace);
 	if (p && p->current) {
 		if (p->current->state != TYPE_NONE)
-			pid_put_sample(sw->next_pid, p->current->state, cpu,
+			pid_put_sample(next_pid, p->current->state, cpu,
 				       p->current->state_since, timestamp,
 				       backtrace);
 
@@ -472,9 +428,9 @@ static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te,
 	if (prev_p->current) {
 		prev_p->current->state = TYPE_NONE;
 		prev_p->current->state_since = timestamp;
-		if (sw->prev_state & 2)
+		if (prev_state & 2)
 			prev_p->current->state = TYPE_BLOCKED;
-		if (sw->prev_state == 0)
+		if (prev_state == 0)
 			prev_p->current->state = TYPE_WAITING;
 	}
 }
@@ -586,61 +542,69 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 }
 
 static int
-process_sample_cpu_idle(struct perf_evsel *evsel __maybe_unused,
+process_sample_cpu_idle(struct perf_evsel *evsel,
 			struct perf_sample *sample,
 			const char *backtrace __maybe_unused)
 {
-	struct power_processor_entry *ppe = sample->raw_data;
+	u32 state = perf_evsel__intval(evsel, sample, "state");
+	u32 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
 
-	if (ppe->state == (u32) PWR_EVENT_EXIT)
-		c_state_end(ppe->cpu_id, sample->time);
+	if (state == (u32)PWR_EVENT_EXIT)
+		c_state_end(cpu_id, sample->time);
 	else
-		c_state_start(ppe->cpu_id, sample->time, ppe->state);
+		c_state_start(cpu_id, sample->time, state);
 	return 0;
 }
 
 static int
-process_sample_cpu_frequency(struct perf_evsel *evsel __maybe_unused,
+process_sample_cpu_frequency(struct perf_evsel *evsel,
 			     struct perf_sample *sample,
 			     const char *backtrace __maybe_unused)
 {
-	struct power_processor_entry *ppe = sample->raw_data;
+	u32 state = perf_evsel__intval(evsel, sample, "state");
+	u32 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
 
-	p_state_change(ppe->cpu_id, sample->time, ppe->state);
+	p_state_change(cpu_id, sample->time, state);
 	return 0;
 }
 
 static int
-process_sample_sched_wakeup(struct perf_evsel *evsel __maybe_unused,
+process_sample_sched_wakeup(struct perf_evsel *evsel,
 			    struct perf_sample *sample,
 			    const char *backtrace)
 {
-	struct trace_entry *te = sample->raw_data;
+	u8 flags = perf_evsel__intval(evsel, sample, "common_flags");
+	int waker = perf_evsel__intval(evsel, sample, "common_pid");
+	int wakee = perf_evsel__intval(evsel, sample, "pid");
 
-	sched_wakeup(sample->cpu, sample->time, sample->pid, te, backtrace);
+	sched_wakeup(sample->cpu, sample->time, waker, wakee, flags, backtrace);
 	return 0;
 }
 
 static int
-process_sample_sched_switch(struct perf_evsel *evsel __maybe_unused,
+process_sample_sched_switch(struct perf_evsel *evsel,
 			    struct perf_sample *sample,
 			    const char *backtrace)
 {
-	struct trace_entry *te = sample->raw_data;
+	int prev_pid = perf_evsel__intval(evsel, sample, "prev_pid");
+	int next_pid = perf_evsel__intval(evsel, sample, "next_pid");
+	u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state");
 
-	sched_switch(sample->cpu, sample->time, te, backtrace);
+	sched_switch(sample->cpu, sample->time, prev_pid, next_pid, prev_state,
+		     backtrace);
 	return 0;
 }
 
 #ifdef SUPPORT_OLD_POWER_EVENTS
 static int
-process_sample_power_start(struct perf_evsel *evsel __maybe_unused,
+process_sample_power_start(struct perf_evsel *evsel,
 			   struct perf_sample *sample,
 			   const char *backtrace __maybe_unused)
 {
-	struct power_entry_old *peo = sample->raw_data;
+	u64 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
+	u64 value = perf_evsel__intval(evsel, sample, "value");
 
-	c_state_start(peo->cpu_id, sample->time, peo->value);
+	c_state_start(cpu_id, sample->time, value);
 	return 0;
 }
 
@@ -654,13 +618,14 @@ process_sample_power_end(struct perf_evsel *evsel __maybe_unused,
 }
 
 static int
-process_sample_power_frequency(struct perf_evsel *evsel __maybe_unused,
+process_sample_power_frequency(struct perf_evsel *evsel,
 			       struct perf_sample *sample,
 			       const char *backtrace __maybe_unused)
 {
-	struct power_entry_old *peo = sample->raw_data;
+	u64 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
+	u64 value = perf_evsel__intval(evsel, sample, "value");
 
-	p_state_change(peo->cpu_id, sample->time, peo->value);
+	p_state_change(cpu_id, sample->time, value);
 	return 0;
 }
 #endif /* SUPPORT_OLD_POWER_EVENTS */
-- 
cgit v0.10.2


From 6e53ad9ff65226f79d5888452992222284c7e4d4 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 27 Nov 2013 16:29:50 -0300
Subject: perf timechart: Remove some needless struct forward declarations

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stanislav Fomichev <stfomichev@yandex-team.ru>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-jomi6mjv5zi9vsn4vmih5xps@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 436cb5f..c246f02 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -55,14 +55,8 @@ static bool		tasks_only;
 static bool		with_backtrace;
 
 
-struct per_pid;
 struct per_pidcomm;
-
 struct cpu_sample;
-struct power_event;
-struct wake_event;
-
-struct sample_wrapper;
 
 /*
  * Datastructure layout:
@@ -155,7 +149,6 @@ struct wake_event {
 static struct power_event    *power_events;
 static struct wake_event     *wake_events;
 
-struct process_filter;
 struct process_filter {
 	char			*name;
 	int			pid;
-- 
cgit v0.10.2


From 972ec653c489fd08ac2904caa98a6fa3f44dc303 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 27 Nov 2013 16:32:56 -0300
Subject: perf timechart: Remove misplaced __maybe_unused

The 'event' parameter _is_ used.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stanislav Fomichev <stfomichev@yandex-team.ru>
Cc: Stephane Eranian <eranian@google.com>
echo Link: http://lkml.kernel.org/n/tip-`ranpwd -l 24`@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index c246f02..680632d 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -511,7 +511,7 @@ typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
 				  const char *backtrace);
 
 static int process_sample_event(struct perf_tool *tool __maybe_unused,
-				union perf_event *event __maybe_unused,
+				union perf_event *event,
 				struct perf_sample *sample,
 				struct perf_evsel *evsel,
 				struct machine *machine __maybe_unused)
-- 
cgit v0.10.2


From 26286141a43251bed548349efbf60b61f1c433e8 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 26 Nov 2013 13:54:12 +0100
Subject: perf tools: Fix tags/TAGS targets rebuilding

Once the tags/TAGS file is generated it's never rebuilt until it's
removed by hand.

The reason is that the Makefile does not treat tags/TAGS as targets but
as files and thus won't rebuilt them once they are in place.

Adding PHONY tags/TAGS targets into Makefile.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/20131126125412.GJ1267@krava.brq.redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 4835618..eefb9fb 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -60,8 +60,11 @@ endef
 
 #
 # Needed if no target specified:
+# (Except for tags and TAGS targets. The reason is that the
+# Makefile does not treat tags/TAGS as targets but as files
+# and thus won't rebuilt them once they are in place.)
 #
-all:
+all tags TAGS:
 	$(print_msg)
 	$(make)
 
@@ -77,3 +80,5 @@ clean:
 %:
 	$(print_msg)
 	$(make)
+
+.PHONY: tags TAGS
-- 
cgit v0.10.2


From f26ca1d699e8b54a50d9faf82327d3c2072aaedd Mon Sep 17 00:00:00 2001
From: Toshi Kani <toshi.kani@hp.com>
Date: Wed, 27 Nov 2013 13:33:09 -0700
Subject: ACPI / PCI / hotplug: Avoid warning when _ADR not present

acpiphp_enumerate_slots() walks ACPI namenamespace under
a PCI host bridge with callback register_slot().
register_slot() evaluates _ADR for all the device objects
and emits a warning message for any error.  Some platforms
have _HID device objects (such as HPET and IPMI), which
trigger unnecessary warning messages.

This patch avoids emitting a warning message when a target
device object does not have _ADR.

Signed-off-by: Toshi Kani <toshi.kani@hp.com>
Cc: 3.12+ <stable@vger.kernel.org> # 3.12+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 1cf605f..438a4d0 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -279,7 +279,9 @@ static acpi_status register_slot(acpi_handle handle, u32 lvl, void *data,
 
 	status = acpi_evaluate_integer(handle, "_ADR", NULL, &adr);
 	if (ACPI_FAILURE(status)) {
-		acpi_handle_warn(handle, "can't evaluate _ADR (%#x)\n", status);
+		if (status != AE_NOT_FOUND)
+			acpi_handle_warn(handle,
+				"can't evaluate _ADR (%#x)\n", status);
 		return AE_OK;
 	}
 
-- 
cgit v0.10.2


From 5a25f7bb5aa1b2f876d9df81c44b516e015022f8 Mon Sep 17 00:00:00 2001
From: James Hogan <james.hogan@imgtec.com>
Date: Mon, 25 Nov 2013 11:14:50 +0000
Subject: metag: smp: don't set irq regs in do_IPI()

Since commit f6b30d32d242 (metag: kick: add missing irq_enter/exit to
kick_handler()), the main kick_handler() function deals with setting and
restoring the irq registers pointer. Therefore do_IPI() which is called
indirectly from kick_handler() doesn't need to do that itself any
longer. Therefore remove that code and do_IPI()'s pt_regs argument.

Signed-off-by: James Hogan <james.hogan@imgtec.com>
Cc: linux-metag@vger.kernel.org
Cc: Thomas Gleixner <tglx@linutronix.de>

diff --git a/arch/metag/kernel/smp.c b/arch/metag/kernel/smp.c
index 7c01131..177ffb4 100644
--- a/arch/metag/kernel/smp.c
+++ b/arch/metag/kernel/smp.c
@@ -517,11 +517,10 @@ static DEFINE_SPINLOCK(stop_lock);
  *
  *  Bit 0 - Inter-processor function call
  */
-static int do_IPI(struct pt_regs *regs)
+static int do_IPI(void)
 {
 	unsigned int cpu = smp_processor_id();
 	struct ipi_data *ipi = &per_cpu(ipi_data, cpu);
-	struct pt_regs *old_regs = set_irq_regs(regs);
 	unsigned long msgs, nextmsg;
 	int handled = 0;
 
@@ -557,8 +556,6 @@ static int do_IPI(struct pt_regs *regs)
 		}
 	}
 
-	set_irq_regs(old_regs);
-
 	return handled;
 }
 
@@ -624,7 +621,7 @@ static void kick_raise_softirq(cpumask_t callmap, unsigned int irq)
 static TBIRES ipi_handler(TBIRES State, int SigNum, int Triggers,
 		   int Inst, PTBI pTBI, int *handled)
 {
-	*handled = do_IPI((struct pt_regs *)State.Sig.pCtx);
+	*handled = do_IPI();
 
 	return State;
 }
-- 
cgit v0.10.2


From 853d9b18f1e861d37e9b271742329f8c1176eabe Mon Sep 17 00:00:00 2001
From: Levente Kurusa <levex@linux.com>
Date: Fri, 29 Nov 2013 21:28:48 +0100
Subject: x86, mce: Call put_device on device_register failure

This patch adds a call to put_device() when the device_register() call
has failed. This is required so that the last reference to the device is
given up.

Signed-off-by: Levente Kurusa <levex@linux.com>
Link: http://lkml.kernel.org/r/5298F900.9000208@linux.com
Signed-off-by: Borislav Petkov <bp@suse.de>

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index b3218cd..a389c1d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -2272,8 +2272,10 @@ static int mce_device_create(unsigned int cpu)
 	dev->release = &mce_device_release;
 
 	err = device_register(dev);
-	if (err)
+	if (err) {
+		put_device(dev);
 		return err;
+	}
 
 	for (i = 0; mce_device_attrs[i]; i++) {
 		err = device_create_file(dev, mce_device_attrs[i]);
-- 
cgit v0.10.2


From 854ff82ab085aed7509f6fb90f79ce6c41ee1fa4 Mon Sep 17 00:00:00 2001
From: Henrik Austad <henrik@austad.us>
Date: Wed, 27 Nov 2013 23:18:00 +0100
Subject: Documentation/robust-futex-API: Count properly to 4

A strictly monotonically increasing sequence is normally used in
numbered lists as they provide an intuitive ordering of the
elements.

However, in situations where race conditions can appear, this
assumption breaks down and you can end up with unpredictable
results, leading to a rather confusing list :-)

This changes the numbered list 1,2,2,2 to the more intuitive
1,2,3,4.

Introduced in:

  2eec9ad91f71 [PATCH] lightweight robust futexes: docs

Signed-off-by: Henrik Austad <henrik@austad.us>
Link: http://lkml.kernel.org/r/1385590680-8110-1-git-send-email-henrik@austad.us
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/Documentation/robust-futex-ABI.txt b/Documentation/robust-futex-ABI.txt
index fd1cd8a..16eb314 100644
--- a/Documentation/robust-futex-ABI.txt
+++ b/Documentation/robust-futex-ABI.txt
@@ -146,8 +146,8 @@ On removal:
  1) set the 'list_op_pending' word to the address of the 'lock entry'
     to be removed,
  2) remove the lock entry for this lock from the 'head' list,
- 2) release the futex lock, and
- 2) clear the 'lock_op_pending' word.
+ 3) release the futex lock, and
+ 4) clear the 'lock_op_pending' word.
 
 On exit, the kernel will consider the address stored in
 'list_op_pending' and the address of each 'lock word' found by walking
-- 
cgit v0.10.2


From 962d9c5757b2ebd30678a88a4f475ae997f4d5dd Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Sat, 30 Nov 2013 15:20:15 +0100
Subject: Revert "smp/cpumask: Make CONFIG_CPUMASK_OFFSTACK=y usable without
 debug dependency"

This reverts commit 9dd1220114e00d8ec5cdc20085bbe198b21e1985.

Revert it until Linus's concerns are addressed: this option should not
allow nonsensical CONFIG_CPUMASK_OFFSTACK and CONFIG_NR_CPUS values, and
it should probably select sane defaults as well.

Cc: Josh Boyer <jwboyer@fedoraproject.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-etcruvuw9neycYf0Rripxrjv@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/lib/Kconfig b/lib/Kconfig
index 3f7fb4d..06dc742 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -342,8 +342,7 @@ config CHECK_SIGNATURE
 	bool
 
 config CPUMASK_OFFSTACK
-	bool "Force CPU masks off stack"
-	depends on SMP
+	bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS
 	help
 	  Use dynamic allocation for cpumask_var_t, instead of putting
 	  them on the stack.  This is a bit more expensive, but avoids
-- 
cgit v0.10.2


From 80c6463e2fa3377febfc98a6672d92d07f3c26c1 Mon Sep 17 00:00:00 2001
From: Shuah Khan <shuah.kh@samsung.com>
Date: Fri, 22 Nov 2013 10:54:28 -0700
Subject: power_supply: Fix Oops from NULL pointer dereference from
 wakeup_source_activate

power_supply_register() calls device_init_wakeup() to register a wakeup
source before initializing dev_name. As a result, device_wakeup_enable()
end up registering wakeup source with a null name when
wakeup_source_register() gets called with dev_name(dev) which is null at
the time.

When kernel is booted with wakeup_source_activate enabled, it will panic
when the trace point code tries to dereference ws->name.

Fixed the problem by moving up the kobject_set_name() call prior to
accesses to dev_name(). Replaced kobject_set_name() with dev_set_name()
which is the right interface to be called from drivers. Fixed the call to
device_del() prior to device_add() in for wakeup_init_failed error
handling code.

Trace after the change:

            bash-2143  [003] d...   132.280697: wakeup_source_activate: BAT1 state=0x20001
     kworker/3:2-1169  [003] d...   132.281305: wakeup_source_deactivate: BAT1 state=0x30000

Oops message:

[  819.769934] device: 'BAT1': device_add
[  819.770078] PM: Adding info for No Bus:BAT1
[  819.770235] BUG: unable to handle kernel NULL pointer dereference at           (null)
[  819.770435] IP: [<ffffffff813381c0>] skip_spaces+0x30/0x30
[  819.770572] PGD 3efd90067 PUD 3eff61067 PMD 0
[  819.770716] Oops: 0000 [#1] SMP
[  819.770829] Modules linked in: arc4 iwldvm mac80211 x86_pkg_temp_thermal coretemp kvm_intel joydev i915 kvm uvcvideo ghash_clmulni_intel videobuf2_vmalloc aesni_intel videobuf2_memops videobuf2_core aes_x86_64 ablk_helper cryptd videodev iwlwifi lrw rfcomm gf128mul glue_helper bnep btusb media bluetooth parport_pc hid_generic ppdev snd_hda_codec_hdmi drm_kms_helper snd_hda_codec_realtek cfg80211 drm tpm_infineon samsung_laptop snd_hda_intel usbhid snd_hda_codec hid snd_hwdep snd_pcm microcode snd_page_alloc snd_timer psmouse i2c_algo_bit lpc_ich tpm_tis video wmi mac_hid serio_raw ext2 lp parport r8169 mii
[  819.771802] CPU: 0 PID: 2167 Comm: bash Not tainted 3.12.0+ #25
[  819.771876] Hardware name: SAMSUNG ELECTRONICS CO., LTD. 900X3C/900X3D/900X4C/900X4D/SAMSUNG_NP1234567890, BIOS P03AAC 07/12/2012
[  819.772022] task: ffff88002e6ddcc0 ti: ffff8804015ca000 task.ti: ffff8804015ca000
[  819.772119] RIP: 0010:[<ffffffff813381c0>]  [<ffffffff813381c0>] skip_spaces+0x30/0x30
[  819.772242] RSP: 0018:ffff8804015cbc70  EFLAGS: 00010046
[  819.772310] RAX: 0000000000000003 RBX: ffff88040cfd6d40 RCX: 0000000000000018
[  819.772397] RDX: 0000000000020001 RSI: 0000000000000000 RDI: 0000000000000000
[  819.772484] RBP: ffff8804015cbcc0 R08: 0000000000000000 R09: ffff8803f0768d40
[  819.772570] R10: ffffea001033b800 R11: 0000000000000000 R12: ffffffff81c519c0
[  819.772656] R13: 0000000000020001 R14: 0000000000000000 R15: 0000000000020001
[  819.772744] FS:  00007ff98309b740(0000) GS:ffff88041f200000(0000) knlGS:0000000000000000
[  819.772845] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  819.772917] CR2: 0000000000000000 CR3: 00000003f59dc000 CR4: 00000000001407f0
[  819.773001] Stack:
[  819.773030]  ffffffff81114003 ffff8804015cbcb0 0000000000000000 0000000000000046
[  819.773146]  ffff880409757a18 ffff8803f065a160 0000000000000000 0000000000020001
[  819.773273]  0000000000000000 0000000000000000 ffff8804015cbce8 ffffffff8143e388
[  819.773387] Call Trace:
[  819.773434]  [<ffffffff81114003>] ? ftrace_raw_event_wakeup_source+0x43/0xe0
[  819.773520]  [<ffffffff8143e388>] wakeup_source_report_event+0xb8/0xd0
[  819.773595]  [<ffffffff8143e3cd>] __pm_stay_awake+0x2d/0x50
[  819.773724]  [<ffffffff8153395c>] power_supply_changed+0x3c/0x90
[  819.773795]  [<ffffffff8153407c>] power_supply_register+0x18c/0x250
[  819.773869]  [<ffffffff813d8d18>] sysfs_add_battery+0x61/0x7b
[  819.773935]  [<ffffffff813d8d69>] battery_notify+0x37/0x3f
[  819.774001]  [<ffffffff816ccb7c>] notifier_call_chain+0x4c/0x70
[  819.774071]  [<ffffffff81073ded>] __blocking_notifier_call_chain+0x4d/0x70
[  819.774149]  [<ffffffff81073e26>] blocking_notifier_call_chain+0x16/0x20
[  819.774227]  [<ffffffff8109397a>] pm_notifier_call_chain+0x1a/0x40
[  819.774316]  [<ffffffff81095b66>] hibernate+0x66/0x1c0
[  819.774407]  [<ffffffff81093931>] state_store+0x71/0xa0
[  819.774507]  [<ffffffff81331d8f>] kobj_attr_store+0xf/0x20
[  819.774613]  [<ffffffff811f8618>] sysfs_write_file+0x128/0x1c0
[  819.774735]  [<ffffffff8118579d>] vfs_write+0xbd/0x1e0
[  819.774841]  [<ffffffff811861d9>] SyS_write+0x49/0xa0
[  819.774939]  [<ffffffff816d1052>] system_call_fastpath+0x16/0x1b
[  819.775055] Code: 89 f8 48 89 e5 f6 82 c0 a6 84 81 20 74 15 0f 1f 44 00 00 48 83 c0 01 0f b6 10 f6 82 c0 a6 84 81 20 75 f0 5d c3 66 0f 1f 44 00 00 <80> 3f 00 55 48 89 e5 74 15 48 89 f8 0f 1f 40 00 48 83 c0 01 80
[  819.775760] RIP  [<ffffffff813381c0>] skip_spaces+0x30/0x30
[  819.775881]  RSP <ffff8804015cbc70>
[  819.775949] CR2: 0000000000000000
[  819.794175] ---[ end trace c4ef25127039952e ]---

Signed-off-by: Shuah Khan <shuah.kh@samsung.com>
Acked-by: Anton Vorontsov <anton@enomsg.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: stable@vger.kernel.org
Signed-off-by: Anton Vorontsov <anton@enomsg.org>

diff --git a/drivers/power/power_supply_core.c b/drivers/power/power_supply_core.c
index 00e6672..557af94 100644
--- a/drivers/power/power_supply_core.c
+++ b/drivers/power/power_supply_core.c
@@ -511,6 +511,10 @@ int power_supply_register(struct device *parent, struct power_supply *psy)
 	dev_set_drvdata(dev, psy);
 	psy->dev = dev;
 
+	rc = dev_set_name(dev, "%s", psy->name);
+	if (rc)
+		goto dev_set_name_failed;
+
 	INIT_WORK(&psy->changed_work, power_supply_changed_work);
 
 	rc = power_supply_check_supplies(psy);
@@ -524,10 +528,6 @@ int power_supply_register(struct device *parent, struct power_supply *psy)
 	if (rc)
 		goto wakeup_init_failed;
 
-	rc = kobject_set_name(&dev->kobj, "%s", psy->name);
-	if (rc)
-		goto kobject_set_name_failed;
-
 	rc = device_add(dev);
 	if (rc)
 		goto device_add_failed;
@@ -553,11 +553,11 @@ create_triggers_failed:
 register_cooler_failed:
 	psy_unregister_thermal(psy);
 register_thermal_failed:
-wakeup_init_failed:
 	device_del(dev);
-kobject_set_name_failed:
 device_add_failed:
+wakeup_init_failed:
 check_supplies_failed:
+dev_set_name_failed:
 	put_device(dev);
 success:
 	return rc;
-- 
cgit v0.10.2


From 93353e8088057dd988362e6cae727af43734b494 Mon Sep 17 00:00:00 2001
From: Austin Boyle <boyle.austin@gmail.com>
Date: Sun, 24 Nov 2013 21:41:49 +1100
Subject: max17042_battery: Fix build errors caused by missing REGMAP_I2C
 config
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

max17042 now uses regmap interface but does not enable config option. This
patch fixes the following build errors:

drivers/power/max17042_battery.c:661:15: error: variable ‘max17042_regmap_config’ has initializer but incomplete type
drivers/power/max17042_battery.c:662:2: error: unknown field ‘reg_bits’ specified in initializer
drivers/power/max17042_battery.c:662:2: warning: excess elements in struct initializer
drivers/power/max17042_battery.c:662:2: warning: (near initialization for ‘max17042_regmap_config’)
drivers/power/max17042_battery.c:663:2: error: unknown field ‘val_bits’ specified in initializer
drivers/power/max17042_battery.c:663:2: warning: excess elements in struct initializer
drivers/power/max17042_battery.c:663:2: warning: (near initialization for ‘max17042_regmap_config’)
drivers/power/max17042_battery.c:664:2: error: unknown field ‘val_format_endian’ specified in initializer
drivers/power/max17042_battery.c:664:23: error: ‘REGMAP_ENDIAN_NATIVE’ undeclared here (not in a function)
drivers/power/max17042_battery.c:664:2: warning: excess elements in struct initializer
drivers/power/max17042_battery.c:664:2: warning: (near initialization for ‘max17042_regmap_config’)
drivers/power/max17042_battery.c: In function ‘max17042_probe’:
drivers/power/max17042_battery.c:684:2: error: implicit declaration of function ‘devm_regmap_init_i2c’

Signed-off-by: Austin Boyle <boyle.austin@gmail.com>
Acked-by: Jonghwa Lee <jonghwa3.lee@samsung.com>
Signed-off-by: Anton Vorontsov <anton@enomsg.org>

diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig
index 5e2054a..85ad58c 100644
--- a/drivers/power/Kconfig
+++ b/drivers/power/Kconfig
@@ -196,6 +196,7 @@ config BATTERY_MAX17040
 config BATTERY_MAX17042
 	tristate "Maxim MAX17042/17047/17050/8997/8966 Fuel Gauge"
 	depends on I2C
+	select REGMAP_I2C
 	help
 	  MAX17042 is fuel-gauge systems for lithium-ion (Li+) batteries
 	  in handheld and portable equipment. The MAX17042 is configured
-- 
cgit v0.10.2


From 6233dd5efdf9e2c2da1b003cfb70307b7b2028e8 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 28 Nov 2013 11:30:13 +0100
Subject: perf record: Unify data output code into perf_record__write function

Unifying current 2 data output functions do_write_output and
write_output into single one perf_record__write.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1385634619-8129-2-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 65615a8..d93e2ee 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -76,7 +76,7 @@ struct perf_record {
 	long			samples;
 };
 
-static int do_write_output(struct perf_record *rec, void *buf, size_t size)
+static int perf_record__write(struct perf_record *rec, void *buf, size_t size)
 {
 	struct perf_data_file *file = &rec->file;
 
@@ -97,21 +97,13 @@ static int do_write_output(struct perf_record *rec, void *buf, size_t size)
 	return 0;
 }
 
-static int write_output(struct perf_record *rec, void *buf, size_t size)
-{
-	return do_write_output(rec, buf, size);
-}
-
 static int process_synthesized_event(struct perf_tool *tool,
 				     union perf_event *event,
 				     struct perf_sample *sample __maybe_unused,
 				     struct machine *machine __maybe_unused)
 {
 	struct perf_record *rec = container_of(tool, struct perf_record, tool);
-	if (write_output(rec, event, event->header.size) < 0)
-		return -1;
-
-	return 0;
+	return perf_record__write(rec, event, event->header.size);
 }
 
 static int perf_record__mmap_read(struct perf_record *rec,
@@ -136,7 +128,7 @@ static int perf_record__mmap_read(struct perf_record *rec,
 		size = md->mask + 1 - (old & md->mask);
 		old += size;
 
-		if (write_output(rec, buf, size) < 0) {
+		if (perf_record__write(rec, buf, size) < 0) {
 			rc = -1;
 			goto out;
 		}
@@ -146,7 +138,7 @@ static int perf_record__mmap_read(struct perf_record *rec,
 	size = head - old;
 	old += size;
 
-	if (write_output(rec, buf, size) < 0) {
+	if (perf_record__write(rec, buf, size) < 0) {
 		rc = -1;
 		goto out;
 	}
@@ -335,8 +327,8 @@ static int perf_record__mmap_read_all(struct perf_record *rec)
 	}
 
 	if (perf_header__has_feat(&rec->session->header, HEADER_TRACING_DATA))
-		rc = write_output(rec, &finished_round_event,
-				  sizeof(finished_round_event));
+		rc = perf_record__write(rec, &finished_round_event,
+					sizeof(finished_round_event));
 
 out:
 	return rc;
-- 
cgit v0.10.2


From 727ebd544f85285a223ecc6a2a57ef90202cdc7b Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 28 Nov 2013 11:30:14 +0100
Subject: perf tools: Use correct return type for readn function

Changing readn function return type to ssize_t because read returns
ssize_t not int.

Changing callers holding variable types as well.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1385634619-8129-3-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 1cd0357..3e755f2 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1709,7 +1709,7 @@ static int process_nrcpus(struct perf_file_section *section __maybe_unused,
 			  struct perf_header *ph, int fd,
 			  void *data __maybe_unused)
 {
-	size_t ret;
+	ssize_t ret;
 	u32 nr;
 
 	ret = readn(fd, &nr, sizeof(nr));
@@ -1753,7 +1753,7 @@ static int process_total_mem(struct perf_file_section *section __maybe_unused,
 			     void *data __maybe_unused)
 {
 	uint64_t mem;
-	size_t ret;
+	ssize_t ret;
 
 	ret = readn(fd, &mem, sizeof(mem));
 	if (ret != sizeof(mem))
@@ -1822,7 +1822,7 @@ static int process_cmdline(struct perf_file_section *section __maybe_unused,
 			   struct perf_header *ph, int fd,
 			   void *data __maybe_unused)
 {
-	size_t ret;
+	ssize_t ret;
 	char *str;
 	u32 nr, i;
 	struct strbuf sb;
@@ -1858,7 +1858,7 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused
 				struct perf_header *ph, int fd,
 				void *data __maybe_unused)
 {
-	size_t ret;
+	ssize_t ret;
 	u32 nr, i;
 	char *str;
 	struct strbuf sb;
@@ -1914,7 +1914,7 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
 				 struct perf_header *ph, int fd,
 				 void *data __maybe_unused)
 {
-	size_t ret;
+	ssize_t ret;
 	u32 nr, node, i;
 	char *str;
 	uint64_t mem_total, mem_free;
@@ -1974,7 +1974,7 @@ static int process_pmu_mappings(struct perf_file_section *section __maybe_unused
 				struct perf_header *ph, int fd,
 				void *data __maybe_unused)
 {
-	size_t ret;
+	ssize_t ret;
 	char *name;
 	u32 pmu_num;
 	u32 type;
@@ -2534,7 +2534,7 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz,
 int perf_file_header__read(struct perf_file_header *header,
 			   struct perf_header *ph, int fd)
 {
-	int ret;
+	ssize_t ret;
 
 	lseek(fd, 0, SEEK_SET);
 
@@ -2628,7 +2628,7 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
 				       struct perf_header *ph, int fd,
 				       bool repipe)
 {
-	int ret;
+	ssize_t ret;
 
 	ret = readn(fd, header, sizeof(*header));
 	if (ret <= 0)
@@ -2669,7 +2669,7 @@ static int read_attr(int fd, struct perf_header *ph,
 	struct perf_event_attr *attr = &f_attr->attr;
 	size_t sz, left;
 	size_t our_sz = sizeof(f_attr->attr);
-	int ret;
+	ssize_t ret;
 
 	memset(f_attr, 0, sizeof(*f_attr));
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index b0b15e2..4ce146b 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1158,7 +1158,7 @@ static int __perf_session__process_pipe_events(struct perf_session *session,
 	void *buf = NULL;
 	int skip = 0;
 	u64 head;
-	int err;
+	ssize_t err;
 	void *p;
 
 	perf_tool__fill_defaults(tool);
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 28a0a89..9440481 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -151,12 +151,12 @@ unsigned long convert_unit(unsigned long value, char *unit)
 	return value;
 }
 
-int readn(int fd, void *buf, size_t n)
+ssize_t readn(int fd, void *buf, size_t n)
 {
 	void *buf_start = buf;
 
 	while (n) {
-		int ret = read(fd, buf, n);
+		ssize_t ret = read(fd, buf, n);
 
 		if (ret <= 0)
 			return ret;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index c8f362d..9f6b928 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -253,7 +253,7 @@ bool strlazymatch(const char *str, const char *pat);
 int strtailcmp(const char *s1, const char *s2);
 char *strxfrchar(char *s, char from, char to);
 unsigned long convert_unit(unsigned long value, char *unit);
-int readn(int fd, void *buf, size_t size);
+ssize_t readn(int fd, void *buf, size_t n);
 
 struct perf_event_attr;
 
-- 
cgit v0.10.2


From 838d14520267769648fb2fc2a637107a1d102590 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 28 Nov 2013 11:30:15 +0100
Subject: perf tools: Fine tune readn function

Added a 'left' variable to make the flow clearer, and added a debug
check for the return value - returning 'n' is more obvious.

Added small comment for readn.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Original-patch-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1385634619-8129-4-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 9440481..6ea0b4a 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -6,6 +6,7 @@
 #endif
 #include <stdio.h>
 #include <stdlib.h>
+#include <linux/kernel.h>
 
 /*
  * XXX We need to find a better place for these things...
@@ -151,21 +152,26 @@ unsigned long convert_unit(unsigned long value, char *unit)
 	return value;
 }
 
+/*
+ * Read exactly 'n' bytes or return an error.
+ */
 ssize_t readn(int fd, void *buf, size_t n)
 {
 	void *buf_start = buf;
+	size_t left = n;
 
-	while (n) {
-		ssize_t ret = read(fd, buf, n);
+	while (left) {
+		ssize_t ret = read(fd, buf, left);
 
 		if (ret <= 0)
 			return ret;
 
-		n -= ret;
-		buf += ret;
+		left -= ret;
+		buf  += ret;
 	}
 
-	return buf - buf_start;
+	BUG_ON((size_t)(buf - buf_start) != n);
+	return n;
 }
 
 size_t hex_width(u64 v)
-- 
cgit v0.10.2


From bc3a502bc2bc78d03526d6abcc5697aab18d5ae9 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 28 Nov 2013 11:30:16 +0100
Subject: perf tools: Add writen function

Adding 'writen' function as a synchronous wrapper for write syscall with
following prototype:

  ssize_t writen(int fd, void *buf, size_t n)

Returns the number of bytes written on success or -1 in case of err.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Requested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1385634619-8129-5-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 6ea0b4a..b1d5376 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -152,16 +152,14 @@ unsigned long convert_unit(unsigned long value, char *unit)
 	return value;
 }
 
-/*
- * Read exactly 'n' bytes or return an error.
- */
-ssize_t readn(int fd, void *buf, size_t n)
+static ssize_t ion(bool is_read, int fd, void *buf, size_t n)
 {
 	void *buf_start = buf;
 	size_t left = n;
 
 	while (left) {
-		ssize_t ret = read(fd, buf, left);
+		ssize_t ret = is_read ? read(fd, buf, left) :
+					write(fd, buf, left);
 
 		if (ret <= 0)
 			return ret;
@@ -174,6 +172,22 @@ ssize_t readn(int fd, void *buf, size_t n)
 	return n;
 }
 
+/*
+ * Read exactly 'n' bytes or return an error.
+ */
+ssize_t readn(int fd, void *buf, size_t n)
+{
+	return ion(true, fd, buf, n);
+}
+
+/*
+ * Write exactly 'n' bytes or return an error.
+ */
+ssize_t writen(int fd, void *buf, size_t n)
+{
+	return ion(false, fd, buf, n);
+}
+
 size_t hex_width(u64 v)
 {
 	size_t n = 1;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 9f6b928..ce0f73d 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -254,6 +254,7 @@ int strtailcmp(const char *s1, const char *s2);
 char *strxfrchar(char *s, char from, char to);
 unsigned long convert_unit(unsigned long value, char *unit);
 ssize_t readn(int fd, void *buf, size_t n);
+ssize_t writen(int fd, void *buf, size_t n);
 
 struct perf_event_attr;
 
-- 
cgit v0.10.2


From 6f9a317f2a2d4950880ecfa7eea53ed79f85255f Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 28 Nov 2013 11:30:17 +0100
Subject: perf tools: Add perf_data_file__write interface

Adding perf_data_file__write interface to centralize output to files.
The function prototype is:

  ssize_t perf_data_file__write(struct perf_data_file *file,
                                void *buf, size_t size);

Returns number of bytes written or -1 in case of error.

NOTE: Also indenting 'struct perf_data_file' members, no functional
      change done.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1385634619-8129-6-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 7d09faf..1fbcd8b 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -118,3 +118,9 @@ void perf_data_file__close(struct perf_data_file *file)
 {
 	close(file->fd);
 }
+
+ssize_t perf_data_file__write(struct perf_data_file *file,
+			      void *buf, size_t size)
+{
+	return writen(file->fd, buf, size);
+}
diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h
index 8c2df80..2b15d0c 100644
--- a/tools/perf/util/data.h
+++ b/tools/perf/util/data.h
@@ -9,12 +9,12 @@ enum perf_data_mode {
 };
 
 struct perf_data_file {
-	const char *path;
-	int fd;
-	bool is_pipe;
-	bool force;
-	unsigned long size;
-	enum perf_data_mode mode;
+	const char		*path;
+	int			 fd;
+	bool			 is_pipe;
+	bool			 force;
+	unsigned long		 size;
+	enum perf_data_mode	 mode;
 };
 
 static inline bool perf_data_file__is_read(struct perf_data_file *file)
@@ -44,5 +44,7 @@ static inline unsigned long perf_data_file__size(struct perf_data_file *file)
 
 int perf_data_file__open(struct perf_data_file *file);
 void perf_data_file__close(struct perf_data_file *file);
+ssize_t perf_data_file__write(struct perf_data_file *file,
+			      void *buf, size_t size);
 
 #endif /* __PERF_DATA_H */
-- 
cgit v0.10.2


From 985b12e633246750b5424f0a28d5f8cea04de07a Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 28 Nov 2013 11:25:19 -0300
Subject: perf timechart: Introduce tool struct

To avoid having all those global variables and to use the interface to
event processing that is based on passing a 'perf_tool' struct that
should be embedded in a per tool specific struct passed to all the
sample processing callbacks.

There are some more globals to move, next patches will do it.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stanislav Fomichev <stfomichev@yandex-team.ru>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-0iah65pq796ezbk5u1lzwy1k@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 680632d..e2d62f1 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -41,19 +41,18 @@
 #define SUPPORT_OLD_POWER_EVENTS 1
 #define PWR_EVENT_EXIT -1
 
-static int proc_num = 15;
-
-static unsigned int	numcpus;
-static u64		min_freq;	/* Lowest CPU frequency seen */
-static u64		max_freq;	/* Highest CPU frequency seen */
-static u64		turbo_frequency;
-
-static u64		first_time, last_time;
-
-static bool		power_only;
-static bool		tasks_only;
-static bool		with_backtrace;
-
+struct timechart {
+	struct perf_tool	tool;
+	int			proc_num;
+	unsigned int		numcpus;
+	u64			min_freq,	/* Lowest CPU frequency seen */
+				max_freq,	/* Highest CPU frequency seen */
+				turbo_frequency,
+				first_time, last_time;
+	bool			power_only,
+				tasks_only,
+				with_backtrace;
+};
 
 struct per_pidcomm;
 struct cpu_sample;
@@ -326,7 +325,7 @@ static void c_state_end(int cpu, u64 timestamp)
 	power_events = pwr;
 }
 
-static void p_state_change(int cpu, u64 timestamp, u64 new_freq)
+static void p_state_change(struct timechart *tchart, int cpu, u64 timestamp, u64 new_freq)
 {
 	struct power_event *pwr;
 
@@ -345,21 +344,21 @@ static void p_state_change(int cpu, u64 timestamp, u64 new_freq)
 	pwr->next = power_events;
 
 	if (!pwr->start_time)
-		pwr->start_time = first_time;
+		pwr->start_time = tchart->first_time;
 
 	power_events = pwr;
 
 	cpus_pstate_state[cpu] = new_freq;
 	cpus_pstate_start_times[cpu] = timestamp;
 
-	if ((u64)new_freq > max_freq)
-		max_freq = new_freq;
+	if ((u64)new_freq > tchart->max_freq)
+		tchart->max_freq = new_freq;
 
-	if (new_freq < min_freq || min_freq == 0)
-		min_freq = new_freq;
+	if (new_freq < tchart->min_freq || tchart->min_freq == 0)
+		tchart->min_freq = new_freq;
 
-	if (new_freq == max_freq - 1000)
-			turbo_frequency = max_freq;
+	if (new_freq == tchart->max_freq - 1000)
+		tchart->turbo_frequency = tchart->max_freq;
 }
 
 static void sched_wakeup(int cpu, u64 timestamp, int waker, int wakee,
@@ -506,36 +505,40 @@ exit:
 	return p;
 }
 
-typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
+typedef int (*tracepoint_handler)(struct timechart *tchart,
+				  struct perf_evsel *evsel,
 				  struct perf_sample *sample,
 				  const char *backtrace);
 
-static int process_sample_event(struct perf_tool *tool __maybe_unused,
+static int process_sample_event(struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
 				struct perf_evsel *evsel,
-				struct machine *machine __maybe_unused)
+				struct machine *machine)
 {
+	struct timechart *tchart = container_of(tool, struct timechart, tool);
+
 	if (evsel->attr.sample_type & PERF_SAMPLE_TIME) {
-		if (!first_time || first_time > sample->time)
-			first_time = sample->time;
-		if (last_time < sample->time)
-			last_time = sample->time;
+		if (!tchart->first_time || tchart->first_time > sample->time)
+			tchart->first_time = sample->time;
+		if (tchart->last_time < sample->time)
+			tchart->last_time = sample->time;
 	}
 
-	if (sample->cpu > numcpus)
-		numcpus = sample->cpu;
+	if (sample->cpu > tchart->numcpus)
+		tchart->numcpus = sample->cpu;
 
 	if (evsel->handler != NULL) {
 		tracepoint_handler f = evsel->handler;
-		return f(evsel, sample, cat_backtrace(event, sample, machine));
+		return f(tchart, evsel, sample, cat_backtrace(event, sample, machine));
 	}
 
 	return 0;
 }
 
 static int
-process_sample_cpu_idle(struct perf_evsel *evsel,
+process_sample_cpu_idle(struct timechart *tchart __maybe_unused,
+			struct perf_evsel *evsel,
 			struct perf_sample *sample,
 			const char *backtrace __maybe_unused)
 {
@@ -550,19 +553,21 @@ process_sample_cpu_idle(struct perf_evsel *evsel,
 }
 
 static int
-process_sample_cpu_frequency(struct perf_evsel *evsel,
+process_sample_cpu_frequency(struct timechart *tchart,
+			     struct perf_evsel *evsel,
 			     struct perf_sample *sample,
 			     const char *backtrace __maybe_unused)
 {
 	u32 state = perf_evsel__intval(evsel, sample, "state");
 	u32 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
 
-	p_state_change(cpu_id, sample->time, state);
+	p_state_change(tchart, cpu_id, sample->time, state);
 	return 0;
 }
 
 static int
-process_sample_sched_wakeup(struct perf_evsel *evsel,
+process_sample_sched_wakeup(struct timechart *tchart __maybe_unused,
+			    struct perf_evsel *evsel,
 			    struct perf_sample *sample,
 			    const char *backtrace)
 {
@@ -575,7 +580,8 @@ process_sample_sched_wakeup(struct perf_evsel *evsel,
 }
 
 static int
-process_sample_sched_switch(struct perf_evsel *evsel,
+process_sample_sched_switch(struct timechart *tchart __maybe_unused,
+			    struct perf_evsel *evsel,
 			    struct perf_sample *sample,
 			    const char *backtrace)
 {
@@ -590,7 +596,8 @@ process_sample_sched_switch(struct perf_evsel *evsel,
 
 #ifdef SUPPORT_OLD_POWER_EVENTS
 static int
-process_sample_power_start(struct perf_evsel *evsel,
+process_sample_power_start(struct timechart *tchart __maybe_unused,
+			   struct perf_evsel *evsel,
 			   struct perf_sample *sample,
 			   const char *backtrace __maybe_unused)
 {
@@ -602,7 +609,8 @@ process_sample_power_start(struct perf_evsel *evsel,
 }
 
 static int
-process_sample_power_end(struct perf_evsel *evsel __maybe_unused,
+process_sample_power_end(struct timechart *tchart __maybe_unused,
+			 struct perf_evsel *evsel __maybe_unused,
 			 struct perf_sample *sample,
 			 const char *backtrace __maybe_unused)
 {
@@ -611,14 +619,15 @@ process_sample_power_end(struct perf_evsel *evsel __maybe_unused,
 }
 
 static int
-process_sample_power_frequency(struct perf_evsel *evsel,
+process_sample_power_frequency(struct timechart *tchart,
+			       struct perf_evsel *evsel,
 			       struct perf_sample *sample,
 			       const char *backtrace __maybe_unused)
 {
 	u64 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
 	u64 value = perf_evsel__intval(evsel, sample, "value");
 
-	p_state_change(cpu_id, sample->time, value);
+	p_state_change(tchart, cpu_id, sample->time, value);
 	return 0;
 }
 #endif /* SUPPORT_OLD_POWER_EVENTS */
@@ -627,12 +636,12 @@ process_sample_power_frequency(struct perf_evsel *evsel,
  * After the last sample we need to wrap up the current C/P state
  * and close out each CPU for these.
  */
-static void end_sample_processing(void)
+static void end_sample_processing(struct timechart *tchart)
 {
 	u64 cpu;
 	struct power_event *pwr;
 
-	for (cpu = 0; cpu <= numcpus; cpu++) {
+	for (cpu = 0; cpu <= tchart->numcpus; cpu++) {
 		/* C state */
 #if 0
 		pwr = zalloc(sizeof(*pwr));
@@ -641,7 +650,7 @@ static void end_sample_processing(void)
 
 		pwr->state = cpus_cstate_state[cpu];
 		pwr->start_time = cpus_cstate_start_times[cpu];
-		pwr->end_time = last_time;
+		pwr->end_time = tchart->last_time;
 		pwr->cpu = cpu;
 		pwr->type = CSTATE;
 		pwr->next = power_events;
@@ -656,15 +665,15 @@ static void end_sample_processing(void)
 
 		pwr->state = cpus_pstate_state[cpu];
 		pwr->start_time = cpus_pstate_start_times[cpu];
-		pwr->end_time = last_time;
+		pwr->end_time = tchart->last_time;
 		pwr->cpu = cpu;
 		pwr->type = PSTATE;
 		pwr->next = power_events;
 
 		if (!pwr->start_time)
-			pwr->start_time = first_time;
+			pwr->start_time = tchart->first_time;
 		if (!pwr->state)
-			pwr->state = min_freq;
+			pwr->state = tchart->min_freq;
 		power_events = pwr;
 	}
 }
@@ -718,7 +727,7 @@ static void sort_pids(void)
 }
 
 
-static void draw_c_p_states(void)
+static void draw_c_p_states(struct timechart *tchart)
 {
 	struct power_event *pwr;
 	pwr = power_events;
@@ -736,7 +745,7 @@ static void draw_c_p_states(void)
 	while (pwr) {
 		if (pwr->type == PSTATE) {
 			if (!pwr->state)
-				pwr->state = min_freq;
+				pwr->state = tchart->min_freq;
 			svg_pstate(pwr->cpu, pwr->start_time, pwr->end_time, pwr->state);
 		}
 		pwr = pwr->next;
@@ -833,14 +842,14 @@ static void draw_cpu_usage(void)
 	}
 }
 
-static void draw_process_bars(void)
+static void draw_process_bars(struct timechart *tchart)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
 	struct cpu_sample *sample;
 	int Y = 0;
 
-	Y = 2 * numcpus + 2;
+	Y = 2 * tchart->numcpus + 2;
 
 	p = all_data;
 	while (p) {
@@ -922,7 +931,7 @@ static int passes_filter(struct per_pid *p, struct per_pidcomm *c)
 	return 0;
 }
 
-static int determine_display_tasks_filtered(void)
+static int determine_display_tasks_filtered(struct timechart *tchart)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
@@ -932,11 +941,11 @@ static int determine_display_tasks_filtered(void)
 	while (p) {
 		p->display = 0;
 		if (p->start_time == 1)
-			p->start_time = first_time;
+			p->start_time = tchart->first_time;
 
 		/* no exit marker, task kept running to the end */
 		if (p->end_time == 0)
-			p->end_time = last_time;
+			p->end_time = tchart->last_time;
 
 		c = p->all;
 
@@ -944,7 +953,7 @@ static int determine_display_tasks_filtered(void)
 			c->display = 0;
 
 			if (c->start_time == 1)
-				c->start_time = first_time;
+				c->start_time = tchart->first_time;
 
 			if (passes_filter(p, c)) {
 				c->display = 1;
@@ -953,7 +962,7 @@ static int determine_display_tasks_filtered(void)
 			}
 
 			if (c->end_time == 0)
-				c->end_time = last_time;
+				c->end_time = tchart->last_time;
 
 			c = c->next;
 		}
@@ -962,24 +971,24 @@ static int determine_display_tasks_filtered(void)
 	return count;
 }
 
-static int determine_display_tasks(u64 threshold)
+static int determine_display_tasks(struct timechart *tchart, u64 threshold)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
 	int count = 0;
 
 	if (process_filter)
-		return determine_display_tasks_filtered();
+		return determine_display_tasks_filtered(tchart);
 
 	p = all_data;
 	while (p) {
 		p->display = 0;
 		if (p->start_time == 1)
-			p->start_time = first_time;
+			p->start_time = tchart->first_time;
 
 		/* no exit marker, task kept running to the end */
 		if (p->end_time == 0)
-			p->end_time = last_time;
+			p->end_time = tchart->last_time;
 		if (p->total_time >= threshold)
 			p->display = 1;
 
@@ -989,7 +998,7 @@ static int determine_display_tasks(u64 threshold)
 			c->display = 0;
 
 			if (c->start_time == 1)
-				c->start_time = first_time;
+				c->start_time = tchart->first_time;
 
 			if (c->total_time >= threshold) {
 				c->display = 1;
@@ -997,7 +1006,7 @@ static int determine_display_tasks(u64 threshold)
 			}
 
 			if (c->end_time == 0)
-				c->end_time = last_time;
+				c->end_time = tchart->last_time;
 
 			c = c->next;
 		}
@@ -1010,52 +1019,45 @@ static int determine_display_tasks(u64 threshold)
 
 #define TIME_THRESH 10000000
 
-static void write_svg_file(const char *filename)
+static void write_svg_file(struct timechart *tchart, const char *filename)
 {
 	u64 i;
 	int count;
 	int thresh = TIME_THRESH;
 
-	numcpus++;
+	tchart->numcpus++;
 
-	if (power_only)
-		proc_num = 0;
+	if (tchart->power_only)
+		tchart->proc_num = 0;
 
 	/* We'd like to show at least proc_num tasks;
 	 * be less picky if we have fewer */
 	do {
-		count = determine_display_tasks(thresh);
+		count = determine_display_tasks(tchart, thresh);
 		thresh /= 10;
-	} while (!process_filter && thresh && count < proc_num);
+	} while (!process_filter && thresh && count < tchart->proc_num);
 
-	open_svg(filename, numcpus, count, first_time, last_time);
+	open_svg(filename, tchart->numcpus, count, tchart->first_time, tchart->last_time);
 
 	svg_time_grid();
 	svg_legenda();
 
-	for (i = 0; i < numcpus; i++)
-		svg_cpu_box(i, max_freq, turbo_frequency);
+	for (i = 0; i < tchart->numcpus; i++)
+		svg_cpu_box(i, tchart->max_freq, tchart->turbo_frequency);
 
 	draw_cpu_usage();
-	if (proc_num)
-		draw_process_bars();
-	if (!tasks_only)
-		draw_c_p_states();
-	if (proc_num)
+	if (tchart->proc_num)
+		draw_process_bars(tchart);
+	if (!tchart->tasks_only)
+		draw_c_p_states(tchart);
+	if (tchart->proc_num)
 		draw_wakeups();
 
 	svg_close();
 }
 
-static int __cmd_timechart(const char *output_name)
+static int __cmd_timechart(struct timechart *tchart, const char *output_name)
 {
-	struct perf_tool perf_timechart = {
-		.comm		 = process_comm_event,
-		.fork		 = process_fork_event,
-		.exit		 = process_exit_event,
-		.sample		 = process_sample_event,
-		.ordered_samples = true,
-	};
 	const struct perf_evsel_str_handler power_tracepoints[] = {
 		{ "power:cpu_idle",		process_sample_cpu_idle },
 		{ "power:cpu_frequency",	process_sample_cpu_frequency },
@@ -1073,7 +1075,7 @@ static int __cmd_timechart(const char *output_name)
 	};
 
 	struct perf_session *session = perf_session__new(&file, false,
-							 &perf_timechart);
+							 &tchart->tool);
 	int ret = -EINVAL;
 
 	if (session == NULL)
@@ -1088,24 +1090,24 @@ static int __cmd_timechart(const char *output_name)
 		goto out_delete;
 	}
 
-	ret = perf_session__process_events(session, &perf_timechart);
+	ret = perf_session__process_events(session, &tchart->tool);
 	if (ret)
 		goto out_delete;
 
-	end_sample_processing();
+	end_sample_processing(tchart);
 
 	sort_pids();
 
-	write_svg_file(output_name);
+	write_svg_file(tchart, output_name);
 
 	pr_info("Written %2.1f seconds of trace to %s.\n",
-		(last_time - first_time) / 1000000000.0, output_name);
+		(tchart->last_time - tchart->first_time) / 1000000000.0, output_name);
 out_delete:
 	perf_session__delete(session);
 	return ret;
 }
 
-static int __cmd_record(int argc, const char **argv)
+static int timechart__record(struct timechart *tchart, int argc, const char **argv)
 {
 	unsigned int rec_argc, i, j;
 	const char **rec_argv;
@@ -1153,15 +1155,15 @@ static int __cmd_record(int argc, const char **argv)
 	}
 #endif
 
-	if (power_only)
+	if (tchart->power_only)
 		tasks_args_nr = 0;
 
-	if (tasks_only) {
+	if (tchart->tasks_only) {
 		power_args_nr = 0;
 		old_power_args_nr = 0;
 	}
 
-	if (!with_backtrace)
+	if (!tchart->with_backtrace)
 		backtrace_args_no = 0;
 
 	record_elems = common_args_nr + tasks_args_nr +
@@ -1207,20 +1209,30 @@ parse_process(const struct option *opt __maybe_unused, const char *arg,
 int cmd_timechart(int argc, const char **argv,
 		  const char *prefix __maybe_unused)
 {
+	struct timechart tchart = {
+		.tool = {
+			.comm		 = process_comm_event,
+			.fork		 = process_fork_event,
+			.exit		 = process_exit_event,
+			.sample		 = process_sample_event,
+			.ordered_samples = true,
+		},
+		.proc_num = 15,
+	};
 	const char *output_name = "output.svg";
 	const struct option timechart_options[] = {
 	OPT_STRING('i', "input", &input_name, "file", "input file name"),
 	OPT_STRING('o', "output", &output_name, "file", "output file name"),
 	OPT_INTEGER('w', "width", &svg_page_width, "page width"),
-	OPT_BOOLEAN('P', "power-only", &power_only, "output power data only"),
-	OPT_BOOLEAN('T', "tasks-only", &tasks_only,
+	OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
+	OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
 		    "output processes data only"),
 	OPT_CALLBACK('p', "process", NULL, "process",
 		      "process selector. Pass a pid or process name.",
 		       parse_process),
 	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
 		    "Look for files with symbols relative to this directory"),
-	OPT_INTEGER('n', "proc-num", &proc_num,
+	OPT_INTEGER('n', "proc-num", &tchart.proc_num,
 		    "min. number of tasks to print"),
 	OPT_END()
 	};
@@ -1230,10 +1242,10 @@ int cmd_timechart(int argc, const char **argv,
 	};
 
 	const struct option record_options[] = {
-	OPT_BOOLEAN('P', "power-only", &power_only, "output power data only"),
-	OPT_BOOLEAN('T', "tasks-only", &tasks_only,
+	OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
+	OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
 		    "output processes data only"),
-	OPT_BOOLEAN('g', "callchain", &with_backtrace, "record callchain"),
+	OPT_BOOLEAN('g', "callchain", &tchart.with_backtrace, "record callchain"),
 	OPT_END()
 	};
 	const char * const record_usage[] = {
@@ -1243,7 +1255,7 @@ int cmd_timechart(int argc, const char **argv,
 	argc = parse_options(argc, argv, timechart_options, timechart_usage,
 			PARSE_OPT_STOP_AT_NON_OPTION);
 
-	if (power_only && tasks_only) {
+	if (tchart.power_only && tchart.tasks_only) {
 		pr_err("-P and -T options cannot be used at the same time.\n");
 		return -1;
 	}
@@ -1254,16 +1266,16 @@ int cmd_timechart(int argc, const char **argv,
 		argc = parse_options(argc, argv, record_options, record_usage,
 				     PARSE_OPT_STOP_AT_NON_OPTION);
 
-		if (power_only && tasks_only) {
+		if (tchart.power_only && tchart.tasks_only) {
 			pr_err("-P and -T options cannot be used at the same time.\n");
 			return -1;
 		}
 
-		return __cmd_record(argc, argv);
+		return timechart__record(&tchart, argc, argv);
 	} else if (argc)
 		usage_with_options(timechart_usage, timechart_options);
 
 	setup_pager();
 
-	return __cmd_timechart(output_name);
+	return __cmd_timechart(&tchart, output_name);
 }
-- 
cgit v0.10.2


From 5e22f6d22bae494ffc23da4032c477c54fd7c2d9 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 28 Nov 2013 11:50:41 -0300
Subject: perf timechart: Move all_data per_pid list to 'struct timechart'

Removing another global variable.

This one tho would be better done by using the machine infrastructure,
searching for the 'struct thread' with a pid, then using thread->priv,
etc.

TODO list material for now.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stanislav Fomichev <stfomichev@yandex-team.ru>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-yyfpudgjvr6mev4bue9u72a2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index e2d62f1..0c955ac 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -41,8 +41,11 @@
 #define SUPPORT_OLD_POWER_EVENTS 1
 #define PWR_EVENT_EXIT -1
 
+struct per_pid;
+
 struct timechart {
 	struct perf_tool	tool;
+	struct per_pid		*all_data;
 	int			proc_num;
 	unsigned int		numcpus;
 	u64			min_freq,	/* Lowest CPU frequency seen */
@@ -123,8 +126,6 @@ struct cpu_sample {
 	const char *backtrace;
 };
 
-static struct per_pid *all_data;
-
 #define CSTATE 1
 #define PSTATE 2
 
@@ -157,9 +158,9 @@ struct process_filter {
 static struct process_filter *process_filter;
 
 
-static struct per_pid *find_create_pid(int pid)
+static struct per_pid *find_create_pid(struct timechart *tchart, int pid)
 {
-	struct per_pid *cursor = all_data;
+	struct per_pid *cursor = tchart->all_data;
 
 	while (cursor) {
 		if (cursor->pid == pid)
@@ -169,16 +170,16 @@ static struct per_pid *find_create_pid(int pid)
 	cursor = zalloc(sizeof(*cursor));
 	assert(cursor != NULL);
 	cursor->pid = pid;
-	cursor->next = all_data;
-	all_data = cursor;
+	cursor->next = tchart->all_data;
+	tchart->all_data = cursor;
 	return cursor;
 }
 
-static void pid_set_comm(int pid, char *comm)
+static void pid_set_comm(struct timechart *tchart, int pid, char *comm)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
-	p = find_create_pid(pid);
+	p = find_create_pid(tchart, pid);
 	c = p->all;
 	while (c) {
 		if (c->comm && strcmp(c->comm, comm) == 0) {
@@ -200,14 +201,14 @@ static void pid_set_comm(int pid, char *comm)
 	p->all = c;
 }
 
-static void pid_fork(int pid, int ppid, u64 timestamp)
+static void pid_fork(struct timechart *tchart, int pid, int ppid, u64 timestamp)
 {
 	struct per_pid *p, *pp;
-	p = find_create_pid(pid);
-	pp = find_create_pid(ppid);
+	p = find_create_pid(tchart, pid);
+	pp = find_create_pid(tchart, ppid);
 	p->ppid = ppid;
 	if (pp->current && pp->current->comm && !p->current)
-		pid_set_comm(pid, pp->current->comm);
+		pid_set_comm(tchart, pid, pp->current->comm);
 
 	p->start_time = timestamp;
 	if (p->current) {
@@ -216,24 +217,24 @@ static void pid_fork(int pid, int ppid, u64 timestamp)
 	}
 }
 
-static void pid_exit(int pid, u64 timestamp)
+static void pid_exit(struct timechart *tchart, int pid, u64 timestamp)
 {
 	struct per_pid *p;
-	p = find_create_pid(pid);
+	p = find_create_pid(tchart, pid);
 	p->end_time = timestamp;
 	if (p->current)
 		p->current->end_time = timestamp;
 }
 
-static void
-pid_put_sample(int pid, int type, unsigned int cpu, u64 start, u64 end,
-	       const char *backtrace)
+static void pid_put_sample(struct timechart *tchart, int pid, int type,
+			   unsigned int cpu, u64 start, u64 end,
+			   const char *backtrace)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
 	struct cpu_sample *sample;
 
-	p = find_create_pid(pid);
+	p = find_create_pid(tchart, pid);
 	c = p->current;
 	if (!c) {
 		c = zalloc(sizeof(*c));
@@ -271,30 +272,33 @@ static int cpus_cstate_state[MAX_CPUS];
 static u64 cpus_pstate_start_times[MAX_CPUS];
 static u64 cpus_pstate_state[MAX_CPUS];
 
-static int process_comm_event(struct perf_tool *tool __maybe_unused,
+static int process_comm_event(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_sample *sample __maybe_unused,
 			      struct machine *machine __maybe_unused)
 {
-	pid_set_comm(event->comm.tid, event->comm.comm);
+	struct timechart *tchart = container_of(tool, struct timechart, tool);
+	pid_set_comm(tchart, event->comm.tid, event->comm.comm);
 	return 0;
 }
 
-static int process_fork_event(struct perf_tool *tool __maybe_unused,
+static int process_fork_event(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_sample *sample __maybe_unused,
 			      struct machine *machine __maybe_unused)
 {
-	pid_fork(event->fork.pid, event->fork.ppid, event->fork.time);
+	struct timechart *tchart = container_of(tool, struct timechart, tool);
+	pid_fork(tchart, event->fork.pid, event->fork.ppid, event->fork.time);
 	return 0;
 }
 
-static int process_exit_event(struct perf_tool *tool __maybe_unused,
+static int process_exit_event(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_sample *sample __maybe_unused,
 			      struct machine *machine __maybe_unused)
 {
-	pid_exit(event->fork.pid, event->fork.time);
+	struct timechart *tchart = container_of(tool, struct timechart, tool);
+	pid_exit(tchart, event->fork.pid, event->fork.time);
 	return 0;
 }
 
@@ -361,8 +365,8 @@ static void p_state_change(struct timechart *tchart, int cpu, u64 timestamp, u64
 		tchart->turbo_frequency = tchart->max_freq;
 }
 
-static void sched_wakeup(int cpu, u64 timestamp, int waker, int wakee,
-			 u8 flags, const char *backtrace)
+static void sched_wakeup(struct timechart *tchart, int cpu, u64 timestamp,
+			 int waker, int wakee, u8 flags, const char *backtrace)
 {
 	struct per_pid *p;
 	struct wake_event *we = zalloc(sizeof(*we));
@@ -380,36 +384,37 @@ static void sched_wakeup(int cpu, u64 timestamp, int waker, int wakee,
 	we->wakee = wakee;
 	we->next = wake_events;
 	wake_events = we;
-	p = find_create_pid(we->wakee);
+	p = find_create_pid(tchart, we->wakee);
 
 	if (p && p->current && p->current->state == TYPE_NONE) {
 		p->current->state_since = timestamp;
 		p->current->state = TYPE_WAITING;
 	}
 	if (p && p->current && p->current->state == TYPE_BLOCKED) {
-		pid_put_sample(p->pid, p->current->state, cpu,
+		pid_put_sample(tchart, p->pid, p->current->state, cpu,
 			       p->current->state_since, timestamp, NULL);
 		p->current->state_since = timestamp;
 		p->current->state = TYPE_WAITING;
 	}
 }
 
-static void sched_switch(int cpu, u64 timestamp, int prev_pid, int next_pid,
-			 u64 prev_state, const char *backtrace)
+static void sched_switch(struct timechart *tchart, int cpu, u64 timestamp,
+			 int prev_pid, int next_pid, u64 prev_state,
+			 const char *backtrace)
 {
 	struct per_pid *p = NULL, *prev_p;
 
-	prev_p = find_create_pid(prev_pid);
+	prev_p = find_create_pid(tchart, prev_pid);
 
-	p = find_create_pid(next_pid);
+	p = find_create_pid(tchart, next_pid);
 
 	if (prev_p->current && prev_p->current->state != TYPE_NONE)
-		pid_put_sample(prev_pid, TYPE_RUNNING, cpu,
+		pid_put_sample(tchart, prev_pid, TYPE_RUNNING, cpu,
 			       prev_p->current->state_since, timestamp,
 			       backtrace);
 	if (p && p->current) {
 		if (p->current->state != TYPE_NONE)
-			pid_put_sample(next_pid, p->current->state, cpu,
+			pid_put_sample(tchart, next_pid, p->current->state, cpu,
 				       p->current->state_since, timestamp,
 				       backtrace);
 
@@ -566,7 +571,7 @@ process_sample_cpu_frequency(struct timechart *tchart,
 }
 
 static int
-process_sample_sched_wakeup(struct timechart *tchart __maybe_unused,
+process_sample_sched_wakeup(struct timechart *tchart,
 			    struct perf_evsel *evsel,
 			    struct perf_sample *sample,
 			    const char *backtrace)
@@ -575,12 +580,12 @@ process_sample_sched_wakeup(struct timechart *tchart __maybe_unused,
 	int waker = perf_evsel__intval(evsel, sample, "common_pid");
 	int wakee = perf_evsel__intval(evsel, sample, "pid");
 
-	sched_wakeup(sample->cpu, sample->time, waker, wakee, flags, backtrace);
+	sched_wakeup(tchart, sample->cpu, sample->time, waker, wakee, flags, backtrace);
 	return 0;
 }
 
 static int
-process_sample_sched_switch(struct timechart *tchart __maybe_unused,
+process_sample_sched_switch(struct timechart *tchart,
 			    struct perf_evsel *evsel,
 			    struct perf_sample *sample,
 			    const char *backtrace)
@@ -589,8 +594,8 @@ process_sample_sched_switch(struct timechart *tchart __maybe_unused,
 	int next_pid = perf_evsel__intval(evsel, sample, "next_pid");
 	u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state");
 
-	sched_switch(sample->cpu, sample->time, prev_pid, next_pid, prev_state,
-		     backtrace);
+	sched_switch(tchart, sample->cpu, sample->time, prev_pid, next_pid,
+		     prev_state, backtrace);
 	return 0;
 }
 
@@ -681,16 +686,16 @@ static void end_sample_processing(struct timechart *tchart)
 /*
  * Sort the pid datastructure
  */
-static void sort_pids(void)
+static void sort_pids(struct timechart *tchart)
 {
 	struct per_pid *new_list, *p, *cursor, *prev;
 	/* sort by ppid first, then by pid, lowest to highest */
 
 	new_list = NULL;
 
-	while (all_data) {
-		p = all_data;
-		all_data = p->next;
+	while (tchart->all_data) {
+		p = tchart->all_data;
+		tchart->all_data = p->next;
 		p->next = NULL;
 
 		if (new_list == NULL) {
@@ -723,7 +728,7 @@ static void sort_pids(void)
 				prev->next = p;
 		}
 	}
-	all_data = new_list;
+	tchart->all_data = new_list;
 }
 
 
@@ -752,7 +757,7 @@ static void draw_c_p_states(struct timechart *tchart)
 	}
 }
 
-static void draw_wakeups(void)
+static void draw_wakeups(struct timechart *tchart)
 {
 	struct wake_event *we;
 	struct per_pid *p;
@@ -764,7 +769,7 @@ static void draw_wakeups(void)
 		char *task_from = NULL, *task_to = NULL;
 
 		/* locate the column of the waker and wakee */
-		p = all_data;
+		p = tchart->all_data;
 		while (p) {
 			if (p->pid == we->waker || p->pid == we->wakee) {
 				c = p->all;
@@ -820,12 +825,12 @@ static void draw_wakeups(void)
 	}
 }
 
-static void draw_cpu_usage(void)
+static void draw_cpu_usage(struct timechart *tchart)
 {
 	struct per_pid *p;
 	struct per_pidcomm *c;
 	struct cpu_sample *sample;
-	p = all_data;
+	p = tchart->all_data;
 	while (p) {
 		c = p->all;
 		while (c) {
@@ -851,7 +856,7 @@ static void draw_process_bars(struct timechart *tchart)
 
 	Y = 2 * tchart->numcpus + 2;
 
-	p = all_data;
+	p = tchart->all_data;
 	while (p) {
 		c = p->all;
 		while (c) {
@@ -937,7 +942,7 @@ static int determine_display_tasks_filtered(struct timechart *tchart)
 	struct per_pidcomm *c;
 	int count = 0;
 
-	p = all_data;
+	p = tchart->all_data;
 	while (p) {
 		p->display = 0;
 		if (p->start_time == 1)
@@ -980,7 +985,7 @@ static int determine_display_tasks(struct timechart *tchart, u64 threshold)
 	if (process_filter)
 		return determine_display_tasks_filtered(tchart);
 
-	p = all_data;
+	p = tchart->all_data;
 	while (p) {
 		p->display = 0;
 		if (p->start_time == 1)
@@ -1045,13 +1050,13 @@ static void write_svg_file(struct timechart *tchart, const char *filename)
 	for (i = 0; i < tchart->numcpus; i++)
 		svg_cpu_box(i, tchart->max_freq, tchart->turbo_frequency);
 
-	draw_cpu_usage();
+	draw_cpu_usage(tchart);
 	if (tchart->proc_num)
 		draw_process_bars(tchart);
 	if (!tchart->tasks_only)
 		draw_c_p_states(tchart);
 	if (tchart->proc_num)
-		draw_wakeups();
+		draw_wakeups(tchart);
 
 	svg_close();
 }
@@ -1096,7 +1101,7 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
 
 	end_sample_processing(tchart);
 
-	sort_pids();
+	sort_pids(tchart);
 
 	write_svg_file(tchart, output_name);
 
-- 
cgit v0.10.2


From 66cc3ada4ec3c277a21cba9996cc0cab3409033d Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 28 Nov 2013 13:23:05 -0300
Subject: perf timechart: Move power_events list to 'struct timechart'

Removing another global variable.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stanislav Fomichev <stfomichev@yandex-team.ru>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-2akef3p9caau56itf5mugd2b@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 0c955ac..8ee0ff1 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -42,10 +42,12 @@
 #define PWR_EVENT_EXIT -1
 
 struct per_pid;
+struct power_event;
 
 struct timechart {
 	struct perf_tool	tool;
 	struct per_pid		*all_data;
+	struct power_event	*power_events;
 	int			proc_num;
 	unsigned int		numcpus;
 	u64			min_freq,	/* Lowest CPU frequency seen */
@@ -146,7 +148,6 @@ struct wake_event {
 	const char *backtrace;
 };
 
-static struct power_event    *power_events;
 static struct wake_event     *wake_events;
 
 struct process_filter {
@@ -312,7 +313,7 @@ static void c_state_start(int cpu, u64 timestamp, int state)
 	cpus_cstate_state[cpu] = state;
 }
 
-static void c_state_end(int cpu, u64 timestamp)
+static void c_state_end(struct timechart *tchart, int cpu, u64 timestamp)
 {
 	struct power_event *pwr = zalloc(sizeof(*pwr));
 
@@ -324,9 +325,9 @@ static void c_state_end(int cpu, u64 timestamp)
 	pwr->end_time = timestamp;
 	pwr->cpu = cpu;
 	pwr->type = CSTATE;
-	pwr->next = power_events;
+	pwr->next = tchart->power_events;
 
-	power_events = pwr;
+	tchart->power_events = pwr;
 }
 
 static void p_state_change(struct timechart *tchart, int cpu, u64 timestamp, u64 new_freq)
@@ -345,12 +346,12 @@ static void p_state_change(struct timechart *tchart, int cpu, u64 timestamp, u64
 	pwr->end_time = timestamp;
 	pwr->cpu = cpu;
 	pwr->type = PSTATE;
-	pwr->next = power_events;
+	pwr->next = tchart->power_events;
 
 	if (!pwr->start_time)
 		pwr->start_time = tchart->first_time;
 
-	power_events = pwr;
+	tchart->power_events = pwr;
 
 	cpus_pstate_state[cpu] = new_freq;
 	cpus_pstate_start_times[cpu] = timestamp;
@@ -551,7 +552,7 @@ process_sample_cpu_idle(struct timechart *tchart __maybe_unused,
 	u32 cpu_id = perf_evsel__intval(evsel, sample, "cpu_id");
 
 	if (state == (u32)PWR_EVENT_EXIT)
-		c_state_end(cpu_id, sample->time);
+		c_state_end(tchart, cpu_id, sample->time);
 	else
 		c_state_start(cpu_id, sample->time, state);
 	return 0;
@@ -614,12 +615,12 @@ process_sample_power_start(struct timechart *tchart __maybe_unused,
 }
 
 static int
-process_sample_power_end(struct timechart *tchart __maybe_unused,
+process_sample_power_end(struct timechart *tchart,
 			 struct perf_evsel *evsel __maybe_unused,
 			 struct perf_sample *sample,
 			 const char *backtrace __maybe_unused)
 {
-	c_state_end(sample->cpu, sample->time);
+	c_state_end(tchart, sample->cpu, sample->time);
 	return 0;
 }
 
@@ -658,9 +659,9 @@ static void end_sample_processing(struct timechart *tchart)
 		pwr->end_time = tchart->last_time;
 		pwr->cpu = cpu;
 		pwr->type = CSTATE;
-		pwr->next = power_events;
+		pwr->next = tchart->power_events;
 
-		power_events = pwr;
+		tchart->power_events = pwr;
 #endif
 		/* P state */
 
@@ -673,13 +674,13 @@ static void end_sample_processing(struct timechart *tchart)
 		pwr->end_time = tchart->last_time;
 		pwr->cpu = cpu;
 		pwr->type = PSTATE;
-		pwr->next = power_events;
+		pwr->next = tchart->power_events;
 
 		if (!pwr->start_time)
 			pwr->start_time = tchart->first_time;
 		if (!pwr->state)
 			pwr->state = tchart->min_freq;
-		power_events = pwr;
+		tchart->power_events = pwr;
 	}
 }
 
@@ -735,7 +736,7 @@ static void sort_pids(struct timechart *tchart)
 static void draw_c_p_states(struct timechart *tchart)
 {
 	struct power_event *pwr;
-	pwr = power_events;
+	pwr = tchart->power_events;
 
 	/*
 	 * two pass drawing so that the P state bars are on top of the C state blocks
@@ -746,7 +747,7 @@ static void draw_c_p_states(struct timechart *tchart)
 		pwr = pwr->next;
 	}
 
-	pwr = power_events;
+	pwr = tchart->power_events;
 	while (pwr) {
 		if (pwr->type == PSTATE) {
 			if (!pwr->state)
-- 
cgit v0.10.2


From 436b0da02fc12970f2f5ecdef03160c7a401b121 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 28 Nov 2013 13:26:33 -0300
Subject: perf timechart: Move wake_events list to 'struct timechart'

Removing another global variable.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stanislav Fomichev <stfomichev@yandex-team.ru>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-14rpuci11l2s0o01yta87kxe@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 8ee0ff1..0bda620 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -43,11 +43,13 @@
 
 struct per_pid;
 struct power_event;
+struct wake_event;
 
 struct timechart {
 	struct perf_tool	tool;
 	struct per_pid		*all_data;
 	struct power_event	*power_events;
+	struct wake_event	*wake_events;
 	int			proc_num;
 	unsigned int		numcpus;
 	u64			min_freq,	/* Lowest CPU frequency seen */
@@ -148,8 +150,6 @@ struct wake_event {
 	const char *backtrace;
 };
 
-static struct wake_event     *wake_events;
-
 struct process_filter {
 	char			*name;
 	int			pid;
@@ -383,8 +383,8 @@ static void sched_wakeup(struct timechart *tchart, int cpu, u64 timestamp,
 		we->waker = -1;
 
 	we->wakee = wakee;
-	we->next = wake_events;
-	wake_events = we;
+	we->next = tchart->wake_events;
+	tchart->wake_events = we;
 	p = find_create_pid(tchart, we->wakee);
 
 	if (p && p->current && p->current->state == TYPE_NONE) {
@@ -764,7 +764,7 @@ static void draw_wakeups(struct timechart *tchart)
 	struct per_pid *p;
 	struct per_pidcomm *c;
 
-	we = wake_events;
+	we = tchart->wake_events;
 	while (we) {
 		int from = 0, to = 0;
 		char *task_from = NULL, *task_to = NULL;
-- 
cgit v0.10.2


From 6305edfc4079668ce02e360a6e5aeea88b9dd279 Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Mon, 2 Dec 2013 10:26:48 -0500
Subject: perf tools: Correct the message in feature-libnuma checking.

The package required for numa is named numactl-devel in Fedora or RHEL,
and libnuma-devel in OpenSuSE, and libnuma-dev in Ubuntu.

This patch corrects the package name in warning message in
feature-libnuma checking.

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Acked-by: Peter Hurley <peter@hurleysoftware.com>
Cc: Peter Hurley <peter@hurleysoftware.com>
Link: http://lkml.kernel.org/r/1385998008-6851-1-git-send-email-yangds.fnst@cn.fujitsu.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index f7d11a8..36e66ac 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -533,7 +533,7 @@ endif
 
 ifndef NO_LIBNUMA
   ifeq ($(feature-libnuma), 0)
-    msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numa-libs-devel or libnuma-dev);
+    msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numactl-devel/libnuma-devel/libnuma-dev);
     NO_LIBNUMA := 1
   else
     CFLAGS += -DHAVE_LIBNUMA_SUPPORT
-- 
cgit v0.10.2


From bc32358b569247ceabba14dab297070a8fb255c4 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 28 Nov 2013 12:33:01 +0100
Subject: perf tools: Include test-stackprotector-all.c in test-all

We're missing test-stackprotector-all.c in test-all check, adding it.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1385638408-23519-3-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c
index 59e7a70..9b8a544 100644
--- a/tools/perf/config/feature-checks/test-all.c
+++ b/tools/perf/config/feature-checks/test-all.c
@@ -85,6 +85,10 @@
 # include "test-timerfd.c"
 #undef main
 
+#define main main_test_stackprotector_all
+# include "test-stackprotector-all.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -106,6 +110,7 @@ int main(int argc, char *argv[])
 	main_test_backtrace();
 	main_test_libnuma();
 	main_test_timerfd();
+	main_test_stackprotector_all();
 
 	return 0;
 }
-- 
cgit v0.10.2


From f885037ef6400ce4a4c122a88845dea2c9bca256 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 28 Nov 2013 17:57:22 +0100
Subject: perf trace: Honour -m option

Currently trace command supports '-m' option, but does not honours its
value and keeps the default.

Changing the perf_evlist__mmap function call to use the '-m' configured
value.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1385657842-8914-1-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index e9f345e2..9f2a242 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1890,7 +1890,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (err < 0)
 		goto out_error_open;
 
-	err = perf_evlist__mmap(evlist, UINT_MAX, false);
+	err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
 	if (err < 0) {
 		fprintf(trace->output, "Couldn't mmap the events: %s\n", strerror(errno));
 		goto out_close_evlist;
-- 
cgit v0.10.2


From e8fcaa5c54e3b0371230e5d43a6f650c667da9c5 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Wed, 7 Aug 2013 22:28:01 +0200
Subject: nohz: Convert a few places to use local per cpu accesses

A few functions use remote per CPU access APIs when they
deal with local values.

Just do the right conversion to improve performance, code
readability and debug checks.

While at it, lets extend some of these function names with *_this_cpu()
suffix in order to display their purpose more clearly.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>

diff --git a/include/linux/tick.h b/include/linux/tick.h
index 5128d33..a004f66 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -104,7 +104,7 @@ extern struct cpumask *tick_get_broadcast_oneshot_mask(void);
 extern void tick_clock_notify(void);
 extern int tick_check_oneshot_change(int allow_nohz);
 extern struct tick_sched *tick_get_tick_sched(int cpu);
-extern void tick_check_idle(int cpu);
+extern void tick_check_idle(void);
 extern int tick_oneshot_mode_active(void);
 #  ifndef arch_needs_cpu
 #   define arch_needs_cpu(cpu) (0)
@@ -112,7 +112,7 @@ extern int tick_oneshot_mode_active(void);
 # else
 static inline void tick_clock_notify(void) { }
 static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
-static inline void tick_check_idle(int cpu) { }
+static inline void tick_check_idle(void) { }
 static inline int tick_oneshot_mode_active(void) { return 0; }
 # endif
 
@@ -121,7 +121,7 @@ static inline void tick_init(void) { }
 static inline void tick_cancel_sched_timer(int cpu) { }
 static inline void tick_clock_notify(void) { }
 static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
-static inline void tick_check_idle(int cpu) { }
+static inline void tick_check_idle(void) { }
 static inline int tick_oneshot_mode_active(void) { return 0; }
 #endif /* !CONFIG_GENERIC_CLOCKEVENTS */
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 11025cc..11348de 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -311,8 +311,6 @@ asmlinkage void do_softirq(void)
  */
 void irq_enter(void)
 {
-	int cpu = smp_processor_id();
-
 	rcu_irq_enter();
 	if (is_idle_task(current) && !in_interrupt()) {
 		/*
@@ -320,7 +318,7 @@ void irq_enter(void)
 		 * here, as softirq will be serviced on return from interrupt.
 		 */
 		local_bh_disable();
-		tick_check_idle(cpu);
+		tick_check_idle();
 		_local_bh_enable();
 	}
 
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 9532690..43780ab 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -538,10 +538,10 @@ int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
  * Called from irq_enter() when idle was interrupted to reenable the
  * per cpu device.
  */
-void tick_check_oneshot_broadcast(int cpu)
+void tick_check_oneshot_broadcast_this_cpu(void)
 {
-	if (cpumask_test_cpu(cpu, tick_broadcast_oneshot_mask)) {
-		struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
+	if (cpumask_test_cpu(smp_processor_id(), tick_broadcast_oneshot_mask)) {
+		struct tick_device *td = &__get_cpu_var(tick_cpu_device);
 
 		/*
 		 * We might be in the middle of switching over from
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 18e71f7..e2bced5 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -51,7 +51,7 @@ extern void tick_broadcast_switch_to_oneshot(void);
 extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
 extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
 extern int tick_broadcast_oneshot_active(void);
-extern void tick_check_oneshot_broadcast(int cpu);
+extern void tick_check_oneshot_broadcast_this_cpu(void);
 bool tick_broadcast_oneshot_available(void);
 # else /* BROADCAST */
 static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
@@ -62,7 +62,7 @@ static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
 static inline void tick_broadcast_switch_to_oneshot(void) { }
 static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
 static inline int tick_broadcast_oneshot_active(void) { return 0; }
-static inline void tick_check_oneshot_broadcast(int cpu) { }
+static inline void tick_check_oneshot_broadcast_this_cpu(void) { }
 static inline bool tick_broadcast_oneshot_available(void) { return true; }
 # endif /* !BROADCAST */
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 3612fc7..2afd43f 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -391,11 +391,9 @@ __setup("nohz=", setup_tick_nohz);
  */
 static void tick_nohz_update_jiffies(ktime_t now)
 {
-	int cpu = smp_processor_id();
-	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 	unsigned long flags;
 
-	ts->idle_waketime = now;
+	__this_cpu_write(tick_cpu_sched.idle_waketime, now);
 
 	local_irq_save(flags);
 	tick_do_update_jiffies64(now);
@@ -426,17 +424,15 @@ update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_upda
 
 }
 
-static void tick_nohz_stop_idle(int cpu, ktime_t now)
+static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
 {
-	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-
-	update_ts_time_stats(cpu, ts, now, NULL);
+	update_ts_time_stats(smp_processor_id(), ts, now, NULL);
 	ts->idle_active = 0;
 
 	sched_clock_idle_wakeup_event(0);
 }
 
-static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts)
+static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
 {
 	ktime_t now = ktime_get();
 
@@ -752,7 +748,7 @@ static void __tick_nohz_idle_enter(struct tick_sched *ts)
 	ktime_t now, expires;
 	int cpu = smp_processor_id();
 
-	now = tick_nohz_start_idle(cpu, ts);
+	now = tick_nohz_start_idle(ts);
 
 	if (can_stop_idle_tick(cpu, ts)) {
 		int was_stopped = ts->tick_stopped;
@@ -914,8 +910,7 @@ static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
  */
 void tick_nohz_idle_exit(void)
 {
-	int cpu = smp_processor_id();
-	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
 	ktime_t now;
 
 	local_irq_disable();
@@ -928,7 +923,7 @@ void tick_nohz_idle_exit(void)
 		now = ktime_get();
 
 	if (ts->idle_active)
-		tick_nohz_stop_idle(cpu, now);
+		tick_nohz_stop_idle(ts, now);
 
 	if (ts->tick_stopped) {
 		tick_nohz_restart_sched_tick(ts, now);
@@ -1012,12 +1007,10 @@ static void tick_nohz_switch_to_nohz(void)
  * timer and do not touch the other magic bits which need to be done
  * when idle is left.
  */
-static void tick_nohz_kick_tick(int cpu, ktime_t now)
+static void tick_nohz_kick_tick(struct tick_sched *ts, ktime_t now)
 {
 #if 0
 	/* Switch back to 2.6.27 behaviour */
-
-	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 	ktime_t delta;
 
 	/*
@@ -1032,36 +1025,36 @@ static void tick_nohz_kick_tick(int cpu, ktime_t now)
 #endif
 }
 
-static inline void tick_check_nohz(int cpu)
+static inline void tick_check_nohz_this_cpu(void)
 {
-	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+	struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
 	ktime_t now;
 
 	if (!ts->idle_active && !ts->tick_stopped)
 		return;
 	now = ktime_get();
 	if (ts->idle_active)
-		tick_nohz_stop_idle(cpu, now);
+		tick_nohz_stop_idle(ts, now);
 	if (ts->tick_stopped) {
 		tick_nohz_update_jiffies(now);
-		tick_nohz_kick_tick(cpu, now);
+		tick_nohz_kick_tick(ts, now);
 	}
 }
 
 #else
 
 static inline void tick_nohz_switch_to_nohz(void) { }
-static inline void tick_check_nohz(int cpu) { }
+static inline void tick_check_nohz_this_cpu(void) { }
 
 #endif /* CONFIG_NO_HZ_COMMON */
 
 /*
  * Called from irq_enter to notify about the possible interruption of idle()
  */
-void tick_check_idle(int cpu)
+void tick_check_idle(void)
 {
-	tick_check_oneshot_broadcast(cpu);
-	tick_check_nohz(cpu);
+	tick_check_oneshot_broadcast_this_cpu();
+	tick_check_nohz_this_cpu();
 }
 
 /*
-- 
cgit v0.10.2


From 99c8b1ea0972be82ce1842d830e0173e70907065 Mon Sep 17 00:00:00 2001
From: Paul Gortmaker <paul.gortmaker@windriver.com>
Date: Thu, 24 Oct 2013 10:07:47 -0400
Subject: trivial: fix spelling in CONTEXT_TRACKING_FORCE help text

Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>

diff --git a/init/Kconfig b/init/Kconfig
index 79383d3..12d61f8 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -532,7 +532,7 @@ config CONTEXT_TRACKING_FORCE
 	  dynticks subsystem by forcing the context tracking on all
 	  CPUs in the system.
 
-	  Say Y only if you're working on the developpement of an
+	  Say Y only if you're working on the development of an
 	  architecture backend for the context tracking.
 
 	  Say N otherwise, this option brings an overhead that you
-- 
cgit v0.10.2


From 58135f574f1b791c926622387780ed3d090116d6 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Wed, 6 Nov 2013 14:45:57 +0100
Subject: context_tracking: Wrap static key check into more intuitive function
 name

Use a function with a meaningful name to check the global context
tracking state. static_key_false() is a bit confusing for reviewers.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>

diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index 1581587..37b81bd 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -17,13 +17,13 @@ extern void __context_tracking_task_switch(struct task_struct *prev,
 
 static inline void user_enter(void)
 {
-	if (static_key_false(&context_tracking_enabled))
+	if (context_tracking_is_enabled())
 		context_tracking_user_enter();
 
 }
 static inline void user_exit(void)
 {
-	if (static_key_false(&context_tracking_enabled))
+	if (context_tracking_is_enabled())
 		context_tracking_user_exit();
 }
 
@@ -31,7 +31,7 @@ static inline enum ctx_state exception_enter(void)
 {
 	enum ctx_state prev_ctx;
 
-	if (!static_key_false(&context_tracking_enabled))
+	if (!context_tracking_is_enabled())
 		return 0;
 
 	prev_ctx = this_cpu_read(context_tracking.state);
@@ -42,7 +42,7 @@ static inline enum ctx_state exception_enter(void)
 
 static inline void exception_exit(enum ctx_state prev_ctx)
 {
-	if (static_key_false(&context_tracking_enabled)) {
+	if (context_tracking_is_enabled()) {
 		if (prev_ctx == IN_USER)
 			context_tracking_user_enter();
 	}
@@ -51,7 +51,7 @@ static inline void exception_exit(enum ctx_state prev_ctx)
 static inline void context_tracking_task_switch(struct task_struct *prev,
 						struct task_struct *next)
 {
-	if (static_key_false(&context_tracking_enabled))
+	if (context_tracking_is_enabled())
 		__context_tracking_task_switch(prev, next);
 }
 #else
diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h
index 0f1979d..0db535b 100644
--- a/include/linux/context_tracking_state.h
+++ b/include/linux/context_tracking_state.h
@@ -22,6 +22,10 @@ struct context_tracking {
 extern struct static_key context_tracking_enabled;
 DECLARE_PER_CPU(struct context_tracking, context_tracking);
 
+static inline bool context_tracking_is_enabled(void)
+{
+	return static_key_false(&context_tracking_enabled);
+}
 static inline bool context_tracking_in_user(void)
 {
 	return __this_cpu_read(context_tracking.state) == IN_USER;
diff --git a/include/linux/tick.h b/include/linux/tick.h
index a004f66..0175d86 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -165,7 +165,7 @@ extern cpumask_var_t tick_nohz_full_mask;
 
 static inline bool tick_nohz_full_enabled(void)
 {
-	if (!static_key_false(&context_tracking_enabled))
+	if (!context_tracking_is_enabled())
 		return false;
 
 	return tick_nohz_full_running;
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index f5b72b3..807c732 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -19,7 +19,7 @@ static inline bool vtime_accounting_enabled(void) { return true; }
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 static inline bool vtime_accounting_enabled(void)
 {
-	if (static_key_false(&context_tracking_enabled)) {
+	if (context_tracking_is_enabled()) {
 		if (context_tracking_active())
 			return true;
 	}
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index e5f3917..6cb20d2 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -53,10 +53,10 @@ void context_tracking_user_enter(void)
 	/*
 	 * Repeat the user_enter() check here because some archs may be calling
 	 * this from asm and if no CPU needs context tracking, they shouldn't
-	 * go further. Repeat the check here until they support the static key
-	 * check.
+	 * go further. Repeat the check here until they support the inline static
+	 * key check.
 	 */
-	if (!static_key_false(&context_tracking_enabled))
+	if (!context_tracking_is_enabled())
 		return;
 
 	/*
@@ -160,7 +160,7 @@ void context_tracking_user_exit(void)
 {
 	unsigned long flags;
 
-	if (!static_key_false(&context_tracking_enabled))
+	if (!context_tracking_is_enabled())
 		return;
 
 	if (in_interrupt())
-- 
cgit v0.10.2


From d0df09ebfc126b23c1005f98ddecc9907f9c5d25 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Wed, 6 Nov 2013 15:11:57 +0100
Subject: context_tracking: Rename context_tracking_active() to
 context_tracking_cpu_is_enabled()

We currently have a confusing couple of API naming with the existing
context_tracking_active() and context_tracking_is_enabled().

Lets keep the latter one, context_tracking_is_enabled(), for global
context tracking state check and use context_tracking_cpu_is_enabled()
for local state check.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>

diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h
index 0db535b..97a8122 100644
--- a/include/linux/context_tracking_state.h
+++ b/include/linux/context_tracking_state.h
@@ -26,14 +26,15 @@ static inline bool context_tracking_is_enabled(void)
 {
 	return static_key_false(&context_tracking_enabled);
 }
-static inline bool context_tracking_in_user(void)
+
+static inline bool context_tracking_cpu_is_enabled(void)
 {
-	return __this_cpu_read(context_tracking.state) == IN_USER;
+	return __this_cpu_read(context_tracking.active);
 }
 
-static inline bool context_tracking_active(void)
+static inline bool context_tracking_in_user(void)
 {
-	return __this_cpu_read(context_tracking.active);
+	return __this_cpu_read(context_tracking.state) == IN_USER;
 }
 #else
 static inline bool context_tracking_in_user(void) { return false; }
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index 807c732..c5165fd 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -20,7 +20,7 @@ static inline bool vtime_accounting_enabled(void) { return true; }
 static inline bool vtime_accounting_enabled(void)
 {
 	if (context_tracking_is_enabled()) {
-		if (context_tracking_active())
+		if (context_tracking_cpu_is_enabled())
 			return true;
 	}
 
-- 
cgit v0.10.2


From d4283c654130c3d01b6842d3821dbdc3c15ceb46 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Wed, 6 Nov 2013 15:42:04 +0100
Subject: posix-timers: Spare workqueue if there is no full dynticks CPU to
 kick

After a posix cpu timer is set, a workqueue is scheduled in order to
kick the full dynticks CPUs and let them restart their tick if
necessary in case the task they are running is concerned by the
new timer.

This kick is implemented by way of IPIs, which require interrupts
to be enabled, hence the need for a workqueue to raise them because
the posix cpu timer set path has interrupts disabled.

Now if there is no full dynticks CPU on the system, the workqueue is
still scheduled but it simply won't send any IPI and return immediately.

So lets spare that worqueue when it is not needed.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>

diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index c7f31aa..35509c5 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -608,7 +608,8 @@ static DECLARE_WORK(nohz_kick_work, nohz_kick_work_fn);
  */
 static void posix_cpu_timer_kick_nohz(void)
 {
-	schedule_work(&nohz_kick_work);
+	if (context_tracking_is_enabled())
+		schedule_work(&nohz_kick_work);
 }
 
 bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk)
-- 
cgit v0.10.2


From c925077c33fc9a546e7cf6c3be2adf4a2afe2608 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Wed, 6 Nov 2013 17:18:30 +0100
Subject: posix-timers: Fix full dynticks CPUs kick on timer rescheduling

A posix CPU timer can be rearmed while it is firing or after it is
notified with a signal. This can happen for example with timers that
were set with a non zero interval in timer_settime().

This rearming can happen in two places:

1) On timer firing time, which happens on the target's tick. If the timer
can't trigger a signal because it is ignored, it reschedules itself
to honour the timer interval.

2) On signal handling from the timer's notification target. This one
can be a different task than the timer's target itself. Once the
signal is notified, the notification target rearms the timer, again
to honour the timer interval.

When a timer is rearmed, we need to notify the full dynticks CPUs
such that they restart their tick in case they are running tasks that
may have a share in elapsing this timer.

Now the 1st case above handles full dynticks CPUs with a call to
posix_cpu_timer_kick_nohz() from the posix cpu timer firing code. But
the second case ignores the fact that some CPUs may run non-idle tasks
with their tick off. As a result, when a timer is resheduled after its signal
notification, the full dynticks CPUs may completely ignore it and not
tick on the timer as expected

This patch fixes this bug by handling both cases in one. All we need
is to move the kick to the rearming common code in posix_cpu_timer_schedule().

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Olivier Langlois <olivier@olivierlanglois.net>

diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 35509c5..79747b7 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -1091,7 +1091,8 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 			put_task_struct(p);
 			timer->it.cpu.task = p = NULL;
 			timer->it.cpu.expires = 0;
-			goto out_unlock;
+			read_unlock(&tasklist_lock);
+			goto out;
 		} else if (unlikely(p->exit_state) && thread_group_empty(p)) {
 			/*
 			 * We've noticed that the thread is dead, but
@@ -1100,7 +1101,8 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 			 */
 			cpu_timer_sample_group(timer->it_clock, p, &now);
 			clear_dead_task(timer, now);
-			goto out_unlock;
+			read_unlock(&tasklist_lock);
+			goto out;
 		}
 		spin_lock(&p->sighand->siglock);
 		cpu_timer_sample_group(timer->it_clock, p, &now);
@@ -1114,10 +1116,11 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 	BUG_ON(!irqs_disabled());
 	arm_timer(timer);
 	spin_unlock(&p->sighand->siglock);
-
-out_unlock:
 	read_unlock(&tasklist_lock);
 
+	/* Kick full dynticks CPUs in case they need to tick on the new timer */
+	posix_cpu_timer_kick_nohz();
+
 out:
 	timer->it_overrun_last = timer->it_overrun;
 	timer->it_overrun = -1;
@@ -1257,13 +1260,6 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 			cpu_timer_fire(timer);
 		spin_unlock(&timer->it_lock);
 	}
-
-	/*
-	 * In case some timers were rescheduled after the queue got emptied,
-	 * wake up full dynticks CPUs.
-	 */
-	if (tsk->signal->cputimer.running)
-		posix_cpu_timer_kick_nohz();
 }
 
 /*
-- 
cgit v0.10.2


From 1de425c7b271220df5c1bd28e45ca97ca3f4dae8 Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <tkhai@yandex.ru>
Date: Tue, 3 Dec 2013 20:12:37 +0400
Subject: sparc64: Fix build regression

This patch fixes build error which was introduced by commit

812cb83a56a908729c453a7db3fb2c262119bc9d (Implement HAVE_CONTEXT_TRACKING).

[*]https://lkml.org/lkml/2013/11/23/103

Signed-off-by: Kirill Tkhai <tkhai@yandex.ru>
CC: David Miller <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/arch/sparc/kernel/kgdb_64.c b/arch/sparc/kernel/kgdb_64.c
index 60b19f5..b45fe3f 100644
--- a/arch/sparc/kernel/kgdb_64.c
+++ b/arch/sparc/kernel/kgdb_64.c
@@ -6,6 +6,7 @@
 #include <linux/kgdb.h>
 #include <linux/kdebug.h>
 #include <linux/ftrace.h>
+#include <linux/context_tracking.h>
 
 #include <asm/cacheflush.h>
 #include <asm/kdebug.h>
-- 
cgit v0.10.2


From 5a5d8e4844987b6d8d64d583eb33dd926973a270 Mon Sep 17 00:00:00 2001
From: Satoru Takeuchi <satoru.takeuchi@gmail.com>
Date: Sun, 1 Dec 2013 07:57:58 +0900
Subject: ktest: Make the signal to terminate the console configurable

 Currently ktest sends SIGINT to terminate the console.
 However, there are consoles which do not exit by this signal, for example,
 in my case, "virsh console <guest OS>". In such case, ktest is blocked in
 close_console(). It prevents this automate test.

This patch adds new option CLOSE_CONSOLE_SIGNAL which mean the
signal to terminate the console. Since its default value is "INT",
the original behavior isn't changed.

Link: http://lkml.kernel.org/r/87zjol8pl5.wl%satoru.takeuchi@gmail.com

Signed-off-by: Satoru Takeuchi <satoru.takeuchi@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 0d7fd8b..5dc5704 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -25,6 +25,7 @@ my %default = (
     "TEST_TYPE"			=> "build",
     "BUILD_TYPE"		=> "randconfig",
     "MAKE_CMD"			=> "make",
+    "CLOSE_CONSOLE_SIGNAL"	=> "INT",
     "TIMEOUT"			=> 120,
     "TMP_DIR"			=> "/tmp/ktest/\${MACHINE}",
     "SLEEP_TIME"		=> 60,	# sleep time between tests
@@ -163,6 +164,7 @@ my $timeout;
 my $booted_timeout;
 my $detect_triplefault;
 my $console;
+my $close_console_signal;
 my $reboot_success_line;
 my $success_line;
 my $stop_after_success;
@@ -285,6 +287,7 @@ my %option_map = (
     "TIMEOUT"			=> \$timeout,
     "BOOTED_TIMEOUT"		=> \$booted_timeout,
     "CONSOLE"			=> \$console,
+    "CLOSE_CONSOLE_SIGNAL"	=> \$close_console_signal,
     "DETECT_TRIPLE_FAULT"	=> \$detect_triplefault,
     "SUCCESS_LINE"		=> \$success_line,
     "REBOOT_SUCCESS_LINE"	=> \$reboot_success_line,
@@ -1296,7 +1299,7 @@ sub close_console {
     my ($fp, $pid) = @_;
 
     doprint "kill child process $pid\n";
-    kill 2, $pid;
+    kill $close_console_signal, $pid;
 
     print "closing!\n";
     close($fp);
-- 
cgit v0.10.2


From 298a0d1d575026edec7fbb9b7e8cbb8fe18498cd Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Tue, 3 Dec 2013 11:57:23 -0500
Subject: ktest: Add documentation of CLOSE_CONSOLE_SIGNAL

The sample.conf file needs to document all available options.
With the new CLOSE_CONSOE_SIGNAL option, it too needs to be
document.

Cc: Satoru Takeuchi <satoru.takeuchi@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

diff --git a/tools/testing/ktest/sample.conf b/tools/testing/ktest/sample.conf
index 0a290fb..2eb4bd2 100644
--- a/tools/testing/ktest/sample.conf
+++ b/tools/testing/ktest/sample.conf
@@ -328,6 +328,13 @@
 # For a virtual machine with guest name "Guest".
 #CONSOLE =  virsh console Guest
 
+# Signal to send to kill console.
+# ktest.pl will create a child process to monitor the console.
+# When the console is finished, ktest will kill the child process
+# with this signal.
+# (default INT)
+#CLOSE_CONSOLE_SIGNAL = HUP
+
 # Required version ending to differentiate the test
 # from other linux builds on the system.
 #LOCALVERSION = -test
-- 
cgit v0.10.2


From c9592ecb98d1e6d6ab2b54895314a46abfa69db4 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 9 Oct 2013 14:34:00 -0700
Subject: rcu: Fix typo in Documentation/RCU/trace.txt

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index f3778f8..7f5c57d 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -443,7 +443,7 @@ The output of "cat rcu/rcuboost" looks as follows:
     balk: nt=0 egt=6541 bt=0 nb=0 ny=126 nos=0
 
 This information is output only for rcu_preempt.  Each two-line entry
-corresponds to a leaf rcu_node strcuture.  The fields are as follows:
+corresponds to a leaf rcu_node structure.  The fields are as follows:
 
 o	"n:m" is the CPU-number range for the corresponding two-line
 	entry.  In the sample output above, the first entry covers
-- 
cgit v0.10.2


From 97e63f0caf0e977a1648b50943909c87a3f683d3 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sun, 27 Oct 2013 09:44:03 -0700
Subject: rcu: Fix formatting blows in kernel-parameters.txt

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 50680a5..9063e74 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2625,7 +2625,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			for RCU-preempt, and "s" for RCU-sched, and "N"
 			is the CPU number.  This reduces OS jitter on the
 			offloaded CPUs, which can be useful for HPC and
-
 			real-time workloads.  It can also improve energy
 			efficiency for asymmetric multiprocessors.
 
@@ -2641,8 +2640,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			periodically wake up to do the polling.
 
 	rcutree.blimit=	[KNL]
-			Set maximum number of finished RCU callbacks to process
-			in one batch.
+			Set maximum number of finished RCU callbacks to
+			process in one batch.
 
 	rcutree.rcu_fanout_leaf= [KNL]
 			Increase the number of CPUs assigned to each
@@ -2661,8 +2660,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			value is one, and maximum value is HZ.
 
 	rcutree.qhimark= [KNL]
-			Set threshold of queued
-			RCU callbacks over which batch limiting is disabled.
+			Set threshold of queued RCU callbacks beyond which
+			batch limiting is disabled.
 
 	rcutree.qlowmark= [KNL]
 			Set threshold of queued RCU callbacks below which
-- 
cgit v0.10.2


From 9873552fc1b01ef9bddc9fec4c492d9fa8b27f51 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sat, 2 Nov 2013 10:17:52 -0700
Subject: documentation: Fix circular-buffer example.

The code sample in Documentation/circular-buffers.txt appears to have a
few ordering bugs.  This patch therefore applies the needed fixes.

Reported-by: Lech Fomicki <lfomicki@poczta.fm>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/Documentation/circular-buffers.txt b/Documentation/circular-buffers.txt
index 8117e5b..a36bed3 100644
--- a/Documentation/circular-buffers.txt
+++ b/Documentation/circular-buffers.txt
@@ -170,7 +170,7 @@ The producer will look something like this:
 
 		smp_wmb(); /* commit the item before incrementing the head */
 
-		buffer->head = (head + 1) & (buffer->size - 1);
+		ACCESS_ONCE(buffer->head) = (head + 1) & (buffer->size - 1);
 
 		/* wake_up() will make sure that the head is committed before
 		 * waking anyone up */
@@ -183,9 +183,14 @@ This will instruct the CPU that the contents of the new item must be written
 before the head index makes it available to the consumer and then instructs the
 CPU that the revised head index must be written before the consumer is woken.
 
-Note that wake_up() doesn't have to be the exact mechanism used, but whatever
-is used must guarantee a (write) memory barrier between the update of the head
-index and the change of state of the consumer, if a change of state occurs.
+Note that wake_up() does not guarantee any sort of barrier unless something
+is actually awakened.  We therefore cannot rely on it for ordering.  However,
+there is always one element of the array left empty.  Therefore, the
+producer must produce two elements before it could possibly corrupt the
+element currently being read by the consumer.  Therefore, the unlock-lock
+pair between consecutive invocations of the consumer provides the necessary
+ordering between the read of the index indicating that the consumer has
+vacated a given element and the write by the producer to that same element.
 
 
 THE CONSUMER
@@ -200,7 +205,7 @@ The consumer will look something like this:
 
 	if (CIRC_CNT(head, tail, buffer->size) >= 1) {
 		/* read index before reading contents at that index */
-		smp_read_barrier_depends();
+		smp_rmb();
 
 		/* extract one item from the buffer */
 		struct item *item = buffer[tail];
@@ -209,7 +214,7 @@ The consumer will look something like this:
 
 		smp_mb(); /* finish reading descriptor before incrementing tail */
 
-		buffer->tail = (tail + 1) & (buffer->size - 1);
+		ACCESS_ONCE(buffer->tail) = (tail + 1) & (buffer->size - 1);
 	}
 
 	spin_unlock(&consumer_lock);
@@ -223,7 +228,10 @@ Note the use of ACCESS_ONCE() in both algorithms to read the opposition index.
 This prevents the compiler from discarding and reloading its cached value -
 which some compilers will do across smp_read_barrier_depends().  This isn't
 strictly needed if you can be sure that the opposition index will _only_ be
-used the once.
+used the once.  Similarly, ACCESS_ONCE() is used in both algorithms to
+write the thread's index.  This documents the fact that we are writing
+to something that can be read concurrently and also prevents the compiler
+from tearing the store.
 
 
 ===============
-- 
cgit v0.10.2


From 6c43c091bdc56b8cab888cfa6b0ee9effb5fc255 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 4 Nov 2013 11:20:56 -0800
Subject: documentation: Update circular buffer for load-acquire/store-release

This commit replaces full barriers by targeted use of load-acquire and
store-release.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Restore comments as suggested by David Howells. ]

diff --git a/Documentation/circular-buffers.txt b/Documentation/circular-buffers.txt
index a36bed3..88951b1 100644
--- a/Documentation/circular-buffers.txt
+++ b/Documentation/circular-buffers.txt
@@ -160,6 +160,7 @@ The producer will look something like this:
 	spin_lock(&producer_lock);
 
 	unsigned long head = buffer->head;
+	/* The spin_unlock() and next spin_lock() provide needed ordering. */
 	unsigned long tail = ACCESS_ONCE(buffer->tail);
 
 	if (CIRC_SPACE(head, tail, buffer->size) >= 1) {
@@ -168,9 +169,8 @@ The producer will look something like this:
 
 		produce_item(item);
 
-		smp_wmb(); /* commit the item before incrementing the head */
-
-		ACCESS_ONCE(buffer->head) = (head + 1) & (buffer->size - 1);
+		smp_store_release(buffer->head,
+				  (head + 1) & (buffer->size - 1));
 
 		/* wake_up() will make sure that the head is committed before
 		 * waking anyone up */
@@ -200,21 +200,20 @@ The consumer will look something like this:
 
 	spin_lock(&consumer_lock);
 
-	unsigned long head = ACCESS_ONCE(buffer->head);
+	/* Read index before reading contents at that index. */
+	unsigned long head = smp_load_acquire(buffer->head);
 	unsigned long tail = buffer->tail;
 
 	if (CIRC_CNT(head, tail, buffer->size) >= 1) {
-		/* read index before reading contents at that index */
-		smp_rmb();
 
 		/* extract one item from the buffer */
 		struct item *item = buffer[tail];
 
 		consume_item(item);
 
-		smp_mb(); /* finish reading descriptor before incrementing tail */
-
-		ACCESS_ONCE(buffer->tail) = (tail + 1) & (buffer->size - 1);
+		/* Finish reading descriptor before incrementing tail. */
+		smp_store_release(buffer->tail,
+				  (tail + 1) & (buffer->size - 1));
 	}
 
 	spin_unlock(&consumer_lock);
@@ -223,15 +222,17 @@ This will instruct the CPU to make sure the index is up to date before reading
 the new item, and then it shall make sure the CPU has finished reading the item
 before it writes the new tail pointer, which will erase the item.
 
-
-Note the use of ACCESS_ONCE() in both algorithms to read the opposition index.
-This prevents the compiler from discarding and reloading its cached value -
-which some compilers will do across smp_read_barrier_depends().  This isn't
-strictly needed if you can be sure that the opposition index will _only_ be
-used the once.  Similarly, ACCESS_ONCE() is used in both algorithms to
-write the thread's index.  This documents the fact that we are writing
-to something that can be read concurrently and also prevents the compiler
-from tearing the store.
+Note the use of ACCESS_ONCE() and smp_load_acquire() to read the
+opposition index.  This prevents the compiler from discarding and
+reloading its cached value - which some compilers will do across
+smp_read_barrier_depends().  This isn't strictly needed if you can
+be sure that the opposition index will _only_ be used the once.
+The smp_load_acquire() additionally forces the CPU to order against
+subsequent memory references.  Similarly, smp_store_release() is used
+in both algorithms to write the thread's index.  This documents the
+fact that we are writing to something that can be read concurrently,
+prevents the compiler from tearing the store, and enforces ordering
+against previous accesses.
 
 
 ===============
-- 
cgit v0.10.2


From 6193c76aba8ec3cc5f083c35efbab9ed924125f6 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 23 Sep 2013 13:57:18 -0700
Subject: rcu: Kick CPU halfway to RCU CPU stall warning

When an RCU CPU stall warning occurs, the CPU invokes resched_cpu() on
itself.  This can help move the grace period forward in some situations,
but it would be even better to do this -before- the RCU CPU stall warning.
This commit therefore causes resched_cpu() to be called every five jiffies
once the system is halfway to an RCU CPU stall warning.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index dd08198..5243ebe 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -755,6 +755,12 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp,
 }
 
 /*
+ * This function really isn't for public consumption, but RCU is special in
+ * that context switches can allow the state machine to make progress.
+ */
+extern void resched_cpu(int cpu);
+
+/*
  * Return true if the specified CPU has passed through a quiescent
  * state by virtue of being in or having passed through an dynticks
  * idle state since the last call to dyntick_save_progress_counter()
@@ -812,16 +818,34 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 	 */
 	rcu_kick_nohz_cpu(rdp->cpu);
 
+	/*
+	 * Alternatively, the CPU might be running in the kernel
+	 * for an extended period of time without a quiescent state.
+	 * Attempt to force the CPU through the scheduler to gain the
+	 * needed quiescent state, but only if the grace period has gone
+	 * on for an uncommonly long time.  If there are many stuck CPUs,
+	 * we will beat on the first one until it gets unstuck, then move
+	 * to the next.  Only do this for the primary flavor of RCU.
+	 */
+	if (rdp->rsp == rcu_state &&
+	    ULONG_CMP_GE(ACCESS_ONCE(jiffies), rdp->rsp->jiffies_resched)) {
+		rdp->rsp->jiffies_resched += 5;
+		resched_cpu(rdp->cpu);
+	}
+
 	return 0;
 }
 
 static void record_gp_stall_check_time(struct rcu_state *rsp)
 {
 	unsigned long j = ACCESS_ONCE(jiffies);
+	unsigned long j1;
 
 	rsp->gp_start = j;
 	smp_wmb(); /* Record start time before stall time. */
-	rsp->jiffies_stall = j + rcu_jiffies_till_stall_check();
+	j1 = rcu_jiffies_till_stall_check();
+	rsp->jiffies_stall = j + j1;
+	rsp->jiffies_resched = j + j1 / 2;
 }
 
 /*
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 52be957..8e34d86 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -453,6 +453,8 @@ struct rcu_state {
 						/*  but in jiffies. */
 	unsigned long jiffies_stall;		/* Time at which to check */
 						/*  for CPU stalls. */
+	unsigned long jiffies_resched;		/* Time at which to resched */
+						/*  a reluctant CPU. */
 	unsigned long gp_max;			/* Maximum GP duration in */
 						/*  jiffies. */
 	const char *name;			/* Name of structure. */
-- 
cgit v0.10.2


From 78e4bc34e5d966cfd95f1238565afc399d56225c Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 24 Sep 2013 15:04:06 -0700
Subject: rcu: Fix and comment ordering around wait_event()

It is all too easy to forget that wait_event() does not necessarily
imply a full memory barrier.  The case where it does not is where the
condition transitions to true just as wait_event() starts execution.
This is actually a feature: The standard use of wait_event() involves
locking, in which case the locks provide the needed ordering (you hold a
lock across the wake_up() and acquire that same lock after wait_event()
returns).

Given that I did forget that wait_event() does not necessarily imply a
full memory barrier in one case, this commit fixes that case.  This commit
also adds comments calling out the placement of existing memory barriers
relied on by wait_event() calls.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/kernel/rcu/torture.c b/kernel/rcu/torture.c
index 3929cd4..69a4ec8 100644
--- a/kernel/rcu/torture.c
+++ b/kernel/rcu/torture.c
@@ -1578,6 +1578,7 @@ static int rcu_torture_barrier_cbs(void *arg)
 {
 	long myid = (long)arg;
 	bool lastphase = 0;
+	bool newphase;
 	struct rcu_head rcu;
 
 	init_rcu_head_on_stack(&rcu);
@@ -1585,10 +1586,11 @@ static int rcu_torture_barrier_cbs(void *arg)
 	set_user_nice(current, 19);
 	do {
 		wait_event(barrier_cbs_wq[myid],
-			   barrier_phase != lastphase ||
+			   (newphase =
+			    ACCESS_ONCE(barrier_phase)) != lastphase ||
 			   kthread_should_stop() ||
 			   fullstop != FULLSTOP_DONTSTOP);
-		lastphase = barrier_phase;
+		lastphase = newphase;
 		smp_mb(); /* ensure barrier_phase load before ->call(). */
 		if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
 			break;
@@ -1625,7 +1627,7 @@ static int rcu_torture_barrier(void *arg)
 		if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP)
 			break;
 		n_barrier_attempts++;
-		cur_ops->cb_barrier();
+		cur_ops->cb_barrier(); /* Implies smp_mb() for wait_event(). */
 		if (atomic_read(&barrier_cbs_invoked) != n_barrier_cbs) {
 			n_rcu_torture_barrier_error++;
 			WARN_ON_ONCE(1);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 5243ebe..abef9c3 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1533,6 +1533,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 		rdp = this_cpu_ptr(rsp->rda);
 		if (rnp == rdp->mynode)
 			__note_gp_changes(rsp, rnp, rdp);
+		/* smp_mb() provided by prior unlock-lock pair. */
 		nocb += rcu_future_gp_cleanup(rsp, rnp);
 		raw_spin_unlock_irq(&rnp->lock);
 		cond_resched();
@@ -1577,6 +1578,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			wait_event_interruptible(rsp->gp_wq,
 						 ACCESS_ONCE(rsp->gp_flags) &
 						 RCU_GP_FLAG_INIT);
+			/* Locking provides needed memory barrier. */
 			if (rcu_gp_init(rsp))
 				break;
 			cond_resched();
@@ -1606,6 +1608,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 					(!ACCESS_ONCE(rnp->qsmask) &&
 					 !rcu_preempt_blocked_readers_cgp(rnp)),
 					j);
+			/* Locking provides needed memory barriers. */
 			/* If grace period done, leave loop. */
 			if (!ACCESS_ONCE(rnp->qsmask) &&
 			    !rcu_preempt_blocked_readers_cgp(rnp))
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 6abb03d..b023e54 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -779,8 +779,10 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 		}
 		if (rnp->parent == NULL) {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
-			if (wake)
+			if (wake) {
+				smp_mb(); /* EGP done before wake_up(). */
 				wake_up(&sync_rcu_preempt_exp_wq);
+			}
 			break;
 		}
 		mask = rnp->grpmask;
@@ -1852,6 +1854,7 @@ static int rcu_oom_notify(struct notifier_block *self,
 
 	/* Wait for callbacks from earlier instance to complete. */
 	wait_event(oom_callback_wq, atomic_read(&oom_callback_count) == 0);
+	smp_mb(); /* Ensure callback reuse happens after callback invocation. */
 
 	/*
 	 * Prevent premature wakeup: ensure that all increments happen
@@ -2250,6 +2253,7 @@ static int rcu_nocb_kthread(void *arg)
 			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
 					    TPS("Sleep"));
 			wait_event_interruptible(rdp->nocb_wq, rdp->nocb_head);
+			/* Memory barrier provide by xchg() below. */
 		} else if (firsttime) {
 			firsttime = 0;
 			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
-- 
cgit v0.10.2


From 96d3fd0d315a949e30adc80f086031c5cdf070d1 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 4 Oct 2013 14:33:34 -0700
Subject: rcu: Break call_rcu() deadlock involving scheduler and perf

Dave Jones got the following lockdep splat:

>  ======================================================
>  [ INFO: possible circular locking dependency detected ]
>  3.12.0-rc3+ #92 Not tainted
>  -------------------------------------------------------
>  trinity-child2/15191 is trying to acquire lock:
>   (&rdp->nocb_wq){......}, at: [<ffffffff8108ff43>] __wake_up+0x23/0x50
>
> but task is already holding lock:
>   (&ctx->lock){-.-...}, at: [<ffffffff81154c19>] perf_event_exit_task+0x109/0x230
>
> which lock already depends on the new lock.
>
>
> the existing dependency chain (in reverse order) is:
>
> -> #3 (&ctx->lock){-.-...}:
>         [<ffffffff810cc243>] lock_acquire+0x93/0x200
>         [<ffffffff81733f90>] _raw_spin_lock+0x40/0x80
>         [<ffffffff811500ff>] __perf_event_task_sched_out+0x2df/0x5e0
>         [<ffffffff81091b83>] perf_event_task_sched_out+0x93/0xa0
>         [<ffffffff81732052>] __schedule+0x1d2/0xa20
>         [<ffffffff81732f30>] preempt_schedule_irq+0x50/0xb0
>         [<ffffffff817352b6>] retint_kernel+0x26/0x30
>         [<ffffffff813eed04>] tty_flip_buffer_push+0x34/0x50
>         [<ffffffff813f0504>] pty_write+0x54/0x60
>         [<ffffffff813e900d>] n_tty_write+0x32d/0x4e0
>         [<ffffffff813e5838>] tty_write+0x158/0x2d0
>         [<ffffffff811c4850>] vfs_write+0xc0/0x1f0
>         [<ffffffff811c52cc>] SyS_write+0x4c/0xa0
>         [<ffffffff8173d4e4>] tracesys+0xdd/0xe2
>
> -> #2 (&rq->lock){-.-.-.}:
>         [<ffffffff810cc243>] lock_acquire+0x93/0x200
>         [<ffffffff81733f90>] _raw_spin_lock+0x40/0x80
>         [<ffffffff810980b2>] wake_up_new_task+0xc2/0x2e0
>         [<ffffffff81054336>] do_fork+0x126/0x460
>         [<ffffffff81054696>] kernel_thread+0x26/0x30
>         [<ffffffff8171ff93>] rest_init+0x23/0x140
>         [<ffffffff81ee1e4b>] start_kernel+0x3f6/0x403
>         [<ffffffff81ee1571>] x86_64_start_reservations+0x2a/0x2c
>         [<ffffffff81ee1664>] x86_64_start_kernel+0xf1/0xf4
>
> -> #1 (&p->pi_lock){-.-.-.}:
>         [<ffffffff810cc243>] lock_acquire+0x93/0x200
>         [<ffffffff8173419b>] _raw_spin_lock_irqsave+0x4b/0x90
>         [<ffffffff810979d1>] try_to_wake_up+0x31/0x350
>         [<ffffffff81097d62>] default_wake_function+0x12/0x20
>         [<ffffffff81084af8>] autoremove_wake_function+0x18/0x40
>         [<ffffffff8108ea38>] __wake_up_common+0x58/0x90
>         [<ffffffff8108ff59>] __wake_up+0x39/0x50
>         [<ffffffff8110d4f8>] __call_rcu_nocb_enqueue+0xa8/0xc0
>         [<ffffffff81111450>] __call_rcu+0x140/0x820
>         [<ffffffff81111b8d>] call_rcu+0x1d/0x20
>         [<ffffffff81093697>] cpu_attach_domain+0x287/0x360
>         [<ffffffff81099d7e>] build_sched_domains+0xe5e/0x10a0
>         [<ffffffff81efa7fc>] sched_init_smp+0x3b7/0x47a
>         [<ffffffff81ee1f4e>] kernel_init_freeable+0xf6/0x202
>         [<ffffffff817200be>] kernel_init+0xe/0x190
>         [<ffffffff8173d22c>] ret_from_fork+0x7c/0xb0
>
> -> #0 (&rdp->nocb_wq){......}:
>         [<ffffffff810cb7ca>] __lock_acquire+0x191a/0x1be0
>         [<ffffffff810cc243>] lock_acquire+0x93/0x200
>         [<ffffffff8173419b>] _raw_spin_lock_irqsave+0x4b/0x90
>         [<ffffffff8108ff43>] __wake_up+0x23/0x50
>         [<ffffffff8110d4f8>] __call_rcu_nocb_enqueue+0xa8/0xc0
>         [<ffffffff81111450>] __call_rcu+0x140/0x820
>         [<ffffffff81111bb0>] kfree_call_rcu+0x20/0x30
>         [<ffffffff81149abf>] put_ctx+0x4f/0x70
>         [<ffffffff81154c3e>] perf_event_exit_task+0x12e/0x230
>         [<ffffffff81056b8d>] do_exit+0x30d/0xcc0
>         [<ffffffff8105893c>] do_group_exit+0x4c/0xc0
>         [<ffffffff810589c4>] SyS_exit_group+0x14/0x20
>         [<ffffffff8173d4e4>] tracesys+0xdd/0xe2
>
> other info that might help us debug this:
>
> Chain exists of:
>   &rdp->nocb_wq --> &rq->lock --> &ctx->lock
>
>   Possible unsafe locking scenario:
>
>         CPU0                    CPU1
>         ----                    ----
>    lock(&ctx->lock);
>                                 lock(&rq->lock);
>                                 lock(&ctx->lock);
>    lock(&rdp->nocb_wq);
>
>  *** DEADLOCK ***
>
> 1 lock held by trinity-child2/15191:
>  #0:  (&ctx->lock){-.-...}, at: [<ffffffff81154c19>] perf_event_exit_task+0x109/0x230
>
> stack backtrace:
> CPU: 2 PID: 15191 Comm: trinity-child2 Not tainted 3.12.0-rc3+ #92
>  ffffffff82565b70 ffff880070c2dbf8 ffffffff8172a363 ffffffff824edf40
>  ffff880070c2dc38 ffffffff81726741 ffff880070c2dc90 ffff88022383b1c0
>  ffff88022383aac0 0000000000000000 ffff88022383b188 ffff88022383b1c0
> Call Trace:
>  [<ffffffff8172a363>] dump_stack+0x4e/0x82
>  [<ffffffff81726741>] print_circular_bug+0x200/0x20f
>  [<ffffffff810cb7ca>] __lock_acquire+0x191a/0x1be0
>  [<ffffffff810c6439>] ? get_lock_stats+0x19/0x60
>  [<ffffffff8100b2f4>] ? native_sched_clock+0x24/0x80
>  [<ffffffff810cc243>] lock_acquire+0x93/0x200
>  [<ffffffff8108ff43>] ? __wake_up+0x23/0x50
>  [<ffffffff8173419b>] _raw_spin_lock_irqsave+0x4b/0x90
>  [<ffffffff8108ff43>] ? __wake_up+0x23/0x50
>  [<ffffffff8108ff43>] __wake_up+0x23/0x50
>  [<ffffffff8110d4f8>] __call_rcu_nocb_enqueue+0xa8/0xc0
>  [<ffffffff81111450>] __call_rcu+0x140/0x820
>  [<ffffffff8109bc8f>] ? local_clock+0x3f/0x50
>  [<ffffffff81111bb0>] kfree_call_rcu+0x20/0x30
>  [<ffffffff81149abf>] put_ctx+0x4f/0x70
>  [<ffffffff81154c3e>] perf_event_exit_task+0x12e/0x230
>  [<ffffffff81056b8d>] do_exit+0x30d/0xcc0
>  [<ffffffff810c9af5>] ? trace_hardirqs_on_caller+0x115/0x1e0
>  [<ffffffff810c9bcd>] ? trace_hardirqs_on+0xd/0x10
>  [<ffffffff8105893c>] do_group_exit+0x4c/0xc0
>  [<ffffffff810589c4>] SyS_exit_group+0x14/0x20
>  [<ffffffff8173d4e4>] tracesys+0xdd/0xe2

The underlying problem is that perf is invoking call_rcu() with the
scheduler locks held, but in NOCB mode, call_rcu() will with high
probability invoke the scheduler -- which just might want to use its
locks.  The reason that call_rcu() needs to invoke the scheduler is
to wake up the corresponding rcuo callback-offload kthread, which
does the job of starting up a grace period and invoking the callbacks
afterwards.

One solution (championed on a related problem by Lai Jiangshan) is to
simply defer the wakeup to some point where scheduler locks are no longer
held.  Since we don't want to unnecessarily incur the cost of such
deferral, the task before us is threefold:

1.	Determine when it is likely that a relevant scheduler lock is held.

2.	Defer the wakeup in such cases.

3.	Ensure that all deferred wakeups eventually happen, preferably
	sooner rather than later.

We use irqs_disabled_flags() as a proxy for relevant scheduler locks
being held.  This works because the relevant locks are always acquired
with interrupts disabled.  We may defer more often than needed, but that
is at least safe.

The wakeup deferral is tracked via a new field in the per-CPU and
per-RCU-flavor rcu_data structure, namely ->nocb_defer_wakeup.

This flag is checked by the RCU core processing.  The __rcu_pending()
function now checks this flag, which causes rcu_check_callbacks()
to initiate RCU core processing at each scheduling-clock interrupt
where this flag is set.  Of course this is not sufficient because
scheduling-clock interrupts are often turned off (the things we used to
be able to count on!).  So the flags are also checked on entry to any
state that RCU considers to be idle, which includes both NO_HZ_IDLE idle
state and NO_HZ_FULL user-mode-execution state.

This approach should allow call_rcu() to be invoked regardless of what
locks you might be holding, the key word being "should".

Reported-by: Dave Jones <davej@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>

diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index f3778f8..b8c3c81 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -396,14 +396,14 @@ o	Each element of the form "3/3 ..>. 0:7 ^0" represents one rcu_node
 
 The output of "cat rcu/rcu_sched/rcu_pending" looks as follows:
 
-  0!np=26111 qsp=29 rpq=5386 cbr=1 cng=570 gpc=3674 gps=577 nn=15903
-  1!np=28913 qsp=35 rpq=6097 cbr=1 cng=448 gpc=3700 gps=554 nn=18113
-  2!np=32740 qsp=37 rpq=6202 cbr=0 cng=476 gpc=4627 gps=546 nn=20889
-  3 np=23679 qsp=22 rpq=5044 cbr=1 cng=415 gpc=3403 gps=347 nn=14469
-  4!np=30714 qsp=4 rpq=5574 cbr=0 cng=528 gpc=3931 gps=639 nn=20042
-  5 np=28910 qsp=2 rpq=5246 cbr=0 cng=428 gpc=4105 gps=709 nn=18422
-  6!np=38648 qsp=5 rpq=7076 cbr=0 cng=840 gpc=4072 gps=961 nn=25699
-  7 np=37275 qsp=2 rpq=6873 cbr=0 cng=868 gpc=3416 gps=971 nn=25147
+  0!np=26111 qsp=29 rpq=5386 cbr=1 cng=570 gpc=3674 gps=577 nn=15903 ndw=0
+  1!np=28913 qsp=35 rpq=6097 cbr=1 cng=448 gpc=3700 gps=554 nn=18113 ndw=0
+  2!np=32740 qsp=37 rpq=6202 cbr=0 cng=476 gpc=4627 gps=546 nn=20889 ndw=0
+  3 np=23679 qsp=22 rpq=5044 cbr=1 cng=415 gpc=3403 gps=347 nn=14469 ndw=0
+  4!np=30714 qsp=4 rpq=5574 cbr=0 cng=528 gpc=3931 gps=639 nn=20042 ndw=0
+  5 np=28910 qsp=2 rpq=5246 cbr=0 cng=428 gpc=4105 gps=709 nn=18422 ndw=0
+  6!np=38648 qsp=5 rpq=7076 cbr=0 cng=840 gpc=4072 gps=961 nn=25699 ndw=0
+  7 np=37275 qsp=2 rpq=6873 cbr=0 cng=868 gpc=3416 gps=971 nn=25147 ndw=0
 
 The fields are as follows:
 
@@ -432,6 +432,10 @@ o	"gpc" is the number of times that an old grace period had
 o	"gps" is the number of times that a new grace period had started,
 	but this CPU was not yet aware of it.
 
+o	"ndw" is the number of times that a wakeup of an rcuo
+	callback-offload kthread had to be deferred in order to avoid
+	deadlock.
+
 o	"nn" is the number of times that this CPU needed nothing.
 
 
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index abef9c3..264f028 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -369,6 +369,9 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
 static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
 				bool user)
 {
+	struct rcu_state *rsp;
+	struct rcu_data *rdp;
+
 	trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
 	if (!user && !is_idle_task(current)) {
 		struct task_struct *idle __maybe_unused =
@@ -380,6 +383,10 @@ static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
 			  current->pid, current->comm,
 			  idle->pid, idle->comm); /* must be idle task! */
 	}
+	for_each_rcu_flavor(rsp) {
+		rdp = this_cpu_ptr(rsp->rda);
+		do_nocb_deferred_wakeup(rdp);
+	}
 	rcu_prepare_for_idle(smp_processor_id());
 	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
 	smp_mb__before_atomic_inc();  /* See above. */
@@ -1928,13 +1935,13 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
  * Adopt the RCU callbacks from the specified rcu_state structure's
  * orphanage.  The caller must hold the ->orphan_lock.
  */
-static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
+static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
 {
 	int i;
 	struct rcu_data *rdp = __this_cpu_ptr(rsp->rda);
 
 	/* No-CBs CPUs are handled specially. */
-	if (rcu_nocb_adopt_orphan_cbs(rsp, rdp))
+	if (rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
 		return;
 
 	/* Do the accounting first. */
@@ -2013,7 +2020,7 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 
 	/* Orphan the dead CPU's callbacks, and adopt them if appropriate. */
 	rcu_send_cbs_to_orphanage(cpu, rsp, rnp, rdp);
-	rcu_adopt_orphan_cbs(rsp);
+	rcu_adopt_orphan_cbs(rsp, flags);
 
 	/* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */
 	mask = rdp->grpmask;	/* rnp->grplo is constant. */
@@ -2330,6 +2337,9 @@ __rcu_process_callbacks(struct rcu_state *rsp)
 	/* If there are callbacks ready, invoke them. */
 	if (cpu_has_callbacks_ready_to_invoke(rdp))
 		invoke_rcu_callbacks(rsp, rdp);
+
+	/* Do any needed deferred wakeups of rcuo kthreads. */
+	do_nocb_deferred_wakeup(rdp);
 }
 
 /*
@@ -2464,7 +2474,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 
 		if (cpu != -1)
 			rdp = per_cpu_ptr(rsp->rda, cpu);
-		offline = !__call_rcu_nocb(rdp, head, lazy);
+		offline = !__call_rcu_nocb(rdp, head, lazy, flags);
 		WARN_ON_ONCE(offline);
 		/* _call_rcu() is illegal on offline CPU; leak the callback. */
 		local_irq_restore(flags);
@@ -2817,6 +2827,12 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 		return 1;
 	}
 
+	/* Does this CPU need a deferred NOCB wakeup? */
+	if (rcu_nocb_need_deferred_wakeup(rdp)) {
+		rdp->n_rp_nocb_defer_wakeup++;
+		return 1;
+	}
+
 	/* nothing to do */
 	rdp->n_rp_need_nothing++;
 	return 0;
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 8e34d86..a87adfc 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -317,6 +317,7 @@ struct rcu_data {
 	unsigned long n_rp_cpu_needs_gp;
 	unsigned long n_rp_gp_completed;
 	unsigned long n_rp_gp_started;
+	unsigned long n_rp_nocb_defer_wakeup;
 	unsigned long n_rp_need_nothing;
 
 	/* 6) _rcu_barrier() and OOM callbacks. */
@@ -335,6 +336,7 @@ struct rcu_data {
 	int nocb_p_count_lazy;		/*  (approximate). */
 	wait_queue_head_t nocb_wq;	/* For nocb kthreads to sleep on. */
 	struct task_struct *nocb_kthread;
+	bool nocb_defer_wakeup;		/* Defer wakeup of nocb_kthread. */
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
 	/* 8) RCU CPU stall data. */
@@ -550,9 +552,12 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq);
 static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp);
 static void rcu_init_one_nocb(struct rcu_node *rnp);
 static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
-			    bool lazy);
+			    bool lazy, unsigned long flags);
 static bool rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
-				      struct rcu_data *rdp);
+				      struct rcu_data *rdp,
+				      unsigned long flags);
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp);
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp);
 static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
 static void rcu_spawn_nocb_kthreads(struct rcu_state *rsp);
 static void rcu_kick_nohz_cpu(int cpu);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index b023e54..752ffaa 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2104,7 +2104,8 @@ bool rcu_is_nocb_cpu(int cpu)
 static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 				    struct rcu_head *rhp,
 				    struct rcu_head **rhtp,
-				    int rhcount, int rhcount_lazy)
+				    int rhcount, int rhcount_lazy,
+				    unsigned long flags)
 {
 	int len;
 	struct rcu_head **old_rhpp;
@@ -2125,9 +2126,16 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 	}
 	len = atomic_long_read(&rdp->nocb_q_count);
 	if (old_rhpp == &rdp->nocb_head) {
-		wake_up(&rdp->nocb_wq); /* ... only if queue was empty ... */
+		if (!irqs_disabled_flags(flags)) {
+			wake_up(&rdp->nocb_wq); /* ... if queue was empty ... */
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    TPS("WakeEmpty"));
+		} else {
+			rdp->nocb_defer_wakeup = true;
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    TPS("WakeEmptyIsDeferred"));
+		}
 		rdp->qlen_last_fqs_check = 0;
-		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeEmpty"));
 	} else if (len > rdp->qlen_last_fqs_check + qhimark) {
 		wake_up_process(t); /* ... or if many callbacks queued. */
 		rdp->qlen_last_fqs_check = LONG_MAX / 2;
@@ -2148,12 +2156,12 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
  * "rcuo" kthread can find it.
  */
 static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
-			    bool lazy)
+			    bool lazy, unsigned long flags)
 {
 
 	if (!rcu_is_nocb_cpu(rdp->cpu))
 		return 0;
-	__call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy);
+	__call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy, flags);
 	if (__is_kfree_rcu_offset((unsigned long)rhp->func))
 		trace_rcu_kfree_callback(rdp->rsp->name, rhp,
 					 (unsigned long)rhp->func,
@@ -2171,7 +2179,8 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
  * not a no-CBs CPU.
  */
 static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
-						     struct rcu_data *rdp)
+						     struct rcu_data *rdp,
+						     unsigned long flags)
 {
 	long ql = rsp->qlen;
 	long qll = rsp->qlen_lazy;
@@ -2185,14 +2194,14 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
 	/* First, enqueue the donelist, if any.  This preserves CB ordering. */
 	if (rsp->orphan_donelist != NULL) {
 		__call_rcu_nocb_enqueue(rdp, rsp->orphan_donelist,
-					rsp->orphan_donetail, ql, qll);
+					rsp->orphan_donetail, ql, qll, flags);
 		ql = qll = 0;
 		rsp->orphan_donelist = NULL;
 		rsp->orphan_donetail = &rsp->orphan_donelist;
 	}
 	if (rsp->orphan_nxtlist != NULL) {
 		__call_rcu_nocb_enqueue(rdp, rsp->orphan_nxtlist,
-					rsp->orphan_nxttail, ql, qll);
+					rsp->orphan_nxttail, ql, qll, flags);
 		ql = qll = 0;
 		rsp->orphan_nxtlist = NULL;
 		rsp->orphan_nxttail = &rsp->orphan_nxtlist;
@@ -2314,6 +2323,22 @@ static int rcu_nocb_kthread(void *arg)
 	return 0;
 }
 
+/* Is a deferred wakeup of rcu_nocb_kthread() required? */
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+{
+	return ACCESS_ONCE(rdp->nocb_defer_wakeup);
+}
+
+/* Do a deferred wakeup of rcu_nocb_kthread(). */
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+{
+	if (!rcu_nocb_need_deferred_wakeup(rdp))
+		return;
+	ACCESS_ONCE(rdp->nocb_defer_wakeup) = false;
+	wake_up(&rdp->nocb_wq);
+	trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWakeEmpty"));
+}
+
 /* Initialize per-rcu_data variables for no-CBs CPUs. */
 static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 {
@@ -2369,13 +2394,14 @@ static void rcu_init_one_nocb(struct rcu_node *rnp)
 }
 
 static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
-			    bool lazy)
+			    bool lazy, unsigned long flags)
 {
 	return 0;
 }
 
 static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_state *rsp,
-						     struct rcu_data *rdp)
+						     struct rcu_data *rdp,
+						     unsigned long flags)
 {
 	return 0;
 }
@@ -2384,6 +2410,15 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 {
 }
 
+static bool rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
+{
+	return false;
+}
+
+static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
+{
+}
+
 static void __init rcu_spawn_nocb_kthreads(struct rcu_state *rsp)
 {
 }
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index 3596797..4def475 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -364,9 +364,10 @@ static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->n_rp_report_qs,
 		   rdp->n_rp_cb_ready,
 		   rdp->n_rp_cpu_needs_gp);
-	seq_printf(m, "gpc=%ld gps=%ld nn=%ld\n",
+	seq_printf(m, "gpc=%ld gps=%ld nn=%ld ndw%ld\n",
 		   rdp->n_rp_gp_completed,
 		   rdp->n_rp_gp_started,
+		   rdp->n_rp_nocb_defer_wakeup,
 		   rdp->n_rp_need_nothing);
 }
 
-- 
cgit v0.10.2


From 3a5924052aec266f1035f2ff610b60b7d10dbe7f Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 4 Oct 2013 18:48:55 -0700
Subject: rcu: Allow task-level idle entry/exit nesting

The current task-level idle entry/exit code forces an entry/exit on
each call, regardless of the nesting level.  This commit therefore
properly accounts for nesting.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Frederic Weisbecker <fweisbec@gmail.com>

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 264f028..518e084 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -418,11 +418,12 @@ static void rcu_eqs_enter(bool user)
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
-	if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
+	if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
 		rdtp->dynticks_nesting = 0;
-	else
+		rcu_eqs_enter_common(rdtp, oldval, user);
+	} else {
 		rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE;
-	rcu_eqs_enter_common(rdtp, oldval, user);
+	}
 }
 
 /**
@@ -540,11 +541,12 @@ static void rcu_eqs_exit(bool user)
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	WARN_ON_ONCE(oldval < 0);
-	if (oldval & DYNTICK_TASK_NEST_MASK)
+	if (oldval & DYNTICK_TASK_NEST_MASK) {
 		rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
-	else
+	} else {
 		rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
-	rcu_eqs_exit_common(rdtp, oldval, user);
+		rcu_eqs_exit_common(rdtp, oldval, user);
+	}
 }
 
 /**
-- 
cgit v0.10.2


From 4461212aa0c604c5214856f0ae10a2b335f7e73a Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 9 Oct 2013 08:09:29 -0700
Subject: rcu: Fix srcu_barrier() docbook header

The srcu_barrier() docbook header left out the "sp" argument, so this
commit adds that argument's docbook text.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index 01d5ccb..0f0c631 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -491,6 +491,7 @@ EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
 
 /**
  * srcu_barrier - Wait until all in-flight call_srcu() callbacks complete.
+ * @sp: srcu_struct on which to wait for in-flight callbacks.
  */
 void srcu_barrier(struct srcu_struct *sp)
 {
-- 
cgit v0.10.2


From 3947909814f38d524829bc41bd4c11068a15f0cd Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 9 Oct 2013 15:20:33 -0700
Subject: rcu: Let the world know when RCU adjusts its geometry

Some RCU bugs have been specific to the layout of the rcu_node tree,
but RCU will silently adjust the tree at boot time if appropriate.
This obscures valuable debugging information, so print a message when
this happens.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 518e084..3049950 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3391,6 +3391,8 @@ static void __init rcu_init_geometry(void)
 	if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF &&
 	    nr_cpu_ids == NR_CPUS)
 		return;
+	pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%d\n",
+		rcu_fanout_leaf, nr_cpu_ids);
 
 	/*
 	 * Compute number of nodes that can be handled an rcu_node tree
-- 
cgit v0.10.2


From c87b9c601ac862b1fa41a9d759a3c05711a8391d Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sat, 28 Sep 2013 14:12:21 -0700
Subject: rcutorture: Add KVM-based test framework

This commit adds the test framework that I used to test RCU under KVM.
This consists of a group of scripts and Kconfig fragments.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/MAINTAINERS b/MAINTAINERS
index f216db8..a0a7c4a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7033,6 +7033,12 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
 F:	Documentation/RCU/torture.txt
 F:	kernel/rcu/torture.c
 
+RCUTORTURE TEST FRAMEWORK
+M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
+S:	Supported
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+F:	tools/testing/selftests/rcutorture
+
 RDC R-321X SoC
 M:	Florian Fainelli <florian@openwrt.org>
 S:	Maintained
diff --git a/tools/testing/selftests/rcutorture/.gitignore b/tools/testing/selftests/rcutorture/.gitignore
new file mode 100644
index 0000000..05838f6
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/.gitignore
@@ -0,0 +1,6 @@
+initrd
+linux-2.6
+b[0-9]*
+rcu-test-image
+res
+*.swp
diff --git a/tools/testing/selftests/rcutorture/bin/config2frag.sh b/tools/testing/selftests/rcutorture/bin/config2frag.sh
new file mode 100644
index 0000000..252f769
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/config2frag.sh
@@ -0,0 +1,25 @@
+#!/bin/sh
+# Usage: sh config2frag.sh < .config > configfrag
+#
+# Converts the "# CONFIG_XXX is not set" to "CONFIG_XXX=n" so that the
+# resulting file becomes a legitimate Kconfig fragment.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+#
+# Copyright (C) IBM Corporation, 2013
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+LANG=C sed -e 's/^# CONFIG_\([a-zA-Z0-9_]*\) is not set$/CONFIG_\1=n/'
diff --git a/tools/testing/selftests/rcutorture/bin/configNR_CPUS.sh b/tools/testing/selftests/rcutorture/bin/configNR_CPUS.sh
new file mode 100755
index 0000000..9e8b112
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/configNR_CPUS.sh
@@ -0,0 +1,45 @@
+#!/bin/bash
+#
+# Extract the number of CPUs expected from the specified Kconfig-file
+# fragment by checking CONFIG_SMP and CONFIG_NR_CPUS.  If the specified
+# file gives no clue, base the number on the number of idle CPUs on
+# the system.
+#
+# Usage: configNR_CPUS.sh config-frag
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+#
+# Copyright (C) IBM Corporation, 2013
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+cf=$1
+if test ! -r $cf
+then
+	echo Unreadable config fragment $cf 1>&2
+	exit -1
+fi
+if grep -q '^CONFIG_SMP=n$' $cf
+then
+	echo 1
+	exit 0
+fi
+if grep -q '^CONFIG_NR_CPUS=' $cf
+then
+	grep '^CONFIG_NR_CPUS=' $cf | 
+		sed -e 's/^CONFIG_NR_CPUS=\([0-9]*\).*$/\1/'
+	exit 0
+fi
+cpus2use.sh
diff --git a/tools/testing/selftests/rcutorture/bin/configcheck.sh b/tools/testing/selftests/rcutorture/bin/configcheck.sh
new file mode 100755
index 0000000..a3e5b92
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/configcheck.sh
@@ -0,0 +1,54 @@
+#!/bin/sh
+# Usage: sh configcheck.sh .config .config-template
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+#
+# Copyright (C) IBM Corporation, 2011
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+T=/tmp/abat-chk-config.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
+
+cat $1 > $T/.config
+
+cat $2 | sed -e 's/\(.*\)=n/# \1 is not set/' -e 's/^#CHECK#//' |
+awk	'
+BEGIN	{
+		print "if grep -q \"" $0 "\" < '"$T/.config"'";
+		print "then";
+		print "\t:";
+		print "else";
+		if ($1 == "#") {
+			print "\tif grep -q \"" $2 "\" < '"$T/.config"'";
+			print "\tthen";
+			print "\t\tif test \"$firsttime\" = \"\""
+			print "\t\tthen"
+			print "\t\t\tfirsttime=1"
+			print "\t\tfi"
+			print "\t\techo \":" $2 ": improperly set\"";
+			print "\telse";
+			print "\t\t:";
+			print "\tfi";
+		} else {
+			print "\tif test \"$firsttime\" = \"\""
+			print "\tthen"
+			print "\t\tfirsttime=1"
+			print "\tfi"
+			print "\techo \":" $0 ": improperly set\"";
+		}
+		print "fi";
+	}' | sh
diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh
new file mode 100755
index 0000000..1f09d59
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/configinit.sh
@@ -0,0 +1,83 @@
+#!/bin/sh
+#
+# sh configinit.sh config-spec-file [ build output dir ]
+#
+# Create a .config file from the spec file.  Run from the kernel source tree.
+# Exits with 0 if all went well, with 1 if all went well but the config
+# did not match, and some other number for other failures.
+#
+# The first argument is the .config specification file, which contains
+# desired settings, for example, "CONFIG_NO_HZ=y".  For best results,
+# this should be a full pathname.
+#
+# The second argument is a optional path to a build output directory,
+# for example, "O=/tmp/foo".  If this argument is omitted, the .config
+# file will be generated directly in the current directory.
+
+echo configinit.sh $*
+
+T=/tmp/configinit.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
+
+# Capture config spec file.
+
+c=$1
+buildloc=$2
+builddir=
+if test -n $buildloc
+then
+	if echo $buildloc | grep -q '^O='
+	then
+		builddir=`echo $buildloc | sed -e 's/^O=//'`
+		if test ! -d $builddir
+		then
+			mkdir $builddir
+		fi
+	else
+		echo Bad build directory: \"$builddir\"
+		exit 2
+	fi
+fi
+
+sed -e 's/^\(CONFIG[0-9A-Z_]*\)=.*$/grep -v "^# \1" |/' < $c > $T/u.sh
+sed -e 's/^\(CONFIG[0-9A-Z_]*=\).*$/grep -v \1 |/' < $c >> $T/u.sh
+grep '^grep' < $T/u.sh > $T/upd.sh
+echo "cat - $c" >> $T/upd.sh
+make mrproper
+make $buildloc distclean > $builddir/Make.distclean 2>&1
+make $buildloc defconfig > $builddir/Make.defconfig.out 2>&1
+mv $builddir/.config $builddir/.config.sav
+sh $T/upd.sh < $builddir/.config.sav > $builddir/.config
+cp $builddir/.config $builddir/.config.new
+yes '' | make $buildloc oldconfig > $builddir/Make.modconfig.out 2>&1
+
+# verify new config matches specification.
+
+sed -e 's/"//g' < $c > $T/c
+sed -e 's/"//g' < $builddir/.config > $T/.config
+sed -e 's/\(.*\)=n/# \1 is not set/' -e 's/^#CHECK#//' < $c |
+awk	'
+	{
+		print "if grep -q \"" $0 "\" < '"$T/.config"'";
+		print "then";
+		print "\t:";
+		print "else";
+		if ($1 == "#") {
+			print "\tif grep -q \"" $2 "\" < '"$T/.config"'";
+			print "\tthen";
+			print "\t\techo \":" $2 ": improperly set\"";
+			print "\telse";
+			print "\t\t:";
+			print "\tfi";
+		} else {
+			print "\techo \":" $0 ": improperly set\"";
+		}
+		print "fi";
+	}' | sh > $T/diagnostics
+if test -s $T/diagnostics
+then
+	cat $T/diagnostics
+	exit 1
+fi
+exit 0
diff --git a/tools/testing/selftests/rcutorture/bin/cpus2use.sh b/tools/testing/selftests/rcutorture/bin/cpus2use.sh
new file mode 100755
index 0000000..277a3f6
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/cpus2use.sh
@@ -0,0 +1,41 @@
+#!/bin/bash
+#
+# Get an estimate of how CPU-hoggy to be.
+#
+# Usage: cpus2use.sh
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+#
+# Copyright (C) IBM Corporation, 2013
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+ncpus=`grep '^processor' /proc/cpuinfo | wc -l`
+idlecpus=`mpstat | tail -1 | \
+	awk -v ncpus=$ncpus '{ print ncpus * ($7 + $12) / 100 }'`
+awk -v ncpus=$ncpus -v idlecpus=$idlecpus < /dev/null '
+BEGIN {
+	cpus2use = idlecpus;
+	if (cpus2use < 1)
+		cpus2use = 1;
+	if (cpus2use < ncpus / 10)
+		cpus2use = ncpus / 10;
+	if (cpus2use == int(cpus2use))
+		cpus2use = int(cpus2use)
+	else
+		cpus2use = int(cpus2use) + 1
+	print cpus2use;
+}'
+
diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
new file mode 100644
index 0000000..db1c32a
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -0,0 +1,42 @@
+#!/bin/bash
+#
+# Shell functions for the rest of the scripts.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+#
+# Copyright (C) IBM Corporation, 2013
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+# bootparam_hotplug_cpu bootparam-string
+#
+# Returns 1 if the specified boot-parameter string tells rcutorture to
+# test CPU-hotplug operations.
+bootparam_hotplug_cpu () {
+	echo "$1" | grep -q "rcutorture\.onoff_"
+}
+
+# configfrag_hotplug_cpu config-fragment-file
+#
+# Returns 1 if the config fragment specifies hotplug CPU.
+configfrag_hotplug_cpu () {
+	cf=$1
+	if test ! -r $cf
+	then
+		echo Unreadable config fragment $cf 1>&2
+		exit -1
+	fi
+	grep -q '^CONFIG_HOTPLUG_CPU=y$' $cf
+}
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
new file mode 100755
index 0000000..07bbecc
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
@@ -0,0 +1,71 @@
+#!/bin/bash
+#
+# Build a kvm-ready Linux kernel from the tree in the current directory.
+#
+# Usage: sh kvm-build.sh config-template build-dir more-configs
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+#
+# Copyright (C) IBM Corporation, 2011
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+config_template=${1}
+if test -z "$config_template" -o ! -f "$config_template" -o ! -r "$config_template"
+then
+	echo "kvm-build.sh :$config_template: Not a readable file"
+	exit 1
+fi
+builddir=${2}
+if test -z "$builddir" -o ! -d "$builddir" -o ! -w "$builddir"
+then
+	echo "kvm-build.sh :$builddir: Not a writable directory, cannot build into it"
+	exit 1
+fi
+moreconfigs=${3}
+if test -z "$moreconfigs" -o ! -r "$moreconfigs"
+then
+	echo "kvm-build.sh :$moreconfigs: Not a readable file"
+	exit 1
+fi
+
+T=/tmp/test-linux.sh.$$
+trap 'rm -rf $T' 0
+mkdir $T
+
+cat ${config_template} | grep -v CONFIG_RCU_TORTURE_TEST > $T/config
+cat << ___EOF___ >> $T/config
+CONFIG_INITRAMFS_SOURCE="$KVM/initrd"
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_CONSOLE=y
+___EOF___
+cat $moreconfigs >> $T/config
+
+configinit.sh $T/config O=$builddir
+retval=$?
+if test $retval -gt 1
+then
+	exit 2
+fi
+ncpus=`cpus2use.sh`
+make O=$builddir -j$ncpus > $builddir/Make.out 2>&1
+retval=$?
+if test $retval -ne 0 || grep "rcu[^/]*": < $builddir/Make.out | egrep -q "Stop|Error|error:|warning:" || egrep -q "Stop|Error|error:" < $builddir/Make.out
+then
+	echo Kernel build error
+	egrep "Stop|Error|error:|warning:" < $builddir/Make.out
+	echo Run aborted.
+	exit 3
+fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
new file mode 100755
index 0000000..0876af7
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -0,0 +1,46 @@
+#!/bin/bash
+#
+# Given the results directories for previous KVM runs of rcutorture,
+# check the build and console output for errors.  Given a directory
+# containing results directories, this recursively checks them all.
+#
+# Usage: sh kvm-recheck.sh configdir resdir ...
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+#
+# Copyright (C) IBM Corporation, 2011
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH
+configdir=${1}
+shift
+for rd in "$@"
+do
+	dirs=`find $rd -name Make.defconfig.out -print | sort | sed -e 's,/[^/]*$,,' | sort -u`
+	for i in $dirs
+	do
+		configfile=`echo $i | sed -e 's/^.*\///'`
+		echo $i
+		configcheck.sh $i/.config $configdir/$configfile
+		parse-build.sh $i/Make.out $configfile
+		parse-rcutorture.sh $i/console.log $configfile
+		parse-console.sh $i/console.log $configfile
+		if test -r $i/Warnings
+		then
+			cat $i/Warnings
+		fi
+	done
+done
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
new file mode 100755
index 0000000..ae5c2ff
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
@@ -0,0 +1,189 @@
+#!/bin/bash
+#
+# Run a kvm-based test of the specified tree on the specified configs.
+# Fully automated run and error checking, no graphics console.
+#
+# Execute this in the source tree.  Do not run it as a background task
+# because qemu does not seem to like that much.
+#
+# Usage: sh kvm-test-1-rcu.sh config builddir resdir minutes qemu-args bootargs
+#
+# qemu-args defaults to "" -- you will want "-nographic" if running headless.
+# bootargs defaults to	"root=/dev/sda noapic selinux=0 console=ttyS0"
+#			"initcall_debug debug rcutorture.stat_interval=15"
+#			"rcutorture.shutdown_secs=$((minutes * 60))"
+#			"rcutorture.rcutorture_runnable=1"
+#
+# Anything you specify for either qemu-args or bootargs is appended to
+# the default values.  The "-smp" value is deduced from the contents of
+# the config fragment.
+#
+# More sophisticated argument parsing is clearly needed.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+#
+# Copyright (C) IBM Corporation, 2011
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+grace=120
+
+T=/tmp/kvm-test-1-rcu.sh.$$
+trap 'rm -rf $T' 0
+
+. $KVM/bin/functions.sh
+
+config_template=${1}
+title=`echo $config_template | sed -e 's/^.*\///'`
+builddir=${2}
+if test -z "$builddir" -o ! -d "$builddir" -o ! -w "$builddir"
+then
+	echo "kvm-test-1-rcu.sh :$builddir: Not a writable directory, cannot build into it"
+	exit 1
+fi
+resdir=${3}
+if test -z "$resdir" -o ! -d "$resdir" -o ! -w "$resdir"
+then
+	echo "kvm-test-1-rcu.sh :$resdir: Not a writable directory, cannot build into it"
+	exit 1
+fi
+cp $config_template $resdir/ConfigFragment
+echo ' ---' `date`: Starting build
+cat << '___EOF___' >> $T
+CONFIG_RCU_TORTURE_TEST=y
+___EOF___
+# Optimizations below this point
+# CONFIG_USB=n
+# CONFIG_SECURITY=n
+# CONFIG_NFS_FS=n
+# CONFIG_SOUND=n
+# CONFIG_INPUT_JOYSTICK=n
+# CONFIG_INPUT_TABLET=n
+# CONFIG_INPUT_TOUCHSCREEN=n
+# CONFIG_INPUT_MISC=n
+# CONFIG_INPUT_MOUSE=n
+# # CONFIG_NET=n # disables console access, so accept the slower build.
+# CONFIG_SCSI=n
+# CONFIG_ATA=n
+# CONFIG_FAT_FS=n
+# CONFIG_MSDOS_FS=n
+# CONFIG_VFAT_FS=n
+# CONFIG_ISO9660_FS=n
+# CONFIG_QUOTA=n
+# CONFIG_HID=n
+# CONFIG_CRYPTO=n
+# CONFIG_PCCARD=n
+# CONFIG_PCMCIA=n
+# CONFIG_CARDBUS=n
+# CONFIG_YENTA=n
+if kvm-build.sh $config_template $builddir $T
+then
+	cp $builddir/Make*.out $resdir
+	cp $builddir/.config $resdir
+	cp $builddir/arch/x86/boot/bzImage $resdir
+	parse-build.sh $resdir/Make.out $title
+else
+	cp $builddir/Make*.out $resdir
+	echo Build failed, not running KVM, see $resdir.
+	exit 1
+fi
+minutes=$4
+seconds=$(($minutes * 60))
+qemu_args=$5
+boot_args=$6
+
+cd $KVM
+kstarttime=`awk 'BEGIN { print systime() }' < /dev/null`
+echo ' ---' `date`: Starting kernel
+if file linux-2.6/*.o | grep -q 64-bit
+then
+	QEMU=qemu-system-x86_64
+else
+	QEMU=qemu-system-i386
+fi
+
+# Generate -smp qemu argument.
+cpu_count=`configNR_CPUS.sh $config_template`
+ncpus=`grep '^processor' /proc/cpuinfo | wc -l`
+if test $cpu_count -gt $ncpus
+then
+	echo CPU count limited from $cpu_count to $ncpus
+	touch $resdir/Warnings
+	echo CPU count limited from $cpu_count to $ncpus >> $resdir/Warnings
+	cpu_count=$ncpus
+fi
+if echo $qemu_args | grep -q -e -smp
+then
+	echo CPU count specified by caller
+else
+	qemu_args="$qemu_args -smp $cpu_count"
+fi
+
+# Generate CPU-hotplug boot parameters
+if ! bootparam_hotplug_cpu "$bootargs"
+then
+	if configfrag_hotplug_cpu $builddir/.config
+	then
+		echo Kernel configured for CPU hotplug, adding rcutorture.
+		bootargs="$bootargs rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30"
+	fi
+fi
+
+echo $QEMU -name rcu-test -serial file:$builddir/console.log $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append \"noapic selinux=0 console=ttyS0 initcall_debug debug rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1 $boot_args\" > $resdir/qemu-cmd
+$QEMU -name rcu-test -serial file:$builddir/console.log $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append "noapic selinux=0 console=ttyS0 initcall_debug debug rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1 $boot_args" &
+qemu_pid=$!
+commandcompleted=0
+echo Monitoring qemu job at pid $qemu_pid
+for ((i=0;i<$seconds;i++))
+do
+	if kill -0 $qemu_pid > /dev/null 2>&1
+	then
+		sleep 1
+	else
+		commandcompleted=1
+		kruntime=`awk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null`
+		if test $kruntime -lt $seconds
+		then
+			echo Completed in $kruntime vs. $seconds >> $resdir/Warnings 2>&1
+		else
+			echo ' ---' `date`: Kernel done
+		fi
+		break
+	fi
+done
+if test $commandcompleted -eq 0
+then
+	echo Grace period for qemu job at pid $qemu_pid
+	for ((i=0;i<=$grace;i++))
+	do
+		if kill -0 $qemu_pid > /dev/null 2>&1
+		then
+			sleep 1
+		else
+			break
+		fi
+		if test $i -eq $grace
+		then
+			kruntime=`awk 'BEGIN { print systime() - '"$kstarttime"' }'`
+			echo "!!! Hang at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1
+			kill -KILL $qemu_pid
+		fi
+	done
+fi
+
+cp $builddir/console.log $resdir
+parse-rcutorture.sh $resdir/console.log $title >> $resdir/Warnings 2>&1
+parse-console.sh $resdir/console.log $title >> $resdir/Warnings 2>&1
+cat $resdir/Warnings
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
new file mode 100644
index 0000000..46c75ee
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -0,0 +1,173 @@
+#!/bin/bash
+#
+# Run a series of 14 tests under KVM.  These are not particularly
+# well-selected or well-tuned, but are the current set.  Run from the
+# top level of the source tree.
+#
+# Edit the definitions below to set the locations of the various directories,
+# as well as the test duration.
+#
+# Usage: sh kvm.sh [ options ]
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+#
+# Copyright (C) IBM Corporation, 2011
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+scriptname=$0
+
+dur=30
+KVM=`pwd`/tools/testing/selftests/rcutorture; export KVM
+builddir=${KVM}/b1
+resdir=""
+configs=" sysidleY.2013.06.19a \
+	  sysidleN.2013.06.19a \
+	  P1-S-T-NH-SD-SMP-HP \
+	  P2-2-t-nh-sd-SMP-hp \
+	  P3-3-T-nh-SD-SMP-hp \
+	  P4-A-t-NH-sd-SMP-HP \
+	  P5-U-T-NH-sd-SMP-hp \
+	  P6---t-nh-SD-smp-hp \
+	  N1-S-T-NH-SD-SMP-HP \
+	  N2-2-t-nh-sd-SMP-hp \
+	  N3-3-T-nh-SD-SMP-hp \
+	  N4-A-t-NH-sd-SMP-HP \
+	  N5-U-T-NH-sd-SMP-hp \
+	  PT1-nh \
+	  PT2-NH \
+	  NT1-nh \
+	  NT3-NH"
+
+usage () {
+	echo "Usage: $scriptname optional arguments:"
+	echo "       --builddir absolute-pathname"
+	echo "       --configs \"config-file list\""
+	echo "       --duration minutes"
+	echo "       --rcu-kvm absolute-pathname"
+	echo "       --results absolute-pathname"
+	echo "       --relbuilddir relative-pathname"
+	exit 1
+}
+
+# checkarg --argname argtype $# arg mustmatch cannotmatch
+checkarg () {
+	if test $3 -le 1
+	then
+		echo $1 needs argument $2 matching \"$5\"
+		usage
+	fi
+	if echo "$4" | grep -q -e "$5"
+	then
+		:
+	else
+		echo $1 $2 \"$4\" must match \"$5\"
+		usage
+	fi
+	if echo "$4" | grep -q -e "$6"
+	then
+		echo $1 $2 \"$4\" must not match \"$6\"
+		usage
+	fi
+}
+
+while test $# -gt 0
+do
+	echo ":$1:"
+	case "$1" in
+	--builddir)
+		checkarg --builddir "(absolute pathname)" "$#" "$2" '^/' error
+		builddir=$2
+		gotbuilddir=1
+		shift
+		;;
+	--configs)
+		checkarg --configs "(list of config files)" "$#" "$2" '^[^/]*$' '^--'
+		configs="$2"
+		shift
+		;;
+	--duration)
+		checkarg --duration "(minutes)" $# "$2" '^[0-9]*$' error
+		dur=$2
+		shift
+		;;
+	--rcu-kvm)
+		checkarg --rcu-kvm "(absolute pathname)" "$#" "$2" '^/' error
+		KVM=$2; export KVM
+		if -z "$gotbuilddir"
+		then
+			builddir=${KVM}/b1
+		fi
+		if -n "$gotrelbuilddir"
+		then
+			builddir=${KVM}/${relbuilddir}
+		fi
+		shift
+		;;
+	--relbuilddir)
+		checkarg --relbuilddir "(relative pathname)" "$#" "$2" '^[^/]*$' '^--'
+		relbuilddir=$2
+		gotrelbuilddir=1
+		builddir=${KVM}/${relbuilddir}
+		shift
+		;;
+	--results)
+		checkarg --results "(absolute pathname)" "$#" "$2" '^/' error
+		resdir=$2
+		shift
+		;;
+	*)
+		usage
+		;;
+	esac
+	shift
+done
+
+echo "builddir=$builddir"
+echo "dur=$dur"
+echo "KVM=$KVM"
+echo "resdir=$resdir"
+
+PATH=${KVM}/bin:$PATH; export PATH
+CONFIGFRAG=${KVM}/configs; export CONFIGFRAG
+
+if test -z "$resdir"
+then
+	resdir=$KVM/res
+	mkdir $resdir || :
+	ds=`date +%Y.%m.%d-%H:%M:%S`
+	mkdir $resdir/$ds
+	echo Datestamp: $ds
+else
+	mkdir -p "$resdir"
+	ds=""
+fi
+pwd > $resdir/$ds/testid.txt
+if test -d .git
+then
+	git status >> $resdir/$ds/testid.txt
+	git rev-parse HEAD >> $resdir/$ds/testid.txt
+fi
+builddir=$KVM/b1
+mkdir $builddir || :
+
+for CF in $configs
+do
+	rd=$resdir/$ds/$CF
+	mkdir $rd || :
+	echo Results directory: $rd
+	kvm-test-1-rcu.sh $CONFIGFRAG/$CF $builddir $rd $dur "-nographic" "rcutorture.test_no_idle_hz=1 rcutorture.n_barrier_cbs=4 rcutorture.verbose=1"
+done
+# Tracing: trace_event=rcu:rcu_nocb_grace_period,rcu:rcu_grace_period,rcu:rcu_grace_period_init,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_torture_read,rcu:rcu_invoke_callback,rcu:rcu_fqs,rcu:rcu_dyntick,rcu:rcu_unlock_preempted_task
diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh
new file mode 100755
index 0000000..2e0e9f7
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh
@@ -0,0 +1,47 @@
+#!/bin/sh
+#
+# Check the build output from an rcutorture run for goodness.
+# The "file" is a pathname on the local system, and "title" is
+# a text string for error-message purposes.
+#
+# The file must contain kernel build output.
+#
+# Usage:
+#	sh parse-build.sh file title
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+#
+# Copyright (C) IBM Corporation, 2011
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+T=$1
+title=$2
+
+if grep -q CC < $T
+then
+	:
+else
+	echo $title no build
+	exit 1
+fi
+
+if egrep -q "error:|rcu[^/]*\.c.*warning:|rcu.*\.h.*warning:" < $T
+then
+	echo $title build errors:
+	egrep "error:|rcu[^/]*\.c.*warning:|rcu.*\.h.*warning:" < $T
+	exit 2
+fi
+exit 0
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
new file mode 100755
index 0000000..bc1496f
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -0,0 +1,39 @@
+#!/bin/sh
+#
+# Check the console output from an rcutorture run for oopses.
+# The "file" is a pathname on the local system, and "title" is
+# a text string for error-message purposes.
+#
+# Usage:
+#	sh parse-console.sh file title
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+#
+# Copyright (C) IBM Corporation, 2011
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+T=/tmp/abat-chk-badness.sh.$$
+trap 'rm -f $T' 0
+
+file="$1"
+title="$2"
+
+egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T
+if test -s $T
+then
+	echo Assertion failure in $file $title
+	cat $T
+fi
diff --git a/tools/testing/selftests/rcutorture/bin/parse-rcutorture.sh b/tools/testing/selftests/rcutorture/bin/parse-rcutorture.sh
new file mode 100755
index 0000000..37368a0
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/parse-rcutorture.sh
@@ -0,0 +1,104 @@
+#!/bin/sh
+#
+# Check the console output from an rcutorture run for goodness.
+# The "file" is a pathname on the local system, and "title" is
+# a text string for error-message purposes.
+#
+# The file must contain rcutorture output, but can be interspersed
+# with other dmesg text.
+#
+# Usage:
+#	sh parse-rcutorture.sh file title
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+#
+# Copyright (C) IBM Corporation, 2011
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+T=/tmp/parse-rcutorture.sh.$$
+file="$1"
+title="$2"
+
+trap 'rm -f $T.seq' 0
+
+# check for presence of rcutorture.txt file
+
+if test -f "$file" -a -r "$file"
+then
+	:
+else
+	echo $title unreadable rcutorture.txt file: $file
+	exit 1
+fi
+
+# check for abject failure
+
+if grep -q FAILURE $file || grep -q -e '-torture.*!!!' $file
+then
+	nerrs=`grep --binary-files=text '!!!' $file | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'`
+	echo $title FAILURE, $nerrs instances
+	echo "   " $url
+	exit
+fi
+
+grep --binary-files=text 'torture:.*ver:' $file | grep --binary-files=text -v '(null)' | sed -e 's/^(initramfs)[^]]*] //' -e 's/^\[[^]]*] //' |
+awk '
+BEGIN	{
+	ver = 0;
+	badseq = 0;
+	}
+
+	{
+	if (!badseq && ($5 + 0 != $5 || $5 <= ver)) {
+		badseqno1 = ver;
+		badseqno2 = $5;
+		badseqnr = NR;
+		badseq = 1;
+	}
+	ver = $5
+	}
+
+END	{
+	if (badseq) {
+		if (badseqno1 == badseqno2 && badseqno2 == ver)
+			print "RCU GP HANG at " ver " rcutorture stat " badseqnr;
+		else
+			print "BAD SEQ " badseqno1 ":" badseqno2 " last:" ver " RCU version " badseqnr;
+	}
+	}' > $T.seq
+
+if grep -q SUCCESS $file
+then
+	if test -s $T.seq
+	then
+		echo WARNING $title `cat $T.seq`
+		echo "   " $file
+		exit 2
+	fi
+else
+	if grep -q RCU_HOTPLUG $file
+	then
+		echo WARNING: HOTPLUG FAILURES $title `cat $T.seq`
+		echo "   " $file
+		exit 3
+	fi
+	echo $title no success message, `grep --binary-files=text 'ver:' $file | wc -l` successful RCU version messages
+	if test -s $T.seq
+	then
+		echo WARNING $title `cat $T.seq`
+	fi
+	exit 2
+fi
diff --git a/tools/testing/selftests/rcutorture/configs/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/N1-S-T-NH-SD-SMP-HP
new file mode 100644
index 0000000..d81e11d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/N1-S-T-NH-SD-SMP-HP
@@ -0,0 +1,19 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/N2-2-t-nh-sd-SMP-hp
new file mode 100644
index 0000000..02e4185
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/N2-2-t-nh-sd-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=4
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/N3-3-T-nh-SD-SMP-hp
new file mode 100644
index 0000000..b3100f6
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/N3-3-T-nh-SD-SMP-hp
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/N4-A-t-NH-sd-SMP-HP
new file mode 100644
index 0000000..c56b445
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/N4-A-t-NH-sd-SMP-HP
@@ -0,0 +1,18 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/N5-U-T-NH-sd-SMP-hp
new file mode 100644
index 0000000..90d924f
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/N5-U-T-NH-sd-SMP-hp
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/N6---t-nh-SD-smp-hp b/tools/testing/selftests/rcutorture/configs/N6---t-nh-SD-smp-hp
new file mode 100644
index 0000000..0ccc36d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/N6---t-nh-SD-smp-hp
@@ -0,0 +1,19 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_NR_CPUS=1
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/N7-4-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/N7-4-T-NH-SD-SMP-HP
new file mode 100644
index 0000000..3f640cf
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/N7-4-T-NH-SD-SMP-HP
@@ -0,0 +1,26 @@
+CONFIG_RCU_TRACE=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=16
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_NONE=y
+CONFIG_RCU_NOCB_CPU_ZERO=n
+CONFIG_RCU_NOCB_CPU_ALL=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/N8-2-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/N8-2-T-NH-SD-SMP-HP
new file mode 100644
index 0000000..285da2d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/N8-2-T-NH-SD-SMP-HP
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=14
+CONFIG_NR_CPUS=16
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/NT1-nh b/tools/testing/selftests/rcutorture/configs/NT1-nh
new file mode 100644
index 0000000..023f312
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/NT1-nh
@@ -0,0 +1,23 @@
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=n
+#
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/NT3-NH b/tools/testing/selftests/rcutorture/configs/NT3-NH
new file mode 100644
index 0000000..6fd0235
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/NT3-NH
@@ -0,0 +1,20 @@
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=y
+#
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/P1-S-T-NH-SD-SMP-HP
new file mode 100644
index 0000000..9647c44
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/P1-S-T-NH-SD-SMP-HP
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/P2-2-t-nh-sd-SMP-hp
new file mode 100644
index 0000000..0f3b667
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/P2-2-t-nh-sd-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=4
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/P3-3-T-nh-SD-SMP-hp
new file mode 100644
index 0000000..b035e14
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/P3-3-T-nh-SD-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/P4-A-t-NH-sd-SMP-HP
new file mode 100644
index 0000000..3ccf6a9
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/P4-A-t-NH-sd-SMP-HP
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_RT_MUTEXES=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/P5-U-T-NH-sd-SMP-hp
new file mode 100644
index 0000000..ef624ce
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/P5-U-T-NH-sd-SMP-hp
@@ -0,0 +1,28 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_PROVE_RCU_DELAY=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_RT_MUTEXES=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/P6---t-nh-SD-smp-hp b/tools/testing/selftests/rcutorture/configs/P6---t-nh-SD-smp-hp
new file mode 100644
index 0000000..f4c9175
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/P6---t-nh-SD-smp-hp
@@ -0,0 +1,18 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=n
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-HP
new file mode 100644
index 0000000..77a8c5b
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-HP
@@ -0,0 +1,30 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=16
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_NONE=n
+CONFIG_RCU_NOCB_CPU_ZERO=n
+CONFIG_RCU_NOCB_CPU_ALL=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_SLUB=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-HP-all b/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-HP-all
new file mode 100644
index 0000000..0eecebc
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-HP-all
@@ -0,0 +1,30 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=16
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_NONE=y
+CONFIG_RCU_NOCB_CPU_ZERO=n
+CONFIG_RCU_NOCB_CPU_ALL=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_SLUB=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-HP-none b/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-HP-none
new file mode 100644
index 0000000..0eecebc
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-HP-none
@@ -0,0 +1,30 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=16
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_NONE=y
+CONFIG_RCU_NOCB_CPU_ZERO=n
+CONFIG_RCU_NOCB_CPU_ALL=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_SLUB=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-hp
new file mode 100644
index 0000000..588bc70
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-hp
@@ -0,0 +1,30 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=16
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_NONE=n
+CONFIG_RCU_NOCB_CPU_ZERO=y
+CONFIG_RCU_NOCB_CPU_ALL=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_SLUB=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/PT1-nh b/tools/testing/selftests/rcutorture/configs/PT1-nh
new file mode 100644
index 0000000..e3361c3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/PT1-nh
@@ -0,0 +1,23 @@
+CONFIG_TINY_PREEMPT_RCU=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=n
+#
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/PT2-NH b/tools/testing/selftests/rcutorture/configs/PT2-NH
new file mode 100644
index 0000000..64abfc3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/PT2-NH
@@ -0,0 +1,22 @@
+CONFIG_TINY_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=y
+#
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/sysidleN.2013.06.19a b/tools/testing/selftests/rcutorture/configs/sysidleN.2013.06.19a
new file mode 100644
index 0000000..9dbcde3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/sysidleN.2013.06.19a
@@ -0,0 +1,23 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=n
+CONFIG_NO_HZ_FULL=y
+CONFIG_NO_HZ_FULL_SYSIDLE=n
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/sysidleY.2013.06.19a b/tools/testing/selftests/rcutorture/configs/sysidleY.2013.06.19a
new file mode 100644
index 0000000..d24dd6148
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/sysidleY.2013.06.19a
@@ -0,0 +1,26 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=n
+CONFIG_NO_HZ_FULL=y
+CONFIG_NO_HZ_FULL_SYSIDLE=y
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+
diff --git a/tools/testing/selftests/rcutorture/doc/initrd.txt b/tools/testing/selftests/rcutorture/doc/initrd.txt
new file mode 100644
index 0000000..49d134c
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/doc/initrd.txt
@@ -0,0 +1,90 @@
+This document describes one way to create the initrd directory hierarchy
+in order to allow an initrd to be built into your kernel.  The trick
+here is to steal the initrd file used on your Linux laptop, Ubuntu in
+this case.  There are probably much better ways of doing this.
+
+That said, here are the commands:
+
+------------------------------------------------------------------------
+zcat /initrd.img > /tmp/initrd.img.zcat
+mkdir initrd
+cd initrd
+cpio -id < /tmp/initrd.img.zcat
+------------------------------------------------------------------------
+
+Interestingly enough, if you are running rcutorture, you don't really
+need userspace in many cases.  Running without userspace has the
+advantage of allowing you to test your kernel independently of the
+distro in place, the root-filesystem layout, and so on.  To make this
+happen, put the following script in the initrd's tree's "/init" file,
+with 0755 mode.
+
+------------------------------------------------------------------------
+#!/bin/sh
+
+[ -d /dev ] || mkdir -m 0755 /dev
+[ -d /root ] || mkdir -m 0700 /root
+[ -d /sys ] || mkdir /sys
+[ -d /proc ] || mkdir /proc
+[ -d /tmp ] || mkdir /tmp
+mkdir -p /var/lock
+mount -t sysfs -o nodev,noexec,nosuid sysfs /sys
+mount -t proc -o nodev,noexec,nosuid proc /proc
+# Some things don't work properly without /etc/mtab.
+ln -sf /proc/mounts /etc/mtab
+
+# Note that this only becomes /dev on the real filesystem if udev's scripts
+# are used; which they will be, but it's worth pointing out
+if ! mount -t devtmpfs -o mode=0755 udev /dev; then
+	echo "W: devtmpfs not available, falling back to tmpfs for /dev"
+	mount -t tmpfs -o mode=0755 udev /dev
+	[ -e /dev/console ] || mknod --mode=600 /dev/console c 5 1
+	[ -e /dev/kmsg ] || mknod --mode=644 /dev/kmsg c 1 11
+	[ -e /dev/null ] || mknod --mode=666 /dev/null c 1 3
+fi
+
+mkdir /dev/pts
+mount -t devpts -o noexec,nosuid,gid=5,mode=0620 devpts /dev/pts || true
+mount -t tmpfs -o "nosuid,size=20%,mode=0755" tmpfs /run
+mkdir /run/initramfs
+# compatibility symlink for the pre-oneiric locations
+ln -s /run/initramfs /dev/.initramfs
+
+# Export relevant variables
+export ROOT=
+export ROOTDELAY=
+export ROOTFLAGS=
+export ROOTFSTYPE=
+export IP=
+export BOOT=
+export BOOTIF=
+export UBIMTD=
+export break=
+export init=/sbin/init
+export quiet=n
+export readonly=y
+export rootmnt=/root
+export debug=
+export panic=
+export blacklist=
+export resume=
+export resume_offset=
+export recovery=
+
+for i in /sys/devices/system/cpu/cpu*/online
+do
+	case $i in
+	'/sys/devices/system/cpu/cpu0/online')
+		;;
+	'/sys/devices/system/cpu/cpu*/online')
+		;;
+	*)
+		echo 1 > $i
+		;;
+	esac
+done
+
+while :
+do
+	sleep 10
+done
diff --git a/tools/testing/selftests/rcutorture/doc/rcu-test-image.txt b/tools/testing/selftests/rcutorture/doc/rcu-test-image.txt
new file mode 100644
index 0000000..66efb59
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/doc/rcu-test-image.txt
@@ -0,0 +1,42 @@
+This document describes one way to created the rcu-test-image file
+that contains the filesystem used by the guest-OS kernel.  There are
+probably much better ways of doing this, and this filesystem could no
+doubt be smaller.  It is probably also possible to simply download
+an appropriate image from any number of places.
+
+That said, here are the commands:
+
+------------------------------------------------------------------------
+dd if=/dev/zero of=rcu-test-image bs=400M count=1
+mkfs.ext3 ./rcu-test-image
+sudo mount -o loop ./rcu-test-image /mnt
+
+# Replace "precise" below with your favorite Ubuntu release.
+# Empirical evidence says this image will work for 64-bit, but...
+# Note that debootstrap does take a few minutes to run.  Or longer.
+sudo debootstrap --verbose --arch i386 precise /mnt http://archive.ubuntu.com/ubuntu
+cat << '___EOF___' | sudo dd of=/mnt/etc/fstab
+# UNCONFIGURED FSTAB FOR BASE SYSTEM
+#
+/dev/vda        /               ext3    defaults        1 1
+dev             /dev            tmpfs   rw              0 0
+tmpfs           /dev/shm        tmpfs   defaults        0 0
+devpts          /dev/pts        devpts  gid=5,mode=620  0 0
+sysfs           /sys            sysfs   defaults        0 0
+proc            /proc           proc    defaults        0 0
+___EOF___
+sudo umount /mnt
+------------------------------------------------------------------------
+
+
+References:
+
+	http://sripathikodi.blogspot.com/2010/02/creating-kvm-bootable-fedora-system.html
+	https://help.ubuntu.com/community/KVM/CreateGuests
+	https://help.ubuntu.com/community/JeOSVMBuilder
+	http://wiki.libvirt.org/page/UbuntuKVMWalkthrough
+	http://www.moe.co.uk/2011/01/07/pci_add_option_rom-failed-to-find-romfile-pxe-rtl8139-bin/ -- "apt-get install kvm-pxe"
+	http://www.landley.net/writing/rootfs-howto.html
+	http://en.wikipedia.org/wiki/Initrd
+	http://en.wikipedia.org/wiki/Cpio
+	http://wiki.libvirt.org/page/UbuntuKVMWalkthrough
-- 
cgit v0.10.2


From 847bfd254399eebc8752d39f43628e6c1baac076 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sat, 28 Sep 2013 18:44:11 -0700
Subject: rcutorture: Add datestamp argument to kvm.sh

Allow datestamp to be specified to allow tests to be broken up and run
in parallel.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 46c75ee..9fcceed 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -50,11 +50,13 @@ configs=" sysidleY.2013.06.19a \
 	  PT2-NH \
 	  NT1-nh \
 	  NT3-NH"
+ds=`date +%Y.%m.%d-%H:%M:%S`
 
 usage () {
 	echo "Usage: $scriptname optional arguments:"
 	echo "       --builddir absolute-pathname"
 	echo "       --configs \"config-file list\""
+	echo "       --datestamp string"
 	echo "       --duration minutes"
 	echo "       --rcu-kvm absolute-pathname"
 	echo "       --results absolute-pathname"
@@ -98,6 +100,11 @@ do
 		configs="$2"
 		shift
 		;;
+	--datestamp)
+		checkarg --datestamp "(relative pathname)" "$#" "$2" '^[^/]*$' '^--'
+		ds=$2
+		shift
+		;;
 	--duration)
 		checkarg --duration "(minutes)" $# "$2" '^[0-9]*$' error
 		dur=$2
@@ -147,13 +154,12 @@ if test -z "$resdir"
 then
 	resdir=$KVM/res
 	mkdir $resdir || :
-	ds=`date +%Y.%m.%d-%H:%M:%S`
-	mkdir $resdir/$ds
-	echo Datestamp: $ds
 else
-	mkdir -p "$resdir"
-	ds=""
+	mkdir -p "$resdir" || :
 fi
+mkdir $resdir/$ds
+echo Datestamp: $ds
+
 pwd > $resdir/$ds/testid.txt
 if test -d .git
 then
-- 
cgit v0.10.2


From bb918535a15a0c9ca217a99394dcae0c44711f1c Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sat, 28 Sep 2013 20:37:45 -0700
Subject: rcutorture: Add kernel-version argument

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
index ae5c2ff..3b53078 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
@@ -61,6 +61,7 @@ then
 fi
 cp $config_template $resdir/ConfigFragment
 echo ' ---' `date`: Starting build
+echo ' ---' Kconfig fragment at: $config_template
 cat << '___EOF___' >> $T
 CONFIG_RCU_TORTURE_TEST=y
 ___EOF___
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 9fcceed..7deb7b4 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -51,6 +51,7 @@ configs=" sysidleY.2013.06.19a \
 	  NT1-nh \
 	  NT3-NH"
 ds=`date +%Y.%m.%d-%H:%M:%S`
+kversion=""
 
 usage () {
 	echo "Usage: $scriptname optional arguments:"
@@ -58,6 +59,7 @@ usage () {
 	echo "       --configs \"config-file list\""
 	echo "       --datestamp string"
 	echo "       --duration minutes"
+	echo "       --kversion vN.NN"
 	echo "       --rcu-kvm absolute-pathname"
 	echo "       --results absolute-pathname"
 	echo "       --relbuilddir relative-pathname"
@@ -110,6 +112,11 @@ do
 		dur=$2
 		shift
 		;;
+	--kversion)
+		checkarg --kversion "(kernel version)" $# "$2" '^v[0-9.]*$' error
+		kversion=$2
+		shift
+		;;
 	--rcu-kvm)
 		checkarg --rcu-kvm "(absolute pathname)" "$#" "$2" '^/' error
 		KVM=$2; export KVM
@@ -174,6 +181,6 @@ do
 	rd=$resdir/$ds/$CF
 	mkdir $rd || :
 	echo Results directory: $rd
-	kvm-test-1-rcu.sh $CONFIGFRAG/$CF $builddir $rd $dur "-nographic" "rcutorture.test_no_idle_hz=1 rcutorture.n_barrier_cbs=4 rcutorture.verbose=1"
+	kvm-test-1-rcu.sh $CONFIGFRAG/$kversion/$CF $builddir $rd $dur "-nographic" "rcutorture.test_no_idle_hz=1 rcutorture.n_barrier_cbs=4 rcutorture.verbose=1"
 done
 # Tracing: trace_event=rcu:rcu_nocb_grace_period,rcu:rcu_grace_period,rcu:rcu_grace_period_init,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_torture_read,rcu:rcu_invoke_callback,rcu:rcu_fqs,rcu:rcu_dyntick,rcu:rcu_unlock_preempted_task
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v0.0/N1-S-T-NH-SD-SMP-HP
new file mode 100644
index 0000000..d81e11d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/N1-S-T-NH-SD-SMP-HP
@@ -0,0 +1,19 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v0.0/N2-2-t-nh-sd-SMP-hp
new file mode 100644
index 0000000..02e4185
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/N2-2-t-nh-sd-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=4
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/v0.0/N3-3-T-nh-SD-SMP-hp
new file mode 100644
index 0000000..b3100f6
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/N3-3-T-nh-SD-SMP-hp
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/v0.0/N4-A-t-NH-sd-SMP-HP
new file mode 100644
index 0000000..c56b445
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/N4-A-t-NH-sd-SMP-HP
@@ -0,0 +1,18 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v0.0/N5-U-T-NH-sd-SMP-hp
new file mode 100644
index 0000000..90d924f
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/N5-U-T-NH-sd-SMP-hp
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/NT1-nh b/tools/testing/selftests/rcutorture/configs/v0.0/NT1-nh
new file mode 100644
index 0000000..023f312
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/NT1-nh
@@ -0,0 +1,23 @@
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=n
+#
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/NT3-NH b/tools/testing/selftests/rcutorture/configs/v0.0/NT3-NH
new file mode 100644
index 0000000..6fd0235
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/NT3-NH
@@ -0,0 +1,20 @@
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=y
+#
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v0.0/P1-S-T-NH-SD-SMP-HP
new file mode 100644
index 0000000..9647c44
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/P1-S-T-NH-SD-SMP-HP
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v0.0/P2-2-t-nh-sd-SMP-hp
new file mode 100644
index 0000000..0f3b667
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/P2-2-t-nh-sd-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=4
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/v0.0/P3-3-T-nh-SD-SMP-hp
new file mode 100644
index 0000000..b035e14
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/P3-3-T-nh-SD-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/v0.0/P4-A-t-NH-sd-SMP-HP
new file mode 100644
index 0000000..3ccf6a9
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/P4-A-t-NH-sd-SMP-HP
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_RT_MUTEXES=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v0.0/P5-U-T-NH-sd-SMP-hp
new file mode 100644
index 0000000..ef624ce
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/P5-U-T-NH-sd-SMP-hp
@@ -0,0 +1,28 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_PROVE_RCU_DELAY=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_RT_MUTEXES=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/PT1-nh b/tools/testing/selftests/rcutorture/configs/v0.0/PT1-nh
new file mode 100644
index 0000000..e3361c3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/PT1-nh
@@ -0,0 +1,23 @@
+CONFIG_TINY_PREEMPT_RCU=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=n
+#
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/PT2-NH b/tools/testing/selftests/rcutorture/configs/v0.0/PT2-NH
new file mode 100644
index 0000000..64abfc3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/PT2-NH
@@ -0,0 +1,22 @@
+CONFIG_TINY_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=y
+#
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.3/N1-S-T-NH-SD-SMP-HP
new file mode 100644
index 0000000..d81e11d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/N1-S-T-NH-SD-SMP-HP
@@ -0,0 +1,19 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.3/N2-2-t-nh-sd-SMP-hp
new file mode 100644
index 0000000..02e4185
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/N2-2-t-nh-sd-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=4
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.3/N3-3-T-nh-SD-SMP-hp
new file mode 100644
index 0000000..b3100f6
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/N3-3-T-nh-SD-SMP-hp
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.3/N4-A-t-NH-sd-SMP-HP
new file mode 100644
index 0000000..c56b445
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/N4-A-t-NH-sd-SMP-HP
@@ -0,0 +1,18 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.3/N5-U-T-NH-sd-SMP-hp
new file mode 100644
index 0000000..90d924f
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/N5-U-T-NH-sd-SMP-hp
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/NT1-nh b/tools/testing/selftests/rcutorture/configs/v3.3/NT1-nh
new file mode 100644
index 0000000..023f312
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/NT1-nh
@@ -0,0 +1,23 @@
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=n
+#
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/NT3-NH b/tools/testing/selftests/rcutorture/configs/v3.3/NT3-NH
new file mode 100644
index 0000000..6fd0235
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/NT3-NH
@@ -0,0 +1,20 @@
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=y
+#
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.3/P1-S-T-NH-SD-SMP-HP
new file mode 100644
index 0000000..9647c44
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/P1-S-T-NH-SD-SMP-HP
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.3/P2-2-t-nh-sd-SMP-hp
new file mode 100644
index 0000000..0f3b667
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/P2-2-t-nh-sd-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=4
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.3/P3-3-T-nh-SD-SMP-hp
new file mode 100644
index 0000000..b035e14
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/P3-3-T-nh-SD-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.3/P4-A-t-NH-sd-SMP-HP
new file mode 100644
index 0000000..3ccf6a9
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/P4-A-t-NH-sd-SMP-HP
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_RT_MUTEXES=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.3/P5-U-T-NH-sd-SMP-hp
new file mode 100644
index 0000000..ef624ce
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/P5-U-T-NH-sd-SMP-hp
@@ -0,0 +1,28 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_PROVE_RCU_DELAY=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_RT_MUTEXES=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/PT1-nh b/tools/testing/selftests/rcutorture/configs/v3.3/PT1-nh
new file mode 100644
index 0000000..e3361c3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/PT1-nh
@@ -0,0 +1,23 @@
+CONFIG_TINY_PREEMPT_RCU=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=n
+#
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/PT2-NH b/tools/testing/selftests/rcutorture/configs/v3.3/PT2-NH
new file mode 100644
index 0000000..64abfc3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/PT2-NH
@@ -0,0 +1,22 @@
+CONFIG_TINY_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=y
+#
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.5/N1-S-T-NH-SD-SMP-HP
new file mode 100644
index 0000000..d81e11d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/N1-S-T-NH-SD-SMP-HP
@@ -0,0 +1,19 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.5/N2-2-t-nh-sd-SMP-hp
new file mode 100644
index 0000000..02e4185
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/N2-2-t-nh-sd-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=4
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.5/N3-3-T-nh-SD-SMP-hp
new file mode 100644
index 0000000..b3100f6
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/N3-3-T-nh-SD-SMP-hp
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.5/N4-A-t-NH-sd-SMP-HP
new file mode 100644
index 0000000..c56b445
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/N4-A-t-NH-sd-SMP-HP
@@ -0,0 +1,18 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.5/N5-U-T-NH-sd-SMP-hp
new file mode 100644
index 0000000..90d924f
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/N5-U-T-NH-sd-SMP-hp
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/NT1-nh b/tools/testing/selftests/rcutorture/configs/v3.5/NT1-nh
new file mode 100644
index 0000000..023f312
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/NT1-nh
@@ -0,0 +1,23 @@
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=n
+#
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/NT3-NH b/tools/testing/selftests/rcutorture/configs/v3.5/NT3-NH
new file mode 100644
index 0000000..6fd0235
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/NT3-NH
@@ -0,0 +1,20 @@
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=y
+#
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.5/P1-S-T-NH-SD-SMP-HP
new file mode 100644
index 0000000..9647c44
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/P1-S-T-NH-SD-SMP-HP
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.5/P2-2-t-nh-sd-SMP-hp
new file mode 100644
index 0000000..0f3b667
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/P2-2-t-nh-sd-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=4
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.5/P3-3-T-nh-SD-SMP-hp
new file mode 100644
index 0000000..b035e14
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/P3-3-T-nh-SD-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.5/P4-A-t-NH-sd-SMP-HP
new file mode 100644
index 0000000..3ccf6a9
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/P4-A-t-NH-sd-SMP-HP
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_RT_MUTEXES=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.5/P5-U-T-NH-sd-SMP-hp
new file mode 100644
index 0000000..ef624ce
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/P5-U-T-NH-sd-SMP-hp
@@ -0,0 +1,28 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_PROVE_RCU_DELAY=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_RT_MUTEXES=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/PT1-nh b/tools/testing/selftests/rcutorture/configs/v3.5/PT1-nh
new file mode 100644
index 0000000..e3361c3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/PT1-nh
@@ -0,0 +1,23 @@
+CONFIG_TINY_PREEMPT_RCU=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=n
+#
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/PT2-NH b/tools/testing/selftests/rcutorture/configs/v3.5/PT2-NH
new file mode 100644
index 0000000..64abfc3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/PT2-NH
@@ -0,0 +1,22 @@
+CONFIG_TINY_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=y
+#
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
-- 
cgit v0.10.2


From 4275be83b807c2926d2b23e67eb61692a1810080 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sun, 29 Sep 2013 11:13:46 -0700
Subject: rcutorture: Add per-version default Kconfig fragments and module
 parameters

Different Kconfig parameters apply to different kernel versions, as
do different rcutorture module parameters.  This commit allows the
rcutorture test scripts to adjust for different kernel versions.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index db1c32a..d4c15f8 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -32,11 +32,10 @@ bootparam_hotplug_cpu () {
 #
 # Returns 1 if the config fragment specifies hotplug CPU.
 configfrag_hotplug_cpu () {
-	cf=$1
-	if test ! -r $cf
+	if test ! -r "$1"
 	then
-		echo Unreadable config fragment $cf 1>&2
+		echo Unreadable config fragment "$1" 1>&2
 		exit -1
 	fi
-	grep -q '^CONFIG_HOTPLUG_CPU=y$' $cf
+	grep -q '^CONFIG_HOTPLUG_CPU=y$' "$1"
 }
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
index 3b53078..0a3f037 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
@@ -44,6 +44,7 @@ T=/tmp/kvm-test-1-rcu.sh.$$
 trap 'rm -rf $T' 0
 
 . $KVM/bin/functions.sh
+. $KVPATH/ver_functions.sh
 
 config_template=${1}
 title=`echo $config_template | sed -e 's/^.*\///'`
@@ -133,14 +134,9 @@ else
 fi
 
 # Generate CPU-hotplug boot parameters
-if ! bootparam_hotplug_cpu "$bootargs"
-then
-	if configfrag_hotplug_cpu $builddir/.config
-	then
-		echo Kernel configured for CPU hotplug, adding rcutorture.
-		bootargs="$bootargs rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30"
-	fi
-fi
+boot_args="`rcutorture_param_onoff "$boot_args" $builddir/.config`"
+# Generate rcu_barrier() boot parameter
+boot_args="`rcutorture_param_n_barrier_cbs "$boot_args"`"
 
 echo $QEMU -name rcu-test -serial file:$builddir/console.log $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append \"noapic selinux=0 console=ttyS0 initcall_debug debug rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1 $boot_args\" > $resdir/qemu-cmd
 $QEMU -name rcu-test -serial file:$builddir/console.log $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append "noapic selinux=0 console=ttyS0 initcall_debug debug rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1 $boot_args" &
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 7deb7b4..92f726b 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -33,23 +33,7 @@ dur=30
 KVM=`pwd`/tools/testing/selftests/rcutorture; export KVM
 builddir=${KVM}/b1
 resdir=""
-configs=" sysidleY.2013.06.19a \
-	  sysidleN.2013.06.19a \
-	  P1-S-T-NH-SD-SMP-HP \
-	  P2-2-t-nh-sd-SMP-hp \
-	  P3-3-T-nh-SD-SMP-hp \
-	  P4-A-t-NH-sd-SMP-HP \
-	  P5-U-T-NH-sd-SMP-hp \
-	  P6---t-nh-SD-smp-hp \
-	  N1-S-T-NH-SD-SMP-HP \
-	  N2-2-t-nh-sd-SMP-hp \
-	  N3-3-T-nh-SD-SMP-hp \
-	  N4-A-t-NH-sd-SMP-HP \
-	  N5-U-T-NH-sd-SMP-hp \
-	  PT1-nh \
-	  PT2-NH \
-	  NT1-nh \
-	  NT3-NH"
+configs=""
 ds=`date +%Y.%m.%d-%H:%M:%S`
 kversion=""
 
@@ -156,6 +140,12 @@ echo "resdir=$resdir"
 
 PATH=${KVM}/bin:$PATH; export PATH
 CONFIGFRAG=${KVM}/configs; export CONFIGFRAG
+KVPATH=${CONFIGFRAG}/$kversion; export KVPATH
+
+if test -z "$configs"
+then
+	configs="`cat $CONFIGFRAG/$kversion/CFLIST`"
+fi
 
 if test -z "$resdir"
 then
@@ -181,6 +171,6 @@ do
 	rd=$resdir/$ds/$CF
 	mkdir $rd || :
 	echo Results directory: $rd
-	kvm-test-1-rcu.sh $CONFIGFRAG/$kversion/$CF $builddir $rd $dur "-nographic" "rcutorture.test_no_idle_hz=1 rcutorture.n_barrier_cbs=4 rcutorture.verbose=1"
+	kvm-test-1-rcu.sh $CONFIGFRAG/$kversion/$CF $builddir $rd $dur "-nographic" "rcutorture.test_no_idle_hz=1 rcutorture.verbose=1"
 done
 # Tracing: trace_event=rcu:rcu_nocb_grace_period,rcu:rcu_grace_period,rcu:rcu_grace_period_init,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_torture_read,rcu:rcu_invoke_callback,rcu:rcu_fqs,rcu:rcu_dyntick,rcu:rcu_unlock_preempted_task
diff --git a/tools/testing/selftests/rcutorture/configs/CFLIST b/tools/testing/selftests/rcutorture/configs/CFLIST
new file mode 100644
index 0000000..da4cbc66
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/CFLIST
@@ -0,0 +1,17 @@
+sysidleY.2013.06.19a
+sysidleN.2013.06.19a
+P1-S-T-NH-SD-SMP-HP
+P2-2-t-nh-sd-SMP-hp
+P3-3-T-nh-SD-SMP-hp
+P4-A-t-NH-sd-SMP-HP
+P5-U-T-NH-sd-SMP-hp
+P6---t-nh-SD-smp-hp
+N1-S-T-NH-SD-SMP-HP
+N2-2-t-nh-sd-SMP-hp
+N3-3-T-nh-SD-SMP-hp
+N4-A-t-NH-sd-SMP-HP
+N5-U-T-NH-sd-SMP-hp
+PT1-nh
+PT2-NH
+NT1-nh
+NT3-NH
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/CFLIST b/tools/testing/selftests/rcutorture/configs/v0.0/CFLIST
new file mode 100644
index 0000000..1822394
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/CFLIST
@@ -0,0 +1,14 @@
+P1-S-T-NH-SD-SMP-HP
+P2-2-t-nh-sd-SMP-hp
+P3-3-T-nh-SD-SMP-hp
+P4-A-t-NH-sd-SMP-HP
+P5-U-T-NH-sd-SMP-hp
+N1-S-T-NH-SD-SMP-HP
+N2-2-t-nh-sd-SMP-hp
+N3-3-T-nh-SD-SMP-hp
+N4-A-t-NH-sd-SMP-HP
+N5-U-T-NH-sd-SMP-hp
+PT1-nh
+PT2-NH
+NT1-nh
+NT3-NH
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v0.0/N1-S-T-NH-SD-SMP-HP
index d81e11d..d3ef873 100644
--- a/tools/testing/selftests/rcutorture/configs/v0.0/N1-S-T-NH-SD-SMP-HP
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/N1-S-T-NH-SD-SMP-HP
@@ -1,5 +1,4 @@
 CONFIG_RCU_TRACE=y
-CONFIG_RCU_FAST_NO_HZ=y
 CONFIG_NO_HZ=y
 CONFIG_SMP=y
 CONFIG_RCU_FANOUT=8
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v0.0/P1-S-T-NH-SD-SMP-HP
index 9647c44..f72402d 100644
--- a/tools/testing/selftests/rcutorture/configs/v0.0/P1-S-T-NH-SD-SMP-HP
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/P1-S-T-NH-SD-SMP-HP
@@ -1,7 +1,6 @@
 CONFIG_RCU_TRACE=y
 CONFIG_RCU_CPU_STALL_INFO=y
 CONFIG_NO_HZ=y
-CONFIG_RCU_FAST_NO_HZ=y
 CONFIG_SMP=y
 CONFIG_RCU_FANOUT=8
 CONFIG_NR_CPUS=8
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/v0.0/ver_functions.sh
new file mode 100644
index 0000000..af7d59b
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/ver_functions.sh
@@ -0,0 +1,35 @@
+#!/bin/bash
+#
+# Kernel-version-dependent shell functions for the rest of the scripts.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+#
+# Copyright (C) IBM Corporation, 2013
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+# rcutorture_param_n_barrier_cbs bootparam-string
+#
+# Adds n_barrier_cbs rcutorture module parameter to kernels having it.
+rcutorture_param_n_barrier_cbs () {
+	echo $1
+}
+
+# rcutorture_param_onoff bootparam-string config-file
+#
+# Adds onoff rcutorture module parameters to kernels having it.
+rcutorture_param_onoff () {
+	echo $1
+}
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/CFLIST b/tools/testing/selftests/rcutorture/configs/v3.3/CFLIST
new file mode 100644
index 0000000..1822394
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/CFLIST
@@ -0,0 +1,14 @@
+P1-S-T-NH-SD-SMP-HP
+P2-2-t-nh-sd-SMP-hp
+P3-3-T-nh-SD-SMP-hp
+P4-A-t-NH-sd-SMP-HP
+P5-U-T-NH-sd-SMP-hp
+N1-S-T-NH-SD-SMP-HP
+N2-2-t-nh-sd-SMP-hp
+N3-3-T-nh-SD-SMP-hp
+N4-A-t-NH-sd-SMP-HP
+N5-U-T-NH-sd-SMP-hp
+PT1-nh
+PT2-NH
+NT1-nh
+NT3-NH
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/v3.3/ver_functions.sh
new file mode 100644
index 0000000..921fec9
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/ver_functions.sh
@@ -0,0 +1,41 @@
+#!/bin/bash
+#
+# Kernel-version-dependent shell functions for the rest of the scripts.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+#
+# Copyright (C) IBM Corporation, 2013
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+# rcutorture_param_n_barrier_cbs bootparam-string
+#
+# Adds n_barrier_cbs rcutorture module parameter to kernels having it.
+rcutorture_param_n_barrier_cbs () {
+	echo $1
+}
+
+# rcutorture_param_onoff bootparam-string config-file
+#
+# Adds onoff rcutorture module parameters to kernels having it.
+rcutorture_param_onoff () {
+	if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2"
+	then
+		echo CPU-hotplug kernel, adding rcutorture onoff.
+		echo $1 rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
+	else
+		echo $1
+	fi
+}
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/CFLIST b/tools/testing/selftests/rcutorture/configs/v3.5/CFLIST
new file mode 100644
index 0000000..1822394
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/CFLIST
@@ -0,0 +1,14 @@
+P1-S-T-NH-SD-SMP-HP
+P2-2-t-nh-sd-SMP-hp
+P3-3-T-nh-SD-SMP-hp
+P4-A-t-NH-sd-SMP-HP
+P5-U-T-NH-sd-SMP-hp
+N1-S-T-NH-SD-SMP-HP
+N2-2-t-nh-sd-SMP-hp
+N3-3-T-nh-SD-SMP-hp
+N4-A-t-NH-sd-SMP-HP
+N5-U-T-NH-sd-SMP-hp
+PT1-nh
+PT2-NH
+NT1-nh
+NT3-NH
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/v3.5/ver_functions.sh
new file mode 100644
index 0000000..4019744
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/ver_functions.sh
@@ -0,0 +1,46 @@
+#!/bin/bash
+#
+# Kernel-version-dependent shell functions for the rest of the scripts.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+#
+# Copyright (C) IBM Corporation, 2013
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+# rcutorture_param_n_barrier_cbs bootparam-string
+#
+# Adds n_barrier_cbs rcutorture module parameter to kernels having it.
+rcutorture_param_n_barrier_cbs () {
+	if echo $1 | grep -q "rcutorture\.n_barrier_cbs"
+	then
+		echo $1
+	else
+		echo $1 rcutorture.n_barrier_cbs=4
+	fi
+}
+
+# rcutorture_param_onoff bootparam-string config-file
+#
+# Adds onoff rcutorture module parameters to kernels having it.
+rcutorture_param_onoff () {
+	if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2"
+	then
+		echo CPU-hotplug kernel, adding rcutorture onoff.
+		echo $1 rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
+	else
+		echo $1
+	fi
+}
diff --git a/tools/testing/selftests/rcutorture/configs/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/ver_functions.sh
new file mode 100644
index 0000000..f99f23b
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/ver_functions.sh
@@ -0,0 +1,46 @@
+#!/bin/bash
+#
+# Kernel-version-dependent shell functions for the rest of the scripts.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+#
+# Copyright (C) IBM Corporation, 2013
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+# rcutorture_param_n_barrier_cbs bootparam-string
+#
+# Adds n_barrier_cbs rcutorture module parameter to kernels having it.
+rcutorture_param_n_barrier_cbs () {
+	if echo $1 | grep -q "rcutorture\.n_barrier_cbs"
+	then
+		echo $1
+	else
+		echo $1 rcutorture.n_barrier_cbs=4
+	fi
+}
+
+# rcutorture_param_onoff bootparam-string config-file
+#
+# Adds onoff rcutorture module parameters to kernels having it.
+rcutorture_param_onoff () {
+	if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2"
+	then
+		echo CPU-hotplug kernel, adding rcutorture onoff. 1>&2
+		echo $1 rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
+	else
+		echo $1
+	fi
+}
-- 
cgit v0.10.2


From 0cc2441447eafd4e0742b6363e416967167c5137 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sun, 29 Sep 2013 20:22:32 -0700
Subject: rcutorture: Add per-Kconfig fragment boot parameters

Some Kconfig fragments require rcutorture module parameters to
do optimal testing, for example, a configuration for SRCU would
need rcutorture.torture_type=srcu.  This commit therefore adds a
per-Kconfig-fragment boot-parameter capability.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index d4c15f8..8f91241 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -28,6 +28,18 @@ bootparam_hotplug_cpu () {
 	echo "$1" | grep -q "rcutorture\.onoff_"
 }
 
+# configfrag_boot_params bootparam-string config-fragment-file
+#
+# Adds boot parameters from the .boot file, if any.
+configfrag_boot_params () {
+	if test -r "$2.boot"
+	then
+		echo $1 `grep -v '^#' "$2.boot" | tr '\012' ' '`
+	else
+		echo $1
+	fi
+}
+
 # configfrag_hotplug_cpu config-fragment-file
 #
 # Returns 1 if the config fragment specifies hotplug CPU.
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
index 0a3f037..618aa4d 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
@@ -137,6 +137,8 @@ fi
 boot_args="`rcutorture_param_onoff "$boot_args" $builddir/.config`"
 # Generate rcu_barrier() boot parameter
 boot_args="`rcutorture_param_n_barrier_cbs "$boot_args"`"
+# Pull in Kconfig-fragment boot parameters
+boot_args="`configfrag_boot_params "$boot_args" "$config_template"`"
 
 echo $QEMU -name rcu-test -serial file:$builddir/console.log $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append \"noapic selinux=0 console=ttyS0 initcall_debug debug rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1 $boot_args\" > $resdir/qemu-cmd
 $QEMU -name rcu-test -serial file:$builddir/console.log $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append "noapic selinux=0 console=ttyS0 initcall_debug debug rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1 $boot_args" &
-- 
cgit v0.10.2


From ccb51a893c8c2b7c933b93f5c298e00b9d6eb76f Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 30 Sep 2013 08:09:12 -0700
Subject: rcutorture: Add v3.12 version, which adds sysidle testing

The v3.12 version of the kernel added the CONFIG_NO_HZ_FULL_SYSIDLE
Kconfig parameter, so this commit adds a version transition at that
point.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/CFLIST b/tools/testing/selftests/rcutorture/configs/v3.12/CFLIST
new file mode 100644
index 0000000..da4cbc66
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/CFLIST
@@ -0,0 +1,17 @@
+sysidleY.2013.06.19a
+sysidleN.2013.06.19a
+P1-S-T-NH-SD-SMP-HP
+P2-2-t-nh-sd-SMP-hp
+P3-3-T-nh-SD-SMP-hp
+P4-A-t-NH-sd-SMP-HP
+P5-U-T-NH-sd-SMP-hp
+P6---t-nh-SD-smp-hp
+N1-S-T-NH-SD-SMP-HP
+N2-2-t-nh-sd-SMP-hp
+N3-3-T-nh-SD-SMP-hp
+N4-A-t-NH-sd-SMP-HP
+N5-U-T-NH-sd-SMP-hp
+PT1-nh
+PT2-NH
+NT1-nh
+NT3-NH
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.12/N1-S-T-NH-SD-SMP-HP
new file mode 100644
index 0000000..d81e11d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/N1-S-T-NH-SD-SMP-HP
@@ -0,0 +1,19 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.12/N2-2-t-nh-sd-SMP-hp
new file mode 100644
index 0000000..02e4185
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/N2-2-t-nh-sd-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=4
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.12/N3-3-T-nh-SD-SMP-hp
new file mode 100644
index 0000000..b3100f6
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/N3-3-T-nh-SD-SMP-hp
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.12/N4-A-t-NH-sd-SMP-HP
new file mode 100644
index 0000000..c56b445
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/N4-A-t-NH-sd-SMP-HP
@@ -0,0 +1,18 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.12/N5-U-T-NH-sd-SMP-hp
new file mode 100644
index 0000000..90d924f
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/N5-U-T-NH-sd-SMP-hp
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N6---t-nh-SD-smp-hp b/tools/testing/selftests/rcutorture/configs/v3.12/N6---t-nh-SD-smp-hp
new file mode 100644
index 0000000..0ccc36d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/N6---t-nh-SD-smp-hp
@@ -0,0 +1,19 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_NR_CPUS=1
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N7-4-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.12/N7-4-T-NH-SD-SMP-HP
new file mode 100644
index 0000000..3f640cf
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/N7-4-T-NH-SD-SMP-HP
@@ -0,0 +1,26 @@
+CONFIG_RCU_TRACE=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=16
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_NONE=y
+CONFIG_RCU_NOCB_CPU_ZERO=n
+CONFIG_RCU_NOCB_CPU_ALL=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/N8-2-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.12/N8-2-T-NH-SD-SMP-HP
new file mode 100644
index 0000000..285da2d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/N8-2-T-NH-SD-SMP-HP
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=14
+CONFIG_NR_CPUS=16
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/NT1-nh b/tools/testing/selftests/rcutorture/configs/v3.12/NT1-nh
new file mode 100644
index 0000000..023f312
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/NT1-nh
@@ -0,0 +1,23 @@
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=n
+#
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/NT3-NH b/tools/testing/selftests/rcutorture/configs/v3.12/NT3-NH
new file mode 100644
index 0000000..6fd0235
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/NT3-NH
@@ -0,0 +1,20 @@
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=y
+#
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.12/P1-S-T-NH-SD-SMP-HP
new file mode 100644
index 0000000..9647c44
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P1-S-T-NH-SD-SMP-HP
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=8
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.12/P2-2-t-nh-sd-SMP-hp
new file mode 100644
index 0000000..0f3b667
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P2-2-t-nh-sd-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=4
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.12/P3-3-T-nh-SD-SMP-hp
new file mode 100644
index 0000000..b035e14
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P3-3-T-nh-SD-SMP-hp
@@ -0,0 +1,20 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=n
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.12/P4-A-t-NH-sd-SMP-HP
new file mode 100644
index 0000000..3ccf6a9
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P4-A-t-NH-sd-SMP-HP
@@ -0,0 +1,22 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_RT_MUTEXES=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.12/P5-U-T-NH-sd-SMP-hp
new file mode 100644
index 0000000..ef624ce
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P5-U-T-NH-sd-SMP-hp
@@ -0,0 +1,28 @@
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=6
+CONFIG_NR_CPUS=8
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_PROVE_RCU_DELAY=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_RT_MUTEXES=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P6---t-nh-SD-smp-hp b/tools/testing/selftests/rcutorture/configs/v3.12/P6---t-nh-SD-smp-hp
new file mode 100644
index 0000000..f4c9175
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P6---t-nh-SD-smp-hp
@@ -0,0 +1,18 @@
+CONFIG_RCU_TRACE=n
+CONFIG_NO_HZ=n
+CONFIG_SMP=n
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP
new file mode 100644
index 0000000..77a8c5b
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP
@@ -0,0 +1,30 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=16
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_NONE=n
+CONFIG_RCU_NOCB_CPU_ZERO=n
+CONFIG_RCU_NOCB_CPU_ALL=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_SLUB=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-all b/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-all
new file mode 100644
index 0000000..0eecebc
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-all
@@ -0,0 +1,30 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=16
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_NONE=y
+CONFIG_RCU_NOCB_CPU_ZERO=n
+CONFIG_RCU_NOCB_CPU_ALL=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_SLUB=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-none b/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-none
new file mode 100644
index 0000000..0eecebc
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-HP-none
@@ -0,0 +1,30 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=16
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_NONE=y
+CONFIG_RCU_NOCB_CPU_ZERO=n
+CONFIG_RCU_NOCB_CPU_ALL=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_SLUB=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-hp
new file mode 100644
index 0000000..588bc70
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/P7-4-T-NH-SD-SMP-hp
@@ -0,0 +1,30 @@
+CONFIG_RCU_TRACE=y
+CONFIG_NO_HZ=y
+CONFIG_SMP=y
+CONFIG_RCU_FANOUT=2
+CONFIG_NR_CPUS=16
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_NONE=n
+CONFIG_RCU_NOCB_CPU_ZERO=y
+CONFIG_RCU_NOCB_CPU_ALL=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_SLUB=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/PT1-nh b/tools/testing/selftests/rcutorture/configs/v3.12/PT1-nh
new file mode 100644
index 0000000..e3361c3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/PT1-nh
@@ -0,0 +1,23 @@
+CONFIG_TINY_PREEMPT_RCU=y
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_RCU_TRACE=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=n
+#
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
diff --git a/tools/testing/selftests/rcutorture/configs/v3.12/PT2-NH b/tools/testing/selftests/rcutorture/configs/v3.12/PT2-NH
new file mode 100644
index 0000000..64abfc3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/v3.12/PT2-NH
@@ -0,0 +1,22 @@
+CONFIG_TINY_PREEMPT_RCU=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_MODULE_UNLOAD=y
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+#
+CONFIG_SMP=n
+#
+CONFIG_HOTPLUG_CPU=n
+#
+CONFIG_NO_HZ=y
+#
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_PRINTK_TIME=y
+
-- 
cgit v0.10.2


From a0b8e0853a87ef008a819e8cbe905735934396da Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 30 Sep 2013 09:47:38 -0700
Subject: rcutorture: Add SRCU Kconfig-fragment files

Use .boot facility to ease inclusion of SRCU into automated testing.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/configs/SRCU-N b/tools/testing/selftests/rcutorture/configs/SRCU-N
new file mode 100644
index 0000000..10a0e27
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/SRCU-N
@@ -0,0 +1,8 @@
+CONFIG_RCU_TRACE=n
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/SRCU-N.boot b/tools/testing/selftests/rcutorture/configs/SRCU-N.boot
new file mode 100644
index 0000000..238bfe3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/SRCU-N.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=srcu
diff --git a/tools/testing/selftests/rcutorture/configs/SRCU-P b/tools/testing/selftests/rcutorture/configs/SRCU-P
new file mode 100644
index 0000000..6650e00
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/SRCU-P
@@ -0,0 +1,8 @@
+CONFIG_RCU_TRACE=n
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/SRCU-P.boot b/tools/testing/selftests/rcutorture/configs/SRCU-P.boot
new file mode 100644
index 0000000..238bfe3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/SRCU-P.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=srcu
-- 
cgit v0.10.2


From 27ac1ddf214741d152909f89981ee2bdf16318c9 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 30 Sep 2013 12:32:45 -0700
Subject: rcutorture: Refactor TREE_RCU test cases

The TREE_RCU test cases were first put in place many years ago, and have
been incrementally modified rather than being reworked.  This commit
therefore completes a long-overdue reworking of the TREE_RCU test cases.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/configs/CFLIST b/tools/testing/selftests/rcutorture/configs/CFLIST
index da4cbc66..884491b 100644
--- a/tools/testing/selftests/rcutorture/configs/CFLIST
+++ b/tools/testing/selftests/rcutorture/configs/CFLIST
@@ -1,17 +1,13 @@
-sysidleY.2013.06.19a
-sysidleN.2013.06.19a
-P1-S-T-NH-SD-SMP-HP
-P2-2-t-nh-sd-SMP-hp
-P3-3-T-nh-SD-SMP-hp
-P4-A-t-NH-sd-SMP-HP
-P5-U-T-NH-sd-SMP-hp
-P6---t-nh-SD-smp-hp
-N1-S-T-NH-SD-SMP-HP
-N2-2-t-nh-sd-SMP-hp
-N3-3-T-nh-SD-SMP-hp
-N4-A-t-NH-sd-SMP-HP
-N5-U-T-NH-sd-SMP-hp
-PT1-nh
-PT2-NH
+TREE01
+TREE02
+TREE03
+TREE04
+TREE05
+TREE06
+TREE07
+TREE08
+TREE09
+SRCU-N
+SRCU-P
 NT1-nh
 NT3-NH
diff --git a/tools/testing/selftests/rcutorture/configs/N1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/N1-S-T-NH-SD-SMP-HP
deleted file mode 100644
index d81e11d..0000000
--- a/tools/testing/selftests/rcutorture/configs/N1-S-T-NH-SD-SMP-HP
+++ /dev/null
@@ -1,19 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_FAST_NO_HZ=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=8
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/N2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/N2-2-t-nh-sd-SMP-hp
deleted file mode 100644
index 02e4185..0000000
--- a/tools/testing/selftests/rcutorture/configs/N2-2-t-nh-sd-SMP-hp
+++ /dev/null
@@ -1,20 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=4
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/N3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/N3-3-T-nh-SD-SMP-hp
deleted file mode 100644
index b3100f6..0000000
--- a/tools/testing/selftests/rcutorture/configs/N3-3-T-nh-SD-SMP-hp
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/N4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/N4-A-t-NH-sd-SMP-HP
deleted file mode 100644
index c56b445..0000000
--- a/tools/testing/selftests/rcutorture/configs/N4-A-t-NH-sd-SMP-HP
+++ /dev/null
@@ -1,18 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/N5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/N5-U-T-NH-sd-SMP-hp
deleted file mode 100644
index 90d924f..0000000
--- a/tools/testing/selftests/rcutorture/configs/N5-U-T-NH-sd-SMP-hp
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=y
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/N6---t-nh-SD-smp-hp b/tools/testing/selftests/rcutorture/configs/N6---t-nh-SD-smp-hp
deleted file mode 100644
index 0ccc36d..0000000
--- a/tools/testing/selftests/rcutorture/configs/N6---t-nh-SD-smp-hp
+++ /dev/null
@@ -1,19 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_NR_CPUS=1
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/N7-4-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/N7-4-T-NH-SD-SMP-HP
deleted file mode 100644
index 3f640cf..0000000
--- a/tools/testing/selftests/rcutorture/configs/N7-4-T-NH-SD-SMP-HP
+++ /dev/null
@@ -1,26 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=16
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_RCU_NOCB_CPU=y
-CONFIG_RCU_NOCB_CPU_NONE=y
-CONFIG_RCU_NOCB_CPU_ZERO=n
-CONFIG_RCU_NOCB_CPU_ALL=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/N8-2-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/N8-2-T-NH-SD-SMP-HP
deleted file mode 100644
index 285da2d..0000000
--- a/tools/testing/selftests/rcutorture/configs/N8-2-T-NH-SD-SMP-HP
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=14
-CONFIG_NR_CPUS=16
-CONFIG_RCU_FANOUT_EXACT=y
-CONFIG_HOTPLUG_CPU=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-#CHECK#CONFIG_TREE_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/P1-S-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/P1-S-T-NH-SD-SMP-HP
deleted file mode 100644
index 9647c44..0000000
--- a/tools/testing/selftests/rcutorture/configs/P1-S-T-NH-SD-SMP-HP
+++ /dev/null
@@ -1,20 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ=y
-CONFIG_RCU_FAST_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=8
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/P2-2-t-nh-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/P2-2-t-nh-sd-SMP-hp
deleted file mode 100644
index 0f3b667..0000000
--- a/tools/testing/selftests/rcutorture/configs/P2-2-t-nh-sd-SMP-hp
+++ /dev/null
@@ -1,20 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=4
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/P3-3-T-nh-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/P3-3-T-nh-SD-SMP-hp
deleted file mode 100644
index b035e14..0000000
--- a/tools/testing/selftests/rcutorture/configs/P3-3-T-nh-SD-SMP-hp
+++ /dev/null
@@ -1,20 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_NO_HZ=n
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/P4-A-t-NH-sd-SMP-HP b/tools/testing/selftests/rcutorture/configs/P4-A-t-NH-sd-SMP-HP
deleted file mode 100644
index 3ccf6a9..0000000
--- a/tools/testing/selftests/rcutorture/configs/P4-A-t-NH-sd-SMP-HP
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_RT_MUTEXES=y
-CONFIG_RCU_BOOST=y
-CONFIG_RCU_BOOST_PRIO=2
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/P5-U-T-NH-sd-SMP-hp b/tools/testing/selftests/rcutorture/configs/P5-U-T-NH-sd-SMP-hp
deleted file mode 100644
index ef624ce..0000000
--- a/tools/testing/selftests/rcutorture/configs/P5-U-T-NH-sd-SMP-hp
+++ /dev/null
@@ -1,28 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=6
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=y
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_PROVE_RCU_DELAY=y
-CONFIG_DEBUG_OBJECTS=y
-CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
-CONFIG_RT_MUTEXES=y
-CONFIG_RCU_BOOST=y
-CONFIG_RCU_BOOST_PRIO=2
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/P6---t-nh-SD-smp-hp b/tools/testing/selftests/rcutorture/configs/P6---t-nh-SD-smp-hp
deleted file mode 100644
index f4c9175..0000000
--- a/tools/testing/selftests/rcutorture/configs/P6---t-nh-SD-smp-hp
+++ /dev/null
@@ -1,18 +0,0 @@
-CONFIG_RCU_TRACE=n
-CONFIG_NO_HZ=n
-CONFIG_SMP=n
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-HP b/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-HP
deleted file mode 100644
index 77a8c5b..0000000
--- a/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-HP
+++ /dev/null
@@ -1,30 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=16
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_RCU_NOCB_CPU=y
-CONFIG_RCU_NOCB_CPU_NONE=n
-CONFIG_RCU_NOCB_CPU_ZERO=n
-CONFIG_RCU_NOCB_CPU_ALL=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_OBJECTS=y
-CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_SLUB=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-HP-all b/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-HP-all
deleted file mode 100644
index 0eecebc..0000000
--- a/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-HP-all
+++ /dev/null
@@ -1,30 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=16
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_RCU_NOCB_CPU=y
-CONFIG_RCU_NOCB_CPU_NONE=y
-CONFIG_RCU_NOCB_CPU_ZERO=n
-CONFIG_RCU_NOCB_CPU_ALL=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_OBJECTS=y
-CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_SLUB=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-HP-none b/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-HP-none
deleted file mode 100644
index 0eecebc..0000000
--- a/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-HP-none
+++ /dev/null
@@ -1,30 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=16
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_RCU_NOCB_CPU=y
-CONFIG_RCU_NOCB_CPU_NONE=y
-CONFIG_RCU_NOCB_CPU_ZERO=n
-CONFIG_RCU_NOCB_CPU_ALL=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_OBJECTS=y
-CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_SLUB=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-hp b/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-hp
deleted file mode 100644
index 588bc70..0000000
--- a/tools/testing/selftests/rcutorture/configs/P7-4-T-NH-SD-SMP-hp
+++ /dev/null
@@ -1,30 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=2
-CONFIG_NR_CPUS=16
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=n
-CONFIG_RCU_NOCB_CPU=y
-CONFIG_RCU_NOCB_CPU_NONE=n
-CONFIG_RCU_NOCB_CPU_ZERO=y
-CONFIG_RCU_NOCB_CPU_ALL=n
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_OBJECTS=y
-CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_SLUB=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/TREE01 b/tools/testing/selftests/rcutorture/configs/TREE01
new file mode 100644
index 0000000..141119a
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE01
@@ -0,0 +1,23 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_RCU_TRACE=y
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_FANOUT=8
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_ZERO=y
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_RCU_DELAY=n
+CONFIG_RCU_CPU_STALL_INFO=n
+CONFIG_RCU_CPU_STALL_VERBOSE=n
+CONFIG_RCU_BOOST=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE01.boot b/tools/testing/selftests/rcutorture/configs/TREE01.boot
new file mode 100644
index 0000000..0fc8a34
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE01.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=rcu_bh
diff --git a/tools/testing/selftests/rcutorture/configs/TREE02 b/tools/testing/selftests/rcutorture/configs/TREE02
new file mode 100644
index 0000000..2d4d096
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE02
@@ -0,0 +1,26 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_FAST_NO_HZ=n 
+CONFIG_RCU_TRACE=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_RCU_FANOUT=3
+CONFIG_RCU_FANOUT_LEAF=3
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_RCU_NOCB_CPU=n
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_PROVE_LOCKING=n
+CONFIG_PROVE_RCU_DELAY=n
+CONFIG_RCU_CPU_STALL_INFO=n
+CONFIG_RCU_CPU_STALL_VERBOSE=y
+CONFIG_RCU_BOOST=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE03 b/tools/testing/selftests/rcutorture/configs/TREE03
new file mode 100644
index 0000000..a47de5b
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE03
@@ -0,0 +1,23 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_HZ_PERIODIC=y
+CONFIG_NO_HZ_IDLE=n
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_TRACE=y
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_FANOUT=4
+CONFIG_RCU_FANOUT_LEAF=4
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_RCU_NOCB_CPU=n
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_RCU_DELAY=n
+CONFIG_RCU_CPU_STALL_INFO=n
+CONFIG_RCU_CPU_STALL_VERBOSE=n
+CONFIG_RCU_BOOST=y
+CONFIG_RCU_BOOST_PRIO=2
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE04 b/tools/testing/selftests/rcutorture/configs/TREE04
new file mode 100644
index 0000000..8d839b8
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE04
@@ -0,0 +1,25 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=n
+CONFIG_NO_HZ_FULL=y
+CONFIG_NO_HZ_FULL_ALL=y
+CONFIG_RCU_FAST_NO_HZ=y
+CONFIG_RCU_TRACE=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_RCU_FANOUT=2
+CONFIG_RCU_FANOUT_LEAF=2
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_RCU_NOCB_CPU=n
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_RCU_DELAY=n
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_RCU_CPU_STALL_VERBOSE=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE04.boot b/tools/testing/selftests/rcutorture/configs/TREE04.boot
new file mode 100644
index 0000000..0fc8a34
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE04.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=rcu_bh
diff --git a/tools/testing/selftests/rcutorture/configs/TREE05 b/tools/testing/selftests/rcutorture/configs/TREE05
new file mode 100644
index 0000000..b5ba72e
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE05
@@ -0,0 +1,25 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_FAST_NO_HZ=n
+CONFIG_RCU_TRACE=n
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_FANOUT=6
+CONFIG_RCU_FANOUT_LEAF=6
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_NONE=y
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_PROVE_RCU_DELAY=y
+CONFIG_RCU_CPU_STALL_INFO=n
+CONFIG_RCU_CPU_STALL_VERBOSE=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE05.boot b/tools/testing/selftests/rcutorture/configs/TREE05.boot
new file mode 100644
index 0000000..3b42b8b
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE05.boot
@@ -0,0 +1 @@
+rcutorture.torture_type=sched
diff --git a/tools/testing/selftests/rcutorture/configs/TREE06 b/tools/testing/selftests/rcutorture/configs/TREE06
new file mode 100644
index 0000000..7c95ab4
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE06
@@ -0,0 +1,26 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_FAST_NO_HZ=n
+CONFIG_RCU_TRACE=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_RCU_FANOUT=6
+CONFIG_RCU_FANOUT_LEAF=6
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_RCU_NOCB_CPU=n
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU=y
+CONFIG_PROVE_RCU_DELAY=n
+CONFIG_RCU_CPU_STALL_INFO=n
+CONFIG_RCU_CPU_STALL_VERBOSE=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE07 b/tools/testing/selftests/rcutorture/configs/TREE07
new file mode 100644
index 0000000..1467404
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE07
@@ -0,0 +1,24 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=16
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TREE_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=n
+CONFIG_NO_HZ_FULL=y
+CONFIG_NO_HZ_FULL_ALL=y
+CONFIG_NO_HZ_FULL_SYSIDLE=y
+CONFIG_RCU_FAST_NO_HZ=n
+CONFIG_RCU_TRACE=y
+CONFIG_HOTPLUG_CPU=y
+CONFIG_RCU_FANOUT=2
+CONFIG_RCU_FANOUT_LEAF=2
+CONFIG_RCU_FANOUT_EXACT=n
+CONFIG_RCU_NOCB_CPU=n
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_RCU_DELAY=n
+CONFIG_RCU_CPU_STALL_INFO=y
+CONFIG_RCU_CPU_STALL_VERBOSE=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE08 b/tools/testing/selftests/rcutorture/configs/TREE08
new file mode 100644
index 0000000..7d097a6
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE08
@@ -0,0 +1,26 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=16
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_FAST_NO_HZ=n
+CONFIG_RCU_TRACE=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_RCU_FANOUT=3
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_RCU_FANOUT_LEAF=2
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_ALL=y
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_RCU_DELAY=n
+CONFIG_RCU_CPU_STALL_INFO=n
+CONFIG_RCU_CPU_STALL_VERBOSE=n
+CONFIG_RCU_BOOST=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TREE09 b/tools/testing/selftests/rcutorture/configs/TREE09
new file mode 100644
index 0000000..0d1ec0d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE09
@@ -0,0 +1,21 @@
+CONFIG_SMP=n
+CONFIG_NR_CPUS=1
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_TRACE=n
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_RCU_NOCB_CPU=n
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_RCU_DELAY=n
+CONFIG_RCU_CPU_STALL_INFO=n
+CONFIG_RCU_CPU_STALL_VERBOSE=n
+CONFIG_RCU_BOOST=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/sysidleN.2013.06.19a b/tools/testing/selftests/rcutorture/configs/sysidleN.2013.06.19a
deleted file mode 100644
index 9dbcde3..0000000
--- a/tools/testing/selftests/rcutorture/configs/sysidleN.2013.06.19a
+++ /dev/null
@@ -1,23 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ_PERIODIC=n
-CONFIG_NO_HZ_IDLE=n
-CONFIG_NO_HZ_FULL=y
-CONFIG_NO_HZ_FULL_SYSIDLE=n
-CONFIG_RCU_FAST_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=8
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/sysidleY.2013.06.19a b/tools/testing/selftests/rcutorture/configs/sysidleY.2013.06.19a
deleted file mode 100644
index d24dd6148..0000000
--- a/tools/testing/selftests/rcutorture/configs/sysidleY.2013.06.19a
+++ /dev/null
@@ -1,26 +0,0 @@
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_CPU_STALL_INFO=y
-CONFIG_NO_HZ_PERIODIC=n
-CONFIG_NO_HZ_IDLE=n
-CONFIG_NO_HZ_FULL=y
-CONFIG_NO_HZ_FULL_SYSIDLE=y
-CONFIG_RCU_FAST_NO_HZ=y
-CONFIG_SMP=y
-CONFIG_RCU_FANOUT=8
-CONFIG_NR_CPUS=8
-CONFIG_RCU_FANOUT_EXACT=n
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-#CHECK#CONFIG_TREE_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-
diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-Kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-Kconfig.txt
new file mode 100644
index 0000000..adbb76c
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-Kconfig.txt
@@ -0,0 +1,95 @@
+This document gives a brief rationale for the TREE_RCU-related test
+cases, a group that includes TREE_PREEMPT_RCU.
+
+
+Kconfig Parameters:
+
+CONFIG_DEBUG_LOCK_ALLOC -- Do three, covering CONFIG_PROVE_LOCKING & not.
+CONFIG_DEBUG_OBJECTS_RCU_HEAD -- Do one.
+CONFIG_HOTPLUG_CPU -- Do half.  (Every second.)
+CONFIG_HZ_PERIODIC -- Do one.
+CONFIG_NO_HZ_IDLE -- Do those not otherwise specified. (Groups of two.)
+CONFIG_NO_HZ_FULL -- Do two, one with CONFIG_NO_HZ_FULL_SYSIDLE.
+CONFIG_NO_HZ_FULL_SYSIDLE -- Do one.
+CONFIG_PREEMPT -- Do half.  (First three and #8.)
+CONFIG_PROVE_LOCKING -- Do all but two, covering CONFIG_PROVE_RCU and not.
+CONFIG_PROVE_RCU -- Do all but one under CONFIG_PROVE_LOCKING.
+CONFIG_PROVE_RCU_DELAY -- Do one.
+CONFIG_RCU_BOOST -- one of TREE_PREEMPT_RCU.
+CONFIG_RCU_BOOST_PRIO -- set to 2 for _BOOST testing.
+CONFIG_RCU_CPU_STALL_INFO -- do one with and without _VERBOSE.
+CONFIG_RCU_CPU_STALL_VERBOSE -- do one with and without _INFO.
+CONFIG_RCU_FANOUT -- Cover hierarchy as currently, but overlap with others.
+CONFIG_RCU_FANOUT_EXACT -- Do one.
+CONFIG_RCU_FANOUT_LEAF -- Do one non-default.
+CONFIG_RCU_FAST_NO_HZ -- Do one, but not with CONFIG_RCU_NOCB_CPU_ALL.
+CONFIG_RCU_NOCB_CPU -- Do three, see below.
+CONFIG_RCU_NOCB_CPU_ALL -- Do one.
+CONFIG_RCU_NOCB_CPU_NONE -- Do one.
+CONFIG_RCU_NOCB_CPU_ZERO -- Do one.
+CONFIG_RCU_TRACE -- Do half.
+CONFIG_SMP -- Need one !SMP for TREE_PREEMPT_RCU.
+RCU-bh: Do one with PREEMPT and one with !PREEMPT.
+RCU-sched: Do one with PREEMPT but not BOOST.
+
+
+Hierarchy:
+
+TREE01.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=8, CONFIG_RCU_FANOUT_EXACT=n.
+TREE02.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=3, CONFIG_RCU_FANOUT_EXACT=n,
+	CONFIG_RCU_FANOUT_LEAF=3.
+TREE03.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=4, CONFIG_RCU_FANOUT_EXACT=n,
+	CONFIG_RCU_FANOUT_LEAF=4.
+TREE04.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=2, CONFIG_RCU_FANOUT_EXACT=n,
+	CONFIG_RCU_FANOUT_LEAF=2.
+TREE05.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=6, CONFIG_RCU_FANOUT_EXACT=n
+	CONFIG_RCU_FANOUT_LEAF=6.
+TREE06.	CONFIG_NR_CPUS=8, CONFIG_RCU_FANOUT=6, CONFIG_RCU_FANOUT_EXACT=y
+	CONFIG_RCU_FANOUT_LEAF=6.
+TREE07.	CONFIG_NR_CPUS=16, CONFIG_RCU_FANOUT=2, CONFIG_RCU_FANOUT_EXACT=n,
+	CONFIG_RCU_FANOUT_LEAF=2.
+TREE08.	CONFIG_NR_CPUS=16, CONFIG_RCU_FANOUT=3, CONFIG_RCU_FANOUT_EXACT=y,
+	CONFIG_RCU_FANOUT_LEAF=2.
+TREE09.	CONFIG_NR_CPUS=1.
+
+
+Kconfig Parameters Ignored:
+
+CONFIG_64BIT
+
+	Used only to check CONFIG_RCU_FANOUT value, inspection suffices.
+
+CONFIG_NO_HZ_FULL_SYSIDLE_SMALL
+
+	Defer until Frederic uses this.
+
+CONFIG_PREEMPT_COUNT
+CONFIG_PREEMPT_RCU
+
+	Redundant with CONFIG_PREEMPT, ignore.
+
+CONFIG_RCU_BOOST_DELAY
+
+	Inspection suffices, ignore.
+
+CONFIG_RCU_CPU_STALL_TIMEOUT
+
+	Inspection suffices, ignore.
+
+CONFIG_RCU_STALL_COMMON
+
+	Implied by TREE_RCU and TREE_PREEMPT_RCU.
+
+CONFIG_RCU_TORTURE_TEST
+CONFIG_RCU_TORTURE_TEST_RUNNABLE
+
+	Always used in KVM testing.
+
+CONFIG_RCU_USER_QS
+
+	Redundant with CONFIG_NO_HZ_FULL.
+
+CONFIG_TREE_PREEMPT_RCU
+CONFIG_TREE_RCU
+
+	These are controlled by CONFIG_PREEMPT.
-- 
cgit v0.10.2


From 0f66f92d11f80d0972b180f0151e629fc0c12cb1 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 30 Sep 2013 13:21:08 -0700
Subject: rcutorture: Refactor TINY_RCU test cases

The TINY_RCU test cases were first put in place many years ago, and have
been incrementally modified rather than being reworked.  This commit
therefore completes a long-overdue reworking of the TINY_RCU test cases.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/configs/CFLIST b/tools/testing/selftests/rcutorture/configs/CFLIST
index 884491b..cd3d29c 100644
--- a/tools/testing/selftests/rcutorture/configs/CFLIST
+++ b/tools/testing/selftests/rcutorture/configs/CFLIST
@@ -9,5 +9,5 @@ TREE08
 TREE09
 SRCU-N
 SRCU-P
-NT1-nh
-NT3-NH
+TINY01
+TINY02
diff --git a/tools/testing/selftests/rcutorture/configs/NT1-nh b/tools/testing/selftests/rcutorture/configs/NT1-nh
deleted file mode 100644
index 023f312..0000000
--- a/tools/testing/selftests/rcutorture/configs/NT1-nh
+++ /dev/null
@@ -1,23 +0,0 @@
-#CHECK#CONFIG_TINY_RCU=y
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=n
-#
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/NT3-NH b/tools/testing/selftests/rcutorture/configs/NT3-NH
deleted file mode 100644
index 6fd0235..0000000
--- a/tools/testing/selftests/rcutorture/configs/NT3-NH
+++ /dev/null
@@ -1,20 +0,0 @@
-#CHECK#CONFIG_TINY_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=y
-#
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=n
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/PT1-nh b/tools/testing/selftests/rcutorture/configs/PT1-nh
deleted file mode 100644
index e3361c3..0000000
--- a/tools/testing/selftests/rcutorture/configs/PT1-nh
+++ /dev/null
@@ -1,23 +0,0 @@
-CONFIG_TINY_PREEMPT_RCU=y
-CONFIG_RCU_BOOST=y
-CONFIG_RCU_BOOST_PRIO=2
-CONFIG_RCU_TRACE=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=n
-#
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/PT2-NH b/tools/testing/selftests/rcutorture/configs/PT2-NH
deleted file mode 100644
index 64abfc3..0000000
--- a/tools/testing/selftests/rcutorture/configs/PT2-NH
+++ /dev/null
@@ -1,22 +0,0 @@
-CONFIG_TINY_PREEMPT_RCU=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_MODULE_UNLOAD=y
-CONFIG_SUSPEND=n
-CONFIG_HIBERNATION=n
-#
-CONFIG_SMP=n
-#
-CONFIG_HOTPLUG_CPU=n
-#
-CONFIG_NO_HZ=y
-#
-CONFIG_PREEMPT_NONE=n
-CONFIG_PREEMPT_VOLUNTARY=n
-CONFIG_PREEMPT=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_PROVE_RCU=y
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_PRINTK_TIME=y
-
diff --git a/tools/testing/selftests/rcutorture/configs/TINY01 b/tools/testing/selftests/rcutorture/configs/TINY01
new file mode 100644
index 0000000..0c2823f
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TINY01
@@ -0,0 +1,13 @@
+CONFIG_SMP=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_TRACE=n
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PREEMPT_COUNT=n
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/configs/TINY02 b/tools/testing/selftests/rcutorture/configs/TINY02
new file mode 100644
index 0000000..e5072d7
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TINY02
@@ -0,0 +1,13 @@
+CONFIG_SMP=n
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+#CHECK#CONFIG_TINY_RCU=y
+CONFIG_HZ_PERIODIC=y
+CONFIG_NO_HZ_IDLE=n
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_TRACE=y
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PREEMPT_COUNT=y
+CONFIG_PRINTK_TIME=y
diff --git a/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt
new file mode 100644
index 0000000..28db67b
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/doc/TINY_RCU.txt
@@ -0,0 +1,40 @@
+This document gives a brief rationale for the TINY_RCU test cases.
+
+
+Kconfig Parameters:
+
+CONFIG_DEBUG_LOCK_ALLOC -- Do all three and none of the three.
+CONFIG_PREEMPT_COUNT
+CONFIG_RCU_TRACE
+
+The theory here is that randconfig testing will hit the other six possible
+combinations of these parameters.
+
+
+Kconfig Parameters Ignored:
+
+CONFIG_DEBUG_OBJECTS_RCU_HEAD
+CONFIG_PROVE_RCU
+
+	In common code tested by TREE_RCU test cases.
+
+CONFIG_NO_HZ_FULL_SYSIDLE
+CONFIG_RCU_NOCB_CPU
+CONFIG_RCU_USER_QS
+
+	Meaningless for TINY_RCU.
+
+CONFIG_RCU_STALL_COMMON
+CONFIG_RCU_TORTURE_TEST
+
+	Redundant with CONFIG_RCU_TRACE.
+
+CONFIG_HOTPLUG_CPU
+CONFIG_PREEMPT
+CONFIG_PREEMPT_RCU
+CONFIG_SMP
+CONFIG_TINY_RCU
+CONFIG_TREE_PREEMPT_RCU
+CONFIG_TREE_RCU
+
+	All forced by CONFIG_TINY_RCU.
-- 
cgit v0.10.2


From 330a76f15651a715a54bc2022586a7be151c9963 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 30 Sep 2013 14:49:43 -0700
Subject: rcutorture: Make test output less chatty

This commit drops no-longer-needed diagnostics from the output.  Some of
them are retained in logfiles, in case they are ever needed.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh
index 1f09d59..926fbd3 100755
--- a/tools/testing/selftests/rcutorture/bin/configinit.sh
+++ b/tools/testing/selftests/rcutorture/bin/configinit.sh
@@ -14,8 +14,6 @@
 # for example, "O=/tmp/foo".  If this argument is omitted, the .config
 # file will be generated directly in the current directory.
 
-echo configinit.sh $*
-
 T=/tmp/configinit.sh.$$
 trap 'rm -rf $T' 0
 mkdir $T
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
index 618aa4d..5526550 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
@@ -62,7 +62,7 @@ then
 fi
 cp $config_template $resdir/ConfigFragment
 echo ' ---' `date`: Starting build
-echo ' ---' Kconfig fragment at: $config_template
+echo ' ---' Kconfig fragment at: $config_template >> $resdir/log
 cat << '___EOF___' >> $T
 CONFIG_RCU_TORTURE_TEST=y
 ___EOF___
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 92f726b..bf6d68e 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -28,6 +28,7 @@
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
 scriptname=$0
+args="$*"
 
 dur=30
 KVM=`pwd`/tools/testing/selftests/rcutorture; export KVM
@@ -73,7 +74,6 @@ checkarg () {
 
 while test $# -gt 0
 do
-	echo ":$1:"
 	case "$1" in
 	--builddir)
 		checkarg --builddir "(absolute pathname)" "$#" "$2" '^/' error
@@ -133,11 +133,6 @@ do
 	shift
 done
 
-echo "builddir=$builddir"
-echo "dur=$dur"
-echo "KVM=$KVM"
-echo "resdir=$resdir"
-
 PATH=${KVM}/bin:$PATH; export PATH
 CONFIGFRAG=${KVM}/configs; export CONFIGFRAG
 KVPATH=${CONFIGFRAG}/$kversion; export KVPATH
@@ -150,12 +145,19 @@ fi
 if test -z "$resdir"
 then
 	resdir=$KVM/res
-	mkdir $resdir || :
+	if ! test -e $resdir
+	then
+		mkdir $resdir || :
+	fi
 else
-	mkdir -p "$resdir" || :
+	if ! test -e $resdir
+	then
+		mkdir -p "$resdir" || :
+	fi
 fi
 mkdir $resdir/$ds
-echo Datestamp: $ds
+touch $resdir/$ds/log
+echo $scriptname $args >> $resdir/$ds/log
 
 pwd > $resdir/$ds/testid.txt
 if test -d .git
@@ -164,7 +166,10 @@ then
 	git rev-parse HEAD >> $resdir/$ds/testid.txt
 fi
 builddir=$KVM/b1
-mkdir $builddir || :
+if ! test -e $builddir
+then
+	mkdir $builddir || :
+fi
 
 for CF in $configs
 do
-- 
cgit v0.10.2


From 50d48a1d154ef9ece016512817dbbd33c598f162 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 30 Sep 2013 15:16:14 -0700
Subject: rcutorture: Eliminate duplicate .config-check code

The commit uses configcheck.sh from within configinit.sh, replacing the
imperfect inline expansion that was there before.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh
index 926fbd3..939c16c 100755
--- a/tools/testing/selftests/rcutorture/bin/configinit.sh
+++ b/tools/testing/selftests/rcutorture/bin/configinit.sh
@@ -51,31 +51,6 @@ cp $builddir/.config $builddir/.config.new
 yes '' | make $buildloc oldconfig > $builddir/Make.modconfig.out 2>&1
 
 # verify new config matches specification.
+configcheck.sh $builddir/.config $c
 
-sed -e 's/"//g' < $c > $T/c
-sed -e 's/"//g' < $builddir/.config > $T/.config
-sed -e 's/\(.*\)=n/# \1 is not set/' -e 's/^#CHECK#//' < $c |
-awk	'
-	{
-		print "if grep -q \"" $0 "\" < '"$T/.config"'";
-		print "then";
-		print "\t:";
-		print "else";
-		if ($1 == "#") {
-			print "\tif grep -q \"" $2 "\" < '"$T/.config"'";
-			print "\tthen";
-			print "\t\techo \":" $2 ": improperly set\"";
-			print "\telse";
-			print "\t\t:";
-			print "\tfi";
-		} else {
-			print "\techo \":" $0 ": improperly set\"";
-		}
-		print "fi";
-	}' | sh > $T/diagnostics
-if test -s $T/diagnostics
-then
-	cat $T/diagnostics
-	exit 1
-fi
 exit 0
-- 
cgit v0.10.2


From 4f8a031279f5c17ad76b6833c64b8f86a450ebda Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 30 Sep 2013 17:17:57 -0700
Subject: rcutorture: Abstract qemu-flavor identification

The task of working out which flavor of qemu to use gets more complex
as more types of CPUs are supported.  Adding Power makes three in addition
to 32-bit and 64-bit x86, so it is time to pull this out into a function.
This commit therefore creates an identify_qemu function and also adds
a --qemu-cmd command-line argument for the inevitable case where the
identify_qemu cannot figure it out.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index 8f91241..c974414 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -51,3 +51,30 @@ configfrag_hotplug_cpu () {
 	fi
 	grep -q '^CONFIG_HOTPLUG_CPU=y$' "$1"
 }
+
+# identify_qemu builddir
+#
+# Returns our best guess as to which qemu command is appropriate for
+# the kernel at hand.  Override with the RCU_QEMU_CMD environment variable.
+identify_qemu () {
+	local u="`file "$1"`"
+	if test -n "$RCU_QEMU_CMD"
+	then
+		echo $RCU_QEMU_CMD
+	elif echo $u | grep -q x86-64
+	then
+		echo qemu-system-x86_64
+	elif echo $u | grep -q "Intel 80386"
+	then
+		echo qemu-system-i386
+	elif uname -a | grep -q ppc64
+	then
+		echo qemu-system-ppc64
+	else
+		echo Cannot figure out what qemu command to use! 1>&2
+		# Usually this will be one of /usr/bin/qemu-system-*
+		# Use RCU_QEMU_CMD environment variable or appropriate
+		# argument to top-level script.
+		exit 1
+	fi
+}
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
index 5526550..ddf3bd6 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
@@ -109,12 +109,9 @@ boot_args=$6
 cd $KVM
 kstarttime=`awk 'BEGIN { print systime() }' < /dev/null`
 echo ' ---' `date`: Starting kernel
-if file linux-2.6/*.o | grep -q 64-bit
-then
-	QEMU=qemu-system-x86_64
-else
-	QEMU=qemu-system-i386
-fi
+
+# Determine the appropriate flavor of qemu command.
+QEMU="`identify_qemu $builddir/vmlinux.o`"
 
 # Generate -smp qemu argument.
 cpu_count=`configNR_CPUS.sh $config_template`
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index bf6d68e..89164c2 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -45,6 +45,7 @@ usage () {
 	echo "       --datestamp string"
 	echo "       --duration minutes"
 	echo "       --kversion vN.NN"
+	echo "       --qemu-cmd qemu-system-..."
 	echo "       --rcu-kvm absolute-pathname"
 	echo "       --results absolute-pathname"
 	echo "       --relbuilddir relative-pathname"
@@ -101,6 +102,11 @@ do
 		kversion=$2
 		shift
 		;;
+	--qemu-cmd)
+		checkarg --qemu-cmd "(qemu-system-...)" $# "$2" 'qemu-system-' '^--'
+		RCU_QEMU_CMD="$2"; export RCU_QEMU_CMD
+		shift
+		;;
 	--rcu-kvm)
 		checkarg --rcu-kvm "(absolute pathname)" "$#" "$2" '^/' error
 		KVM=$2; export KVM
-- 
cgit v0.10.2


From 14db63f575db5e27a733f873e17930f3071076ef Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 Oct 2013 08:48:18 -0700
Subject: rcutorture: Remove decorative qemu argument

The qemu -name argument doesn't seem to be useful in this environment,
so this commit removes it.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
index ddf3bd6..5e2e79b5 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
@@ -137,7 +137,7 @@ boot_args="`rcutorture_param_n_barrier_cbs "$boot_args"`"
 # Pull in Kconfig-fragment boot parameters
 boot_args="`configfrag_boot_params "$boot_args" "$config_template"`"
 
-echo $QEMU -name rcu-test -serial file:$builddir/console.log $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append \"noapic selinux=0 console=ttyS0 initcall_debug debug rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1 $boot_args\" > $resdir/qemu-cmd
+echo $QEMU -serial file:$builddir/console.log $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append \"noapic selinux=0 console=ttyS0 initcall_debug debug rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1 $boot_args\" > $resdir/qemu-cmd
 $QEMU -name rcu-test -serial file:$builddir/console.log $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append "noapic selinux=0 console=ttyS0 initcall_debug debug rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1 $boot_args" &
 qemu_pid=$!
 commandcompleted=0
-- 
cgit v0.10.2


From 2bcdf4e31ae4e215b1e61831d9defa3632cb7bd3 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 Oct 2013 10:14:09 -0700
Subject: rcutorture: Eliminate --rcu-kvm argument

The --rcu-kvm argument was intended to allow the scripts to live in
an alternate location.  Unfortunately, this prevents the kvm.sh script
from using common functions until after it finished parsing arguments,
because it doesn't know where to find them until then.  However, "cp -a"
and "ln -s" work pretty well, so lack of an --rcu-kvm argument can be
easily worked around.

This commit therefore removes this argument.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 89164c2..2af5494 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -46,7 +46,6 @@ usage () {
 	echo "       --duration minutes"
 	echo "       --kversion vN.NN"
 	echo "       --qemu-cmd qemu-system-..."
-	echo "       --rcu-kvm absolute-pathname"
 	echo "       --results absolute-pathname"
 	echo "       --relbuilddir relative-pathname"
 	exit 1
@@ -107,19 +106,6 @@ do
 		RCU_QEMU_CMD="$2"; export RCU_QEMU_CMD
 		shift
 		;;
-	--rcu-kvm)
-		checkarg --rcu-kvm "(absolute pathname)" "$#" "$2" '^/' error
-		KVM=$2; export KVM
-		if -z "$gotbuilddir"
-		then
-			builddir=${KVM}/b1
-		fi
-		if -n "$gotrelbuilddir"
-		then
-			builddir=${KVM}/${relbuilddir}
-		fi
-		shift
-		;;
 	--relbuilddir)
 		checkarg --relbuilddir "(relative pathname)" "$#" "$2" '^[^/]*$' '^--'
 		relbuilddir=$2
@@ -133,6 +119,7 @@ do
 		shift
 		;;
 	*)
+		echo Unknown argument $1
 		usage
 		;;
 	esac
-- 
cgit v0.10.2


From 315c540d46f8f11fe2a84e627d9473e90441ae96 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 4 Oct 2013 13:15:55 -0700
Subject: rcutorture: Refactor to enable non-x86 architectures

This commit expands the checks for what architecture is running to generate
additional qemu-system- commands, then uses the resulting qemu-system-
command name to choose different qemu arguments as needed for different
architectures.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index c974414..d0d19eb 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -78,3 +78,81 @@ identify_qemu () {
 		exit 1
 	fi
 }
+
+# identify_qemu_append qemu-cmd
+#
+# Output arguments for the qemu "-append" string based on CPU type
+# and the RCU_QEMU_INTERACTIVE environment variable.
+identify_qemu_append () {
+	case "$1" in
+	qemu-system-x86_64|qemu-system-i386)
+		echo noapic selinux=0 initcall_debug debug
+		;;
+	esac
+	if test -n "$RCU_QEMU_INTERACTIVE"
+	then
+		echo root=/dev/sda
+	else
+		echo console=ttyS0
+	fi
+}
+
+# identify_qemu_args qemu-cmd serial-file
+#
+# Output arguments for qemu arguments based on the RCU_QEMU_MAC
+# and RCU_QEMU_INTERACTIVE environment variables.
+identify_qemu_args () {
+	case "$1" in
+	qemu-system-x86_64|qemu-system-i386)
+		;;
+	qemu-system-ppc64)
+		echo -enable-kvm -M pseries -cpu POWER7 -nodefaults
+		echo -device spapr-vscsi
+		if test -n "$RCU_QEMU_INTERACTIVE" -a -n "$RCU_QEMU_MAC"
+		then
+			echo -device spapr-vlan,netdev=net0,mac=$RCU_QEMU_MAC
+			echo -netdev bridge,br=br0,id=net0
+		elif test -n "$RCU_QEMU_INTERACTIVE"
+		then
+			echo -net nic -net user
+		fi
+		;;
+	esac
+	if test -n "$RCU_QEMU_INTERACTIVE"
+	then
+		echo -monitor stdio -serial pty -S
+	else
+		echo -serial file:$2
+	fi
+}
+
+# identify_qemu_vcpus
+#
+# Returns the number of virtual CPUs available to the aggregate of the
+# guest OSes.
+identify_qemu_vcpus () {
+	lscpu | grep '^CPU(s):' | sed -e 's/CPU(s)://'
+}
+
+# specify_qemu_cpus qemu-cmd qemu-args #cpus
+#
+# Appends a string containing "-smp XXX" to qemu-args, unless the incoming
+# qemu-args already contains "-smp".
+specify_qemu_cpus () {
+	local nt;
+
+	if echo $2 | grep -q -e -smp
+	then
+		echo $2
+	else
+		case "$1" in
+		qemu-system-x86_64|qemu-system-i386)
+			echo $2 -smp $3
+			;;
+		qemu-system-ppc64)
+			nt="`lscpu | grep '^NUMA node0' | sed -e 's/^[^,]*,\([0-9]*\),.*$/\1/'`"
+			echo $2 -smp cores=`expr \( $3 + $nt - 1 \) / $nt`,threads=$nt
+			;;
+		esac
+	fi
+}
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
index 5e2e79b5..9fd546c 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
@@ -115,20 +115,21 @@ QEMU="`identify_qemu $builddir/vmlinux.o`"
 
 # Generate -smp qemu argument.
 cpu_count=`configNR_CPUS.sh $config_template`
-ncpus=`grep '^processor' /proc/cpuinfo | wc -l`
-if test $cpu_count -gt $ncpus
+vcpus=`identify_qemu_vcpus`
+if test $cpu_count -gt $vcpus
 then
-	echo CPU count limited from $cpu_count to $ncpus
+	echo CPU count limited from $cpu_count to $vcpus
 	touch $resdir/Warnings
-	echo CPU count limited from $cpu_count to $ncpus >> $resdir/Warnings
-	cpu_count=$ncpus
-fi
-if echo $qemu_args | grep -q -e -smp
-then
-	echo CPU count specified by caller
-else
-	qemu_args="$qemu_args -smp $cpu_count"
+	echo CPU count limited from $cpu_count to $vcpus >> $resdir/Warnings
+	cpu_count=$vcpus
 fi
+qemu_args="`specify_qemu_cpus "$QEMU" "$qemu_args" "$cpu_count"`"
+
+# Generate architecture-specific and interaction-specific qemu arguments
+qemu_args="$qemu_args `identify_qemu_args "$QEMU" "$builddir/console.log"`"
+
+# Generate qemu -append arguments
+qemu_append="`identify_qemu_append "$QEMU"`"
 
 # Generate CPU-hotplug boot parameters
 boot_args="`rcutorture_param_onoff "$boot_args" $builddir/.config`"
@@ -137,8 +138,8 @@ boot_args="`rcutorture_param_n_barrier_cbs "$boot_args"`"
 # Pull in Kconfig-fragment boot parameters
 boot_args="`configfrag_boot_params "$boot_args" "$config_template"`"
 
-echo $QEMU -serial file:$builddir/console.log $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append \"noapic selinux=0 console=ttyS0 initcall_debug debug rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1 $boot_args\" > $resdir/qemu-cmd
-$QEMU -name rcu-test -serial file:$builddir/console.log $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append "noapic selinux=0 console=ttyS0 initcall_debug debug rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1 $boot_args" &
+echo $QEMU $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append \"$qemu_append rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1 $boot_args\" > $resdir/qemu-cmd
+$QEMU $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append "$qemu_append rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1 $boot_args" &
 qemu_pid=$!
 commandcompleted=0
 echo Monitoring qemu job at pid $qemu_pid
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 2af5494..979c341 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -44,7 +44,9 @@ usage () {
 	echo "       --configs \"config-file list\""
 	echo "       --datestamp string"
 	echo "       --duration minutes"
+	echo "       --interactive"
 	echo "       --kversion vN.NN"
+	echo "       --mac nn:nn:nn:nn:nn:nn"
 	echo "       --qemu-cmd qemu-system-..."
 	echo "       --results absolute-pathname"
 	echo "       --relbuilddir relative-pathname"
@@ -96,11 +98,19 @@ do
 		dur=$2
 		shift
 		;;
+	--interactive)
+		RCU_QEMU_INTERACTIVE=1; export RCU_QEMU_INTERACTIVE
+		;;
 	--kversion)
 		checkarg --kversion "(kernel version)" $# "$2" '^v[0-9.]*$' error
 		kversion=$2
 		shift
 		;;
+	--mac)
+		checkarg --mac "(MAC address)" $# "$2" '^\([0-9a-fA-F]\{2\}:\)\{5\}[0-9a-fA-F]\{2\}$' error
+		RCU_QEMU_MAC=$2; export RCU_QEMU_MAC
+		shift
+		;;
 	--qemu-cmd)
 		checkarg --qemu-cmd "(qemu-system-...)" $# "$2" 'qemu-system-' '^--'
 		RCU_QEMU_CMD="$2"; export RCU_QEMU_CMD
-- 
cgit v0.10.2


From be70a73a1ab46860533dfa933d7b188ca053f0ec Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 9 Oct 2013 11:02:00 -0700
Subject: rcutorture: Allow Kconfig-related boot parameters to override

As it stands, the default kernel boot parameters generated from
the Kconfig fragment will override any supplied with the .boot
file that can optionally accompany a Kconfig fragment.  Rearrange
ordering to permit the specific .boot arguments to override those
generated by analyzing the Kconfig fragment.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
index 9fd546c..93342f7 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
@@ -131,15 +131,17 @@ qemu_args="$qemu_args `identify_qemu_args "$QEMU" "$builddir/console.log"`"
 # Generate qemu -append arguments
 qemu_append="`identify_qemu_append "$QEMU"`"
 
+# Pull in Kconfig-fragment boot parameters
+boot_args="`configfrag_boot_params "$boot_args" "$config_template"`"
 # Generate CPU-hotplug boot parameters
 boot_args="`rcutorture_param_onoff "$boot_args" $builddir/.config`"
 # Generate rcu_barrier() boot parameter
 boot_args="`rcutorture_param_n_barrier_cbs "$boot_args"`"
-# Pull in Kconfig-fragment boot parameters
-boot_args="`configfrag_boot_params "$boot_args" "$config_template"`"
+# Pull in standard rcutorture boot arguments
+boot_args="$boot_args rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1"
 
-echo $QEMU $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append \"$qemu_append rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1 $boot_args\" > $resdir/qemu-cmd
-$QEMU $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append "$qemu_append rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1 $boot_args" &
+echo $QEMU $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
+$QEMU $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append "$qemu_append $boot_args" &
 qemu_pid=$!
 commandcompleted=0
 echo Monitoring qemu job at pid $qemu_pid
-- 
cgit v0.10.2


From 06d9d1b2e2e58347af37f00856156a550522b2cb Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 9 Oct 2013 15:02:54 -0700
Subject: rcutorture: Eliminate configdir argument from kvm-recheck.sh script

Don't grab the configuration fragment from the configs directory because
it might well have been changed since the test was run.  Instead, use
the ConfigFragment file that was placed in the results directory.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index 0876af7..26e82b5 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -4,7 +4,7 @@
 # check the build and console output for errors.  Given a directory
 # containing results directories, this recursively checks them all.
 #
-# Usage: sh kvm-recheck.sh configdir resdir ...
+# Usage: sh kvm-recheck.sh resdir ...
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -25,8 +25,6 @@
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
 PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH
-configdir=${1}
-shift
 for rd in "$@"
 do
 	dirs=`find $rd -name Make.defconfig.out -print | sort | sed -e 's,/[^/]*$,,' | sort -u`
@@ -34,7 +32,7 @@ do
 	do
 		configfile=`echo $i | sed -e 's/^.*\///'`
 		echo $i
-		configcheck.sh $i/.config $configdir/$configfile
+		configcheck.sh $i/.config $i/ConfigFragment
 		parse-build.sh $i/Make.out $configfile
 		parse-rcutorture.sh $i/console.log $configfile
 		parse-console.sh $i/console.log $configfile
-- 
cgit v0.10.2


From 1127481392c8b95ad5066b6be99b3482522d4c89 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Thu, 10 Oct 2013 14:52:07 -0700
Subject: rcutorture: Add --buildonly dry-run capability

This commit adds --buildonly, which does the builds specified by the
--configs argument, but does not boot or test the resulting kernels.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
index 93342f7..3df1581 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
@@ -141,6 +141,11 @@ boot_args="`rcutorture_param_n_barrier_cbs "$boot_args"`"
 boot_args="$boot_args rcutorture.stat_interval=15 rcutorture.shutdown_secs=$seconds rcutorture.rcutorture_runnable=1"
 
 echo $QEMU $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
+if test -n "$RCU_BUILDONLY"
+then
+	echo Build-only run specified, boot/test omitted.
+	exit 0
+fi
 $QEMU $qemu_args -m 512 -kernel $builddir/arch/x86/boot/bzImage -append "$qemu_append $boot_args" &
 qemu_pid=$!
 commandcompleted=0
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 979c341..6c67d0c 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -41,6 +41,7 @@ kversion=""
 usage () {
 	echo "Usage: $scriptname optional arguments:"
 	echo "       --builddir absolute-pathname"
+	echo "       --buildonly"
 	echo "       --configs \"config-file list\""
 	echo "       --datestamp string"
 	echo "       --duration minutes"
@@ -83,6 +84,9 @@ do
 		gotbuilddir=1
 		shift
 		;;
+	--buildonly)
+		RCU_BUILDONLY=1; export RCU_BUILDONLY
+		;;
 	--configs)
 		checkarg --configs "(list of config files)" "$#" "$2" '^[^/]*$' '^--'
 		configs="$2"
-- 
cgit v0.10.2


From 7dca927328fce6f6854486c4c2355ffbe1469240 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 14 Oct 2013 08:19:39 -0700
Subject: rcutorture: Add --bootargs argument to specify additional boot
 arguments

This commit allows easy specification of trace_event lists, among other
things.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 6c67d0c..2fb91d4 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -40,6 +40,7 @@ kversion=""
 
 usage () {
 	echo "Usage: $scriptname optional arguments:"
+	echo "       --bootargs kernel-boot-arguments"
 	echo "       --builddir absolute-pathname"
 	echo "       --buildonly"
 	echo "       --configs \"config-file list\""
@@ -78,6 +79,11 @@ checkarg () {
 while test $# -gt 0
 do
 	case "$1" in
+	--bootargs)
+		checkarg --bootargs "(list of kernel boot arguments)" "$#" "$2" '.*' '^--'
+		RCU_BOOTARGS="$2"
+		shift
+		;;
 	--builddir)
 		checkarg --builddir "(absolute pathname)" "$#" "$2" '^/' error
 		builddir=$2
@@ -183,6 +189,6 @@ do
 	rd=$resdir/$ds/$CF
 	mkdir $rd || :
 	echo Results directory: $rd
-	kvm-test-1-rcu.sh $CONFIGFRAG/$kversion/$CF $builddir $rd $dur "-nographic" "rcutorture.test_no_idle_hz=1 rcutorture.verbose=1"
+	kvm-test-1-rcu.sh $CONFIGFRAG/$kversion/$CF $builddir $rd $dur "-nographic" "rcutorture.test_no_idle_hz=1 rcutorture.verbose=1 $RCU_BOOTARGS"
 done
 # Tracing: trace_event=rcu:rcu_nocb_grace_period,rcu:rcu_grace_period,rcu:rcu_grace_period_init,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_torture_read,rcu:rcu_invoke_callback,rcu:rcu_fqs,rcu:rcu_dyntick,rcu:rcu_unlock_preempted_task
-- 
cgit v0.10.2


From e9ce640001c681a1ec01a996dfae2f8fa5d1cfba Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 15 Oct 2013 09:22:48 -0700
Subject: rcutorture: Add --qemu-args argument to kvm.sh

This commits adds the --qemu-args argument to kvm.sh that is required
to pass boot devices down through to qemu.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 2fb91d4..7d6ca33 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -49,6 +49,7 @@ usage () {
 	echo "       --interactive"
 	echo "       --kversion vN.NN"
 	echo "       --mac nn:nn:nn:nn:nn:nn"
+	echo "       --qemu-args qemu-system-..."
 	echo "       --qemu-cmd qemu-system-..."
 	echo "       --results absolute-pathname"
 	echo "       --relbuilddir relative-pathname"
@@ -85,7 +86,7 @@ do
 		shift
 		;;
 	--builddir)
-		checkarg --builddir "(absolute pathname)" "$#" "$2" '^/' error
+		checkarg --builddir "(absolute pathname)" "$#" "$2" '^/' '^error'
 		builddir=$2
 		gotbuilddir=1
 		shift
@@ -104,7 +105,7 @@ do
 		shift
 		;;
 	--duration)
-		checkarg --duration "(minutes)" $# "$2" '^[0-9]*$' error
+		checkarg --duration "(minutes)" $# "$2" '^[0-9]*$' '^error'
 		dur=$2
 		shift
 		;;
@@ -112,7 +113,7 @@ do
 		RCU_QEMU_INTERACTIVE=1; export RCU_QEMU_INTERACTIVE
 		;;
 	--kversion)
-		checkarg --kversion "(kernel version)" $# "$2" '^v[0-9.]*$' error
+		checkarg --kversion "(kernel version)" $# "$2" '^v[0-9.]*$' '^error'
 		kversion=$2
 		shift
 		;;
@@ -121,6 +122,11 @@ do
 		RCU_QEMU_MAC=$2; export RCU_QEMU_MAC
 		shift
 		;;
+	--qemu-args)
+		checkarg --qemu-args "-qemu args" $# "$2" '^-' '^error'
+		RCU_QEMU_ARG="$2"
+		shift
+		;;
 	--qemu-cmd)
 		checkarg --qemu-cmd "(qemu-system-...)" $# "$2" 'qemu-system-' '^--'
 		RCU_QEMU_CMD="$2"; export RCU_QEMU_CMD
@@ -134,7 +140,7 @@ do
 		shift
 		;;
 	--results)
-		checkarg --results "(absolute pathname)" "$#" "$2" '^/' error
+		checkarg --results "(absolute pathname)" "$#" "$2" '^/' '^error'
 		resdir=$2
 		shift
 		;;
@@ -189,6 +195,6 @@ do
 	rd=$resdir/$ds/$CF
 	mkdir $rd || :
 	echo Results directory: $rd
-	kvm-test-1-rcu.sh $CONFIGFRAG/$kversion/$CF $builddir $rd $dur "-nographic" "rcutorture.test_no_idle_hz=1 rcutorture.verbose=1 $RCU_BOOTARGS"
+	kvm-test-1-rcu.sh $CONFIGFRAG/$kversion/$CF $builddir $rd $dur "-nographic $RCU_QEMU_ARG" "rcutorture.test_no_idle_hz=1 rcutorture.verbose=1 $RCU_BOOTARGS"
 done
 # Tracing: trace_event=rcu:rcu_nocb_grace_period,rcu:rcu_grace_period,rcu:rcu_grace_period_init,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_torture_read,rcu:rcu_invoke_callback,rcu:rcu_fqs,rcu:rcu_dyntick,rcu:rcu_unlock_preempted_task
-- 
cgit v0.10.2


From 73931b5ee92d013b7b7d62927cca2a8dfdf3a9d3 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 15 Oct 2013 10:42:25 -0700
Subject: rcutorture: Add --no-initrd argument to kvm.sh

This commit adds the --no-initrd argument to kvm.sh, which permits
initrd to be contained in a root partition specified by the --bootargs
argument.  Without --no-initrd, the kernel build expects an initrd
directory in the same rcutorture directory that contains bin and configs.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
index 07bbecc..618ef2c 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
@@ -47,7 +47,7 @@ mkdir $T
 
 cat ${config_template} | grep -v CONFIG_RCU_TORTURE_TEST > $T/config
 cat << ___EOF___ >> $T/config
-CONFIG_INITRAMFS_SOURCE="$KVM/initrd"
+CONFIG_INITRAMFS_SOURCE="$RCU_INITRD"
 CONFIG_VIRTIO_PCI=y
 CONFIG_VIRTIO_CONSOLE=y
 ___EOF___
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 7d6ca33..a833160 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -31,8 +31,9 @@ scriptname=$0
 args="$*"
 
 dur=30
-KVM=`pwd`/tools/testing/selftests/rcutorture; export KVM
-builddir=${KVM}/b1
+KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
+builddir="${KVM}/b1"
+RCU_INITRD="$KVM/initrd"; export RCU_INITRD
 resdir=""
 configs=""
 ds=`date +%Y.%m.%d-%H:%M:%S`
@@ -49,6 +50,7 @@ usage () {
 	echo "       --interactive"
 	echo "       --kversion vN.NN"
 	echo "       --mac nn:nn:nn:nn:nn:nn"
+	echo "       --no-initrd"
 	echo "       --qemu-args qemu-system-..."
 	echo "       --qemu-cmd qemu-system-..."
 	echo "       --results absolute-pathname"
@@ -122,6 +124,9 @@ do
 		RCU_QEMU_MAC=$2; export RCU_QEMU_MAC
 		shift
 		;;
+	--no-initrd)
+		RCU_INITRD=""; export RCU_INITRD
+		;;
 	--qemu-args)
 		checkarg --qemu-args "-qemu args" $# "$2" '^-' '^error'
 		RCU_QEMU_ARG="$2"
-- 
cgit v0.10.2


From 74878fb6368eb254d5bedd8f21a165562222919f Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 15 Oct 2013 11:51:23 -0700
Subject: rcutorture: Add --kmake-arg argument to kvm.sh

This commit adds the --kmake-arg to kvm.sh, which allows passing in
things like "V=1" to see the build commands, as well as enabling the
CROSS_COMPILE= make macro used for cross-building.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
index 618ef2c..8c4aa7d 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
@@ -60,7 +60,7 @@ then
 	exit 2
 fi
 ncpus=`cpus2use.sh`
-make O=$builddir -j$ncpus > $builddir/Make.out 2>&1
+make O=$builddir -j$ncpus $RCU_KMAKE_ARG > $builddir/Make.out 2>&1
 retval=$?
 if test $retval -ne 0 || grep "rcu[^/]*": < $builddir/Make.out | egrep -q "Stop|Error|error:|warning:" || egrep -q "Stop|Error|error:" < $builddir/Make.out
 then
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index a833160..69b6523 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -34,6 +34,7 @@ dur=30
 KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
 builddir="${KVM}/b1"
 RCU_INITRD="$KVM/initrd"; export RCU_INITRD
+RCU_KMAKE_ARG=""; export RCU_KMAKE_ARG
 resdir=""
 configs=""
 ds=`date +%Y.%m.%d-%H:%M:%S`
@@ -48,6 +49,7 @@ usage () {
 	echo "       --datestamp string"
 	echo "       --duration minutes"
 	echo "       --interactive"
+	echo "       --kmake-arg kernel-make-arguments"
 	echo "       --kversion vN.NN"
 	echo "       --mac nn:nn:nn:nn:nn:nn"
 	echo "       --no-initrd"
@@ -114,6 +116,11 @@ do
 	--interactive)
 		RCU_QEMU_INTERACTIVE=1; export RCU_QEMU_INTERACTIVE
 		;;
+	--kmake-arg)
+		checkarg --kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$'
+		RCU_KMAKE_ARG="$2"; export RCU_KMAKE_ARG
+		shift
+		;;
 	--kversion)
 		checkarg --kversion "(kernel version)" $# "$2" '^v[0-9.]*$' '^error'
 		kversion=$2
-- 
cgit v0.10.2


From 0ef42bbe541ab0e8fc0238a67bf80b8f19c1712f Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 15 Oct 2013 12:08:45 -0700
Subject: rcutorture: Add tracing-enabled version of TREE08

The TREE08 Kconfig fragment does not enable tracing, which is appropriate
for its test case.  However, this can be inconvenient in cases where
TREE08 locates RCU bugs.  This commit therefore adds a TREE08-T that
differs from TREE08 only in enabling CONFIG_RCU_TRACE.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/configs/TREE08-T b/tools/testing/selftests/rcutorture/configs/TREE08-T
new file mode 100644
index 0000000..442c4e4
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/TREE08-T
@@ -0,0 +1,26 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=16
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
+#CHECK#CONFIG_TREE_PREEMPT_RCU=y
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_FAST_NO_HZ=n
+CONFIG_RCU_TRACE=y
+CONFIG_HOTPLUG_CPU=n
+CONFIG_SUSPEND=n
+CONFIG_HIBERNATION=n
+CONFIG_RCU_FANOUT=3
+CONFIG_RCU_FANOUT_EXACT=y
+CONFIG_RCU_FANOUT_LEAF=2
+CONFIG_RCU_NOCB_CPU=y
+CONFIG_RCU_NOCB_CPU_ALL=y
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_RCU_DELAY=n
+CONFIG_RCU_CPU_STALL_INFO=n
+CONFIG_RCU_CPU_STALL_VERBOSE=n
+CONFIG_RCU_BOOST=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_PRINTK_TIME=y
-- 
cgit v0.10.2


From 782ab4cd2eeb6a680dce8ff76d9ae4edeefe415c Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 15 Oct 2013 12:11:24 -0700
Subject: rcutorture: Update comment in kvm.sh listing typical RCU trace events

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 69b6523..02ac41e 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -209,4 +209,4 @@ do
 	echo Results directory: $rd
 	kvm-test-1-rcu.sh $CONFIGFRAG/$kversion/$CF $builddir $rd $dur "-nographic $RCU_QEMU_ARG" "rcutorture.test_no_idle_hz=1 rcutorture.verbose=1 $RCU_BOOTARGS"
 done
-# Tracing: trace_event=rcu:rcu_nocb_grace_period,rcu:rcu_grace_period,rcu:rcu_grace_period_init,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_torture_read,rcu:rcu_invoke_callback,rcu:rcu_fqs,rcu:rcu_dyntick,rcu:rcu_unlock_preempted_task
+# Tracing: trace_event=rcu:rcu_grace_period,rcu:rcu_future_grace_period,rcu:rcu_grace_period_init,rcu:rcu_nocb_wake,rcu:rcu_preempt_task,rcu:rcu_unlock_preempted_task,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_kfree_callback,rcu:rcu_batch_start,rcu:rcu_invoke_callback,rcu:rcu_invoke_kfree_callback,rcu:rcu_batch_end,rcu:rcu_torture_read,rcu:rcu_barrier
-- 
cgit v0.10.2


From e1362651f713e359dd76f0df74bce393a9372316 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 15 Oct 2013 12:22:32 -0700
Subject: rcutorture: Test summary at end of run with less chattiness

The commit causes kvm.sh to invoke kvm-recheck.sh at the end of each
run, and causes kvm-recheck.sh to print only the name of the test, not
the full path to the corresponding Kconfig file.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index 26e82b5..874cd32 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -31,7 +31,7 @@ do
 	for i in $dirs
 	do
 		configfile=`echo $i | sed -e 's/^.*\///'`
-		echo $i
+		echo $configfile
 		configcheck.sh $i/.config $i/ConfigFragment
 		parse-build.sh $i/Make.out $configfile
 		parse-rcutorture.sh $i/console.log $configfile
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 02ac41e..b8d2789 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -210,3 +210,6 @@ do
 	kvm-test-1-rcu.sh $CONFIGFRAG/$kversion/$CF $builddir $rd $dur "-nographic $RCU_QEMU_ARG" "rcutorture.test_no_idle_hz=1 rcutorture.verbose=1 $RCU_BOOTARGS"
 done
 # Tracing: trace_event=rcu:rcu_grace_period,rcu:rcu_future_grace_period,rcu:rcu_grace_period_init,rcu:rcu_nocb_wake,rcu:rcu_preempt_task,rcu:rcu_unlock_preempted_task,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_kfree_callback,rcu:rcu_batch_start,rcu:rcu_invoke_callback,rcu:rcu_invoke_kfree_callback,rcu:rcu_batch_end,rcu:rcu_torture_read,rcu:rcu_barrier
+
+echo " --- `date` Test summary:"
+kvm-recheck.sh $resdir/$ds
-- 
cgit v0.10.2


From f43f8f73510c1013fe9449d7732e8f73a75b6fde Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sat, 19 Oct 2013 06:28:21 -0700
Subject: rcutorture: Record results from repeated runs of the same test
 scenario

Repeatedly running a given test, for example, by repeating the name
as in "--configs "TREE08 TREE08 TREE08" records the results only of
the last run of this test.  This is because the earlier results are
overwritten by the later results.

This commit therefore checks for earlier results, using numbered
file extensions to distinguish multiple runs.  The earlier example
would therefore create directories TREE01, TREE01.2, and TREE01.3.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index b8d2789..0783ec9 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -204,8 +204,22 @@ fi
 
 for CF in $configs
 do
+	# Running TREE01 multiple times creates TREE01, TREE01.2, TREE01.3, ...
 	rd=$resdir/$ds/$CF
-	mkdir $rd || :
+	if test -d "${rd}"
+	then
+		n="`ls -d "${rd}"* | grep '\.[0-9]\+$' |
+			sed -e 's/^.*\.\([0-9]\+\)/\1/' |
+			sort -k1n | tail -1`"
+		if test -z "$n"
+		then
+			rd="${rd}.2"
+		else
+			n="`expr $n + 1`"
+			rd="${rd}.${n}"
+		fi
+	fi
+	mkdir "${rd}"
 	echo Results directory: $rd
 	kvm-test-1-rcu.sh $CONFIGFRAG/$kversion/$CF $builddir $rd $dur "-nographic $RCU_QEMU_ARG" "rcutorture.test_no_idle_hz=1 rcutorture.verbose=1 $RCU_BOOTARGS"
 done
-- 
cgit v0.10.2


From 6d40cc0cb4311d0c5aa4a106cc86a3d45a9ad86c Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 28 Oct 2013 06:34:22 -0700
Subject: rcutorture: Flag errors and warnings with color coding

The output of the rcutorture scripts often requires interpretation, so
this commit simplifies this interpretation by tagging messages as
BUGs (colored red) or WARNINGs (colored yellow).

Reported-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index d0d19eb..963b6f0 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -134,6 +134,22 @@ identify_qemu_vcpus () {
 	lscpu | grep '^CPU(s):' | sed -e 's/CPU(s)://'
 }
 
+# print_bug
+#
+# Prints "BUG: " in red followed by remaining arguments
+print_bug () {
+	printf '\033[031mBUG: \033[m'
+	echo $*
+}
+
+# print_warning
+#
+# Prints "WARNING: " in yellow followed by remaining arguments
+print_warning () {
+	printf '\033[033mWARNING: \033[m'
+	echo $*
+}
+
 # specify_qemu_cpus qemu-cmd qemu-args #cpus
 #
 # Appends a string containing "-smp XXX" to qemu-args, unless the incoming
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
index 3df1581..46f97d3 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
@@ -188,6 +188,5 @@ then
 fi
 
 cp $builddir/console.log $resdir
-parse-rcutorture.sh $resdir/console.log $title >> $resdir/Warnings 2>&1
-parse-console.sh $resdir/console.log $title >> $resdir/Warnings 2>&1
-cat $resdir/Warnings
+parse-rcutorture.sh $resdir/console.log $title
+parse-console.sh $resdir/console.log $title
diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh
index 2e0e9f7..9da2c7b 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh
@@ -30,18 +30,28 @@
 T=$1
 title=$2
 
+. functions.sh
+
 if grep -q CC < $T
 then
 	:
 else
-	echo $title no build
+	print_bug $title no build
 	exit 1
 fi
 
-if egrep -q "error:|rcu[^/]*\.c.*warning:|rcu.*\.h.*warning:" < $T
+if grep -q "error:" < $T
+then
+	print_bug $title build errors:
+	grep "error:" < $T
+	exit 2
+fi
+exit 0
+
+if egrep -q "rcu[^/]*\.c.*warning:|rcu.*\.h.*warning:" < $T
 then
-	echo $title build errors:
-	egrep "error:|rcu[^/]*\.c.*warning:|rcu.*\.h.*warning:" < $T
+	print_warning $title build errors:
+	egrep "rcu[^/]*\.c.*warning:|rcu.*\.h.*warning:" < $T
 	exit 2
 fi
 exit 0
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index bc1496f..8f4be78 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -31,9 +31,11 @@ trap 'rm -f $T' 0
 file="$1"
 title="$2"
 
+. functions.sh
+
 egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T
 if test -s $T
 then
-	echo Assertion failure in $file $title
+	print_warning Assertion failure in $file $title
 	cat $T
 fi
diff --git a/tools/testing/selftests/rcutorture/bin/parse-rcutorture.sh b/tools/testing/selftests/rcutorture/bin/parse-rcutorture.sh
index 37368a0..ac2f75a 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-rcutorture.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-rcutorture.sh
@@ -34,6 +34,8 @@ title="$2"
 
 trap 'rm -f $T.seq' 0
 
+. functions.sh
+
 # check for presence of rcutorture.txt file
 
 if test -f "$file" -a -r "$file"
@@ -49,7 +51,7 @@ fi
 if grep -q FAILURE $file || grep -q -e '-torture.*!!!' $file
 then
 	nerrs=`grep --binary-files=text '!!!' $file | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'`
-	echo $title FAILURE, $nerrs instances
+	print_bug $title FAILURE, $nerrs instances
 	echo "   " $url
 	exit
 fi
@@ -84,21 +86,21 @@ if grep -q SUCCESS $file
 then
 	if test -s $T.seq
 	then
-		echo WARNING $title `cat $T.seq`
+		print_warning $title $title `cat $T.seq`
 		echo "   " $file
 		exit 2
 	fi
 else
 	if grep -q RCU_HOTPLUG $file
 	then
-		echo WARNING: HOTPLUG FAILURES $title `cat $T.seq`
+		print_warning HOTPLUG FAILURES $title `cat $T.seq`
 		echo "   " $file
 		exit 3
 	fi
 	echo $title no success message, `grep --binary-files=text 'ver:' $file | wc -l` successful RCU version messages
 	if test -s $T.seq
 	then
-		echo WARNING $title `cat $T.seq`
+		print_warning $title `cat $T.seq`
 	fi
 	exit 2
 fi
-- 
cgit v0.10.2


From 32caccb8f47c032df55e77102ea43c627f1ca507 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 28 Oct 2013 08:57:29 -0700
Subject: rcutorture: Move checkarg to functions.sh

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Greg KH <gregkh@linuxfoundation.org>

diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index 963b6f0..3052f1b 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -28,6 +28,30 @@ bootparam_hotplug_cpu () {
 	echo "$1" | grep -q "rcutorture\.onoff_"
 }
 
+# checkarg --argname argtype $# arg mustmatch cannotmatch
+#
+# Checks the specified argument "arg" against the mustmatch and cannotmatch
+# patterns.
+checkarg () {
+	if test $3 -le 1
+	then
+		echo $1 needs argument $2 matching \"$5\"
+		usage
+	fi
+	if echo "$4" | grep -q -e "$5"
+	then
+		:
+	else
+		echo $1 $2 \"$4\" must match \"$5\"
+		usage
+	fi
+	if echo "$4" | grep -q -e "$6"
+	then
+		echo $1 $2 \"$4\" must not match \"$6\"
+		usage
+	fi
+}
+
 # configfrag_boot_params bootparam-string config-fragment-file
 #
 # Adds boot parameters from the .boot file, if any.
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 0783ec9..7ba375e 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -32,6 +32,7 @@ args="$*"
 
 dur=30
 KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
+PATH=${KVM}/bin:$PATH; export PATH
 builddir="${KVM}/b1"
 RCU_INITRD="$KVM/initrd"; export RCU_INITRD
 RCU_KMAKE_ARG=""; export RCU_KMAKE_ARG
@@ -40,6 +41,8 @@ configs=""
 ds=`date +%Y.%m.%d-%H:%M:%S`
 kversion=""
 
+. functions.sh
+
 usage () {
 	echo "Usage: $scriptname optional arguments:"
 	echo "       --bootargs kernel-boot-arguments"
@@ -60,27 +63,6 @@ usage () {
 	exit 1
 }
 
-# checkarg --argname argtype $# arg mustmatch cannotmatch
-checkarg () {
-	if test $3 -le 1
-	then
-		echo $1 needs argument $2 matching \"$5\"
-		usage
-	fi
-	if echo "$4" | grep -q -e "$5"
-	then
-		:
-	else
-		echo $1 $2 \"$4\" must match \"$5\"
-		usage
-	fi
-	if echo "$4" | grep -q -e "$6"
-	then
-		echo $1 $2 \"$4\" must not match \"$6\"
-		usage
-	fi
-}
-
 while test $# -gt 0
 do
 	case "$1" in
@@ -164,7 +146,6 @@ do
 	shift
 done
 
-PATH=${KVM}/bin:$PATH; export PATH
 CONFIGFRAG=${KVM}/configs; export CONFIGFRAG
 KVPATH=${CONFIGFRAG}/$kversion; export KVPATH
 
-- 
cgit v0.10.2


From 0e342a87d5f0cd06697c3fdc5e8b49c61e558231 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 3 Dec 2013 09:54:18 -0800
Subject: rcutorture: Stop tracking FSF's postal address

All of the rcutorture scripts has the usual GPL header, which contains
a long-obsolete postal address for FSF.  To avoid the need to track the
FSF office's movements, this commit substitutes the URL where GPL may
be found.

Reported-by: Greg KH <gregkh@linuxfoundation.org>
Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/tools/testing/selftests/rcutorture/bin/config2frag.sh b/tools/testing/selftests/rcutorture/bin/config2frag.sh
index 252f769..9f9ffcd 100644
--- a/tools/testing/selftests/rcutorture/bin/config2frag.sh
+++ b/tools/testing/selftests/rcutorture/bin/config2frag.sh
@@ -15,8 +15,8 @@
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
 #
 # Copyright (C) IBM Corporation, 2013
 #
diff --git a/tools/testing/selftests/rcutorture/bin/configNR_CPUS.sh b/tools/testing/selftests/rcutorture/bin/configNR_CPUS.sh
index 9e8b112..43540f1 100755
--- a/tools/testing/selftests/rcutorture/bin/configNR_CPUS.sh
+++ b/tools/testing/selftests/rcutorture/bin/configNR_CPUS.sh
@@ -18,8 +18,8 @@
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
 #
 # Copyright (C) IBM Corporation, 2013
 #
diff --git a/tools/testing/selftests/rcutorture/bin/configcheck.sh b/tools/testing/selftests/rcutorture/bin/configcheck.sh
index a3e5b92..d686537 100755
--- a/tools/testing/selftests/rcutorture/bin/configcheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/configcheck.sh
@@ -12,8 +12,8 @@
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
 #
 # Copyright (C) IBM Corporation, 2011
 #
diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh
index 939c16c..a1be6e6 100755
--- a/tools/testing/selftests/rcutorture/bin/configinit.sh
+++ b/tools/testing/selftests/rcutorture/bin/configinit.sh
@@ -13,6 +13,24 @@
 # The second argument is a optional path to a build output directory,
 # for example, "O=/tmp/foo".  If this argument is omitted, the .config
 # file will be generated directly in the current directory.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
+#
+# Copyright (C) IBM Corporation, 2013
+#
+# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
 T=/tmp/configinit.sh.$$
 trap 'rm -rf $T' 0
diff --git a/tools/testing/selftests/rcutorture/bin/cpus2use.sh b/tools/testing/selftests/rcutorture/bin/cpus2use.sh
index 277a3f6..abe14b7 100755
--- a/tools/testing/selftests/rcutorture/bin/cpus2use.sh
+++ b/tools/testing/selftests/rcutorture/bin/cpus2use.sh
@@ -15,8 +15,8 @@
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
 #
 # Copyright (C) IBM Corporation, 2013
 #
diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index 3052f1b..587561d 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -13,8 +13,8 @@
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
 #
 # Copyright (C) IBM Corporation, 2013
 #
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
index 8c4aa7d..197901e 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
@@ -15,8 +15,8 @@
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
 #
 # Copyright (C) IBM Corporation, 2011
 #
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index 874cd32..baef09f 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -17,8 +17,8 @@
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
 #
 # Copyright (C) IBM Corporation, 2011
 #
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
index 46f97d3..151b237 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-rcu.sh
@@ -31,8 +31,8 @@
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
 #
 # Copyright (C) IBM Corporation, 2011
 #
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 7ba375e..1b7923b 100644
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -20,8 +20,8 @@
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
 #
 # Copyright (C) IBM Corporation, 2011
 #
diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh
index 9da2c7b..5432309 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh
@@ -20,8 +20,8 @@
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
 #
 # Copyright (C) IBM Corporation, 2011
 #
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 8f4be78..4185d4c 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -18,8 +18,8 @@
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
 #
 # Copyright (C) IBM Corporation, 2011
 #
diff --git a/tools/testing/selftests/rcutorture/bin/parse-rcutorture.sh b/tools/testing/selftests/rcutorture/bin/parse-rcutorture.sh
index ac2f75a..dd0a275 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-rcutorture.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-rcutorture.sh
@@ -21,8 +21,8 @@
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
 #
 # Copyright (C) IBM Corporation, 2011
 #
diff --git a/tools/testing/selftests/rcutorture/configs/v0.0/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/v0.0/ver_functions.sh
index af7d59b..e805253 100644
--- a/tools/testing/selftests/rcutorture/configs/v0.0/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/v0.0/ver_functions.sh
@@ -13,8 +13,8 @@
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
 #
 # Copyright (C) IBM Corporation, 2013
 #
diff --git a/tools/testing/selftests/rcutorture/configs/v3.3/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/v3.3/ver_functions.sh
index 921fec9..c37432f 100644
--- a/tools/testing/selftests/rcutorture/configs/v3.3/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/v3.3/ver_functions.sh
@@ -13,8 +13,8 @@
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
 #
 # Copyright (C) IBM Corporation, 2013
 #
diff --git a/tools/testing/selftests/rcutorture/configs/v3.5/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/v3.5/ver_functions.sh
index 4019744..6a5f13a 100644
--- a/tools/testing/selftests/rcutorture/configs/v3.5/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/v3.5/ver_functions.sh
@@ -13,8 +13,8 @@
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
 #
 # Copyright (C) IBM Corporation, 2013
 #
diff --git a/tools/testing/selftests/rcutorture/configs/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/ver_functions.sh
index f99f23b..5e40ead 100644
--- a/tools/testing/selftests/rcutorture/configs/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/ver_functions.sh
@@ -13,8 +13,8 @@
 # GNU General Public License for more details.
 #
 # You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+# along with this program; if not, you can access it online at
+# http://www.gnu.org/licenses/gpl-2.0.html.
 #
 # Copyright (C) IBM Corporation, 2013
 #
-- 
cgit v0.10.2


From bd0976dd3379e790b031cef7f477c58b82a65fc2 Mon Sep 17 00:00:00 2001
From: Marco Piazza <mpiazza@gmail.com>
Date: Thu, 28 Nov 2013 00:15:25 +0100
Subject: Bluetooth: Add support for Toshiba Bluetooth device [0930:0220]

This patch adds support for new Toshiba Bluetooth device.

T:  Bus=05 Lev=01 Prnt=01 Port=02 Cnt=02 Dev#=  4 Spd=12  MxCh= 0
D:  Ver= 1.10 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=0930 ProdID=0220 Rev=00.02
C:  #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=100mA
I:  If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
I:  If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb

Signed-off-by: Marco Piazza <mpiazza@gmail.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>

diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c
index 6bfc1bb..dceb85f 100644
--- a/drivers/bluetooth/ath3k.c
+++ b/drivers/bluetooth/ath3k.c
@@ -87,6 +87,7 @@ static const struct usb_device_id ath3k_table[] = {
 	{ USB_DEVICE(0x0CF3, 0xE004) },
 	{ USB_DEVICE(0x0CF3, 0xE005) },
 	{ USB_DEVICE(0x0930, 0x0219) },
+	{ USB_DEVICE(0x0930, 0x0220) },
 	{ USB_DEVICE(0x0489, 0xe057) },
 	{ USB_DEVICE(0x13d3, 0x3393) },
 	{ USB_DEVICE(0x0489, 0xe04e) },
@@ -129,6 +130,7 @@ static const struct usb_device_id ath3k_blist_tbl[] = {
 	{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe04e), .driver_info = BTUSB_ATH3012 },
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index c0ff34f..3980fd1 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -154,6 +154,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 },
+	{ USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe057), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 },
 	{ USB_DEVICE(0x0489, 0xe04e), .driver_info = BTUSB_ATH3012 },
-- 
cgit v0.10.2


From d88938ebc97df72320609b33aa0cf9a9a98accb1 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 3 Dec 2013 09:23:06 +0200
Subject: perf tools: Use asprintf instead of malloc plus snprintf

The asprintf library function is equivalent to malloc plus snprintf so
use it because it is simpler.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1386055390-13757-4-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index d11aefb..4c8e816 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -227,7 +227,6 @@ char *get_srcline(struct dso *dso, unsigned long addr)
 	unsigned line = 0;
 	char *srcline;
 	char *dso_name = dso->long_name;
-	size_t size;
 
 	if (!dso->has_srcline)
 		return SRCLINE_UNKNOWN;
@@ -241,13 +240,7 @@ char *get_srcline(struct dso *dso, unsigned long addr)
 	if (!addr2line(dso_name, addr, &file, &line))
 		goto out;
 
-	/* just calculate actual length */
-	size = snprintf(NULL, 0, "%s:%u", file, line) + 1;
-
-	srcline = malloc(size);
-	if (srcline)
-		snprintf(srcline, size, "%s:%u", file, line);
-	else
+	if (asprintf(&srcline, "%s:%u", file, line) < 0)
 		srcline = SRCLINE_UNKNOWN;
 
 	free(file);
-- 
cgit v0.10.2


From 454ff00f969e515c4cbfd52718ec5e01c7d9aeef Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 3 Dec 2013 09:23:07 +0200
Subject: perf symbols: Retain bfd reference to lookup source line numbers

Closng and re-opening for every lookup when using libbfd to lookup
source file name and line number is very very slow.  Instead keep the
reference on struct dso.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1386055390-13757-5-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index af4c687c..68aa55a 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -469,6 +469,7 @@ void dso__delete(struct dso *dso)
 	if (dso->lname_alloc)
 		free(dso->long_name);
 	dso_cache__free(&dso->cache);
+	dso__free_a2l(dso);
 	free(dso);
 }
 
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 9ac666a..d8613dc 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -77,6 +77,7 @@ struct dso {
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
 	struct rb_root	 cache;
+	void		 *a2l;
 	enum dso_kernel_type	kernel;
 	enum dso_swap_type	needs_swap;
 	enum dso_binary_type	symtab_type;
@@ -166,4 +167,6 @@ static inline bool dso__is_kcore(struct dso *dso)
 	       dso->data_type == DSO_BINARY_TYPE__GUEST_KCORE;
 }
 
+void dso__free_a2l(struct dso *dso);
+
 #endif /* __PERF_DSO */
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 4c8e816..25b85b2 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -146,18 +146,24 @@ static void addr2line_cleanup(struct a2l_data *a2l)
 }
 
 static int addr2line(const char *dso_name, unsigned long addr,
-		     char **file, unsigned int *line)
+		     char **file, unsigned int *line, struct dso *dso)
 {
 	int ret = 0;
-	struct a2l_data *a2l;
+	struct a2l_data *a2l = dso->a2l;
+
+	if (!a2l) {
+		dso->a2l = addr2line_init(dso_name);
+		a2l = dso->a2l;
+	}
 
-	a2l = addr2line_init(dso_name);
 	if (a2l == NULL) {
 		pr_warning("addr2line_init failed for %s\n", dso_name);
 		return 0;
 	}
 
 	a2l->addr = addr;
+	a2l->found = false;
+
 	bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l);
 
 	if (a2l->found && a2l->filename) {
@@ -168,14 +174,26 @@ static int addr2line(const char *dso_name, unsigned long addr,
 			ret = 1;
 	}
 
-	addr2line_cleanup(a2l);
 	return ret;
 }
 
+void dso__free_a2l(struct dso *dso)
+{
+	struct a2l_data *a2l = dso->a2l;
+
+	if (!a2l)
+		return;
+
+	addr2line_cleanup(a2l);
+
+	dso->a2l = NULL;
+}
+
 #else /* HAVE_LIBBFD_SUPPORT */
 
 static int addr2line(const char *dso_name, unsigned long addr,
-		     char **file, unsigned int *line_nr)
+		     char **file, unsigned int *line_nr,
+		     struct dso *dso __maybe_unused)
 {
 	FILE *fp;
 	char cmd[PATH_MAX];
@@ -219,6 +237,11 @@ out:
 	pclose(fp);
 	return ret;
 }
+
+void dso__free_a2l(struct dso *dso __maybe_unused)
+{
+}
+
 #endif /* HAVE_LIBBFD_SUPPORT */
 
 char *get_srcline(struct dso *dso, unsigned long addr)
@@ -237,7 +260,7 @@ char *get_srcline(struct dso *dso, unsigned long addr)
 	if (!strncmp(dso_name, "/tmp/perf-", 10))
 		goto out;
 
-	if (!addr2line(dso_name, addr, &file, &line))
+	if (!addr2line(dso_name, addr, &file, &line, dso))
 		goto out;
 
 	if (asprintf(&srcline, "%s:%u", file, line) < 0)
@@ -248,6 +271,7 @@ char *get_srcline(struct dso *dso, unsigned long addr)
 
 out:
 	dso->has_srcline = 0;
+	dso__free_a2l(dso);
 	return SRCLINE_UNKNOWN;
 }
 
-- 
cgit v0.10.2


From 0058aef65eda9c9dde8253af702d542ba7eef697 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 3 Dec 2013 09:23:08 +0200
Subject: perf symbols: Retain symbol source file name to lookup source line
 numbers

Currently, lookup of an ip's source file name and line number is done
using the dso file name.

Instead retain the file name used to lookup the dso's symbols and use
that.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1386055390-13757-6-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 68aa55a..49da968 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -470,6 +470,7 @@ void dso__delete(struct dso *dso)
 		free(dso->long_name);
 	dso_cache__free(&dso->cache);
 	dso__free_a2l(dso);
+	free(dso->symsrc_filename);
 	free(dso);
 }
 
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index d8613dc..7142e52 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -78,6 +78,7 @@ struct dso {
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
 	struct rb_root	 cache;
 	void		 *a2l;
+	char		 *symsrc_filename;
 	enum dso_kernel_type	kernel;
 	enum dso_swap_type	needs_swap;
 	enum dso_binary_type	symtab_type;
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 25b85b2..93795f9 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -249,11 +249,16 @@ char *get_srcline(struct dso *dso, unsigned long addr)
 	char *file = NULL;
 	unsigned line = 0;
 	char *srcline;
-	char *dso_name = dso->long_name;
+	char *dso_name;
 
 	if (!dso->has_srcline)
 		return SRCLINE_UNKNOWN;
 
+	if (dso->symsrc_filename)
+		dso_name = dso->symsrc_filename;
+	else
+		dso_name = dso->long_name;
+
 	if (dso_name[0] == '[')
 		goto out;
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 360eefe..de87dba 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1336,6 +1336,8 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 		if (!syms_ss && symsrc__has_symtab(ss)) {
 			syms_ss = ss;
 			next_slot = true;
+			if (!dso->symsrc_filename)
+				dso->symsrc_filename = strdup(name);
 		}
 
 		if (!runtime_ss && symsrc__possibly_runtime(ss)) {
-- 
cgit v0.10.2


From 906049c8276eb99af997f73d602649a98e360035 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 3 Dec 2013 09:23:10 +0200
Subject: perf tools: Do not disable source line lookup just because of 1
 failure

Looking up an ip's source file name and line number does not succeed
always.  Current logic disables the lookup for a dso entirely on any
failure.  Change it so that disabling never happens if there has ever
been a successful lookup for that dso but disable if the first 123
lookups fail.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1386055390-13757-8-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 49da968..a0c7c59 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -451,6 +451,7 @@ struct dso *dso__new(const char *name)
 		dso->sorted_by_name = 0;
 		dso->has_build_id = 0;
 		dso->has_srcline = 1;
+		dso->a2l_fails = 1;
 		dso->kernel = DSO_TYPE_USER;
 		dso->needs_swap = DSO_SWAP__UNSET;
 		INIT_LIST_HEAD(&dso->node);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 7142e52..384f2d9 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -79,6 +79,7 @@ struct dso {
 	struct rb_root	 cache;
 	void		 *a2l;
 	char		 *symsrc_filename;
+	unsigned int	 a2l_fails;
 	enum dso_kernel_type	kernel;
 	enum dso_swap_type	needs_swap;
 	enum dso_binary_type	symtab_type;
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 93795f9..0c07556 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -244,6 +244,12 @@ void dso__free_a2l(struct dso *dso __maybe_unused)
 
 #endif /* HAVE_LIBBFD_SUPPORT */
 
+/*
+ * Number of addr2line failures (without success) before disabling it for that
+ * dso.
+ */
+#define A2L_FAIL_LIMIT 123
+
 char *get_srcline(struct dso *dso, unsigned long addr)
 {
 	char *file = NULL;
@@ -268,15 +274,21 @@ char *get_srcline(struct dso *dso, unsigned long addr)
 	if (!addr2line(dso_name, addr, &file, &line, dso))
 		goto out;
 
-	if (asprintf(&srcline, "%s:%u", file, line) < 0)
-		srcline = SRCLINE_UNKNOWN;
+	if (asprintf(&srcline, "%s:%u", file, line) < 0) {
+		free(file);
+		goto out;
+	}
+
+	dso->a2l_fails = 0;
 
 	free(file);
 	return srcline;
 
 out:
-	dso->has_srcline = 0;
-	dso__free_a2l(dso);
+	if (dso->a2l_fails && ++dso->a2l_fails > A2L_FAIL_LIMIT) {
+		dso->has_srcline = 0;
+		dso__free_a2l(dso);
+	}
 	return SRCLINE_UNKNOWN;
 }
 
-- 
cgit v0.10.2


From e6d7cee1ecac099786d3ba7a71b1e69cf0ae9a7b Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:15 +0100
Subject: perf tools: Remove stackprotector feature check

We use -fstack-protector-all option to enable stack protecting for all
available functions. There's no reason for enabling -Wstack-protector to
get warning for unprotected functions.

Removing stackprotector feature check which was used to enable the
-Wstack-protector option.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-2-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 36e66ac..0761d57 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -141,7 +141,6 @@ CORE_FEATURE_TESTS =			\
 	libslang			\
 	libunwind			\
 	on-exit				\
-	stackprotector			\
 	stackprotector-all		\
 	timerfd
 
@@ -209,10 +208,6 @@ ifeq ($(feature-stackprotector-all), 1)
   CFLAGS += -fstack-protector-all
 endif
 
-ifeq ($(feature-stackprotector), 1)
-  CFLAGS += -Wstack-protector
-endif
-
 ifeq ($(DEBUG),0)
   ifeq ($(feature-fortify-source), 1)
     CFLAGS += -D_FORTIFY_SOURCE=2
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 87e7900..b8bb749 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -26,7 +26,6 @@ FILES=					\
 	test-libunwind-debug-frame	\
 	test-on-exit			\
 	test-stackprotector-all		\
-	test-stackprotector		\
 	test-timerfd
 
 CC := $(CC) -MD
@@ -38,7 +37,7 @@ BUILD = $(CC) $(CFLAGS) $(LDFLAGS) -o $(OUTPUT)$@ $@.c
 ###############################
 
 test-all:
-	$(BUILD) -Werror -fstack-protector -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma $(LIBUNWIND_LIBS) -lelf -laudit -I/usr/include/slang -lslang $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl
+	$(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma $(LIBUNWIND_LIBS) -lelf -laudit -I/usr/include/slang -lslang $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl
 
 test-hello:
 	$(BUILD)
@@ -46,9 +45,6 @@ test-hello:
 test-stackprotector-all:
 	$(BUILD) -Werror -fstack-protector-all
 
-test-stackprotector:
-	$(BUILD) -Werror -fstack-protector -Wstack-protector
-
 test-fortify-source:
 	$(BUILD) -O2 -Werror -D_FORTIFY_SOURCE=2
 
diff --git a/tools/perf/config/feature-checks/test-stackprotector.c b/tools/perf/config/feature-checks/test-stackprotector.c
deleted file mode 100644
index c9f398d..0000000
--- a/tools/perf/config/feature-checks/test-stackprotector.c
+++ /dev/null
@@ -1,6 +0,0 @@
-#include <stdio.h>
-
-int main(void)
-{
-	return puts("hi");
-}
-- 
cgit v0.10.2


From 2f37573507643407d0a8f38c676ed2e90b795db3 Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Wed, 4 Dec 2013 17:56:39 -0500
Subject: perf tools: Remove condition in machine__get_kernel_start_addr.

In machine__get_kernel_start_addr, the code, which is using
machine->root_dir to build filename, works for both host and guests
initialized from guestmount, as root_dir is set to "" for the host
machine in the machine__init() function.

So this patch remove the branch for machine__is_host.

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/0a81645dd0b384a12cb4f962cf193ef8c3ce2010.1386197481.git.yangds.fnst@cn.fujitsu.com
[ Clarified changeset mentioning root_dir setup in machine__init() ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 84cdb07..bac817a 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -502,15 +502,11 @@ static u64 machine__get_kernel_start_addr(struct machine *machine)
 	char path[PATH_MAX];
 	struct process_args args;
 
-	if (machine__is_host(machine)) {
-		filename = "/proc/kallsyms";
-	} else {
-		if (machine__is_default_guest(machine))
-			filename = (char *)symbol_conf.default_guest_kallsyms;
-		else {
-			sprintf(path, "%s/proc/kallsyms", machine->root_dir);
-			filename = path;
-		}
+	if (machine__is_default_guest(machine))
+		filename = (char *)symbol_conf.default_guest_kallsyms;
+	else {
+		sprintf(path, "%s/proc/kallsyms", machine->root_dir);
+		filename = path;
 	}
 
 	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
-- 
cgit v0.10.2


From 9c105fbc94a67ea5943d309d9a78ca669e0ddc61 Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Wed, 4 Dec 2013 17:56:40 -0500
Subject: perf target: Move the checking of which map function to call into
 function.

Check for cpu_map__dummy_new() or cpu_map__new() to be called in
perf_evlist__create_maps() is more complicated.

This patch moves the checking work into target.h, combining two
conditions and making perf_evlist__create_maps() more readable.

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/b8c41f1fd2c4f0df71eb7b19aea74fb64d46cdda.1386197481.git.yangds.fnst@cn.fujitsu.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 76fa764..7bb6ee1 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -819,13 +819,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 	if (evlist->threads == NULL)
 		return -1;
 
-	if (target->default_per_cpu)
-		evlist->cpus = target->per_thread ?
-					cpu_map__dummy_new() :
-					cpu_map__new(target->cpu_list);
-	else if (target__has_task(target))
-		evlist->cpus = cpu_map__dummy_new();
-	else if (!target__has_cpu(target) && !target->uses_mmap)
+	if (target__uses_dummy_map(target))
 		evlist->cpus = cpu_map__dummy_new();
 	else
 		evlist->cpus = cpu_map__new(target->cpu_list);
diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h
index 31dd2e9..7381b1c 100644
--- a/tools/perf/util/target.h
+++ b/tools/perf/util/target.h
@@ -63,4 +63,17 @@ static inline bool target__none(struct target *target)
 	return !target__has_task(target) && !target__has_cpu(target);
 }
 
+static inline bool target__uses_dummy_map(struct target *target)
+{
+	bool use_dummy = false;
+
+	if (target->default_per_cpu)
+		use_dummy = target->per_thread ? true : false;
+	else if (target__has_task(target) ||
+	         (!target__has_cpu(target) && !target->uses_mmap))
+		use_dummy = true;
+
+	return use_dummy;
+}
+
 #endif /* _PERF_TARGET_H */
-- 
cgit v0.10.2


From ed086d5b8a793955981f0726d8d66a03d801279b Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Wed, 4 Dec 2013 17:56:42 -0500
Subject: perf kvm: Add more detail about buildid-list in man page

As the buildid is read from /sys/kernel/notes, then if we use perf kvm
buildid-list with a perf data file captured by perf kvm record with
--guestkallsyms and --guestmodules, there is no result in output.

This patch add a explanation about it and add a limit of using perf kvm
buildid-list.

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/d605a805486340b53bc261aa64d7632ad0a8cf53.1386197481.git.yangds.fnst@cn.fujitsu.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index 6a06cef..f52f94d 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -37,7 +37,9 @@ There are a couple of variants of perf kvm:
 
   'perf kvm buildid-list' to  display the buildids found in a perf data file,
   so that other tools can be used to fetch packages with matching symbol tables
-  for use by perf report.
+  for use by perf report. As buildid is read from /sys/kernel/notes in os, then
+  if you want to list the buildid for guest, please make sure your perf data file
+  was captured with --guestmount in perf kvm record.
 
   'perf kvm stat <command>' to run a command and gather performance counter
   statistics.
-- 
cgit v0.10.2


From 316bd98a9aa47693215e0d3a5bcc83f51691ba93 Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Wed, 4 Dec 2013 17:56:43 -0500
Subject: perf kvm: Fix spurious '=' use in man page

As option --host and --guest request no input for it, there should not
be a '=' after them in the man page sources.

And --output expects a filename as the input, so there should be a '='
after it.

This patch removes the needless '=' after --guest and --host, and adds a
'=' after --output in perf-kvm.txt.

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/6124d9eb10a3f1f6b399d1db660110bc7a60fd6b.1386197481.git.yangds.fnst@cn.fujitsu.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index f52f94d..7953227 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -60,14 +60,14 @@ There are a couple of variants of perf kvm:
 OPTIONS
 -------
 -i::
---input=::
+--input=<path>::
         Input file name.
 -o::
---output::
+--output=<path>::
         Output file name.
---host=::
+--host::
         Collect host side performance profile.
---guest=::
+--guest::
         Collect guest side performance profile.
 --guestmount=<path>::
 	Guest os root file system mount directory. Users mounts guest os
-- 
cgit v0.10.2


From 8df0b4ad58081773647dd2e0fddd45e8c0022c67 Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Wed, 4 Dec 2013 17:56:41 -0500
Subject: perf kvm: Update the 'record' man page entry for new --guest/--host
 behavior

As we have changed the default behavior of 'perf kvm' to --guest
enabled, the parts of the man page that covers the 'record' subcommand
are outdated.

This patch updates it to show the correct output with
--host/--guest/neither/both of them.

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/3a3a9c1e05acb5a274d1d8369db5a4c6467d6276.1386197481.git.yangds.fnst@cn.fujitsu.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index 7953227..96a9a1d 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -24,10 +24,17 @@ There are a couple of variants of perf kvm:
   of an arbitrary workload.
 
   'perf kvm record <command>' to record the performance counter profile
-  of an arbitrary workload and save it into a perf data file. If both
-  --host and --guest are input, the perf data file name is perf.data.kvm.
-  If there is  no --host but --guest, the file name is perf.data.guest.
-  If there is no --guest but --host, the file name is perf.data.host.
+  of an arbitrary workload and save it into a perf data file. We set the
+  default behavior of perf kvm as --guest, so if neither --host nor --guest
+  is input, the perf data file name is perf.data.guest. If --host is input,
+  the perf data file name is perf.data.kvm. If you want to record data into
+  perf.data.host, please input --host --no-guest. The behaviors are shown as
+  following:
+    Default('')         ->  perf.data.guest
+    --host              ->  perf.data.kvm
+    --guest             ->  perf.data.guest
+    --host --guest      ->  perf.data.kvm
+    --host --no-guest   ->  perf.data.host
 
   'perf kvm report' to display the performance counter profile information
   recorded via perf kvm record.
-- 
cgit v0.10.2


From 779e24e2c777bffa9a6e3d5e821859e67008c98b Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Wed, 4 Dec 2013 16:23:01 +0200
Subject: perf symbols: Fix random fd closing with no libelf

When built without libelf, perf tools was failing to initialize a file
descriptor, but nevertheless closing it.  That sometimes resulted in the
output being truncated because the stdout file descriptor got closed.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1386166981-30197-1-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 2d2dd05..ac7070a 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -253,6 +253,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso __maybe_unused,
 	if (!ss->name)
 		goto out_close;
 
+	ss->fd = fd;
 	ss->type = type;
 
 	return 0;
-- 
cgit v0.10.2


From a2cb3cf20e06ef119ae541c1a08dc1977f7f0fff Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Wed, 4 Dec 2013 16:16:36 +0200
Subject: perf script: Do not call perf_event__preprocess_sample() twice)

The perf_event__preprocess_sample() function is called in
process_sample_event().  Instead of calling it again in
perf_evsel__print_ip(), pass through the resultant addr_location.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/529F3944.9050007@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 952dce9..c555bdd 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -414,7 +414,8 @@ static void print_sample_bts(union perf_event *event,
 			     struct perf_sample *sample,
 			     struct perf_evsel *evsel,
 			     struct machine *machine,
-			     struct thread *thread)
+			     struct thread *thread,
+			     struct addr_location *al)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 
@@ -424,7 +425,7 @@ static void print_sample_bts(union perf_event *event,
 			printf(" ");
 		else
 			printf("\n");
-		perf_evsel__print_ip(evsel, event, sample, machine,
+		perf_evsel__print_ip(evsel, sample, machine, al,
 				     output[attr->type].print_ip_opts,
 				     PERF_MAX_STACK_DEPTH);
 	}
@@ -443,7 +444,7 @@ static void print_sample_bts(union perf_event *event,
 static void process_event(union perf_event *event, struct perf_sample *sample,
 			  struct perf_evsel *evsel, struct machine *machine,
 			  struct thread *thread,
-			  struct addr_location *al __maybe_unused)
+			  struct addr_location *al)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 
@@ -458,7 +459,7 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 	}
 
 	if (is_bts_event(attr)) {
-		print_sample_bts(event, sample, evsel, machine, thread);
+		print_sample_bts(event, sample, evsel, machine, thread, al);
 		return;
 	}
 
@@ -474,7 +475,7 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 		else
 			printf("\n");
 
-		perf_evsel__print_ip(evsel, event, sample, machine,
+		perf_evsel__print_ip(evsel, sample, machine, al,
 				     output[attr->type].print_ip_opts,
 				     PERF_MAX_STACK_DEPTH);
 	}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 4ce146b..8a7da6f 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1487,11 +1487,10 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 	return NULL;
 }
 
-void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
-			  struct perf_sample *sample, struct machine *machine,
+void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
+			  struct machine *machine, struct addr_location *al,
 			  unsigned int print_opts, unsigned int stack_depth)
 {
-	struct addr_location al;
 	struct callchain_cursor_node *node;
 	int print_ip = print_opts & PRINT_IP_OPT_IP;
 	int print_sym = print_opts & PRINT_IP_OPT_SYM;
@@ -1500,15 +1499,10 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 	int print_oneline = print_opts & PRINT_IP_OPT_ONELINE;
 	char s = print_oneline ? ' ' : '\t';
 
-	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
-		error("problem processing %d event, skipping it.\n",
-			event->header.type);
-		return;
-	}
-
 	if (symbol_conf.use_callchain && sample->callchain) {
+		struct addr_location node_al;
 
-		if (machine__resolve_callchain(machine, evsel, al.thread,
+		if (machine__resolve_callchain(machine, evsel, al->thread,
 					       sample, NULL, NULL,
 					       PERF_MAX_STACK_DEPTH) != 0) {
 			if (verbose)
@@ -1517,6 +1511,9 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 		}
 		callchain_cursor_commit(&callchain_cursor);
 
+		if (print_symoffset)
+			node_al = *al;
+
 		while (stack_depth) {
 			node = callchain_cursor_current(&callchain_cursor);
 			if (!node)
@@ -1531,9 +1528,9 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
 			if (print_sym) {
 				printf(" ");
 				if (print_symoffset) {
-					al.addr = node->ip;
-					al.map  = node->map;
-					symbol__fprintf_symname_offs(node->sym, &al, stdout);
+					node_al.addr = node->ip;
+					node_al.map  = node->map;
+					symbol__fprintf_symname_offs(node->sym, &node_al, stdout);
 				} else
 					symbol__fprintf_symname(node->sym, stdout);
 			}
@@ -1553,7 +1550,7 @@ next:
 		}
 
 	} else {
-		if (al.sym && al.sym->ignore)
+		if (al->sym && al->sym->ignore)
 			return;
 
 		if (print_ip)
@@ -1562,15 +1559,15 @@ next:
 		if (print_sym) {
 			printf(" ");
 			if (print_symoffset)
-				symbol__fprintf_symname_offs(al.sym, &al,
+				symbol__fprintf_symname_offs(al->sym, al,
 							     stdout);
 			else
-				symbol__fprintf_symname(al.sym, stdout);
+				symbol__fprintf_symname(al->sym, stdout);
 		}
 
 		if (print_dso) {
 			printf(" (");
-			map__fprintf_dsoname(al.map, stdout);
+			map__fprintf_dsoname(al->map, stdout);
 			printf(")");
 		}
 	}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 50f6409..7e5d4398 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -105,8 +105,8 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
 struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 					    unsigned int type);
 
-void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
-			  struct perf_sample *sample, struct machine *machine,
+void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
+			  struct machine *machine, struct addr_location *al,
 			  unsigned int print_opts, unsigned int stack_depth);
 
 int perf_session__cpu_bitmap(struct perf_session *session,
-- 
cgit v0.10.2


From c877bbd8eceb14c5eac6779cc804fa8b34044736 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:16 +0100
Subject: tools lib traceevent: Add plugin support

Backporting plugin support for traceevent lib.

Backported from Steven Rostedt's trace-cmd repo (HEAD 0f2c2fb):
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/trace-cmd.git

It's now possible to use following interface to load plugins
(shared objects) to enhance pevent object functionality.

The plugin interface/hooks are as follows:
(taken from event-parse.h comments)

- 'pevent_plugin_loader' (required)
    The function name to initialized the plugin.

    int pevent_plugin_loader(struct pevent *pevent)

- 'pevent_plugin_unloader' (optional)
    The function called just before unloading

    int pevent_plugin_unloader(void)

- 'pevent_plugin_options'  (optional)
    Plugin options that can be set before loading

    struct plugin_option pevent_plugin_options[] = {
       {
               .name = "option-name",
               .plugin_alias = "overide-file-name", (optional)
               .description = "description of option to show users",
       },
       {
               .name = NULL,
       },
    };

    Array must end with .name = NULL;

    The plugin_alias (below) can be used to give a shorter
    name to access the variable. Useful if a plugin handles
    more than one event.

    NOTE options support is not backported yet.

- 'pevent_plugin_alias' (optional)
    The name to use for finding options (uses filename if not defined)

New traceevent functions are added to search and load
available plugins:

  struct plugin_list*
  traceevent_load_plugins(struct pevent *pevent)
    - loads plusing for 'struct pevent' object and returns
      loaded plugins list

  void traceevent_unload_plugins(struct plugin_list *plugin_list);
    - unload plugin list

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-3-git-send-email-jolsa@redhat.com
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index fc15020..2ccb5bc 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -180,7 +180,11 @@ $(obj)/%.o: $(src)/%.c
 %.o: $(src)/%.c
 	$(Q)$(call do_compile)
 
-PEVENT_LIB_OBJS = event-parse.o trace-seq.o parse-filter.o parse-utils.o
+PEVENT_LIB_OBJS  = event-parse.o
+PEVENT_LIB_OBJS += event-plugin.o
+PEVENT_LIB_OBJS += trace-seq.o
+PEVENT_LIB_OBJS += parse-filter.o
+PEVENT_LIB_OBJS += parse-utils.o
 PEVENT_LIB_OBJS += kbuffer-parse.o
 
 ALL_OBJS = $(PEVENT_LIB_OBJS)
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 8d73d25..a288860 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -377,6 +377,11 @@ enum pevent_errno {
 };
 #undef _PE
 
+struct plugin_list;
+
+struct plugin_list *traceevent_load_plugins(struct pevent *pevent);
+void traceevent_unload_plugins(struct plugin_list *plugin_list);
+
 struct cmdline;
 struct cmdline_list;
 struct func_map;
diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c
new file mode 100644
index 0000000..d272d87
--- /dev/null
+++ b/tools/lib/traceevent/event-plugin.c
@@ -0,0 +1,202 @@
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+#include <string.h>
+#include <dlfcn.h>
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <dirent.h>
+#include "event-parse.h"
+#include "event-utils.h"
+
+#define LOCAL_PLUGIN_DIR ".traceevent/plugins"
+
+struct plugin_list {
+	struct plugin_list	*next;
+	char			*name;
+	void			*handle;
+};
+
+static void
+load_plugin(struct pevent *pevent, const char *path,
+	    const char *file, void *data)
+{
+	struct plugin_list **plugin_list = data;
+	pevent_plugin_load_func func;
+	struct plugin_list *list;
+	const char *alias;
+	char *plugin;
+	void *handle;
+
+	plugin = malloc_or_die(strlen(path) + strlen(file) + 2);
+
+	strcpy(plugin, path);
+	strcat(plugin, "/");
+	strcat(plugin, file);
+
+	handle = dlopen(plugin, RTLD_NOW | RTLD_GLOBAL);
+	if (!handle) {
+		warning("could not load plugin '%s'\n%s\n",
+			plugin, dlerror());
+		goto out_free;
+	}
+
+	alias = dlsym(handle, PEVENT_PLUGIN_ALIAS_NAME);
+	if (!alias)
+		alias = file;
+
+	func = dlsym(handle, PEVENT_PLUGIN_LOADER_NAME);
+	if (!func) {
+		warning("could not find func '%s' in plugin '%s'\n%s\n",
+			PEVENT_PLUGIN_LOADER_NAME, plugin, dlerror());
+		goto out_free;
+	}
+
+	list = malloc_or_die(sizeof(*list));
+	list->next = *plugin_list;
+	list->handle = handle;
+	list->name = plugin;
+	*plugin_list = list;
+
+	pr_stat("registering plugin: %s", plugin);
+	func(pevent);
+	return;
+
+ out_free:
+	free(plugin);
+}
+
+static void
+load_plugins_dir(struct pevent *pevent, const char *suffix,
+		 const char *path,
+		 void (*load_plugin)(struct pevent *pevent,
+				     const char *path,
+				     const char *name,
+				     void *data),
+		 void *data)
+{
+	struct dirent *dent;
+	struct stat st;
+	DIR *dir;
+	int ret;
+
+	ret = stat(path, &st);
+	if (ret < 0)
+		return;
+
+	if (!S_ISDIR(st.st_mode))
+		return;
+
+	dir = opendir(path);
+	if (!dir)
+		return;
+
+	while ((dent = readdir(dir))) {
+		const char *name = dent->d_name;
+
+		if (strcmp(name, ".") == 0 ||
+		    strcmp(name, "..") == 0)
+			continue;
+
+		/* Only load plugins that end in suffix */
+		if (strcmp(name + (strlen(name) - strlen(suffix)), suffix) != 0)
+			continue;
+
+		load_plugin(pevent, path, name, data);
+	}
+
+	closedir(dir);
+}
+
+static void
+load_plugins(struct pevent *pevent, const char *suffix,
+	     void (*load_plugin)(struct pevent *pevent,
+				 const char *path,
+				 const char *name,
+				 void *data),
+	     void *data)
+{
+	char *home;
+	char *path;
+	char *envdir;
+
+	/*
+	 * If a system plugin directory was defined,
+	 * check that first.
+	 */
+#ifdef PLUGIN_DIR
+	load_plugins_dir(pevent, suffix, PLUGIN_DIR, load_plugin, data);
+#endif
+
+	/*
+	 * Next let the environment-set plugin directory
+	 * override the system defaults.
+	 */
+	envdir = getenv("TRACEEVENT_PLUGIN_DIR");
+	if (envdir)
+		load_plugins_dir(pevent, suffix, envdir, load_plugin, data);
+
+	/*
+	 * Now let the home directory override the environment
+	 * or system defaults.
+	 */
+	home = getenv("HOME");
+	if (!home)
+		return;
+
+	path = malloc_or_die(strlen(home) + strlen(LOCAL_PLUGIN_DIR) + 2);
+
+	strcpy(path, home);
+	strcat(path, "/");
+	strcat(path, LOCAL_PLUGIN_DIR);
+
+	load_plugins_dir(pevent, suffix, path, load_plugin, data);
+
+	free(path);
+}
+
+struct plugin_list*
+traceevent_load_plugins(struct pevent *pevent)
+{
+	struct plugin_list *list = NULL;
+
+	load_plugins(pevent, ".so", load_plugin, &list);
+	return list;
+}
+
+void
+traceevent_unload_plugins(struct plugin_list *plugin_list)
+{
+	pevent_plugin_unload_func func;
+	struct plugin_list *list;
+
+	while (plugin_list) {
+		list = plugin_list;
+		plugin_list = list->next;
+		func = dlsym(list->handle, PEVENT_PLUGIN_UNLOADER_NAME);
+		if (func)
+			func();
+		dlclose(list->handle);
+		free(list->name);
+		free(list);
+	}
+}
-- 
cgit v0.10.2


From e0e96d03f004e8953a731053b61e275f276fff01 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:17 +0100
Subject: tools lib traceevent: Add plugin build support

Backporting missing pieces of plugin building infrastructure:

  - Adding Makefile 'plugins' target to build all
    defined plugins

  - Adding Makefile 'install_plugins' target as 'install_lib'
    target dependency

  - Link plugin objects with shared object building

Backported from Steven Rostedt's trace-cmd repo (HEAD 0f2c2fb):
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/trace-cmd.git

Plugins are by default installed into following locations:

  '$(HOME)/.traceevent/plugins'
     - If we are installing under $(HOME)

  '$(prefix)/lib/traceevent/plugins'
     - Otherwise

This path is propagated to the plugin object as a plugins search path.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-4-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 2ccb5bc..1526798 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -43,6 +43,30 @@ man_dir_SQ = '$(subst ','\'',$(man_dir))'
 export man_dir man_dir_SQ INSTALL
 export DESTDIR DESTDIR_SQ
 
+set_plugin_dir := 1
+
+# Set plugin_dir to preffered global plugin location
+# If we install under $HOME directory we go under
+# $(HOME)/.traceevent/plugins
+#
+# We dont set PLUGIN_DIR in case we install under $HOME
+# directory, because by default the code looks under:
+# $(HOME)/.traceevent/plugins by default.
+#
+ifeq ($(plugin_dir),)
+ifeq ($(prefix),$(HOME))
+override plugin_dir = $(HOME)/.traceevent/plugins
+set_plugin_dir := 0
+else
+override plugin_dir = $(prefix)/lib/traceevent/plugins
+endif
+endif
+
+ifeq ($(set_plugin_dir),1)
+PLUGIN_DIR = -DPLUGIN_DIR="$(DESTDIR)/$(plugin_dir)"
+PLUGIN_DIR_SQ = '$(subst ','\'',$(PLUGIN_DIR))'
+endif
+
 # copy a bit from Linux kbuild
 
 ifeq ("$(origin V)", "command line")
@@ -96,6 +120,7 @@ export prefix bindir src obj
 # Shell quotes
 bindir_SQ = $(subst ','\'',$(bindir))
 bindir_relative_SQ = $(subst ','\'',$(bindir_relative))
+plugin_dir_SQ = $(subst ','\'',$(plugin_dir))
 
 LIB_FILE = libtraceevent.a libtraceevent.so
 
@@ -138,8 +163,8 @@ else
   print_app_build =		echo '  BUILD    '$(OBJ);
   print_fpic_compile =		echo '  CC FPIC  '$(OBJ);
   print_shared_lib_compile =	echo '  BUILD    SHARED LIB '$(OBJ);
-  print_plugin_obj_compile =	echo '  BUILD    PLUGIN OBJ '$(OBJ);
-  print_plugin_build =		echo '  BUILD    PLUGIN     '$(OBJ);
+  print_plugin_obj_compile =	echo '  CC FPIC  '$(OBJ);
+  print_plugin_build =		echo '  BUILD    PLUGIN '$(OBJ);
   print_static_lib_build =	echo '  BUILD    STATIC LIB '$(OBJ);
   print_install =		echo '  INSTALL  '$1'	to	$(DESTDIR_SQ)$2';
 endif
@@ -187,9 +212,11 @@ PEVENT_LIB_OBJS += parse-filter.o
 PEVENT_LIB_OBJS += parse-utils.o
 PEVENT_LIB_OBJS += kbuffer-parse.o
 
-ALL_OBJS = $(PEVENT_LIB_OBJS)
+PLUGINS := $(PLUGIN_OBJS:.o=.so)
+
+ALL_OBJS = $(PEVENT_LIB_OBJS) $(PLUGIN_OBJS)
 
-CMD_TARGETS = $(LIB_FILE)
+CMD_TARGETS = $(LIB_FILE) $(PLUGINS)
 
 TARGETS = $(CMD_TARGETS)
 
@@ -204,9 +231,17 @@ libtraceevent.so: $(PEVENT_LIB_OBJS)
 libtraceevent.a: $(PEVENT_LIB_OBJS)
 	$(Q)$(do_build_static_lib)
 
+plugins: $(PLUGINS)
+
 $(PEVENT_LIB_OBJS): %.o: $(src)/%.c TRACEEVENT-CFLAGS
 	$(Q)$(do_fpic_compile)
 
+$(PLUGIN_OBJS): %.o : $(src)/%.c
+	$(Q)$(do_compile_plugin_obj)
+
+$(PLUGINS): %.so: %.o
+	$(Q)$(do_plugin_build)
+
 define make_version.h
 	(echo '/* This file is automatically generated. Do not modify. */';		\
 	echo \#define VERSION_CODE $(shell						\
@@ -294,9 +329,16 @@ define do_install
 	$(INSTALL) $1 '$(DESTDIR_SQ)$2'
 endef
 
-install_lib: all_cmd
+install_lib: all_cmd install_plugins
 	$(Q)$(call do_install,$(LIB_FILE),$(bindir_SQ))
 
+PLUGINS_INSTALL = $(subst .so,.install,$(PLUGINS))
+
+$(PLUGINS_INSTALL): %.install : %.so force
+	$(Q)$(call do_install,$<,$(plugin_dir_SQ))
+
+install_plugins: $(PLUGINS_INSTALL)
+
 install: install_lib
 
 clean:
-- 
cgit v0.10.2


From 91a058ad3856b0a37cb21250eb4c478d0297a1a3 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:18 +0100
Subject: tools lib traceevent: Add traceevent_host_bigendian function

Adding traceevent_host_bigendian function to get host endianity. It's
used in following patches.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-5-git-send-email-jolsa@redhat.com
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index a288860..54273c0 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -23,6 +23,7 @@
 #include <stdbool.h>
 #include <stdarg.h>
 #include <regex.h>
+#include <string.h>
 
 #ifndef __maybe_unused
 #define __maybe_unused __attribute__((unused))
@@ -527,6 +528,15 @@ __data2host8(struct pevent *pevent, unsigned long long data)
 	__data2host8(pevent, __val);				\
 })
 
+static inline int traceevent_host_bigendian(void)
+{
+	unsigned char str[] = { 0x1, 0x2, 0x3, 0x4 };
+	unsigned int val;
+
+	memcpy(&val, str, 4);
+	return val == 0x01020304;
+}
+
 /* taken from kernel/trace/trace.h */
 enum trace_flag_type {
 	TRACE_FLAG_IRQS_OFF		= 0x01,
-- 
cgit v0.10.2


From 71ad9583ff15d2e95cb8c67a5c963321d9d1877b Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:19 +0100
Subject: tools lib traceevent: Change pevent_parse_format to include pevent
 handle

Changing the pevent_parse_format interface to include the pevent handle.

The goal is to always use pevent object when dealing with traceevent
library. The reason is that we might need additional processing (like
plugins), which is not possible otherwise.

Patches follow to make this happen completely.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-6-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 900fca0..9849873 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -5121,8 +5121,38 @@ enum pevent_errno __pevent_parse_format(struct event_format **eventp,
 	return ret;
 }
 
+static enum pevent_errno
+__pevent_parse_event(struct pevent *pevent,
+		     struct event_format **eventp,
+		     const char *buf, unsigned long size,
+		     const char *sys)
+{
+	int ret = __pevent_parse_format(eventp, pevent, buf, size, sys);
+	struct event_format *event = *eventp;
+
+	if (event == NULL)
+		return ret;
+
+	if (pevent && add_event(pevent, event)) {
+		ret = PEVENT_ERRNO__MEM_ALLOC_FAILED;
+		goto event_add_failed;
+	}
+
+#define PRINT_ARGS 0
+	if (PRINT_ARGS && event->print_fmt.args)
+		print_args(event->print_fmt.args);
+
+	return 0;
+
+event_add_failed:
+	pevent_free_format(event);
+	return ret;
+}
+
 /**
  * pevent_parse_format - parse the event format
+ * @pevent: the handle to the pevent
+ * @eventp: returned format
  * @buf: the buffer storing the event format string
  * @size: the size of @buf
  * @sys: the system the event belongs to
@@ -5134,10 +5164,12 @@ enum pevent_errno __pevent_parse_format(struct event_format **eventp,
  *
  * /sys/kernel/debug/tracing/events/.../.../format
  */
-enum pevent_errno pevent_parse_format(struct event_format **eventp, const char *buf,
+enum pevent_errno pevent_parse_format(struct pevent *pevent,
+				      struct event_format **eventp,
+				      const char *buf,
 				      unsigned long size, const char *sys)
 {
-	return __pevent_parse_format(eventp, NULL, buf, size, sys);
+	return __pevent_parse_event(pevent, eventp, buf, size, sys);
 }
 
 /**
@@ -5158,25 +5190,7 @@ enum pevent_errno pevent_parse_event(struct pevent *pevent, const char *buf,
 				     unsigned long size, const char *sys)
 {
 	struct event_format *event = NULL;
-	int ret = __pevent_parse_format(&event, pevent, buf, size, sys);
-
-	if (event == NULL)
-		return ret;
-
-	if (add_event(pevent, event)) {
-		ret = PEVENT_ERRNO__MEM_ALLOC_FAILED;
-		goto event_add_failed;
-	}
-
-#define PRINT_ARGS 0
-	if (PRINT_ARGS && event->print_fmt.args)
-		print_args(event->print_fmt.args);
-
-	return 0;
-
-event_add_failed:
-	pevent_free_format(event);
-	return ret;
+	return __pevent_parse_event(pevent, &event, buf, size, sys);
 }
 
 #undef _PE
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 54273c0..620c27a 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -562,7 +562,9 @@ int pevent_parse_header_page(struct pevent *pevent, char *buf, unsigned long siz
 
 enum pevent_errno pevent_parse_event(struct pevent *pevent, const char *buf,
 				     unsigned long size, const char *sys);
-enum pevent_errno pevent_parse_format(struct event_format **eventp, const char *buf,
+enum pevent_errno pevent_parse_format(struct pevent *pevent,
+				      struct event_format **eventp,
+				      const char *buf,
 				      unsigned long size, const char *sys);
 void pevent_free_format(struct event_format *event);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index b5fe7f9..6a046ed 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -210,7 +210,7 @@ struct event_format *event_format__new(const char *sys, const char *name)
 		size += n;
 	} while (n > 0);
 
-	pevent_parse_format(&format, bf, size, sys);
+	pevent_parse_format(NULL, &format, bf, size, sys);
 
 out_free_bf:
 	free(bf);
-- 
cgit v0.10.2


From f33c5cd73172c4fb81daa83a4f6d322210172fa0 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:20 +0100
Subject: tools lib traceevent: Harmonize the install messages in
 lib-traceevent

Removing the 'to ...' part out of the install message, because it does
not fit to the rest of the build messages we use.

Before:
  INSTALL  plugin_hrtimer.so    to      /home/jolsa/libexec/perf-core/traceevent/plugins
  INSTALL  plugin_jbd2.so       to      /home/jolsa/libexec/perf-core/traceevent/plugins
  INSTALL  plugin_kmem.so       to      /home/jolsa/libexec/perf-core/traceevent/plugins
  INSTALL  plugin_kvm.so        to      /home/jolsa/libexec/perf-core/traceevent/plugins
  INSTALL  plugin_mac80211.so   to      /home/jolsa/libexec/perf-core/traceevent/plugins
  INSTALL  plugin_sched_switch.so       to      /home/jolsa/libexec/perf-core/traceevent/plugins
  INSTALL  plugin_function.so   to      /home/jolsa/libexec/perf-core/traceevent/plugins
  INSTALL  plugin_xen.so        to      /home/jolsa/libexec/perf-core/traceevent/plugins
  INSTALL  plugin_scsi.so       to      /home/jolsa/libexec/perf-core/traceevent/plugins

Now:
  INSTALL  plugin_jbd2.so
  INSTALL  plugin_hrtimer.so
  INSTALL  plugin_kmem.so
  INSTALL  plugin_kvm.so
  INSTALL  plugin_mac80211.so
  INSTALL  plugin_sched_switch.so
  INSTALL  plugin_function.so
  INSTALL  plugin_xen.so
  INSTALL  plugin_scsi.so

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-7-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 1526798..f946851 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -166,7 +166,7 @@ else
   print_plugin_obj_compile =	echo '  CC FPIC  '$(OBJ);
   print_plugin_build =		echo '  BUILD    PLUGIN '$(OBJ);
   print_static_lib_build =	echo '  BUILD    STATIC LIB '$(OBJ);
-  print_install =		echo '  INSTALL  '$1'	to	$(DESTDIR_SQ)$2';
+  print_install =		echo '  INSTALL  '$1;
 endif
 
 do_fpic_compile =					\
-- 
cgit v0.10.2


From 3d7c0144491bd8c21d53b43032274a85efdfe434 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:21 +0100
Subject: perf tools: Add build and install plugins targets

Adding 'plugins' target along with the libtraceevent.a, so plugins are
built together with traceevent library.

Adding 'install-traceevent-plugins' Makefile install target, instructing
perf to install plugins into:

  $(HOME)/.traceevent/plugins
    - If installed localy under $HOME

  $(DESTDIR)/$(prefix)/$(libdir)/traceevent/plugins
    - If installed globally

Examples:
  $ make install
  ...
  $ find ~/.traceevent/plugins/
  /home/jolsa/.traceevent/plugins/
  /home/jolsa/.traceevent/plugins/plugin_mac80211.so
  /home/jolsa/.traceevent/plugins/plugin_kvm.so
  /home/jolsa/.traceevent/plugins/plugin_scsi.so
  /home/jolsa/.traceevent/plugins/plugin_sched_switch.so
  /home/jolsa/.traceevent/plugins/plugin_xen.so
  /home/jolsa/.traceevent/plugins/plugin_cfg80211.so
  /home/jolsa/.traceevent/plugins/plugin_function.so
  /home/jolsa/.traceevent/plugins/plugin_kmem.so
  /home/jolsa/.traceevent/plugins/plugin_hrtimer.so
  /home/jolsa/.traceevent/plugins/plugin_jbd2.so

  $ sudo make install DESTDIR=/opt/perf/
  ...
  $ find /opt/perf/lib64/traceevent/plugins/
  /opt/perf/lib64/traceevent/plugins/
  /opt/perf/lib64/traceevent/plugins/plugin_kvm.so
  /opt/perf/lib64/traceevent/plugins/plugin_scsi.so
  /opt/perf/lib64/traceevent/plugins/plugin_mac80211.so
  /opt/perf/lib64/traceevent/plugins/plugin_hrtimer.so
  /opt/perf/lib64/traceevent/plugins/plugin_kmem.so
  /opt/perf/lib64/traceevent/plugins/plugin_jbd2.so
  /opt/perf/lib64/traceevent/plugins/plugin_sched_switch.so
  /opt/perf/lib64/traceevent/plugins/plugin_function.so
  /opt/perf/lib64/traceevent/plugins/plugin_cfg80211.so
  /opt/perf/lib64/traceevent/plugins/plugin_xen.so

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-8-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index e416ccc..abc7ac3 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -105,7 +105,7 @@ ifeq ($(config),1)
 include config/Makefile
 endif
 
-export prefix bindir sharedir sysconfdir
+export prefix bindir sharedir sysconfdir DESTDIR
 
 # sparse is architecture-neutral, which means that we need to tell it
 # explicitly what architecture to check for. Fix this up for yours..
@@ -710,13 +710,20 @@ $(LIB_FILE): $(LIB_OBJS)
 # libtraceevent.a
 TE_SOURCES = $(wildcard $(TRACE_EVENT_DIR)*.[ch])
 
-$(LIBTRACEEVENT): $(TE_SOURCES)
-	$(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) CFLAGS="-g -Wall $(EXTRA_CFLAGS)" libtraceevent.a
+LIBTRACEEVENT_FLAGS  = $(QUIET_SUBDIR1) O=$(OUTPUT)
+LIBTRACEEVENT_FLAGS += CFLAGS="-g -Wall $(EXTRA_CFLAGS)"
+LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ)
+
+$(LIBTRACEEVENT): $(TE_SOURCES) $(OUTPUT)PERF-CFLAGS
+	$(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) libtraceevent.a plugins
 
 $(LIBTRACEEVENT)-clean:
 	$(call QUIET_CLEAN, libtraceevent)
 	@$(MAKE) -C $(TRACE_EVENT_DIR) O=$(OUTPUT) clean >/dev/null
 
+install-traceevent-plugins:
+	$(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) install_plugins
+
 LIBLK_SOURCES = $(wildcard $(LK_PATH)*.[ch])
 
 # if subdir is set, we've been called from above so target has been built
@@ -785,7 +792,7 @@ cscope:
 
 ### Detect prefix changes
 TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):\
-             $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ)
+             $(bindir_SQ):$(perfexecdir_SQ):$(template_dir_SQ):$(prefix_SQ):$(plugindir_SQ)
 
 $(OUTPUT)PERF-CFLAGS: .FORCE-PERF-CFLAGS
 	@FLAGS='$(TRACK_CFLAGS)'; \
@@ -849,7 +856,7 @@ endif
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
 		$(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
 
-install: install-bin try-install-man
+install: install-bin try-install-man install-traceevent-plugins
 
 install-python_ext:
 	$(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 0761d57..bae1072 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -593,3 +593,11 @@ else
 perfexec_instdir = $(prefix)/$(perfexecdir)
 endif
 perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
+
+# If we install to $(HOME) we keep the traceevent default:
+# $(HOME)/.traceevent/plugins
+# Otherwise we install plugins into the global $(libdir).
+ifdef DESTDIR
+plugindir=$(libdir)/traceevent/plugins
+plugindir_SQ= $(subst ','\'',$(prefix)/$(plugindir))
+endif
-- 
cgit v0.10.2


From cef82c9f5a3deab94c1f1f02cfc25213844852ed Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:22 +0100
Subject: perf tools: Add filename__read_str util function

Adding filename__read_str util function to read
text file and return it in the char array.

The interface is:
  int filename__read_str(const char *filename, char **buf, size_t *sizep)

  Returns 0/-1 if the read suceeded/fail respectively.

  buf  - place to store the data pointer
  size - place to store data size

v2 change:
  - better error handling suggested by Namhyung Kim.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-9-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index b1d5376..bae8756 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -6,6 +6,8 @@
 #endif
 #include <stdio.h>
 #include <stdlib.h>
+#include <string.h>
+#include <errno.h>
 #include <linux/kernel.h>
 
 /*
@@ -433,3 +435,50 @@ int filename__read_int(const char *filename, int *value)
 	close(fd);
 	return err;
 }
+
+int filename__read_str(const char *filename, char **buf, size_t *sizep)
+{
+	size_t size = 0, alloc_size = 0;
+	void *bf = NULL, *nbf;
+	int fd, n, err = 0;
+
+	fd = open(filename, O_RDONLY);
+	if (fd < 0)
+		return -errno;
+
+	do {
+		if (size == alloc_size) {
+			alloc_size += BUFSIZ;
+			nbf = realloc(bf, alloc_size);
+			if (!nbf) {
+				err = -ENOMEM;
+				break;
+			}
+
+			bf = nbf;
+		}
+
+		n = read(fd, bf + size, alloc_size - size);
+		if (n < 0) {
+			if (size) {
+				pr_warning("read failed %d: %s\n",
+					   errno, strerror(errno));
+				err = 0;
+			} else
+				err = -errno;
+
+			break;
+		}
+
+		size += n;
+	} while (n > 0);
+
+	if (!err) {
+		*sizep = size;
+		*buf   = bf;
+	} else
+		free(bf);
+
+	close(fd);
+	return err;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index ce0f73d..adb39f2 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -308,4 +308,5 @@ char *get_srcline(struct dso *dso, unsigned long addr);
 void free_srcline(char *srcline);
 
 int filename__read_int(const char *filename, int *value);
+int filename__read_str(const char *filename, char **buf, size_t *sizep);
 #endif /* GIT_COMPAT_UTIL_H */
-- 
cgit v0.10.2


From 29f5ffd3d3ff9abdfc98928f7c4cb4097cefe434 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:23 +0100
Subject: perf tools: Add trace-event object

Add trace-event object to keep together 'struct pevent' object with its
loaded plugins with following interface:

int trace_event__init(struct trace_event *t);

  - Initalizes 'struct pevent' object and loads plugins for it

void trace_event__cleanup(struct trace_event *t);

  - Cleanups both 'struct pevent' and plugins

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-10-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index abc7ac3..ca3b87d 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -353,6 +353,7 @@ LIB_OBJS += $(OUTPUT)util/pmu-bison.o
 LIB_OBJS += $(OUTPUT)util/trace-event-read.o
 LIB_OBJS += $(OUTPUT)util/trace-event-info.o
 LIB_OBJS += $(OUTPUT)util/trace-event-scripting.o
+LIB_OBJS += $(OUTPUT)util/trace-event.o
 LIB_OBJS += $(OUTPUT)util/svghelper.o
 LIB_OBJS += $(OUTPUT)util/sort.o
 LIB_OBJS += $(OUTPUT)util/hist.o
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c555bdd..4484886 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1786,7 +1786,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 			return -1;
 		}
 
-		err = scripting_ops->generate_script(session->pevent,
+		err = scripting_ops->generate_script(session->tevent.pevent,
 						     "perf-script");
 		goto out;
 	}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 3e755f2..125cdc9 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2834,11 +2834,11 @@ int perf_session__read_header(struct perf_session *session)
 
 	symbol_conf.nr_events = nr_attrs;
 
-	perf_header__process_sections(header, fd, &session->pevent,
+	perf_header__process_sections(header, fd, &session->tevent,
 				      perf_file_section__process);
 
 	if (perf_evlist__prepare_tracepoint_events(session->evlist,
-						   session->pevent))
+						   session->tevent.pevent))
 		goto out_delete_evlist;
 
 	return 0;
@@ -3003,7 +3003,7 @@ int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
 	lseek(fd, offset + sizeof(struct tracing_data_event),
 	      SEEK_SET);
 
-	size_read = trace_report(fd, &session->pevent,
+	size_read = trace_report(fd, &session->tevent,
 				 session->repipe);
 	padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read;
 
@@ -3025,7 +3025,7 @@ int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
 	}
 
 	perf_evlist__prepare_tracepoint_events(session->evlist,
-					       session->pevent);
+					       session->tevent.pevent);
 
 	return size_read + padding;
 }
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 239036f..595bfc7 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -18,4 +18,5 @@ util/cgroup.c
 util/rblist.c
 util/strlist.c
 util/fs.c
+util/trace-event.c
 ../../lib/rbtree.c
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 7e5d4398..004d3e8 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_SESSION_H
 #define __PERF_SESSION_H
 
+#include "trace-event.h"
 #include "hist.h"
 #include "event.h"
 #include "header.h"
@@ -32,7 +33,7 @@ struct perf_session {
 	struct perf_header	header;
 	struct machines		machines;
 	struct perf_evlist	*evlist;
-	struct pevent		*pevent;
+	struct trace_event	tevent;
 	struct events_stats	stats;
 	bool			repipe;
 	struct ordered_samples	ordered_samples;
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 6681f71..e0d6d07f 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -28,19 +28,6 @@
 #include "util.h"
 #include "trace-event.h"
 
-struct pevent *read_trace_init(int file_bigendian, int host_bigendian)
-{
-	struct pevent *pevent = pevent_alloc();
-
-	if (pevent != NULL) {
-		pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT);
-		pevent_set_file_bigendian(pevent, file_bigendian);
-		pevent_set_host_bigendian(pevent, host_bigendian);
-	}
-
-	return pevent;
-}
-
 static int get_common_field(struct scripting_context *context,
 			    int *offset, int *size, const char *type)
 {
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index f211227..e113e18 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -343,7 +343,7 @@ static int read_event_files(struct pevent *pevent)
 	return 0;
 }
 
-ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe)
+ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 {
 	char buf[BUFSIZ];
 	char test[] = { 23, 8, 68 };
@@ -356,11 +356,9 @@ ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe)
 	int host_bigendian;
 	int file_long_size;
 	int file_page_size;
-	struct pevent *pevent;
+	struct pevent *pevent = NULL;
 	int err;
 
-	*ppevent = NULL;
-
 	repipe = __repipe;
 	input_fd = fd;
 
@@ -390,12 +388,17 @@ ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe)
 	file_bigendian = buf[0];
 	host_bigendian = bigendian();
 
-	pevent = read_trace_init(file_bigendian, host_bigendian);
-	if (pevent == NULL) {
-		pr_debug("read_trace_init failed");
+	if (trace_event__init(tevent)) {
+		pr_debug("trace_event__init failed");
 		goto out;
 	}
 
+	pevent = tevent->pevent;
+
+	pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT);
+	pevent_set_file_bigendian(pevent, file_bigendian);
+	pevent_set_host_bigendian(pevent, host_bigendian);
+
 	if (do_read(buf, 1) < 0)
 		goto out;
 	file_long_size = buf[0];
@@ -432,11 +435,10 @@ ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe)
 		pevent_print_printk(pevent);
 	}
 
-	*ppevent = pevent;
 	pevent = NULL;
 
 out:
 	if (pevent)
-		pevent_free(pevent);
+		trace_event__cleanup(tevent);
 	return size;
 }
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
new file mode 100644
index 0000000..a155a77
--- /dev/null
+++ b/tools/perf/util/trace-event.c
@@ -0,0 +1,21 @@
+
+#include <traceevent/event-parse.h>
+#include "trace-event.h"
+
+int trace_event__init(struct trace_event *t)
+{
+	struct pevent *pevent = pevent_alloc();
+
+	if (pevent) {
+		t->plugin_list = traceevent_load_plugins(pevent);
+		t->pevent  = pevent;
+	}
+
+	return pevent ? 0 : -1;
+}
+
+void trace_event__cleanup(struct trace_event *t)
+{
+	pevent_free(t->pevent);
+	traceevent_unload_plugins(t->plugin_list);
+}
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 04df631..75dded3 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -3,17 +3,24 @@
 
 #include <traceevent/event-parse.h>
 #include "parse-events.h"
-#include "session.h"
 
 struct machine;
 struct perf_sample;
 union perf_event;
 struct perf_tool;
 struct thread;
+struct plugin_list;
+
+struct trace_event {
+	struct pevent		*pevent;
+	struct plugin_list	*plugin_list;
+};
+
+int trace_event__init(struct trace_event *t);
+void trace_event__cleanup(struct trace_event *t);
 
 int bigendian(void);
 
-struct pevent *read_trace_init(int file_bigendian, int host_bigendian);
 void event_format__print(struct event_format *event,
 			 int cpu, void *data, int size);
 
@@ -27,7 +34,7 @@ raw_field_value(struct event_format *event, const char *name, void *data);
 void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size);
 void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size);
 
-ssize_t trace_report(int fd, struct pevent **pevent, bool repipe);
+ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe);
 
 struct event_format *trace_find_next_event(struct pevent *pevent,
 					   struct event_format *event);
-- 
cgit v0.10.2


From 97978b3e30a512beba43720365f53fea8d432c97 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:24 +0100
Subject: perf tools: Add trace-event global object for tracepoint interface

In order to get the proper plugins processing we need to use full
trace-event interface when creating tracepoint events. So far we were
using shortcut to get the parsed format.

Moving current 'event_format__new' function into trace-event object as
'trace_event__tp_format'.

This function uses properly initialized global trace-event object,
ensuring proper plugins processing.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-11-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 9f2a242..56afe33 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -11,6 +11,7 @@
 #include "util/intlist.h"
 #include "util/thread_map.h"
 #include "util/stat.h"
+#include "trace-event.h"
 
 #include <libaudit.h>
 #include <stdlib.h>
@@ -1430,11 +1431,11 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 	sc->fmt  = syscall_fmt__find(sc->name);
 
 	snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->name);
-	sc->tp_format = event_format__new("syscalls", tp_name);
+	sc->tp_format = trace_event__tp_format("syscalls", tp_name);
 
 	if (sc->tp_format == NULL && sc->fmt && sc->fmt->alias) {
 		snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->fmt->alias);
-		sc->tp_format = event_format__new("syscalls", tp_name);
+		sc->tp_format = trace_event__tp_format("syscalls", tp_name);
 	}
 
 	if (sc->tp_format == NULL)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 6a046ed..7b510fd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -23,6 +23,7 @@
 #include "target.h"
 #include "perf_regs.h"
 #include "debug.h"
+#include "trace-event.h"
 
 static struct {
 	bool sample_id_all;
@@ -180,47 +181,6 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 	return evsel;
 }
 
-struct event_format *event_format__new(const char *sys, const char *name)
-{
-	int fd, n;
-	char *filename;
-	void *bf = NULL, *nbf;
-	size_t size = 0, alloc_size = 0;
-	struct event_format *format = NULL;
-
-	if (asprintf(&filename, "%s/%s/%s/format", tracing_events_path, sys, name) < 0)
-		goto out;
-
-	fd = open(filename, O_RDONLY);
-	if (fd < 0)
-		goto out_free_filename;
-
-	do {
-		if (size == alloc_size) {
-			alloc_size += BUFSIZ;
-			nbf = realloc(bf, alloc_size);
-			if (nbf == NULL)
-				goto out_free_bf;
-			bf = nbf;
-		}
-
-		n = read(fd, bf + size, alloc_size - size);
-		if (n < 0)
-			goto out_free_bf;
-		size += n;
-	} while (n > 0);
-
-	pevent_parse_format(NULL, &format, bf, size, sys);
-
-out_free_bf:
-	free(bf);
-	close(fd);
-out_free_filename:
-	free(filename);
-out:
-	return format;
-}
-
 struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx)
 {
 	struct perf_evsel *evsel = zalloc(sizeof(*evsel));
@@ -235,7 +195,7 @@ struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int
 		if (asprintf(&evsel->name, "%s:%s", sys, name) < 0)
 			goto out_free;
 
-		evsel->tp_format = event_format__new(sys, name);
+		evsel->tp_format = trace_event__tp_format(sys, name);
 		if (evsel->tp_format == NULL)
 			goto out_free;
 
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index a155a77..d9f5f61 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -1,6 +1,24 @@
 
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <linux/kernel.h>
 #include <traceevent/event-parse.h>
 #include "trace-event.h"
+#include "util.h"
+
+/*
+ * global trace_event object used by trace_event__tp_format
+ *
+ * TODO There's no cleanup call for this. Add some sort of
+ * __exit function support and call trace_event__cleanup
+ * there.
+ */
+static struct trace_event tevent;
 
 int trace_event__init(struct trace_event *t)
 {
@@ -19,3 +37,46 @@ void trace_event__cleanup(struct trace_event *t)
 	pevent_free(t->pevent);
 	traceevent_unload_plugins(t->plugin_list);
 }
+
+static struct event_format*
+tp_format(const char *sys, const char *name)
+{
+	struct pevent *pevent = tevent.pevent;
+	struct event_format *event = NULL;
+	char path[PATH_MAX];
+	size_t size;
+	char *data;
+
+	scnprintf(path, PATH_MAX, "%s/%s/%s/format",
+		  tracing_events_path, sys, name);
+
+	if (filename__read_str(path, &data, &size))
+		return NULL;
+
+	pevent_parse_format(pevent, &event, data, size, sys);
+
+	free(data);
+	return event;
+}
+
+struct event_format*
+trace_event__tp_format(const char *sys, const char *name)
+{
+	static bool initialized;
+
+	if (!initialized) {
+		int be = traceevent_host_bigendian();
+		struct pevent *pevent;
+
+		if (trace_event__init(&tevent))
+			return NULL;
+
+		pevent = tevent.pevent;
+		pevent_set_flag(pevent, PEVENT_NSEC_OUTPUT);
+		pevent_set_file_bigendian(pevent, be);
+		pevent_set_host_bigendian(pevent, be);
+		initialized = true;
+	}
+
+	return tp_format(sys, name);
+}
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 75dded3..3a01618 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -18,6 +18,8 @@ struct trace_event {
 
 int trace_event__init(struct trace_event *t);
 void trace_event__cleanup(struct trace_event *t);
+struct event_format*
+trace_event__tp_format(const char *sys, const char *name);
 
 int bigendian(void);
 
-- 
cgit v0.10.2


From f772abc63462a48df605259fbe1af3fe9b223926 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:25 +0100
Subject: perf tools: Overload pr_stat traceevent print function

The traceevent lib uses pr_stat to display all standard info. It's
defined as __weak. Overloading it with perf version plugged into perf
output system logic.

Displaying the pr_stat stuff under '-v' option.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-12-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 399e74c..8640a91 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -16,13 +16,11 @@
 int verbose;
 bool dump_trace = false, quiet = false;
 
-int eprintf(int level, const char *fmt, ...)
+static int _eprintf(int level, const char *fmt, va_list args)
 {
-	va_list args;
 	int ret = 0;
 
 	if (verbose >= level) {
-		va_start(args, fmt);
 		if (use_browser >= 1)
 			ui_helpline__vshow(fmt, args);
 		else
@@ -33,6 +31,32 @@ int eprintf(int level, const char *fmt, ...)
 	return ret;
 }
 
+int eprintf(int level, const char *fmt, ...)
+{
+	va_list args;
+	int ret;
+
+	va_start(args, fmt);
+	ret = _eprintf(level, fmt, args);
+	va_end(args);
+
+	return ret;
+}
+
+/*
+ * Overloading libtraceevent standard info print
+ * function, display with -v in perf.
+ */
+void pr_stat(const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	_eprintf(1, fmt, args);
+	va_end(args);
+	eprintf(1, "\n");
+}
+
 int dump_printf(const char *fmt, ...)
 {
 	va_list args;
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index efbd988..443694c 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -17,4 +17,6 @@ void trace_event(union perf_event *event);
 int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2)));
 int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
 
+void pr_stat(const char *fmt, ...);
+
 #endif	/* __PERF_DEBUG_H */
-- 
cgit v0.10.2


From e0549f11e8d57c1a606773342b3b71c74f9986eb Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:26 +0100
Subject: tools lib traceevent: Add jbd2 plugin

Backporting jbd2 plugin.

Backported from Steven Rostedt's trace-cmd repo (HEAD 0f2c2fb):
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/trace-cmd.git

This plugin adds field resolving functions for following tracepoint
events:

  jbd2:jbd2_checkpoint_stats
  jbd2:jbd2_run_stats

The diff of 'perf script' output generated by old and new code:
(data was generated by 'perf record -e 'jbd2:jbd2_run_stats,jbd2:jbd2_checkpoint_stats' -a')

  --- script.jbd2.old
  +++ script.jbd2.new
  -     jbd2/dm-3-8   576 [000]  2983.748423: jbd2:jbd2_checkpoint_stats: [FAILED TO PARSE] dev=265289731 tid=0x3f2bbb chp_time=0x0 forced_to_close=0 written=0 dropped=2
  +     jbd2/dm-3-8   576 [000]  2983.748423: jbd2:jbd2_checkpoint_stats: dev 253,3 tid 4139963 chp_time 0 forced_to_close 0 written 0 dropped 2
  -     jbd2/dm-3-8   576 [000]  2983.852789: jbd2:jbd2_run_stats: [FAILED TO PARSE] dev=265289731 tid=0x3f2bc0 wait=0x0 request_delay=0x0 running=0x138d locked=0x0 flushing=0x0 logging=0x68 handle_count=2995 blocks=17 blocks_logged=18
  +     jbd2/dm-3-8   576 [000]  2983.852789: jbd2:jbd2_run_stats: dev 253,3 tid 4139968 wait 0 request_delay 0 running 5005 locked 0 flushing 0 logging 104 handle_count 2995 blocks 17 blocks_logged 18

This plugin also adds jbd2_dev_to_name function, which was removed from
jdb2 tracepoints recently. Keeping it in for backward compatibility
reasons.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-13-git-send-email-jolsa@redhat.com
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index f946851..6c65400 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -212,6 +212,8 @@ PEVENT_LIB_OBJS += parse-filter.o
 PEVENT_LIB_OBJS += parse-utils.o
 PEVENT_LIB_OBJS += kbuffer-parse.o
 
+PLUGIN_OBJS = plugin_jbd2.o
+
 PLUGINS := $(PLUGIN_OBJS:.o=.so)
 
 ALL_OBJS = $(PEVENT_LIB_OBJS) $(PLUGIN_OBJS)
diff --git a/tools/lib/traceevent/plugin_jbd2.c b/tools/lib/traceevent/plugin_jbd2.c
new file mode 100644
index 0000000..5d85de7
--- /dev/null
+++ b/tools/lib/traceevent/plugin_jbd2.c
@@ -0,0 +1,66 @@
+/*
+ * Copyright (C) 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "event-parse.h"
+
+#define MINORBITS	20
+#define MINORMASK	((1U << MINORBITS) - 1)
+
+#define MAJOR(dev)	((unsigned int) ((dev) >> MINORBITS))
+#define MINOR(dev)	((unsigned int) ((dev) & MINORMASK))
+
+unsigned long long process_jbd2_dev_to_name(struct trace_seq *s,
+					    unsigned long long *args)
+{
+	unsigned int dev = args[0];
+
+	trace_seq_printf(s, "%d:%d", MAJOR(dev), MINOR(dev));
+	return 0;
+}
+
+unsigned long long process_jiffies_to_msecs(struct trace_seq *s,
+					    unsigned long long *args)
+{
+	unsigned long long jiffies = args[0];
+
+	trace_seq_printf(s, "%lld", jiffies);
+	return jiffies;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_print_function(pevent,
+				       process_jbd2_dev_to_name,
+				       PEVENT_FUNC_ARG_STRING,
+				       "jbd2_dev_to_name",
+				       PEVENT_FUNC_ARG_INT,
+				       PEVENT_FUNC_ARG_VOID);
+
+	pevent_register_print_function(pevent,
+				       process_jiffies_to_msecs,
+				       PEVENT_FUNC_ARG_LONG,
+				       "jiffies_to_msecs",
+				       PEVENT_FUNC_ARG_LONG,
+				       PEVENT_FUNC_ARG_VOID);
+	return 0;
+}
-- 
cgit v0.10.2


From d9d13f8be6237950753e093683e9f415f31eccbc Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:27 +0100
Subject: tools lib traceevent: Add hrtimer plugin

Backporting hrtimer plugin.

Backported from Steven Rostedt's trace-cmd repo (HEAD 0f2c2fb):
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/trace-cmd.git

This plugin adds function field resolving for following tracepoint
events:

  timer:hrtimer_expire_entry
  timer:hrtimer_start

The diff of 'perf script' output generated by old and new code: (data
was generated by 'perf record -e 'timer:hrtimer*' -a')

  --- script.hrtimer.old
  +++ script.hrtimer.new
  -         swapper     0 [000] 27405.519092: timer:hrtimer_start: [FAILED TO PARSE] hrtimer=0xffff88021e20e800 function=0xffffffff810c0e10 expires=27398383000000 softexpires=27398383000000
  +         swapper     0 [000] 27405.519103: timer:hrtimer_start: hrtimer=0xffff88021e20e800 function=tick_sched_timer expires=27398383000000 softexpires=27398383000000
  -         swapper     0 [001] 27405.519544: timer:hrtimer_expire_entry: [FAILED TO PARSE] hrtimer=0xffff880211334058 now=27398294182491 function=0xffffffff81086f20
  +         swapper     0 [001] 27405.519544: timer:hrtimer_expire_entry: hrtimer=0xffff880211334058 now=27398294182491 function=posix_timer_fn/0x0

Check the 'function' field is translated into the function name.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-14-git-send-email-jolsa@redhat.com
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 6c65400..9ff2e25 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -212,7 +212,8 @@ PEVENT_LIB_OBJS += parse-filter.o
 PEVENT_LIB_OBJS += parse-utils.o
 PEVENT_LIB_OBJS += kbuffer-parse.o
 
-PLUGIN_OBJS = plugin_jbd2.o
+PLUGIN_OBJS  = plugin_jbd2.o
+PLUGIN_OBJS += plugin_hrtimer.o
 
 PLUGINS := $(PLUGIN_OBJS:.o=.so)
 
diff --git a/tools/lib/traceevent/plugin_hrtimer.c b/tools/lib/traceevent/plugin_hrtimer.c
new file mode 100644
index 0000000..e41d4cf
--- /dev/null
+++ b/tools/lib/traceevent/plugin_hrtimer.c
@@ -0,0 +1,93 @@
+/*
+ * Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ * Copyright (C) 2009 Johannes Berg <johannes@sipsolutions.net>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "event-parse.h"
+
+static int timer_expire_handler(struct trace_seq *s,
+				struct pevent_record *record,
+				struct event_format *event, void *context)
+{
+	trace_seq_printf(s, "hrtimer=");
+
+	if (pevent_print_num_field(s, "0x%llx", event, "timer",
+				   record, 0) == -1)
+		pevent_print_num_field(s, "0x%llx", event, "hrtimer",
+				       record, 1);
+
+	trace_seq_printf(s, " now=");
+
+	pevent_print_num_field(s, "%llu", event, "now", record, 1);
+
+	pevent_print_func_field(s, " function=%s", event, "function",
+				record, 0);
+	return 0;
+}
+
+static int timer_start_handler(struct trace_seq *s,
+			       struct pevent_record *record,
+			       struct event_format *event, void *context)
+{
+	struct pevent *pevent = event->pevent;
+	struct format_field *fn = pevent_find_field(event, "function");
+	void *data = record->data;
+
+	trace_seq_printf(s, "hrtimer=");
+
+	if (pevent_print_num_field(s, "0x%llx", event, "timer",
+				   record, 0) == -1)
+		pevent_print_num_field(s, "0x%llx", event, "hrtimer",
+				       record, 1);
+
+	if (!fn) {
+		trace_seq_printf(s, " function=MISSING");
+	} else {
+		unsigned long long function;
+		const char *func;
+
+		if (pevent_read_number_field(fn, data, &function))
+			trace_seq_printf(s, " function=INVALID");
+
+		func = pevent_find_function(pevent, function);
+
+		trace_seq_printf(s, " function=%s", func);
+	}
+
+	trace_seq_printf(s, " expires=");
+	pevent_print_num_field(s, "%llu", event, "expires", record, 1);
+
+	trace_seq_printf(s, " softexpires=");
+	pevent_print_num_field(s, "%llu", event, "softexpires", record, 1);
+	return 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_event_handler(pevent, -1,
+				      "timer", "hrtimer_expire_entry",
+				      timer_expire_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "timer", "hrtimer_start",
+				      timer_start_handler, NULL);
+	return 0;
+}
-- 
cgit v0.10.2


From f825628840e581f92f1c2e79dfa943f29c054e67 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:28 +0100
Subject: tools lib traceevent: Add kmem plugin

Backporting kmem plugin.

Backported from Steven Rostedt's trace-cmd repo (HEAD 0f2c2fb):
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/trace-cmd.git

This plugin adds call_site field resolving for following tracepoint
events:

  kmem:kfree
  kmem:kmalloc
  kmem:kmalloc_node
  kmem:kmem_cache_alloc
  kmem:kmem_cache_alloc_node
  kmem:kmem_cache_free

The diff of 'perf script' output generated by old and new code: (data
was generated by 'perf record -e 'kmem:*' -a')

  --- script.kmem.old
  +++ script.kmem.new
  -            perf 27846 [001] 29643.403319: kmem:kfree: call_site=ffffffff810e64f6 ptr=(nil)
  +            perf 27846 [001] 29643.403238: kmem:kfree: (__audit_syscall_exit+0x1f6) call_site=ffffffff810e64f6 ptr=(nil)
  -            perf 27846 [001] 29643.403337: kmem:kmem_cache_alloc: call_site=ffffffff812ff0c5 ptr=0xffff88020e155630 bytes_req=560 bytes_alloc=568 gfp_flags=GFP_KERNEL
  +            perf 27846 [001] 29643.403337: kmem:kmem_cache_alloc: (radix_tree_preload+0x35) call_site=ffffffff812ff0c5 ptr=0xffff88020e155630 bytes_req=560 bytes_alloc=568 gfp_flags=GFP_KERNEL
  -            perf 27846 [001] 29643.403342: kmem:kmem_cache_free: call_site=ffffffff8126ec61 ptr=0xffff88020dffe750
  +            perf 27846 [001] 29643.403342: kmem:kmem_cache_free: (jbd2_journal_stop+0x221) call_site=ffffffff8126ec61 ptr=0xffff88020dffe750
  -         firefox   954 [000] 29643.445477: kmem:kmem_cache_alloc_node: call_site=ffffffff8153c64e ptr=0xffff8801cecb4000 bytes_req=256 bytes_alloc=256 gfp_flags=GFP_KERNEL|GFP_REPEAT node=-1
  +         firefox   954 [000] 29643.445477: kmem:kmem_cache_alloc_node: (__alloc_skb+0x4e) call_site=ffffffff8153c64e ptr=0xffff8801cecb4000 bytes_req=256 bytes_alloc=256 gfp_flags=GFP_KERNEL|GFP_REPEAT node=-1
  -            perf 27846 [001] 29643.445510: kmem:kmalloc: call_site=ffffffff81250642 ptr=0xffff88020fd6c300 bytes_req=96 bytes_alloc=96 gfp_flags=GFP_NOFS|GFP_ZERO
  +            perf 27846 [001] 29643.445510: kmem:kmalloc: (ext4_ext_find_extent+0x362) call_site=ffffffff81250642 ptr=0xffff88020fd6c300 bytes_req=96 bytes_alloc=96 gfp_flags=GFP_NOFS|GFP_ZERO
  -               X   888 [002] 29643.445546: kmem:kmalloc_node: call_site=ffffffff8153c67e ptr=0xffff880103828e00 bytes_req=384 bytes_alloc=512 gfp_flags=GFP_KERNEL|GFP_NOWARN|GFP_REPEAT|GFP_NOMEMALLOC node=-1
  +               X   888 [002] 29643.445546: kmem:kmalloc_node: (__alloc_skb+0x7e) call_site=ffffffff8153c67e ptr=0xffff880103828e00 bytes_req=384 bytes_alloc=512 gfp_flags=GFP_KERNEL|GFP_NOWARN|GFP_REPEAT|GFP_NOMEMALLOC node=-1

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-15-git-send-email-jolsa@redhat.com
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 9ff2e25..245d6b4 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -214,6 +214,7 @@ PEVENT_LIB_OBJS += kbuffer-parse.o
 
 PLUGIN_OBJS  = plugin_jbd2.o
 PLUGIN_OBJS += plugin_hrtimer.o
+PLUGIN_OBJS += plugin_kmem.o
 
 PLUGINS := $(PLUGIN_OBJS:.o=.so)
 
diff --git a/tools/lib/traceevent/plugin_kmem.c b/tools/lib/traceevent/plugin_kmem.c
new file mode 100644
index 0000000..7115c80
--- /dev/null
+++ b/tools/lib/traceevent/plugin_kmem.c
@@ -0,0 +1,72 @@
+/*
+ * Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "event-parse.h"
+
+static int call_site_handler(struct trace_seq *s, struct pevent_record *record,
+			     struct event_format *event, void *context)
+{
+	struct format_field *field;
+	unsigned long long val, addr;
+	void *data = record->data;
+	const char *func;
+
+	field = pevent_find_field(event, "call_site");
+	if (!field)
+		return 1;
+
+	if (pevent_read_number_field(field, data, &val))
+		return 1;
+
+	func = pevent_find_function(event->pevent, val);
+	if (!func)
+		return 1;
+
+	addr = pevent_find_function_address(event->pevent, val);
+
+	trace_seq_printf(s, "(%s+0x%x) ", func, (int)(val - addr));
+	return 1;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_event_handler(pevent, -1, "kmem", "kfree",
+				      call_site_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kmem", "kmalloc",
+				      call_site_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kmem", "kmalloc_node",
+				      call_site_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kmem", "kmem_cache_alloc",
+				      call_site_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kmem",
+				      "kmem_cache_alloc_node",
+				      call_site_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kmem", "kmem_cache_free",
+				      call_site_handler, NULL);
+	return 0;
+}
-- 
cgit v0.10.2


From 35d79f9ff88765af3fba6981db8d071872dcc5a8 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:29 +0100
Subject: tools lib traceevent: Add kvm plugin

Backporting kvm plugin.

Backported from Steven Rostedt's trace-cmd repo (HEAD 0f2c2fb):
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/trace-cmd.git

This plugin adds field resolving functions for following
tracepoint events:
  kvm:kvm_exit
  kvm:kvm_emulate_insn
  kvm:kvm_nested_vmexit
  kvm:kvm_nested_vmexit_inject
  kvmmmu:kvm_mmu_get_page
  kvmmmu:kvm_mmu_sync_page
  kvmmmu:kvm_mmu_unsync_page
  kvmmmu:kvm_mmu_zap_page
  kvmmmu:kvm_mmu_prepare_zap_page

The diff of 'perf script' output generated by old and new code:
(data was generated by 'perf record -e 'kvm:*,kvmmmu:*' -a')

  --- script.kvm.old
  +++ script.kvm.new
    qemu-system-x86 17414 [000]  6868.995053: kvm:kvm_exit: reason EPT_VIOLATION rip 0xfff0 info 184 0
    qemu-system-x86 17414 [000]  6868.995109: kvm:kvm_emulate_insn: f0000:c46b:e4 71 (real)
  - qemu-system-x86  3006 [002] 10562.079422: kvmmmu:kvm_mmu_get_page: [FAILED TO PARSE] mmu_valid_gen=0x2 gfn=0 role=122884 root_count=0 unsync=0 created=1
  + qemu-system-x86  3006 [002] 10562.079422: kvmmmu:kvm_mmu_get_page: new sp gfn 0 0/4 q0 direct --- !pge !nxe root 0 sync
  - qemu-system-x86  3006 [002] 10562.080502: kvmmmu:kvm_mmu_prepare_zap_page: [FAILED TO PARSE] mmu_valid_gen=0x2 gfn=0 role=122884 root_count=1 unsync=0
  + qemu-system-x86  3006 [002] 10562.080502: kvmmmu:kvm_mmu_prepare_zap_page: 0/4 q0 direct --- !pge !nxe root 1 sync
    qemu-system-x86  3290 [002] 10708.755312: kvmmmu:fast_page_fault: [FAILED TO PARSE] vcpu_id=0 gva=4094486080 error_code=3 sptep=0xffff88019f1e3670 old_spte=336391285 new_spte=336391287 retry=1
  -          insmod  2576 [001]   781.731666: kvmmmu:kvm_mmu_sync_page: [FAILED TO PARSE] mmu_valid_gen=0x1 gfn=2 role=24624 root_count=10 unsync=1
  +          insmod  2576 [001]   781.731666: kvmmmu:kvm_mmu_sync_page: 3/0 q0 --- !pge !nxe root 10 unsync
  -          insmod  2576 [001]   781.731668: kvmmmu:kvm_mmu_unsync_page: [FAILED TO PARSE] mmu_valid_gen=0x1 gfn=2 role=24624 root_count=10 unsync=1
  +          insmod  2576 [001]   781.731668: kvmmmu:kvm_mmu_unsync_page: 3/0 q0 --- !pge !nxe root 10 unsync

Note:
 - kvm_mmu_zap_page is replaced by kvm_mmu_prepare_zap_page
   in current kernel, keeping it for backward compatibility
 - some of the tracepoints keep the same output even with
   the plugin handling: kvm:kvm_exit, kvm:kvm_emulate_insn
 - the 'kvmmmu:fast_page_fault' is still broken because of
   missing is_writable_pte function and is fixed in another patch
 - ommited following tracepoints from backport because
   the output was buggy
     kvm:kvm_nested_vmexit
     kvm:kvm_nested_vmexit_inject

Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-16-git-send-email-jolsa@redhat.com
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 245d6b4..226a8f9 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -215,6 +215,7 @@ PEVENT_LIB_OBJS += kbuffer-parse.o
 PLUGIN_OBJS  = plugin_jbd2.o
 PLUGIN_OBJS += plugin_hrtimer.o
 PLUGIN_OBJS += plugin_kmem.o
+PLUGIN_OBJS += plugin_kvm.o
 
 PLUGINS := $(PLUGIN_OBJS:.o=.so)
 
diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c
new file mode 100644
index 0000000..be9d9c6
--- /dev/null
+++ b/tools/lib/traceevent/plugin_kvm.c
@@ -0,0 +1,419 @@
+/*
+ * Copyright (C) 2009 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdint.h>
+
+#include "event-parse.h"
+
+#ifdef HAVE_UDIS86
+
+#include <udis86.h>
+
+static ud_t ud;
+
+static void init_disassembler(void)
+{
+	ud_init(&ud);
+	ud_set_syntax(&ud, UD_SYN_ATT);
+}
+
+static const char *disassemble(unsigned char *insn, int len, uint64_t rip,
+			       int cr0_pe, int eflags_vm,
+			       int cs_d, int cs_l)
+{
+	int mode;
+
+	if (!cr0_pe)
+		mode = 16;
+	else if (eflags_vm)
+		mode = 16;
+	else if (cs_l)
+		mode = 64;
+	else if (cs_d)
+		mode = 32;
+	else
+		mode = 16;
+
+	ud_set_pc(&ud, rip);
+	ud_set_mode(&ud, mode);
+	ud_set_input_buffer(&ud, insn, len);
+	ud_disassemble(&ud);
+	return ud_insn_asm(&ud);
+}
+
+#else
+
+static void init_disassembler(void)
+{
+}
+
+static const char *disassemble(unsigned char *insn, int len, uint64_t rip,
+			       int cr0_pe, int eflags_vm,
+			       int cs_d, int cs_l)
+{
+	static char out[15*3+1];
+	int i;
+
+	for (i = 0; i < len; ++i)
+		sprintf(out + i * 3, "%02x ", insn[i]);
+	out[len*3-1] = '\0';
+	return out;
+}
+
+#endif
+
+
+#define VMX_EXIT_REASONS			\
+	_ER(EXCEPTION_NMI,	 0)		\
+	_ER(EXTERNAL_INTERRUPT,	 1)		\
+	_ER(TRIPLE_FAULT,	 2)		\
+	_ER(PENDING_INTERRUPT,	 7)		\
+	_ER(NMI_WINDOW,		 8)		\
+	_ER(TASK_SWITCH,	 9)		\
+	_ER(CPUID,		 10)		\
+	_ER(HLT,		 12)		\
+	_ER(INVD,		 13)		\
+	_ER(INVLPG,		 14)		\
+	_ER(RDPMC,		 15)		\
+	_ER(RDTSC,		 16)		\
+	_ER(VMCALL,		 18)		\
+	_ER(VMCLEAR,		 19)		\
+	_ER(VMLAUNCH,		 20)		\
+	_ER(VMPTRLD,		 21)		\
+	_ER(VMPTRST,		 22)		\
+	_ER(VMREAD,		 23)		\
+	_ER(VMRESUME,		 24)		\
+	_ER(VMWRITE,		 25)		\
+	_ER(VMOFF,		 26)		\
+	_ER(VMON,		 27)		\
+	_ER(CR_ACCESS,		 28)		\
+	_ER(DR_ACCESS,		 29)		\
+	_ER(IO_INSTRUCTION,	 30)		\
+	_ER(MSR_READ,		 31)		\
+	_ER(MSR_WRITE,		 32)		\
+	_ER(MWAIT_INSTRUCTION,	 36)		\
+	_ER(MONITOR_INSTRUCTION, 39)		\
+	_ER(PAUSE_INSTRUCTION,	 40)		\
+	_ER(MCE_DURING_VMENTRY,	 41)		\
+	_ER(TPR_BELOW_THRESHOLD, 43)		\
+	_ER(APIC_ACCESS,	 44)		\
+	_ER(EOI_INDUCED,	 45)		\
+	_ER(EPT_VIOLATION,	 48)		\
+	_ER(EPT_MISCONFIG,	 49)		\
+	_ER(INVEPT,		 50)		\
+	_ER(PREEMPTION_TIMER,	 52)		\
+	_ER(WBINVD,		 54)		\
+	_ER(XSETBV,		 55)		\
+	_ER(APIC_WRITE,		 56)		\
+	_ER(INVPCID,		 58)
+
+#define SVM_EXIT_REASONS \
+	_ER(EXIT_READ_CR0,	0x000)		\
+	_ER(EXIT_READ_CR3,	0x003)		\
+	_ER(EXIT_READ_CR4,	0x004)		\
+	_ER(EXIT_READ_CR8,	0x008)		\
+	_ER(EXIT_WRITE_CR0,	0x010)		\
+	_ER(EXIT_WRITE_CR3,	0x013)		\
+	_ER(EXIT_WRITE_CR4,	0x014)		\
+	_ER(EXIT_WRITE_CR8,	0x018)		\
+	_ER(EXIT_READ_DR0,	0x020)		\
+	_ER(EXIT_READ_DR1,	0x021)		\
+	_ER(EXIT_READ_DR2,	0x022)		\
+	_ER(EXIT_READ_DR3,	0x023)		\
+	_ER(EXIT_READ_DR4,	0x024)		\
+	_ER(EXIT_READ_DR5,	0x025)		\
+	_ER(EXIT_READ_DR6,	0x026)		\
+	_ER(EXIT_READ_DR7,	0x027)		\
+	_ER(EXIT_WRITE_DR0,	0x030)		\
+	_ER(EXIT_WRITE_DR1,	0x031)		\
+	_ER(EXIT_WRITE_DR2,	0x032)		\
+	_ER(EXIT_WRITE_DR3,	0x033)		\
+	_ER(EXIT_WRITE_DR4,	0x034)		\
+	_ER(EXIT_WRITE_DR5,	0x035)		\
+	_ER(EXIT_WRITE_DR6,	0x036)		\
+	_ER(EXIT_WRITE_DR7,	0x037)		\
+	_ER(EXIT_EXCP_BASE,     0x040)		\
+	_ER(EXIT_INTR,		0x060)		\
+	_ER(EXIT_NMI,		0x061)		\
+	_ER(EXIT_SMI,		0x062)		\
+	_ER(EXIT_INIT,		0x063)		\
+	_ER(EXIT_VINTR,		0x064)		\
+	_ER(EXIT_CR0_SEL_WRITE,	0x065)		\
+	_ER(EXIT_IDTR_READ,	0x066)		\
+	_ER(EXIT_GDTR_READ,	0x067)		\
+	_ER(EXIT_LDTR_READ,	0x068)		\
+	_ER(EXIT_TR_READ,	0x069)		\
+	_ER(EXIT_IDTR_WRITE,	0x06a)		\
+	_ER(EXIT_GDTR_WRITE,	0x06b)		\
+	_ER(EXIT_LDTR_WRITE,	0x06c)		\
+	_ER(EXIT_TR_WRITE,	0x06d)		\
+	_ER(EXIT_RDTSC,		0x06e)		\
+	_ER(EXIT_RDPMC,		0x06f)		\
+	_ER(EXIT_PUSHF,		0x070)		\
+	_ER(EXIT_POPF,		0x071)		\
+	_ER(EXIT_CPUID,		0x072)		\
+	_ER(EXIT_RSM,		0x073)		\
+	_ER(EXIT_IRET,		0x074)		\
+	_ER(EXIT_SWINT,		0x075)		\
+	_ER(EXIT_INVD,		0x076)		\
+	_ER(EXIT_PAUSE,		0x077)		\
+	_ER(EXIT_HLT,		0x078)		\
+	_ER(EXIT_INVLPG,	0x079)		\
+	_ER(EXIT_INVLPGA,	0x07a)		\
+	_ER(EXIT_IOIO,		0x07b)		\
+	_ER(EXIT_MSR,		0x07c)		\
+	_ER(EXIT_TASK_SWITCH,	0x07d)		\
+	_ER(EXIT_FERR_FREEZE,	0x07e)		\
+	_ER(EXIT_SHUTDOWN,	0x07f)		\
+	_ER(EXIT_VMRUN,		0x080)		\
+	_ER(EXIT_VMMCALL,	0x081)		\
+	_ER(EXIT_VMLOAD,	0x082)		\
+	_ER(EXIT_VMSAVE,	0x083)		\
+	_ER(EXIT_STGI,		0x084)		\
+	_ER(EXIT_CLGI,		0x085)		\
+	_ER(EXIT_SKINIT,	0x086)		\
+	_ER(EXIT_RDTSCP,	0x087)		\
+	_ER(EXIT_ICEBP,		0x088)		\
+	_ER(EXIT_WBINVD,	0x089)		\
+	_ER(EXIT_MONITOR,	0x08a)		\
+	_ER(EXIT_MWAIT,		0x08b)		\
+	_ER(EXIT_MWAIT_COND,	0x08c)		\
+	_ER(EXIT_NPF,		0x400)		\
+	_ER(EXIT_ERR,		-1)
+
+#define _ER(reason, val)	{ #reason, val },
+struct str_values {
+	const char	*str;
+	int		val;
+};
+
+static struct str_values vmx_exit_reasons[] = {
+	VMX_EXIT_REASONS
+	{ NULL, -1}
+};
+
+static struct str_values svm_exit_reasons[] = {
+	SVM_EXIT_REASONS
+	{ NULL, -1}
+};
+
+static struct isa_exit_reasons {
+	unsigned isa;
+	struct str_values *strings;
+} isa_exit_reasons[] = {
+	{ .isa = 1, .strings = vmx_exit_reasons },
+	{ .isa = 2, .strings = svm_exit_reasons },
+	{ }
+};
+
+static const char *find_exit_reason(unsigned isa, int val)
+{
+	struct str_values *strings = NULL;
+	int i;
+
+	for (i = 0; isa_exit_reasons[i].strings; ++i)
+		if (isa_exit_reasons[i].isa == isa) {
+			strings = isa_exit_reasons[i].strings;
+			break;
+		}
+	if (!strings)
+		return "UNKNOWN-ISA";
+	for (i = 0; strings[i].val >= 0; i++)
+		if (strings[i].val == val)
+			break;
+	if (strings[i].str)
+		return strings[i].str;
+	return "UNKNOWN";
+}
+
+static int kvm_exit_handler(struct trace_seq *s, struct pevent_record *record,
+			    struct event_format *event, void *context)
+{
+	unsigned long long isa;
+	unsigned long long val;
+	unsigned long long info1 = 0, info2 = 0;
+
+	if (pevent_get_field_val(s, event, "exit_reason", record, &val, 1) < 0)
+		return -1;
+
+	if (pevent_get_field_val(s, event, "isa", record, &isa, 0) < 0)
+		isa = 1;
+
+	trace_seq_printf(s, "reason %s", find_exit_reason(isa, val));
+
+	pevent_print_num_field(s, " rip 0x%lx", event, "guest_rip", record, 1);
+
+	if (pevent_get_field_val(s, event, "info1", record, &info1, 0) >= 0
+	    && pevent_get_field_val(s, event, "info2", record, &info2, 0) >= 0)
+		trace_seq_printf(s, " info %llx %llx", info1, info2);
+
+	return 0;
+}
+
+#define KVM_EMUL_INSN_F_CR0_PE (1 << 0)
+#define KVM_EMUL_INSN_F_EFL_VM (1 << 1)
+#define KVM_EMUL_INSN_F_CS_D   (1 << 2)
+#define KVM_EMUL_INSN_F_CS_L   (1 << 3)
+
+static int kvm_emulate_insn_handler(struct trace_seq *s,
+				    struct pevent_record *record,
+				    struct event_format *event, void *context)
+{
+	unsigned long long rip, csbase, len, flags, failed;
+	int llen;
+	uint8_t *insn;
+	const char *disasm;
+
+	if (pevent_get_field_val(s, event, "rip", record, &rip, 1) < 0)
+		return -1;
+
+	if (pevent_get_field_val(s, event, "csbase", record, &csbase, 1) < 0)
+		return -1;
+
+	if (pevent_get_field_val(s, event, "len", record, &len, 1) < 0)
+		return -1;
+
+	if (pevent_get_field_val(s, event, "flags", record, &flags, 1) < 0)
+		return -1;
+
+	if (pevent_get_field_val(s, event, "failed", record, &failed, 1) < 0)
+		return -1;
+
+	insn = pevent_get_field_raw(s, event, "insn", record, &llen, 1);
+	if (!insn)
+		return -1;
+
+	disasm = disassemble(insn, len, rip,
+			     flags & KVM_EMUL_INSN_F_CR0_PE,
+			     flags & KVM_EMUL_INSN_F_EFL_VM,
+			     flags & KVM_EMUL_INSN_F_CS_D,
+			     flags & KVM_EMUL_INSN_F_CS_L);
+
+	trace_seq_printf(s, "%llx:%llx: %s%s", csbase, rip, disasm,
+			 failed ? " FAIL" : "");
+	return 0;
+}
+
+union kvm_mmu_page_role {
+	unsigned word;
+	struct {
+		unsigned glevels:4;
+		unsigned level:4;
+		unsigned quadrant:2;
+		unsigned pad_for_nice_hex_output:6;
+		unsigned direct:1;
+		unsigned access:3;
+		unsigned invalid:1;
+		unsigned cr4_pge:1;
+		unsigned nxe:1;
+	};
+};
+
+static int kvm_mmu_print_role(struct trace_seq *s, struct pevent_record *record,
+			      struct event_format *event, void *context)
+{
+	unsigned long long val;
+	static const char *access_str[] = {
+		"---", "--x", "w--", "w-x", "-u-", "-ux", "wu-", "wux"
+	};
+	union kvm_mmu_page_role role;
+
+	if (pevent_get_field_val(s, event, "role", record, &val, 1) < 0)
+		return -1;
+
+	role.word = (int)val;
+
+	/*
+	 * We can only use the structure if file is of the same
+	 * endianess.
+	 */
+	if (pevent_is_file_bigendian(event->pevent) ==
+	    pevent_is_host_bigendian(event->pevent)) {
+
+		trace_seq_printf(s, "%u/%u q%u%s %s%s %spge %snxe",
+				 role.level,
+				 role.glevels,
+				 role.quadrant,
+				 role.direct ? " direct" : "",
+				 access_str[role.access],
+				 role.invalid ? " invalid" : "",
+				 role.cr4_pge ? "" : "!",
+				 role.nxe ? "" : "!");
+	} else
+		trace_seq_printf(s, "WORD: %08x", role.word);
+
+	pevent_print_num_field(s, " root %u ",  event,
+			       "root_count", record, 1);
+
+	if (pevent_get_field_val(s, event, "unsync", record, &val, 1) < 0)
+		return -1;
+
+	trace_seq_printf(s, "%s%c",  val ? "unsync" : "sync", 0);
+	return 0;
+}
+
+static int kvm_mmu_get_page_handler(struct trace_seq *s,
+				    struct pevent_record *record,
+				    struct event_format *event, void *context)
+{
+	unsigned long long val;
+
+	if (pevent_get_field_val(s, event, "created", record, &val, 1) < 0)
+		return -1;
+
+	trace_seq_printf(s, "%s ", val ? "new" : "existing");
+
+	if (pevent_get_field_val(s, event, "gfn", record, &val, 1) < 0)
+		return -1;
+
+	trace_seq_printf(s, "sp gfn %llx ", val);
+	return kvm_mmu_print_role(s, record, event, context);
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	init_disassembler();
+
+	pevent_register_event_handler(pevent, -1, "kvm", "kvm_exit",
+				      kvm_exit_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kvm", "kvm_emulate_insn",
+				      kvm_emulate_insn_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page",
+				      kvm_mmu_get_page_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_sync_page",
+				      kvm_mmu_print_role, NULL);
+
+	pevent_register_event_handler(pevent, -1,
+				      "kvmmmu", "kvm_mmu_unsync_page",
+				      kvm_mmu_print_role, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_zap_page",
+				      kvm_mmu_print_role, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kvmmmu",
+			"kvm_mmu_prepare_zap_page", kvm_mmu_print_role,
+			NULL);
+	return 0;
+}
-- 
cgit v0.10.2


From de705e2e88442c0c5dc6ec8c1f3fb1931def102e Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:30 +0100
Subject: tools lib traceevent: Add mac80211 plugin

Backporting mac80211 plugin.

Backported from Steven Rostedt's trace-cmd repo (HEAD 0f2c2fb):
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/trace-cmd.git

This plugin adds changed field resolving for
mac80211:drv_bss_info_changed tracepoint event.

The diff of 'perf script' output generated by old and new code:
(data was generated by 'perf record -e 'mac80211:drv_bss_info_changed' -a')

  --- script.mac80211.old
  +++ script.mac80211.new
  -        ifconfig  3711 [000]  1290.446492: mac80211:drv_bss_info_changed: phy0 vif:wlan0(2) changed:0x309f
  +        ifconfig  3711 [000]  1290.446492: mac80211:drv_bss_info_changed: phy0 vif:wlan0(2)
  +                                                                 assoc:0 aid:2 cts:0 shortpre:0 shortslot:0 dtimper:1
  +                                                                 bcnint:102 assoc_cap:0x431 basic_rates:0xf enable_beacon:0
  +                                                                 ht_operation_mode:0

Omitting the mac80211:drv_config tracepoint handling because the kernel
tracepoint changed its prototype and the plugin handler is no longer
working.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-17-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 226a8f9..d0e0ca1 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -216,6 +216,7 @@ PLUGIN_OBJS  = plugin_jbd2.o
 PLUGIN_OBJS += plugin_hrtimer.o
 PLUGIN_OBJS += plugin_kmem.o
 PLUGIN_OBJS += plugin_kvm.o
+PLUGIN_OBJS += plugin_mac80211.o
 
 PLUGINS := $(PLUGIN_OBJS:.o=.so)
 
diff --git a/tools/lib/traceevent/plugin_mac80211.c b/tools/lib/traceevent/plugin_mac80211.c
new file mode 100644
index 0000000..558a3b9
--- /dev/null
+++ b/tools/lib/traceevent/plugin_mac80211.c
@@ -0,0 +1,95 @@
+/*
+ * Copyright (C) 2009 Johannes Berg <johannes@sipsolutions.net>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "event-parse.h"
+
+#define INDENT 65
+
+static void print_string(struct trace_seq *s, struct event_format *event,
+			 const char *name, const void *data)
+{
+	struct format_field *f = pevent_find_field(event, name);
+	int offset;
+	int length;
+
+	if (!f) {
+		trace_seq_printf(s, "NOTFOUND:%s", name);
+		return;
+	}
+
+	offset = f->offset;
+	length = f->size;
+
+	if (!strncmp(f->type, "__data_loc", 10)) {
+		unsigned long long v;
+		if (pevent_read_number_field(f, data, &v)) {
+			trace_seq_printf(s, "invalid_data_loc");
+			return;
+		}
+		offset = v & 0xffff;
+		length = v >> 16;
+	}
+
+	trace_seq_printf(s, "%.*s", length, (char *)data + offset);
+}
+
+#define SF(fn)	pevent_print_num_field(s, fn ":%d", event, fn, record, 0)
+#define SFX(fn)	pevent_print_num_field(s, fn ":%#x", event, fn, record, 0)
+#define SP()	trace_seq_putc(s, ' ')
+
+static int drv_bss_info_changed(struct trace_seq *s,
+				struct pevent_record *record,
+				struct event_format *event, void *context)
+{
+	void *data = record->data;
+
+	print_string(s, event, "wiphy_name", data);
+	trace_seq_printf(s, " vif:");
+	print_string(s, event, "vif_name", data);
+	pevent_print_num_field(s, "(%d)", event, "vif_type", record, 1);
+
+	trace_seq_printf(s, "\n%*s", INDENT, "");
+	SF("assoc"); SP();
+	SF("aid"); SP();
+	SF("cts"); SP();
+	SF("shortpre"); SP();
+	SF("shortslot"); SP();
+	SF("dtimper"); SP();
+	trace_seq_printf(s, "\n%*s", INDENT, "");
+	SF("bcnint"); SP();
+	SFX("assoc_cap"); SP();
+	SFX("basic_rates"); SP();
+	SF("enable_beacon");
+	trace_seq_printf(s, "\n%*s", INDENT, "");
+	SF("ht_operation_mode");
+
+	return 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_event_handler(pevent, -1, "mac80211",
+				      "drv_bss_info_changed",
+				      drv_bss_info_changed, NULL);
+	return 0;
+}
-- 
cgit v0.10.2


From 83e815ee1c6b5fdb570374404ab44b24c1325ccb Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:31 +0100
Subject: tools lib traceevent: Add sched_switch plugin

Backporting sched_switch plugin.

Backported from Steven Rostedt's trace-cmd repo (HEAD 0f2c2fb):
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/trace-cmd.git

This plugin adds fields resolving for sched:sched_switch tracepoint
event.

The diff of 'perf script' output generated by old and new code:
(data was generated by 'perf record -e sched:sched_switch -a')

  --- script.sched_switch.old
  +++ script.sched_switch.new
  -            perf   577 [002] 30965.311852: sched:sched_switch: prev_comm=perf prev_pid=577 prev_prio=120 prev_state=S ==> next_comm=swapper/2 next_pid=0 next_prio=120
  +            perf   577 [002] 30965.311852: sched:sched_switch: perf:577 [120] S ==> swapper/2:0 [120]

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-18-git-send-email-jolsa@redhat.com
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index d0e0ca1..1c319a8 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -217,6 +217,7 @@ PLUGIN_OBJS += plugin_hrtimer.o
 PLUGIN_OBJS += plugin_kmem.o
 PLUGIN_OBJS += plugin_kvm.o
 PLUGIN_OBJS += plugin_mac80211.o
+PLUGIN_OBJS += plugin_sched_switch.o
 
 PLUGINS := $(PLUGIN_OBJS:.o=.so)
 
diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c
new file mode 100644
index 0000000..fea3724
--- /dev/null
+++ b/tools/lib/traceevent/plugin_sched_switch.c
@@ -0,0 +1,148 @@
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "event-parse.h"
+
+static void write_state(struct trace_seq *s, int val)
+{
+	const char states[] = "SDTtZXxW";
+	int found = 0;
+	int i;
+
+	for (i = 0; i < (sizeof(states) - 1); i++) {
+		if (!(val & (1 << i)))
+			continue;
+
+		if (found)
+			trace_seq_putc(s, '|');
+
+		found = 1;
+		trace_seq_putc(s, states[i]);
+	}
+
+	if (!found)
+		trace_seq_putc(s, 'R');
+}
+
+static void write_and_save_comm(struct format_field *field,
+				struct pevent_record *record,
+				struct trace_seq *s, int pid)
+{
+	const char *comm;
+	int len;
+
+	comm = (char *)(record->data + field->offset);
+	len = s->len;
+	trace_seq_printf(s, "%.*s",
+			 field->size, comm);
+
+	/* make sure the comm has a \0 at the end. */
+	trace_seq_terminate(s);
+	comm = &s->buffer[len];
+
+	/* Help out the comm to ids. This will handle dups */
+	pevent_register_comm(field->event->pevent, comm, pid);
+}
+
+static int sched_wakeup_handler(struct trace_seq *s,
+				struct pevent_record *record,
+				struct event_format *event, void *context)
+{
+	struct format_field *field;
+	unsigned long long val;
+
+	if (pevent_get_field_val(s, event, "pid", record, &val, 1))
+		return trace_seq_putc(s, '!');
+
+	field = pevent_find_any_field(event, "comm");
+	if (field) {
+		write_and_save_comm(field, record, s, val);
+		trace_seq_putc(s, ':');
+	}
+	trace_seq_printf(s, "%lld", val);
+
+	if (pevent_get_field_val(s, event, "prio", record, &val, 0) == 0)
+		trace_seq_printf(s, " [%lld]", val);
+
+	if (pevent_get_field_val(s, event, "success", record, &val, 1) == 0)
+		trace_seq_printf(s, " success=%lld", val);
+
+	if (pevent_get_field_val(s, event, "target_cpu", record, &val, 0) == 0)
+		trace_seq_printf(s, " CPU:%03llu", val);
+
+	return 0;
+}
+
+static int sched_switch_handler(struct trace_seq *s,
+				struct pevent_record *record,
+				struct event_format *event, void *context)
+{
+	struct format_field *field;
+	unsigned long long val;
+
+	if (pevent_get_field_val(s, event, "prev_pid", record, &val, 1))
+		return trace_seq_putc(s, '!');
+
+	field = pevent_find_any_field(event, "prev_comm");
+	if (field) {
+		write_and_save_comm(field, record, s, val);
+		trace_seq_putc(s, ':');
+	}
+	trace_seq_printf(s, "%lld ", val);
+
+	if (pevent_get_field_val(s, event, "prev_prio", record, &val, 0) == 0)
+		trace_seq_printf(s, "[%lld] ", val);
+
+	if (pevent_get_field_val(s,  event, "prev_state", record, &val, 0) == 0)
+		write_state(s, val);
+
+	trace_seq_puts(s, " ==> ");
+
+	if (pevent_get_field_val(s, event, "next_pid", record, &val, 1))
+		return trace_seq_putc(s, '!');
+
+	field = pevent_find_any_field(event, "next_comm");
+	if (field) {
+		write_and_save_comm(field, record, s, val);
+		trace_seq_putc(s, ':');
+	}
+	trace_seq_printf(s, "%lld", val);
+
+	if (pevent_get_field_val(s, event, "next_prio", record, &val, 0) == 0)
+		trace_seq_printf(s, " [%lld]", val);
+
+	return 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_event_handler(pevent, -1, "sched", "sched_switch",
+				      sched_switch_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "sched", "sched_wakeup",
+				      sched_wakeup_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "sched", "sched_wakeup_new",
+				      sched_wakeup_handler, NULL);
+	return 0;
+}
-- 
cgit v0.10.2


From 07a180a0bfea7029b8cf84a7d8e856539e5c69f5 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:32 +0100
Subject: tools lib traceevent: Add function plugin

Backporting function plugin.

Backported from Steven Rostedt's trace-cmd repo (HEAD 0f2c2fb):
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/trace-cmd.git

This plugin adds function and parent function fields resolving for
ftrace:function tracepoint event.

The diff of 'perf script' output generated by old and new code:
(data was generated by 'perf record -e ftrace:function ls')

  --- script.function.old
  +++ script.function.new
  -              ls 10781 [001] 32667.291379: ftrace:function:  ffffffff811adb80 <-- ffffffff811afc48
  -              ls 10781 [001] 32667.291379: ftrace:function:  ffffffff811b35d0 <-- ffffffff811adb9b
  -              ls 10781 [001] 32667.291380: ftrace:function:  ffffffff811b3520 <-- ffffffff811b35e8
  -              ls 10781 [001] 32667.291380: ftrace:function:  ffffffff811b2720 <-- ffffffff811b3549
  -              ls 10781 [001] 32667.291381: ftrace:function:  ffffffff81297e10 <-- ffffffff811b356c
  -              ls 10781 [001] 32667.291381: ftrace:function:  ffffffff81298f40 <-- ffffffff81297e2c
  -              ls 10781 [001] 32667.291382: ftrace:function:  ffffffff81076160 <-- ffffffff811afbf0
  -              ls 10781 [001] 32667.291383: ftrace:function:  ffffffff811c3eb0 <-- ffffffff811afbfc
  -              ls 10781 [001] 32667.291383: ftrace:function:  ffffffff8164e100 <-- ffffffff811c3ed8
  -              ls 10781 [001] 32667.291384: ftrace:function:  ffffffff811a5d10 <-- ffffffff811c3f53
  -              ls 10781 [001] 32667.291384: ftrace:function:  ffffffff811e8e70 <-- ffffffff811a5d58
  -              ls 10781 [001] 32667.291385: ftrace:function:  ffffffff811f38e0 <-- ffffffff811a5d63
  -              ls 10781 [001] 32667.291385: ftrace:function:  ffffffff811a9ff0 <-- ffffffff811a5d6b
  -              ls 10781 [001] 32667.291386: ftrace:function:  ffffffff811a9fa0 <-- ffffffff811aa015
  -              ls 10781 [001] 32667.291387: ftrace:function:  ffffffff810851c0 <-- ffffffff811aa053
  -              ls 10781 [001] 32667.291387: ftrace:function:  ffffffff81090e00 <-- ffffffff81085211
  +              ls 10781 [001] 32667.291379: ftrace:function: would_dump <-- setup_new_exec
  +              ls 10781 [001] 32667.291379: ftrace:function:    inode_permission <-- would_dump
  +              ls 10781 [001] 32667.291380: ftrace:function:       __inode_permission <-- inode_permission
  +              ls 10781 [001] 32667.291380: ftrace:function:          generic_permission <-- __inode_permission
  +              ls 10781 [001] 32667.291381: ftrace:function:          security_inode_permission <-- __inode_permission
  +              ls 10781 [001] 32667.291381: ftrace:function:             cap_inode_permission <-- security_inode_permission
  +              ls 10781 [001] 32667.291382: ftrace:function: flush_signal_handlers <-- setup_new_exec
  +              ls 10781 [001] 32667.291383: ftrace:function: do_close_on_exec <-- setup_new_exec
  +              ls 10781 [001] 32667.291383: ftrace:function:    _raw_spin_lock <-- do_close_on_exec
  +              ls 10781 [001] 32667.291384: ftrace:function:    filp_close <-- do_close_on_exec
  +              ls 10781 [001] 32667.291384: ftrace:function:       dnotify_flush <-- filp_close
  +              ls 10781 [001] 32667.291385: ftrace:function:       locks_remove_posix <-- filp_close
  +              ls 10781 [001] 32667.291385: ftrace:function:       fput <-- filp_close
  +              ls 10781 [001] 32667.291386: ftrace:function:          file_sb_list_del <-- fput
  +              ls 10781 [001] 32667.291387: ftrace:function:          task_work_add <-- fput
  +              ls 10781 [001] 32667.291387: ftrace:function:             kick_process <-- task_work_add

Removing options support as it's not backported yet.
Currently this plugin supports 2 options:
 'parent' to display parent function
 'indent' to show function call indents

Enabling both of them by default.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-19-git-send-email-jolsa@redhat.com
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 1c319a8..21f9b8f 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -218,6 +218,7 @@ PLUGIN_OBJS += plugin_kmem.o
 PLUGIN_OBJS += plugin_kvm.o
 PLUGIN_OBJS += plugin_mac80211.o
 PLUGIN_OBJS += plugin_sched_switch.o
+PLUGIN_OBJS += plugin_function.o
 
 PLUGINS := $(PLUGIN_OBJS:.o=.so)
 
diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c
new file mode 100644
index 0000000..8deb22e
--- /dev/null
+++ b/tools/lib/traceevent/plugin_function.c
@@ -0,0 +1,151 @@
+/*
+ * Copyright (C) 2009, 2010 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "event-parse.h"
+#include "event-utils.h"
+
+static struct func_stack {
+	int index;
+	int size;
+	char **stack;
+} *fstack;
+
+static int cpus = -1;
+
+#define STK_BLK 10
+
+static void add_child(struct func_stack *stack, const char *child, int pos)
+{
+	int i;
+
+	if (!child)
+		return;
+
+	if (pos < stack->size)
+		free(stack->stack[pos]);
+	else {
+		if (!stack->stack)
+			stack->stack = malloc_or_die(sizeof(char *) * STK_BLK);
+		else
+			stack->stack = realloc(stack->stack, sizeof(char *) *
+					       (stack->size + STK_BLK));
+		for (i = stack->size; i < stack->size + STK_BLK; i++)
+			stack->stack[i] = NULL;
+		stack->size += STK_BLK;
+	}
+
+	stack->stack[pos] = strdup(child);
+}
+
+static int get_index(const char *parent, const char *child, int cpu)
+{
+	int i;
+
+	if (cpu < 0)
+		return 0;
+
+	if (cpu > cpus) {
+		if (fstack)
+			fstack = realloc(fstack, sizeof(*fstack) * (cpu + 1));
+		else
+			fstack = malloc_or_die(sizeof(*fstack) * (cpu + 1));
+
+		/* Account for holes in the cpu count */
+		for (i = cpus + 1; i <= cpu; i++)
+			memset(&fstack[i], 0, sizeof(fstack[i]));
+		cpus = cpu;
+	}
+
+	for (i = 0; i < fstack[cpu].size && fstack[cpu].stack[i]; i++) {
+		if (strcmp(parent, fstack[cpu].stack[i]) == 0) {
+			add_child(&fstack[cpu], child, i+1);
+			return i;
+		}
+	}
+
+	/* Not found */
+	add_child(&fstack[cpu], parent, 0);
+	add_child(&fstack[cpu], child, 1);
+	return 0;
+}
+
+static int function_handler(struct trace_seq *s, struct pevent_record *record,
+			    struct event_format *event, void *context)
+{
+	struct pevent *pevent = event->pevent;
+	unsigned long long function;
+	unsigned long long pfunction;
+	const char *func;
+	const char *parent;
+	int i, index;
+
+	if (pevent_get_field_val(s, event, "ip", record, &function, 1))
+		return trace_seq_putc(s, '!');
+
+	func = pevent_find_function(pevent, function);
+
+	if (pevent_get_field_val(s, event, "parent_ip", record, &pfunction, 1))
+		return trace_seq_putc(s, '!');
+
+	parent = pevent_find_function(pevent, pfunction);
+
+	index = get_index(parent, func, record->cpu);
+
+	for (i = 0; i < index; i++)
+		trace_seq_printf(s, "   ");
+
+	if (func)
+		trace_seq_printf(s, "%s", func);
+	else
+		trace_seq_printf(s, "0x%llx", function);
+
+	trace_seq_printf(s, " <-- ");
+	if (parent)
+		trace_seq_printf(s, "%s", parent);
+	else
+		trace_seq_printf(s, "0x%llx", pfunction);
+
+	return 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_event_handler(pevent, -1, "ftrace", "function",
+				      function_handler, NULL);
+	return 0;
+}
+
+void PEVENT_PLUGIN_UNLOADER(void)
+{
+	int i, x;
+
+	for (i = 0; i <= cpus; i++) {
+		for (x = 0; x < fstack[i].size && fstack[i].stack[x]; x++)
+			free(fstack[i].stack[x]);
+		free(fstack[i].stack);
+	}
+
+	free(fstack);
+	fstack = NULL;
+	cpus = -1;
+}
-- 
cgit v0.10.2


From 40c03ad5925855e47e4b6294323107b2b180ae3d Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:33 +0100
Subject: tools lib traceevent: Add xen plugin

Adding xen plugin.

This plugin adds fields resolving for following tracepoint events:

  xen:xen_mc_entry
  xen:xen_mc_extend_args

The diff of 'perf script' output generated by old and new code: (data
was generated by 'perf record -e 'xen:*' ls')

  --- script.xen.old
  +++ script.xen.new
  -         swapper     0 [002]   136.267492: xen:xen_mc_entry: [FAILED TO PARSE] op=3 nargs=2 args=ARRAY[18, 00, 00, 00, 00, 00, 00, 00, 00, e0, d4, 4b, 04, 88, ff, ff, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00, 00]
  +         swapper     0 [002]   136.267492: xen:xen_mc_entry: op 3(stack_switch) args [18, 0, 0, 0, 0, 0]
  -            perf  1970 [008]   136.273319: xen:xen_mc_extend_args: [FAILED TO PARSE] op=1 args=16 res=1
  +            perf  1970 [008]   136.273319: xen:xen_mc_extend_args: extending op 1(mmu_update) by 16 bytes res ???

NOTE We still do not handle the 'sizeof' and fail to parse following xen
tracepoints:

  xen:xen_mmu_set_pte
  xen:xen_mmu_set_pte_atomic
  xen:xen_mmu_set_domain_pte
  xen:xen_mmu_set_pte_at
  xen:xen_mmu_set_pmd
  xen:xen_mmu_set_pud
  xen:xen_mmu_set_pgd
  xen:xen_mmu_ptep_modify_prot_start
  xen:xen_mmu_ptep_modify_prot_commit

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-20-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 21f9b8f..54af60a 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -219,6 +219,7 @@ PLUGIN_OBJS += plugin_kvm.o
 PLUGIN_OBJS += plugin_mac80211.o
 PLUGIN_OBJS += plugin_sched_switch.o
 PLUGIN_OBJS += plugin_function.o
+PLUGIN_OBJS += plugin_xen.o
 
 PLUGINS := $(PLUGIN_OBJS:.o=.so)
 
diff --git a/tools/lib/traceevent/plugin_xen.c b/tools/lib/traceevent/plugin_xen.c
new file mode 100644
index 0000000..e779429
--- /dev/null
+++ b/tools/lib/traceevent/plugin_xen.c
@@ -0,0 +1,130 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include "event-parse.h"
+
+#define __HYPERVISOR_set_trap_table			0
+#define __HYPERVISOR_mmu_update				1
+#define __HYPERVISOR_set_gdt				2
+#define __HYPERVISOR_stack_switch			3
+#define __HYPERVISOR_set_callbacks			4
+#define __HYPERVISOR_fpu_taskswitch			5
+#define __HYPERVISOR_sched_op_compat			6
+#define __HYPERVISOR_dom0_op				7
+#define __HYPERVISOR_set_debugreg			8
+#define __HYPERVISOR_get_debugreg			9
+#define __HYPERVISOR_update_descriptor			10
+#define __HYPERVISOR_memory_op				12
+#define __HYPERVISOR_multicall				13
+#define __HYPERVISOR_update_va_mapping			14
+#define __HYPERVISOR_set_timer_op			15
+#define __HYPERVISOR_event_channel_op_compat		16
+#define __HYPERVISOR_xen_version			17
+#define __HYPERVISOR_console_io				18
+#define __HYPERVISOR_physdev_op_compat			19
+#define __HYPERVISOR_grant_table_op			20
+#define __HYPERVISOR_vm_assist				21
+#define __HYPERVISOR_update_va_mapping_otherdomain	22
+#define __HYPERVISOR_iret				23 /* x86 only */
+#define __HYPERVISOR_vcpu_op				24
+#define __HYPERVISOR_set_segment_base			25 /* x86/64 only */
+#define __HYPERVISOR_mmuext_op				26
+#define __HYPERVISOR_acm_op				27
+#define __HYPERVISOR_nmi_op				28
+#define __HYPERVISOR_sched_op				29
+#define __HYPERVISOR_callback_op			30
+#define __HYPERVISOR_xenoprof_op			31
+#define __HYPERVISOR_event_channel_op			32
+#define __HYPERVISOR_physdev_op				33
+#define __HYPERVISOR_hvm_op				34
+#define __HYPERVISOR_tmem_op				38
+
+/* Architecture-specific hypercall definitions. */
+#define __HYPERVISOR_arch_0				48
+#define __HYPERVISOR_arch_1				49
+#define __HYPERVISOR_arch_2				50
+#define __HYPERVISOR_arch_3				51
+#define __HYPERVISOR_arch_4				52
+#define __HYPERVISOR_arch_5				53
+#define __HYPERVISOR_arch_6				54
+#define __HYPERVISOR_arch_7				55
+
+#define N(x)	[__HYPERVISOR_##x] = "("#x")"
+static const char *xen_hypercall_names[] = {
+	N(set_trap_table),
+	N(mmu_update),
+	N(set_gdt),
+	N(stack_switch),
+	N(set_callbacks),
+	N(fpu_taskswitch),
+	N(sched_op_compat),
+	N(dom0_op),
+	N(set_debugreg),
+	N(get_debugreg),
+	N(update_descriptor),
+	N(memory_op),
+	N(multicall),
+	N(update_va_mapping),
+	N(set_timer_op),
+	N(event_channel_op_compat),
+	N(xen_version),
+	N(console_io),
+	N(physdev_op_compat),
+	N(grant_table_op),
+	N(vm_assist),
+	N(update_va_mapping_otherdomain),
+	N(iret),
+	N(vcpu_op),
+	N(set_segment_base),
+	N(mmuext_op),
+	N(acm_op),
+	N(nmi_op),
+	N(sched_op),
+	N(callback_op),
+	N(xenoprof_op),
+	N(event_channel_op),
+	N(physdev_op),
+	N(hvm_op),
+
+/* Architecture-specific hypercall definitions. */
+	N(arch_0),
+	N(arch_1),
+	N(arch_2),
+	N(arch_3),
+	N(arch_4),
+	N(arch_5),
+	N(arch_6),
+	N(arch_7),
+};
+#undef N
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+static const char *xen_hypercall_name(unsigned op)
+{
+	if (op < ARRAY_SIZE(xen_hypercall_names) &&
+	    xen_hypercall_names[op] != NULL)
+		return xen_hypercall_names[op];
+
+	return "";
+}
+
+unsigned long long process_xen_hypercall_name(struct trace_seq *s,
+					      unsigned long long *args)
+{
+	unsigned int op = args[0];
+
+	trace_seq_printf(s, "%s", xen_hypercall_name(op));
+	return 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_print_function(pevent,
+				       process_xen_hypercall_name,
+				       PEVENT_FUNC_ARG_STRING,
+				       "xen_hypercall_name",
+				       PEVENT_FUNC_ARG_INT,
+				       PEVENT_FUNC_ARG_VOID);
+	return 0;
+}
-- 
cgit v0.10.2


From 04010929fa33ad3a446b9fd50b82321c1c3cf239 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:34 +0100
Subject: tools lib traceevent: Add scsi plugin

Adding scsi plugin.

This plugin adds fields resolving functions for following tracepoint
events:

  scsi:scsi_dispatch_cmd_start
  scsi:scsi_dispatch_cmd_error
  scsi:scsi_dispatch_cmd_done
  scsi:scsi_dispatch_cmd_timeout

The diff of 'perf script' output generated by old and new code:
(data was generated by 'perf record -e 'scsi:scsi_dispatch_cmd*' -a)

  -         swapper     0 [000]  6620.491019: scsi:scsi_dispatch_cmd_done: [FAILED TO PARSE] host_no=0 channel=0 id=0 lun=0 result=0 opcode=53 cmd_len=10 data_sglen=0 prot_sglen=0 prot_op=0 cmnd=5
  +         swapper     0 [000]  6620.491019: scsi:scsi_dispatch_cmd_done: host_no=0 channel=0 id=0 lun=0 data_sgl=0 prot_sgl=0 prot_op=SCSI_PROT_NORMAL cmnd=(SYNCHRONIZE_CACHE - raw=35 00 00 00 00 00 00 00 00 00) result=(driver=DRIVER_OK host=DID_OK message=COMMAND_COMPLETE status=SAM_STAT_GOOD)
  -     kworker/0:0 21554 [000]  6620.491126: scsi:scsi_dispatch_cmd_start: [FAILED TO PARSE] host_no=0 channel=0 id=0 lun=0 opcode=42 cmd_len=10 data_sglen=1 prot_sglen=0 prot_op=0 cmnd=*
  +     kworker/0:0 21554 [000]  6620.491126: scsi:scsi_dispatch_cmd_start: host_no=0 channel=0 id=0 lun=0 data_sgl=1 prot_sgl=0 prot_op=SCSI_PROT_NORMAL cmnd=(WRITE_10 lba=570899168 txlen=8 protect=0 raw=2a 00 22 07 3a e0 00 00 08 00)
  -     jbd2/dm-3-8   593 [002]  6621.607992: scsi:scsi_dispatch_cmd_error: [FAILED TO PARSE] host_no=0 channel=0 id=0 lun=0 rtn=4182 opcode=53 cmd_len=10 data_sglen=0 prot_sglen=0 prot_op=0 cmnd=5
  +     jbd2/dm-3-8   593 [002]  6621.607992: scsi:scsi_dispatch_cmd_error: host_no=0 channel=0 id=0 lun=0 data_sgl=0 prot_sgl=0 prot_op=SCSI_PROT_NORMAL cmnd=(SYNCHRONIZE_CACHE - raw=35 00 00 00 00 00 00 00 00 00) rtn=4182

NOTE I couldn't generate scsi_dispatch_cmd_timeout tracepoint,
     but it's similar to the rest, so I believe it's ok.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-21-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 54af60a..671f969 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -220,6 +220,7 @@ PLUGIN_OBJS += plugin_mac80211.o
 PLUGIN_OBJS += plugin_sched_switch.o
 PLUGIN_OBJS += plugin_function.o
 PLUGIN_OBJS += plugin_xen.o
+PLUGIN_OBJS += plugin_scsi.o
 
 PLUGINS := $(PLUGIN_OBJS:.o=.so)
 
diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugin_scsi.c
new file mode 100644
index 0000000..6fb8e3e
--- /dev/null
+++ b/tools/lib/traceevent/plugin_scsi.c
@@ -0,0 +1,423 @@
+#include <stdio.h>
+#include <string.h>
+#include <inttypes.h>
+#include "event-parse.h"
+
+typedef unsigned long sector_t;
+typedef uint64_t u64;
+typedef unsigned int u32;
+
+/*
+ *      SCSI opcodes
+ */
+#define TEST_UNIT_READY			0x00
+#define REZERO_UNIT			0x01
+#define REQUEST_SENSE			0x03
+#define FORMAT_UNIT			0x04
+#define READ_BLOCK_LIMITS		0x05
+#define REASSIGN_BLOCKS			0x07
+#define INITIALIZE_ELEMENT_STATUS	0x07
+#define READ_6				0x08
+#define WRITE_6				0x0a
+#define SEEK_6				0x0b
+#define READ_REVERSE			0x0f
+#define WRITE_FILEMARKS			0x10
+#define SPACE				0x11
+#define INQUIRY				0x12
+#define RECOVER_BUFFERED_DATA		0x14
+#define MODE_SELECT			0x15
+#define RESERVE				0x16
+#define RELEASE				0x17
+#define COPY				0x18
+#define ERASE				0x19
+#define MODE_SENSE			0x1a
+#define START_STOP			0x1b
+#define RECEIVE_DIAGNOSTIC		0x1c
+#define SEND_DIAGNOSTIC			0x1d
+#define ALLOW_MEDIUM_REMOVAL		0x1e
+
+#define READ_FORMAT_CAPACITIES		0x23
+#define SET_WINDOW			0x24
+#define READ_CAPACITY			0x25
+#define READ_10				0x28
+#define WRITE_10			0x2a
+#define SEEK_10				0x2b
+#define POSITION_TO_ELEMENT		0x2b
+#define WRITE_VERIFY			0x2e
+#define VERIFY				0x2f
+#define SEARCH_HIGH			0x30
+#define SEARCH_EQUAL			0x31
+#define SEARCH_LOW			0x32
+#define SET_LIMITS			0x33
+#define PRE_FETCH			0x34
+#define READ_POSITION			0x34
+#define SYNCHRONIZE_CACHE		0x35
+#define LOCK_UNLOCK_CACHE		0x36
+#define READ_DEFECT_DATA		0x37
+#define MEDIUM_SCAN			0x38
+#define COMPARE				0x39
+#define COPY_VERIFY			0x3a
+#define WRITE_BUFFER			0x3b
+#define READ_BUFFER			0x3c
+#define UPDATE_BLOCK			0x3d
+#define READ_LONG			0x3e
+#define WRITE_LONG			0x3f
+#define CHANGE_DEFINITION		0x40
+#define WRITE_SAME			0x41
+#define UNMAP				0x42
+#define READ_TOC			0x43
+#define READ_HEADER			0x44
+#define GET_EVENT_STATUS_NOTIFICATION	0x4a
+#define LOG_SELECT			0x4c
+#define LOG_SENSE			0x4d
+#define XDWRITEREAD_10			0x53
+#define MODE_SELECT_10			0x55
+#define RESERVE_10			0x56
+#define RELEASE_10			0x57
+#define MODE_SENSE_10			0x5a
+#define PERSISTENT_RESERVE_IN		0x5e
+#define PERSISTENT_RESERVE_OUT		0x5f
+#define VARIABLE_LENGTH_CMD		0x7f
+#define REPORT_LUNS			0xa0
+#define SECURITY_PROTOCOL_IN		0xa2
+#define MAINTENANCE_IN			0xa3
+#define MAINTENANCE_OUT			0xa4
+#define MOVE_MEDIUM			0xa5
+#define EXCHANGE_MEDIUM			0xa6
+#define READ_12				0xa8
+#define WRITE_12			0xaa
+#define READ_MEDIA_SERIAL_NUMBER	0xab
+#define WRITE_VERIFY_12			0xae
+#define VERIFY_12			0xaf
+#define SEARCH_HIGH_12			0xb0
+#define SEARCH_EQUAL_12			0xb1
+#define SEARCH_LOW_12			0xb2
+#define SECURITY_PROTOCOL_OUT		0xb5
+#define READ_ELEMENT_STATUS		0xb8
+#define SEND_VOLUME_TAG			0xb6
+#define WRITE_LONG_2			0xea
+#define EXTENDED_COPY			0x83
+#define RECEIVE_COPY_RESULTS		0x84
+#define ACCESS_CONTROL_IN		0x86
+#define ACCESS_CONTROL_OUT		0x87
+#define READ_16				0x88
+#define WRITE_16			0x8a
+#define READ_ATTRIBUTE			0x8c
+#define WRITE_ATTRIBUTE			0x8d
+#define VERIFY_16			0x8f
+#define SYNCHRONIZE_CACHE_16		0x91
+#define WRITE_SAME_16			0x93
+#define SERVICE_ACTION_IN		0x9e
+/* values for service action in */
+#define	SAI_READ_CAPACITY_16		0x10
+#define SAI_GET_LBA_STATUS		0x12
+/* values for VARIABLE_LENGTH_CMD service action codes
+ * see spc4r17 Section D.3.5, table D.7 and D.8 */
+#define VLC_SA_RECEIVE_CREDENTIAL	0x1800
+/* values for maintenance in */
+#define MI_REPORT_IDENTIFYING_INFORMATION		0x05
+#define MI_REPORT_TARGET_PGS				0x0a
+#define MI_REPORT_ALIASES				0x0b
+#define MI_REPORT_SUPPORTED_OPERATION_CODES		0x0c
+#define MI_REPORT_SUPPORTED_TASK_MANAGEMENT_FUNCTIONS	0x0d
+#define MI_REPORT_PRIORITY				0x0e
+#define MI_REPORT_TIMESTAMP				0x0f
+#define MI_MANAGEMENT_PROTOCOL_IN			0x10
+/* value for MI_REPORT_TARGET_PGS ext header */
+#define MI_EXT_HDR_PARAM_FMT		0x20
+/* values for maintenance out */
+#define MO_SET_IDENTIFYING_INFORMATION	0x06
+#define MO_SET_TARGET_PGS		0x0a
+#define MO_CHANGE_ALIASES		0x0b
+#define MO_SET_PRIORITY			0x0e
+#define MO_SET_TIMESTAMP		0x0f
+#define MO_MANAGEMENT_PROTOCOL_OUT	0x10
+/* values for variable length command */
+#define XDREAD_32			0x03
+#define XDWRITE_32			0x04
+#define XPWRITE_32			0x06
+#define XDWRITEREAD_32			0x07
+#define READ_32				0x09
+#define VERIFY_32			0x0a
+#define WRITE_32			0x0b
+#define WRITE_SAME_32			0x0d
+
+#define SERVICE_ACTION16(cdb) (cdb[1] & 0x1f)
+#define SERVICE_ACTION32(cdb) ((cdb[8] << 8) | cdb[9])
+
+static const char *
+scsi_trace_misc(struct trace_seq *, unsigned char *, int);
+
+static const char *
+scsi_trace_rw6(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len;
+	sector_t lba = 0, txlen = 0;
+
+	lba |= ((cdb[1] & 0x1F) << 16);
+	lba |=  (cdb[2] << 8);
+	lba |=   cdb[3];
+	txlen = cdb[4];
+
+	trace_seq_printf(p, "lba=%llu txlen=%llu",
+			 (unsigned long long)lba, (unsigned long long)txlen);
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_rw10(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len;
+	sector_t lba = 0, txlen = 0;
+
+	lba |= (cdb[2] << 24);
+	lba |= (cdb[3] << 16);
+	lba |= (cdb[4] << 8);
+	lba |=  cdb[5];
+	txlen |= (cdb[7] << 8);
+	txlen |=  cdb[8];
+
+	trace_seq_printf(p, "lba=%llu txlen=%llu protect=%u",
+			 (unsigned long long)lba, (unsigned long long)txlen,
+			 cdb[1] >> 5);
+
+	if (cdb[0] == WRITE_SAME)
+		trace_seq_printf(p, " unmap=%u", cdb[1] >> 3 & 1);
+
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_rw12(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len;
+	sector_t lba = 0, txlen = 0;
+
+	lba |= (cdb[2] << 24);
+	lba |= (cdb[3] << 16);
+	lba |= (cdb[4] << 8);
+	lba |=  cdb[5];
+	txlen |= (cdb[6] << 24);
+	txlen |= (cdb[7] << 16);
+	txlen |= (cdb[8] << 8);
+	txlen |=  cdb[9];
+
+	trace_seq_printf(p, "lba=%llu txlen=%llu protect=%u",
+			 (unsigned long long)lba, (unsigned long long)txlen,
+			 cdb[1] >> 5);
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_rw16(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len;
+	sector_t lba = 0, txlen = 0;
+
+	lba |= ((u64)cdb[2] << 56);
+	lba |= ((u64)cdb[3] << 48);
+	lba |= ((u64)cdb[4] << 40);
+	lba |= ((u64)cdb[5] << 32);
+	lba |= (cdb[6] << 24);
+	lba |= (cdb[7] << 16);
+	lba |= (cdb[8] << 8);
+	lba |=  cdb[9];
+	txlen |= (cdb[10] << 24);
+	txlen |= (cdb[11] << 16);
+	txlen |= (cdb[12] << 8);
+	txlen |=  cdb[13];
+
+	trace_seq_printf(p, "lba=%llu txlen=%llu protect=%u",
+			 (unsigned long long)lba, (unsigned long long)txlen,
+			 cdb[1] >> 5);
+
+	if (cdb[0] == WRITE_SAME_16)
+		trace_seq_printf(p, " unmap=%u", cdb[1] >> 3 & 1);
+
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_rw32(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len, *cmd;
+	sector_t lba = 0, txlen = 0;
+	u32 ei_lbrt = 0;
+
+	switch (SERVICE_ACTION32(cdb)) {
+	case READ_32:
+		cmd = "READ";
+		break;
+	case VERIFY_32:
+		cmd = "VERIFY";
+		break;
+	case WRITE_32:
+		cmd = "WRITE";
+		break;
+	case WRITE_SAME_32:
+		cmd = "WRITE_SAME";
+		break;
+	default:
+		trace_seq_printf(p, "UNKNOWN");
+		goto out;
+	}
+
+	lba |= ((u64)cdb[12] << 56);
+	lba |= ((u64)cdb[13] << 48);
+	lba |= ((u64)cdb[14] << 40);
+	lba |= ((u64)cdb[15] << 32);
+	lba |= (cdb[16] << 24);
+	lba |= (cdb[17] << 16);
+	lba |= (cdb[18] << 8);
+	lba |=  cdb[19];
+	ei_lbrt |= (cdb[20] << 24);
+	ei_lbrt |= (cdb[21] << 16);
+	ei_lbrt |= (cdb[22] << 8);
+	ei_lbrt |=  cdb[23];
+	txlen |= (cdb[28] << 24);
+	txlen |= (cdb[29] << 16);
+	txlen |= (cdb[30] << 8);
+	txlen |=  cdb[31];
+
+	trace_seq_printf(p, "%s_32 lba=%llu txlen=%llu protect=%u ei_lbrt=%u",
+			 cmd, (unsigned long long)lba,
+			 (unsigned long long)txlen, cdb[10] >> 5, ei_lbrt);
+
+	if (SERVICE_ACTION32(cdb) == WRITE_SAME_32)
+		trace_seq_printf(p, " unmap=%u", cdb[10] >> 3 & 1);
+
+out:
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_unmap(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len;
+	unsigned int regions = cdb[7] << 8 | cdb[8];
+
+	trace_seq_printf(p, "regions=%u", (regions - 8) / 16);
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_service_action_in(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len, *cmd;
+	sector_t lba = 0;
+	u32 alloc_len = 0;
+
+	switch (SERVICE_ACTION16(cdb)) {
+	case SAI_READ_CAPACITY_16:
+		cmd = "READ_CAPACITY_16";
+		break;
+	case SAI_GET_LBA_STATUS:
+		cmd = "GET_LBA_STATUS";
+		break;
+	default:
+		trace_seq_printf(p, "UNKNOWN");
+		goto out;
+	}
+
+	lba |= ((u64)cdb[2] << 56);
+	lba |= ((u64)cdb[3] << 48);
+	lba |= ((u64)cdb[4] << 40);
+	lba |= ((u64)cdb[5] << 32);
+	lba |= (cdb[6] << 24);
+	lba |= (cdb[7] << 16);
+	lba |= (cdb[8] << 8);
+	lba |=  cdb[9];
+	alloc_len |= (cdb[10] << 24);
+	alloc_len |= (cdb[11] << 16);
+	alloc_len |= (cdb[12] << 8);
+	alloc_len |=  cdb[13];
+
+	trace_seq_printf(p, "%s lba=%llu alloc_len=%u", cmd,
+			 (unsigned long long)lba, alloc_len);
+
+out:
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+static const char *
+scsi_trace_varlen(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	switch (SERVICE_ACTION32(cdb)) {
+	case READ_32:
+	case VERIFY_32:
+	case WRITE_32:
+	case WRITE_SAME_32:
+		return scsi_trace_rw32(p, cdb, len);
+	default:
+		return scsi_trace_misc(p, cdb, len);
+	}
+}
+
+static const char *
+scsi_trace_misc(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	const char *ret = p->buffer + p->len;
+
+	trace_seq_printf(p, "-");
+	trace_seq_putc(p, 0);
+	return ret;
+}
+
+const char *
+scsi_trace_parse_cdb(struct trace_seq *p, unsigned char *cdb, int len)
+{
+	switch (cdb[0]) {
+	case READ_6:
+	case WRITE_6:
+		return scsi_trace_rw6(p, cdb, len);
+	case READ_10:
+	case VERIFY:
+	case WRITE_10:
+	case WRITE_SAME:
+		return scsi_trace_rw10(p, cdb, len);
+	case READ_12:
+	case VERIFY_12:
+	case WRITE_12:
+		return scsi_trace_rw12(p, cdb, len);
+	case READ_16:
+	case VERIFY_16:
+	case WRITE_16:
+	case WRITE_SAME_16:
+		return scsi_trace_rw16(p, cdb, len);
+	case UNMAP:
+		return scsi_trace_unmap(p, cdb, len);
+	case SERVICE_ACTION_IN:
+		return scsi_trace_service_action_in(p, cdb, len);
+	case VARIABLE_LENGTH_CMD:
+		return scsi_trace_varlen(p, cdb, len);
+	default:
+		return scsi_trace_misc(p, cdb, len);
+	}
+}
+
+unsigned long long process_scsi_trace_parse_cdb(struct trace_seq *s,
+						unsigned long long *args)
+{
+	scsi_trace_parse_cdb(s, (unsigned char *) args[1], args[2]);
+	return 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_print_function(pevent,
+				       process_scsi_trace_parse_cdb,
+				       PEVENT_FUNC_ARG_STRING,
+				       "scsi_trace_parse_cdb",
+				       PEVENT_FUNC_ARG_PTR,
+				       PEVENT_FUNC_ARG_PTR,
+				       PEVENT_FUNC_ARG_INT,
+				       PEVENT_FUNC_ARG_VOID);
+	return 0;
+}
-- 
cgit v0.10.2


From 943714737374635a134dc3de59a7f062cea53fb3 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:35 +0100
Subject: tools lib traceevent: Add cfg80211 plugin

Adding cfg80211 plugin.

This plugin adds handler for __le16_to_cpup function
t properly parse following tracepoint events:
  cfg80211:cfg80211_tx_mlme_mgmt
  cfg80211:cfg80211_rx_mlme_mgmt
  cfg80211:cfg80211_rx_unprot_mlme_mgmt

The diff of 'perf script' output generated by old and new code:
(data was generated by 'perf record -e 'cfg80211:*' -a')

  --- script.cfg80211.old
  +++ script.cfg80211.new
  -        ifconfig  2705 [003]   662.896560: cfg80211:cfg80211_tx_mlme_mgmt: [FAILED TO PARSE] name=wlan0 ifindex=3 frame=ARRAY[c0, 00, 00, 00, 00, 3a, 98, a0, 30, 51, 10, 0b, a9, c6, f4, 74, 00, 3a, 98, a0, 30, 51, 00, 00, 03, 00]
  +        ifconfig  2705 [003]   662.896560: cfg80211:cfg80211_tx_mlme_mgmt: netdev:wlan0(3), ftype:0xc0
  -   kworker/u16:0  1697 [002]   664.808210: cfg80211:cfg80211_rx_mlme_mgmt: [FAILED TO PARSE] name=wlan0 ifindex=3 frame=ARRAY[b0, 00, da, 00, 10, 0b, a9, c6, f4, 74, d8, 24, bd, a1, 26, 31, d8, 24, bd, a1, 26, 31, 10, b7, 00, 00, 02, 00, 00, 00]
  +   kworker/u16:0  1697 [002]   664.808210: cfg80211:cfg80211_rx_mlme_mgmt: netdev:wlan0(3), ftype:0xb0

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-22-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 671f969..0d9cbb4 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -221,6 +221,7 @@ PLUGIN_OBJS += plugin_sched_switch.o
 PLUGIN_OBJS += plugin_function.o
 PLUGIN_OBJS += plugin_xen.o
 PLUGIN_OBJS += plugin_scsi.o
+PLUGIN_OBJS += plugin_cfg80211.o
 
 PLUGINS := $(PLUGIN_OBJS:.o=.so)
 
diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugin_cfg80211.c
new file mode 100644
index 0000000..dcab8e8
--- /dev/null
+++ b/tools/lib/traceevent/plugin_cfg80211.c
@@ -0,0 +1,24 @@
+#include <stdio.h>
+#include <string.h>
+#include <inttypes.h>
+#include <endian.h>
+#include "event-parse.h"
+
+static unsigned long long
+process___le16_to_cpup(struct trace_seq *s,
+		       unsigned long long *args)
+{
+	uint16_t *val = (uint16_t *) args[0];
+	return val ? (long long) le16toh(*val) : 0;
+}
+
+int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
+{
+	pevent_register_print_function(pevent,
+				       process___le16_to_cpup,
+				       PEVENT_FUNC_ARG_INT,
+				       "__le16_to_cpup",
+				       PEVENT_FUNC_ARG_PTR,
+				       PEVENT_FUNC_ARG_VOID);
+	return 0;
+}
-- 
cgit v0.10.2


From f9bb36afb25d3bfda1c9276a55985b710c8a91ae Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:36 +0100
Subject: tools lib traceevent: Remove malloc_or_die from event-plugin.c

Removing malloc_or_die calls from event-plugin.c,
replacing them with standard malloc and error path.

Suggested-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-23-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c
index d272d87..125f567 100644
--- a/tools/lib/traceevent/event-plugin.c
+++ b/tools/lib/traceevent/event-plugin.c
@@ -47,7 +47,11 @@ load_plugin(struct pevent *pevent, const char *path,
 	char *plugin;
 	void *handle;
 
-	plugin = malloc_or_die(strlen(path) + strlen(file) + 2);
+	plugin = malloc(strlen(path) + strlen(file) + 2);
+	if (!plugin) {
+		warning("could not allocate plugin memory\n");
+		return;
+	}
 
 	strcpy(plugin, path);
 	strcat(plugin, "/");
@@ -71,7 +75,12 @@ load_plugin(struct pevent *pevent, const char *path,
 		goto out_free;
 	}
 
-	list = malloc_or_die(sizeof(*list));
+	list = malloc(sizeof(*list));
+	if (!list) {
+		warning("could not allocate plugin memory\n");
+		goto out_free;
+	}
+
 	list->next = *plugin_list;
 	list->handle = handle;
 	list->name = plugin;
@@ -163,7 +172,11 @@ load_plugins(struct pevent *pevent, const char *suffix,
 	if (!home)
 		return;
 
-	path = malloc_or_die(strlen(home) + strlen(LOCAL_PLUGIN_DIR) + 2);
+	path = malloc(strlen(home) + strlen(LOCAL_PLUGIN_DIR) + 2);
+	if (!path) {
+		warning("could not allocate plugin memory\n");
+		return;
+	}
 
 	strcpy(path, home);
 	strcat(path, "/");
-- 
cgit v0.10.2


From f04015ecb5eb0bf25260de585f0c5f60e84f073a Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:37 +0100
Subject: tools lib traceevent: Use static functions in jbd2 plugin

There's no need for following functions to be global:

  process_jbd2_dev_to_name
  process_jiffies_to_msecs

Make them static.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-24-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/plugin_jbd2.c b/tools/lib/traceevent/plugin_jbd2.c
index 5d85de7..2f93f81 100644
--- a/tools/lib/traceevent/plugin_jbd2.c
+++ b/tools/lib/traceevent/plugin_jbd2.c
@@ -29,8 +29,9 @@
 #define MAJOR(dev)	((unsigned int) ((dev) >> MINORBITS))
 #define MINOR(dev)	((unsigned int) ((dev) & MINORMASK))
 
-unsigned long long process_jbd2_dev_to_name(struct trace_seq *s,
-					    unsigned long long *args)
+static unsigned long long
+process_jbd2_dev_to_name(struct trace_seq *s,
+			 unsigned long long *args)
 {
 	unsigned int dev = args[0];
 
@@ -38,8 +39,9 @@ unsigned long long process_jbd2_dev_to_name(struct trace_seq *s,
 	return 0;
 }
 
-unsigned long long process_jiffies_to_msecs(struct trace_seq *s,
-					    unsigned long long *args)
+static unsigned long long
+process_jiffies_to_msecs(struct trace_seq *s,
+			 unsigned long long *args)
 {
 	unsigned long long jiffies = args[0];
 
-- 
cgit v0.10.2


From b32cea650a16092a654baa2095c78fa917bad4da Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:38 +0100
Subject: tools lib traceevent: Use pevent_print_func_field in hrtimer_start
 handler

The pevent_print_func_field function encompasses all the functionality
used in the hrtimer_start handler. Change the handler to use this
function.

This also unifies the function field output with the
hrtimer_expire_entry handler.

Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-25-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/plugin_hrtimer.c b/tools/lib/traceevent/plugin_hrtimer.c
index e41d4cf..0b0ebf3 100644
--- a/tools/lib/traceevent/plugin_hrtimer.c
+++ b/tools/lib/traceevent/plugin_hrtimer.c
@@ -48,10 +48,6 @@ static int timer_start_handler(struct trace_seq *s,
 			       struct pevent_record *record,
 			       struct event_format *event, void *context)
 {
-	struct pevent *pevent = event->pevent;
-	struct format_field *fn = pevent_find_field(event, "function");
-	void *data = record->data;
-
 	trace_seq_printf(s, "hrtimer=");
 
 	if (pevent_print_num_field(s, "0x%llx", event, "timer",
@@ -59,19 +55,8 @@ static int timer_start_handler(struct trace_seq *s,
 		pevent_print_num_field(s, "0x%llx", event, "hrtimer",
 				       record, 1);
 
-	if (!fn) {
-		trace_seq_printf(s, " function=MISSING");
-	} else {
-		unsigned long long function;
-		const char *func;
-
-		if (pevent_read_number_field(fn, data, &function))
-			trace_seq_printf(s, " function=INVALID");
-
-		func = pevent_find_function(pevent, function);
-
-		trace_seq_printf(s, " function=%s", func);
-	}
+	pevent_print_func_field(s, " function=%s", event, "function",
+				record, 0);
 
 	trace_seq_printf(s, " expires=");
 	pevent_print_num_field(s, "%llu", event, "expires", record, 1);
-- 
cgit v0.10.2


From 39956e78010645ee9d121e6a6eb6d9892e3fc92e Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:39 +0100
Subject: tools lib traceevent: Several cleanups for function plugin

Several cleanups suggested by Namhyung:

  * Remove index field from struct func_stack as it's not needed.

  * Rename get_index into add_and_get_index.

  * Use '%*X' format string capability instead of the loop

Suggested-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-26-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c
index 8deb22e..87acf9c 100644
--- a/tools/lib/traceevent/plugin_function.c
+++ b/tools/lib/traceevent/plugin_function.c
@@ -25,7 +25,6 @@
 #include "event-utils.h"
 
 static struct func_stack {
-	int index;
 	int size;
 	char **stack;
 } *fstack;
@@ -57,7 +56,7 @@ static void add_child(struct func_stack *stack, const char *child, int pos)
 	stack->stack[pos] = strdup(child);
 }
 
-static int get_index(const char *parent, const char *child, int cpu)
+static int add_and_get_index(const char *parent, const char *child, int cpu)
 {
 	int i;
 
@@ -97,7 +96,7 @@ static int function_handler(struct trace_seq *s, struct pevent_record *record,
 	unsigned long long pfunction;
 	const char *func;
 	const char *parent;
-	int i, index;
+	int index;
 
 	if (pevent_get_field_val(s, event, "ip", record, &function, 1))
 		return trace_seq_putc(s, '!');
@@ -109,10 +108,9 @@ static int function_handler(struct trace_seq *s, struct pevent_record *record,
 
 	parent = pevent_find_function(pevent, pfunction);
 
-	index = get_index(parent, func, record->cpu);
+	index = add_and_get_index(parent, func, record->cpu);
 
-	for (i = 0; i < index; i++)
-		trace_seq_printf(s, "   ");
+	trace_seq_printf(s, "%*s", index*3, "");
 
 	if (func)
 		trace_seq_printf(s, "%s", func);
-- 
cgit v0.10.2


From d8e56c98b7ef96a31a64c69df24ab5d80f90e055 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:40 +0100
Subject: tools lib traceevent: Remove malloc_or_die from plugin_function.c

Removing malloc_or_die calls from plugin_function.c, replacing them and
factoring the code with standard realloc and error path.

Suggested-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-27-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c
index 87acf9c..aad92ad 100644
--- a/tools/lib/traceevent/plugin_function.c
+++ b/tools/lib/traceevent/plugin_function.c
@@ -43,11 +43,17 @@ static void add_child(struct func_stack *stack, const char *child, int pos)
 	if (pos < stack->size)
 		free(stack->stack[pos]);
 	else {
-		if (!stack->stack)
-			stack->stack = malloc_or_die(sizeof(char *) * STK_BLK);
-		else
-			stack->stack = realloc(stack->stack, sizeof(char *) *
-					       (stack->size + STK_BLK));
+		char **ptr;
+
+		ptr = realloc(stack->stack, sizeof(char *) *
+			      (stack->size + STK_BLK));
+		if (!ptr) {
+			warning("could not allocate plugin memory\n");
+			return;
+		}
+
+		stack->stack = ptr;
+
 		for (i = stack->size; i < stack->size + STK_BLK; i++)
 			stack->stack[i] = NULL;
 		stack->size += STK_BLK;
@@ -64,10 +70,15 @@ static int add_and_get_index(const char *parent, const char *child, int cpu)
 		return 0;
 
 	if (cpu > cpus) {
-		if (fstack)
-			fstack = realloc(fstack, sizeof(*fstack) * (cpu + 1));
-		else
-			fstack = malloc_or_die(sizeof(*fstack) * (cpu + 1));
+		struct func_stack *ptr;
+
+		ptr = realloc(fstack, sizeof(*fstack) * (cpu + 1));
+		if (!ptr) {
+			warning("could not allocate plugin memory\n");
+			return 0;
+		}
+
+		fstack = ptr;
 
 		/* Account for holes in the cpu count */
 		for (i = cpus + 1; i <= cpu; i++)
-- 
cgit v0.10.2


From 6d65894bc028d0342829ea1e64c9e9efad571124 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 3 Dec 2013 14:09:41 +0100
Subject: tools lib traceevent: Update kvm plugin with is_writable_pte helper

Adding is_writable_pte print helper function, so the
kvmmmu:fast_page_fault print format gets resolved properly.

The diff of 'perf script' output generated by old and new code:
(data was generated by 'perf record -e 'kvm:*,kvmmmu:*' -a')

  --- script.kvm.old
  +++ script.kvm.new
  - qemu-system-x86  3290 [002] 10708.755312: kvmmmu:fast_page_fault: [FAILED TO PARSE] vcpu_id=0 gva=4094486080 error_code=3 sptep=0xffff88019f1e3670 old_spte=336391285 new_spte=336391287 retry=1
  + qemu-system-x86  3290 [002] 10708.755312: kvmmmu:fast_page_fault: vcpu 0 gva f40ce640 error_code P|W sptep 0xffff88019f1e3670 old 0x140cec75 new 140cec77 spurious 0 fixed 1

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386076182-14484-28-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c
index be9d9c6..a0e282c 100644
--- a/tools/lib/traceevent/plugin_kvm.c
+++ b/tools/lib/traceevent/plugin_kvm.c
@@ -389,6 +389,16 @@ static int kvm_mmu_get_page_handler(struct trace_seq *s,
 	return kvm_mmu_print_role(s, record, event, context);
 }
 
+#define PT_WRITABLE_SHIFT 1
+#define PT_WRITABLE_MASK (1ULL << PT_WRITABLE_SHIFT)
+
+static unsigned long long
+process_is_writable_pte(struct trace_seq *s, unsigned long long *args)
+{
+	unsigned long pte = args[0];
+	return pte & PT_WRITABLE_MASK;
+}
+
 int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
 {
 	init_disassembler();
@@ -415,5 +425,12 @@ int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
 	pevent_register_event_handler(pevent, -1, "kvmmmu",
 			"kvm_mmu_prepare_zap_page", kvm_mmu_print_role,
 			NULL);
+
+	pevent_register_print_function(pevent,
+				       process_is_writable_pte,
+				       PEVENT_FUNC_ARG_INT,
+				       "is_writable_pte",
+				       PEVENT_FUNC_ARG_LONG,
+				       PEVENT_FUNC_ARG_VOID);
 	return 0;
 }
-- 
cgit v0.10.2


From 789790791ad254408267eb6a216ae7a90973c05a Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 5 Dec 2013 12:13:54 +0100
Subject: tools/perf/build: Fix install dependency

The traceevents-plugins install targets needs a proper dependency,
otherwise it might be executed prematurely and in parallel to an
actual build.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Link: http://lkml.kernel.org/n/tip-rvlbzena4ovzgqiPm6teBofz@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index ca3b87d..9a8cf37 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -722,7 +722,7 @@ $(LIBTRACEEVENT)-clean:
 	$(call QUIET_CLEAN, libtraceevent)
 	@$(MAKE) -C $(TRACE_EVENT_DIR) O=$(OUTPUT) clean >/dev/null
 
-install-traceevent-plugins:
+install-traceevent-plugins: $(LIBTRACEEVENT)
 	$(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) install_plugins
 
 LIBLK_SOURCES = $(wildcard $(LK_PATH)*.[ch])
-- 
cgit v0.10.2


From 40ea2b42d7c44386cf81d5636d574193da2c8df2 Mon Sep 17 00:00:00 2001
From: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Date: Thu, 5 Dec 2013 19:10:17 +0800
Subject: sched/numa: Drop idx field of task_numa_env struct

Drop unused idx field of task_numa_env struct.

Signed-off-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/1386241817-5051-2-git-send-email-liwanp@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a566c07..49aa01f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1037,7 +1037,7 @@ struct task_numa_env {
 
 	struct numa_stats src_stats, dst_stats;
 
-	int imbalance_pct, idx;
+	int imbalance_pct;
 
 	struct task_struct *best_task;
 	long best_imp;
-- 
cgit v0.10.2


From 9aca7f1792c5d2d5d367bbe5cfe204fe40517929 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 4 Dec 2013 19:41:39 -0700
Subject: perf trace: Add support for syscalls vs raw_syscalls

Older kernels (e.g., RHEL6) do system call tracing via
syscalls:sys_{enter,exit} rather than raw_syscalls. Update perf-trace to
detect lack of raw_syscalls support and try syscalls.

Signed-off-by: David Ahern <dsahern@gmail.com>
Link: http://lkml.kernel.org/r/1386211302-31303-2-git-send-email-dsahern@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 56afe33..a7aa771 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -12,6 +12,7 @@
 #include "util/thread_map.h"
 #include "util/stat.h"
 #include "trace-event.h"
+#include "util/parse-events.h"
 
 #include <libaudit.h>
 #include <stdlib.h>
@@ -173,6 +174,10 @@ static struct perf_evsel *perf_evsel__syscall_newtp(const char *direction, void
 {
 	struct perf_evsel *evsel = perf_evsel__newtp("raw_syscalls", direction);
 
+	/* older kernel (e.g., RHEL6) use syscalls:{enter,exit} */
+	if (evsel == NULL)
+		evsel = perf_evsel__newtp("syscalls", direction);
+
 	if (evsel) {
 		if (perf_evsel__init_syscall_tp(evsel, handler))
 			goto out_delete;
@@ -1801,10 +1806,11 @@ static int trace__record(int argc, const char **argv)
 		"-R",
 		"-m", "1024",
 		"-c", "1",
-		"-e", "raw_syscalls:sys_enter,raw_syscalls:sys_exit",
+		"-e",
 	};
 
-	rec_argc = ARRAY_SIZE(record_args) + argc;
+	/* +1 is for the event string below */
+	rec_argc = ARRAY_SIZE(record_args) + 1 + argc;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
 	if (rec_argv == NULL)
@@ -1813,6 +1819,17 @@ static int trace__record(int argc, const char **argv)
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
 		rec_argv[i] = record_args[i];
 
+	/* event string may be different for older kernels - e.g., RHEL6 */
+	if (is_valid_tracepoint("raw_syscalls:sys_enter"))
+		rec_argv[i] = "raw_syscalls:sys_enter,raw_syscalls:sys_exit";
+	else if (is_valid_tracepoint("syscalls:sys_enter"))
+		rec_argv[i] = "syscalls:sys_enter,syscalls:sys_exit";
+	else {
+		pr_err("Neither raw_syscalls nor syscalls events exist.\n");
+		return -1;
+	}
+	i++;
+
 	for (j = 0; j < (unsigned int)argc; j++, i++)
 		rec_argv[i] = argv[j];
 
@@ -2048,6 +2065,10 @@ static int trace__replay(struct trace *trace)
 
 	evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
 						     "raw_syscalls:sys_enter");
+	/* older kernels have syscalls tp versus raw_syscalls */
+	if (evsel == NULL)
+		evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
+							     "syscalls:sys_enter");
 	if (evsel == NULL) {
 		pr_err("Data file does not have raw_syscalls:sys_enter event\n");
 		goto out;
@@ -2061,6 +2082,9 @@ static int trace__replay(struct trace *trace)
 
 	evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
 						     "raw_syscalls:sys_exit");
+	if (evsel == NULL)
+		evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
+							     "syscalls:sys_exit");
 	if (evsel == NULL) {
 		pr_err("Data file does not have raw_syscalls:sys_exit event\n");
 		goto out;
-- 
cgit v0.10.2


From 3160565f0e005d2ec736ae25cf0a79988c0cbe71 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Wed, 4 Dec 2013 19:41:41 -0700
Subject: perf trace: Fix summary percentage when processing files

Getting a divide by 0 when events are processed from a file:

   perf trace -i perf.data -s
   ...
   dnsmasq (1684), 10 events, inf%, 0.000 msec

The problem is that the event count is not incremented as events are
processed. With this patch:

   perf trace -i perf.data -s
   ...
   dnsmasq (1684), 10 events, 8.9%, 0.000 msec

Signed-off-by: David Ahern <dsahern@gmail.com>
Link: http://lkml.kernel.org/r/1386211302-31303-4-git-send-email-dsahern@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index a7aa771..56bbca5 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1770,8 +1770,10 @@ static int trace__process_sample(struct perf_tool *tool,
 	if (!trace->full_time && trace->base_time == 0)
 		trace->base_time = sample->time;
 
-	if (handler)
+	if (handler) {
+		++trace->nr_events;
 		handler(trace, evsel, sample);
+	}
 
 	return err;
 }
-- 
cgit v0.10.2


From 4c4d684a55fc01dac6bee696efc56b96d0e6c03a Mon Sep 17 00:00:00 2001
From: Ujjal Roy <royujjal@gmail.com>
Date: Wed, 4 Dec 2013 17:27:34 +0530
Subject: cfg80211: fix WARN_ON for re-association to the expired BSS

cfg80211 allows re-association in managed mode and if a user
wants to re-associate to the same AP network after the time
period of IEEE80211_SCAN_RESULT_EXPIRE, cfg80211 warns with
the following message on receiving the connect result event.

------------[ cut here ]------------
WARNING: CPU: 0 PID: 13984 at net/wireless/sme.c:658
         __cfg80211_connect_result+0x3a6/0x3e0 [cfg80211]()
Call Trace:
 [<ffffffff81747a41>] dump_stack+0x46/0x58
 [<ffffffff81045847>] warn_slowpath_common+0x87/0xb0
 [<ffffffff81045885>] warn_slowpath_null+0x15/0x20
 [<ffffffffa05345f6>] __cfg80211_connect_result+0x3a6/0x3e0 [cfg80211]
 [<ffffffff8107168b>] ? update_rq_clock+0x2b/0x50
 [<ffffffff81078c01>] ? update_curr+0x1/0x160
 [<ffffffffa05133d2>] cfg80211_process_wdev_events+0xb2/0x1c0 [cfg80211]
 [<ffffffff81079303>] ? pick_next_task_fair+0x63/0x170
 [<ffffffffa0513518>] cfg80211_process_rdev_events+0x38/0x90 [cfg80211]
 [<ffffffffa050f03d>] cfg80211_event_work+0x1d/0x30 [cfg80211]
 [<ffffffff8105f21f>] process_one_work+0x17f/0x420
 [<ffffffff8105f90a>] worker_thread+0x11a/0x370
 [<ffffffff8105f7f0>] ? rescuer_thread+0x2f0/0x2f0
 [<ffffffff8106638b>] kthread+0xbb/0xc0
 [<ffffffff810662d0>] ? kthread_create_on_node+0x120/0x120
 [<ffffffff817574bc>] ret_from_fork+0x7c/0xb0
 [<ffffffff810662d0>] ? kthread_create_on_node+0x120/0x120
---[ end trace 61f3bddc9c4981f7 ]---

The reason is that, in connect result event cfg80211 unholds
the BSS to which the device is associated (and was held so
far). So, for the event with status successful, when cfg80211
wants to get that BSS from the device's BSS list it gets a
NULL BSS because the BSS has been expired and unheld already.

Fix it by reshuffling the code.

Signed-off-by: Ujjal Roy <royujjal@gmail.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 65f8008..d3c5bd7 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -632,6 +632,16 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 	}
 #endif
 
+	if (!bss && (status == WLAN_STATUS_SUCCESS)) {
+		WARN_ON_ONCE(!wiphy_to_dev(wdev->wiphy)->ops->connect);
+		bss = cfg80211_get_bss(wdev->wiphy, NULL, bssid,
+				       wdev->ssid, wdev->ssid_len,
+				       WLAN_CAPABILITY_ESS,
+				       WLAN_CAPABILITY_ESS);
+		if (bss)
+			cfg80211_hold_bss(bss_from_pub(bss));
+	}
+
 	if (wdev->current_bss) {
 		cfg80211_unhold_bss(wdev->current_bss);
 		cfg80211_put_bss(wdev->wiphy, &wdev->current_bss->pub);
@@ -649,16 +659,8 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 		return;
 	}
 
-	if (!bss) {
-		WARN_ON_ONCE(!wiphy_to_dev(wdev->wiphy)->ops->connect);
-		bss = cfg80211_get_bss(wdev->wiphy, NULL, bssid,
-				       wdev->ssid, wdev->ssid_len,
-				       WLAN_CAPABILITY_ESS,
-				       WLAN_CAPABILITY_ESS);
-		if (WARN_ON(!bss))
-			return;
-		cfg80211_hold_bss(bss_from_pub(bss));
-	}
+	if (WARN_ON(!bss))
+		return;
 
 	wdev->current_bss = bss_from_pub(bss);
 
-- 
cgit v0.10.2


From 1d61cf121d7d9085145553294307e81c25586288 Mon Sep 17 00:00:00 2001
From: Jiang Liu <liuj97@gmail.com>
Date: Thu, 5 Dec 2013 00:13:01 +0800
Subject: smp, metag: kill SMP single function call interrupt

Commit 9a46ad6d6df3 "smp: make smp_call_function_many() use logic
similar to smp_call_function_single()" has unified the way to handle
single and multiple cross-CPU function calls. Now only one interrupt is
needed for architecture specific code to support generic SMP function
call interfaces, so kill the redundant single function call interrupt.

Signed-off-by: Jiang Liu <liuj97@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Shaohua Li <shli@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Jiri Kosina <trivial@kernel.org>
Signed-off-by: James Hogan <james.hogan@imgtec.com>

diff --git a/arch/metag/include/asm/smp.h b/arch/metag/include/asm/smp.h
index e0373f8..1d7e770 100644
--- a/arch/metag/include/asm/smp.h
+++ b/arch/metag/include/asm/smp.h
@@ -7,13 +7,11 @@
 
 enum ipi_msg_type {
 	IPI_CALL_FUNC,
-	IPI_CALL_FUNC_SINGLE,
 	IPI_RESCHEDULE,
 };
 
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
-#define arch_send_call_function_ipi_mask arch_send_call_function_ipi_mask
 
 asmlinkage void secondary_start_kernel(void);
 
diff --git a/arch/metag/kernel/smp.c b/arch/metag/kernel/smp.c
index 177ffb4..f74008b 100644
--- a/arch/metag/kernel/smp.c
+++ b/arch/metag/kernel/smp.c
@@ -491,7 +491,7 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 
 void arch_send_call_function_single_ipi(int cpu)
 {
-	send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
+	send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC);
 }
 
 void show_ipi_list(struct seq_file *p)
@@ -545,10 +545,6 @@ static int do_IPI(void)
 			generic_smp_call_function_interrupt();
 			break;
 
-		case IPI_CALL_FUNC_SINGLE:
-			generic_smp_call_function_single_interrupt();
-			break;
-
 		default:
 			pr_crit("CPU%u: Unknown IPI message 0x%lx\n",
 				cpu, nextmsg);
-- 
cgit v0.10.2


From 7f3f5240ce64b2b59e2a9a338b4a38931724192a Mon Sep 17 00:00:00 2001
From: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
Date: Wed, 4 Dec 2013 11:40:11 -0600
Subject: amd64_edac: Fix condition to verify max channels allowed for F15 M30h

The value returned from 'f15_m30h_determine_channel' will
always be 0x3 max. The condition

	(channel > 4 || channel < 0)

works as hardware never returns a value of 4, but
it leads to static checker analysis errors like
http://marc.info/?l=linux-edac&m=138607615131951&w=2.

Fix that.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
Link: http://lkml.kernel.org/r/20131203130857.GA32170@elgon.mountain
[ Boris: massage commit message a bit. ]
Signed-off-by: Borislav Petkov <bp@suse.de>

diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index b53d0de..e2079b2 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -1578,7 +1578,7 @@ static int f15_m30h_match_to_this_node(struct amd64_pvt *pvt, unsigned range,
 					     num_dcts_intlv, dct_sel);
 
 	/* Verify we stay within the MAX number of channels allowed */
-	if (channel > 4 || channel < 0)
+	if (channel > 3)
 		return -EINVAL;
 
 	leg_mmio_hole = (u8) (dct_cont_base_reg >> 1 & BIT(0));
-- 
cgit v0.10.2


From ba935f40979b32924824759111ed95d35469c5fa Mon Sep 17 00:00:00 2001
From: Jingoo Han <jg1.han@samsung.com>
Date: Fri, 6 Dec 2013 10:23:08 +0100
Subject: EDAC: Remove DEFINE_PCI_DEVICE_TABLE macro

Currently, there is no other bus that has something like this macro for
their device ids. Thus, DEFINE_PCI_DEVICE_TABLE macro should be removed.

Signed-off-by: Jingoo Han <jg1.han@samsung.com>
Link: http://lkml.kernel.org/r/001c01ceefb3$5724d860$056e8920$%han@samsung.com
[ Boris: swap commit message with better one. ]
Signed-off-by: Borislav Petkov <bp@suse.de>

diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index e2079b2..a2f1854 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -2795,7 +2795,7 @@ static void amd64_remove_one_instance(struct pci_dev *pdev)
  * PCI core identifies what devices are on a system during boot, and then
  * inquiry this table to see if this driver is for a given device found.
  */
-static DEFINE_PCI_DEVICE_TABLE(amd64_pci_table) = {
+static const struct pci_device_id amd64_pci_table[] = {
 	{
 		.vendor		= PCI_VENDOR_ID_AMD,
 		.device		= PCI_DEVICE_ID_AMD_K8_NB_MEMCTL,
diff --git a/drivers/edac/amd76x_edac.c b/drivers/edac/amd76x_edac.c
index 96e3ee3..3a501b5 100644
--- a/drivers/edac/amd76x_edac.c
+++ b/drivers/edac/amd76x_edac.c
@@ -333,7 +333,7 @@ static void amd76x_remove_one(struct pci_dev *pdev)
 	edac_mc_free(mci);
 }
 
-static DEFINE_PCI_DEVICE_TABLE(amd76x_pci_tbl) = {
+static const struct pci_device_id amd76x_pci_tbl[] = {
 	{
 	 PCI_VEND_DEV(AMD, FE_GATE_700C), PCI_ANY_ID, PCI_ANY_ID, 0, 0,
 	 AMD762},
diff --git a/drivers/edac/e752x_edac.c b/drivers/edac/e752x_edac.c
index 644fec5..5fb01b0 100644
--- a/drivers/edac/e752x_edac.c
+++ b/drivers/edac/e752x_edac.c
@@ -1421,7 +1421,7 @@ static void e752x_remove_one(struct pci_dev *pdev)
 	edac_mc_free(mci);
 }
 
-static DEFINE_PCI_DEVICE_TABLE(e752x_pci_tbl) = {
+static const struct pci_device_id e752x_pci_tbl[] = {
 	{
 	 PCI_VEND_DEV(INTEL, 7520_0), PCI_ANY_ID, PCI_ANY_ID, 0, 0,
 	 E7520},
diff --git a/drivers/edac/e7xxx_edac.c b/drivers/edac/e7xxx_edac.c
index 1c4056a..3cda79b 100644
--- a/drivers/edac/e7xxx_edac.c
+++ b/drivers/edac/e7xxx_edac.c
@@ -555,7 +555,7 @@ static void e7xxx_remove_one(struct pci_dev *pdev)
 	edac_mc_free(mci);
 }
 
-static DEFINE_PCI_DEVICE_TABLE(e7xxx_pci_tbl) = {
+static const struct pci_device_id e7xxx_pci_tbl[] = {
 	{
 	 PCI_VEND_DEV(INTEL, 7205_0), PCI_ANY_ID, PCI_ANY_ID, 0, 0,
 	 E7205},
diff --git a/drivers/edac/i3000_edac.c b/drivers/edac/i3000_edac.c
index 694efcb..cd28b96 100644
--- a/drivers/edac/i3000_edac.c
+++ b/drivers/edac/i3000_edac.c
@@ -487,7 +487,7 @@ static void i3000_remove_one(struct pci_dev *pdev)
 	edac_mc_free(mci);
 }
 
-static DEFINE_PCI_DEVICE_TABLE(i3000_pci_tbl) = {
+static const struct pci_device_id i3000_pci_tbl[] = {
 	{
 	 PCI_VEND_DEV(INTEL, 3000_HB), PCI_ANY_ID, PCI_ANY_ID, 0, 0,
 	 I3000},
diff --git a/drivers/edac/i3200_edac.c b/drivers/edac/i3200_edac.c
index be10a74..fa1326e 100644
--- a/drivers/edac/i3200_edac.c
+++ b/drivers/edac/i3200_edac.c
@@ -466,7 +466,7 @@ static void i3200_remove_one(struct pci_dev *pdev)
 	edac_mc_free(mci);
 }
 
-static DEFINE_PCI_DEVICE_TABLE(i3200_pci_tbl) = {
+static const struct pci_device_id i3200_pci_tbl[] = {
 	{
 		PCI_VEND_DEV(INTEL, 3200_HB), PCI_ANY_ID, PCI_ANY_ID, 0, 0,
 		I3200},
diff --git a/drivers/edac/i5000_edac.c b/drivers/edac/i5000_edac.c
index 63b2194..72e07e3 100644
--- a/drivers/edac/i5000_edac.c
+++ b/drivers/edac/i5000_edac.c
@@ -1530,7 +1530,7 @@ static void i5000_remove_one(struct pci_dev *pdev)
  *
  *	The "E500P" device is the first device supported.
  */
-static DEFINE_PCI_DEVICE_TABLE(i5000_pci_tbl) = {
+static const struct pci_device_id i5000_pci_tbl[] = {
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_I5000_DEV16),
 	 .driver_data = I5000P},
 
diff --git a/drivers/edac/i5100_edac.c b/drivers/edac/i5100_edac.c
index 157b934..36a38ee 100644
--- a/drivers/edac/i5100_edac.c
+++ b/drivers/edac/i5100_edac.c
@@ -1213,7 +1213,7 @@ static void i5100_remove_one(struct pci_dev *pdev)
 	edac_mc_free(mci);
 }
 
-static DEFINE_PCI_DEVICE_TABLE(i5100_pci_tbl) = {
+static const struct pci_device_id i5100_pci_tbl[] = {
 	/* Device 16, Function 0, Channel 0 Memory Map, Error Flag/Mask, ... */
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_5100_16) },
 	{ 0, }
diff --git a/drivers/edac/i5400_edac.c b/drivers/edac/i5400_edac.c
index 0a05bbc..e080cbf 100644
--- a/drivers/edac/i5400_edac.c
+++ b/drivers/edac/i5400_edac.c
@@ -1416,7 +1416,7 @@ static void i5400_remove_one(struct pci_dev *pdev)
  *
  *	The "E500P" device is the first device supported.
  */
-static DEFINE_PCI_DEVICE_TABLE(i5400_pci_tbl) = {
+static const struct pci_device_id i5400_pci_tbl[] = {
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_5400_ERR)},
 	{0,}			/* 0 terminated list. */
 };
diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c
index 9004c64..d63f479 100644
--- a/drivers/edac/i7300_edac.c
+++ b/drivers/edac/i7300_edac.c
@@ -1160,7 +1160,7 @@ static void i7300_remove_one(struct pci_dev *pdev)
  *
  * Has only 8086:360c PCI ID
  */
-static DEFINE_PCI_DEVICE_TABLE(i7300_pci_tbl) = {
+static const struct pci_device_id i7300_pci_tbl[] = {
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_I7300_MCH_ERR)},
 	{0,}			/* 0 terminated list. */
 };
diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index 80a963d..87533ca 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -394,7 +394,7 @@ static const struct pci_id_table pci_dev_table[] = {
 /*
  *	pci_device_id	table for which devices we are looking for
  */
-static DEFINE_PCI_DEVICE_TABLE(i7core_pci_tbl) = {
+static const struct pci_device_id i7core_pci_tbl[] = {
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_X58_HUB_MGMT)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_LYNNFIELD_QPI_LINK0)},
 	{0,}			/* 0 terminated list. */
diff --git a/drivers/edac/i82443bxgx_edac.c b/drivers/edac/i82443bxgx_edac.c
index 57fdb77..d730e276 100644
--- a/drivers/edac/i82443bxgx_edac.c
+++ b/drivers/edac/i82443bxgx_edac.c
@@ -386,7 +386,7 @@ static void i82443bxgx_edacmc_remove_one(struct pci_dev *pdev)
 
 EXPORT_SYMBOL_GPL(i82443bxgx_edacmc_remove_one);
 
-static DEFINE_PCI_DEVICE_TABLE(i82443bxgx_pci_tbl) = {
+static const struct pci_device_id i82443bxgx_pci_tbl[] = {
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443BX_0)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443BX_2)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443GX_0)},
diff --git a/drivers/edac/i82860_edac.c b/drivers/edac/i82860_edac.c
index 3e3e431..3382f63 100644
--- a/drivers/edac/i82860_edac.c
+++ b/drivers/edac/i82860_edac.c
@@ -288,7 +288,7 @@ static void i82860_remove_one(struct pci_dev *pdev)
 	edac_mc_free(mci);
 }
 
-static DEFINE_PCI_DEVICE_TABLE(i82860_pci_tbl) = {
+static const struct pci_device_id i82860_pci_tbl[] = {
 	{
 	 PCI_VEND_DEV(INTEL, 82860_0), PCI_ANY_ID, PCI_ANY_ID, 0, 0,
 	 I82860},
diff --git a/drivers/edac/i82875p_edac.c b/drivers/edac/i82875p_edac.c
index 2f8535f..80573df 100644
--- a/drivers/edac/i82875p_edac.c
+++ b/drivers/edac/i82875p_edac.c
@@ -527,7 +527,7 @@ static void i82875p_remove_one(struct pci_dev *pdev)
 	edac_mc_free(mci);
 }
 
-static DEFINE_PCI_DEVICE_TABLE(i82875p_pci_tbl) = {
+static const struct pci_device_id i82875p_pci_tbl[] = {
 	{
 	 PCI_VEND_DEV(INTEL, 82875_0), PCI_ANY_ID, PCI_ANY_ID, 0, 0,
 	 I82875P},
diff --git a/drivers/edac/i82975x_edac.c b/drivers/edac/i82975x_edac.c
index 0c8d4b0..10b1052 100644
--- a/drivers/edac/i82975x_edac.c
+++ b/drivers/edac/i82975x_edac.c
@@ -628,7 +628,7 @@ static void i82975x_remove_one(struct pci_dev *pdev)
 	edac_mc_free(mci);
 }
 
-static DEFINE_PCI_DEVICE_TABLE(i82975x_pci_tbl) = {
+static const struct pci_device_id i82975x_pci_tbl[] = {
 	{
 		PCI_VEND_DEV(INTEL, 82975_0), PCI_ANY_ID, PCI_ANY_ID, 0, 0,
 		I82975X
diff --git a/drivers/edac/r82600_edac.c b/drivers/edac/r82600_edac.c
index 2fd6a54..8f936bc 100644
--- a/drivers/edac/r82600_edac.c
+++ b/drivers/edac/r82600_edac.c
@@ -383,7 +383,7 @@ static void r82600_remove_one(struct pci_dev *pdev)
 	edac_mc_free(mci);
 }
 
-static DEFINE_PCI_DEVICE_TABLE(r82600_pci_tbl) = {
+static const struct pci_device_id r82600_pci_tbl[] = {
 	{
 	 PCI_DEVICE(PCI_VENDOR_ID_RADISYS, R82600_BRIDGE_ID)
 	 },
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 8472405..b5d254b 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -461,7 +461,7 @@ static const struct pci_id_table pci_dev_descr_ibridge_table[] = {
 /*
  *	pci_device_id	table for which devices we are looking for
  */
-static DEFINE_PCI_DEVICE_TABLE(sbridge_pci_tbl) = {
+static const struct pci_device_id sbridge_pci_tbl[] = {
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SBRIDGE_IMC_TA)},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TA)},
 	{0,}			/* 0 terminated list. */
diff --git a/drivers/edac/x38_edac.c b/drivers/edac/x38_edac.c
index 1a4df82..4891b45 100644
--- a/drivers/edac/x38_edac.c
+++ b/drivers/edac/x38_edac.c
@@ -448,7 +448,7 @@ static void x38_remove_one(struct pci_dev *pdev)
 	edac_mc_free(mci);
 }
 
-static DEFINE_PCI_DEVICE_TABLE(x38_pci_tbl) = {
+static const struct pci_device_id x38_pci_tbl[] = {
 	{
 	 PCI_VEND_DEV(INTEL, X38_HB), PCI_ANY_ID, PCI_ANY_ID, 0, 0,
 	 X38},
-- 
cgit v0.10.2


From 3a3ffa2e82205921d1189f1055c22dae4c72819a Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Mon, 18 Nov 2013 21:38:20 -0500
Subject: tools lib traceevent: Report better error message on bad function
 args

When Jiri Olsa was writing a function callback for
scsi_trace_parse_cdb(), he thought that the traceevent library had a
bug in it because he was getting this error:

  Error: expected ')' but read ','
  Error: expected ')' but read ','
  Error: expected ')' but read ','
  Error: expected ')' but read ','

But in truth, he didn't have the write number of arguments for the
function callback, and the error was the library detecting the
discrepancy. A better error message would have prevented the confusion:

  Error: function 'scsi_trace_parse_cdb()' only expects 2 arguments but event scsi_dispatch_cmd_timeout has more
  Error: function 'scsi_trace_parse_cdb()' only expects 2 arguments but event scsi_dispatch_cmd_start has more
  Error: function 'scsi_trace_parse_cdb()' only expects 2 arguments but event scsi_dispatch_cmd_error has more
  Error: function 'scsi_trace_parse_cdb()' only expects 2 arguments but event scsi_dispatch_cmd_done has more

Or

  Error: function 'scsi_trace_parse_cdb()' expects 4 arguments but event scsi_dispatch_cmd_timeout only uses 3
  Error: function 'scsi_trace_parse_cdb()' expects 4 arguments but event scsi_dispatch_cmd_start only uses 3
  Error: function 'scsi_trace_parse_cdb()' expects 4 arguments but event scsi_dispatch_cmd_error only uses 3
  Error: function 'scsi_trace_parse_cdb()' expects 4 arguments but event scsi_dispatch_cmd_done only uses 3

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/n/tip-a4c34w62vl0diitvxb7bt3er@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 9849873..22566c2 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -2710,7 +2710,6 @@ process_func_handler(struct event_format *event, struct pevent_function_handler
 	struct print_arg *farg;
 	enum event_type type;
 	char *token;
-	const char *test;
 	int i;
 
 	arg->type = PRINT_FUNC;
@@ -2727,15 +2726,19 @@ process_func_handler(struct event_format *event, struct pevent_function_handler
 		}
 
 		type = process_arg(event, farg, &token);
-		if (i < (func->nr_args - 1))
-			test = ",";
-		else
-			test = ")";
-
-		if (test_type_token(type, token, EVENT_DELIM, test)) {
-			free_arg(farg);
-			free_token(token);
-			return EVENT_ERROR;
+		if (i < (func->nr_args - 1)) {
+			if (type != EVENT_DELIM || strcmp(token, ",") != 0) {
+				warning("Error: function '%s()' expects %d arguments but event %s only uses %d",
+					func->name, func->nr_args,
+					event->name, i + 1);
+				goto err;
+			}
+		} else {
+			if (type != EVENT_DELIM || strcmp(token, ")") != 0) {
+				warning("Error: function '%s()' only expects %d arguments but event %s has more",
+					func->name, func->nr_args, event->name);
+				goto err;
+			}
 		}
 
 		*next_arg = farg;
@@ -2747,6 +2750,11 @@ process_func_handler(struct event_format *event, struct pevent_function_handler
 	*tok = token;
 
 	return type;
+
+err:
+	free_arg(farg);
+	free_token(token);
+	return EVENT_ERROR;
 }
 
 static enum event_type
-- 
cgit v0.10.2


From 6cf30b35475435f453d87838fb14ad3483955a19 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Fri, 24 May 2013 14:10:51 +0200
Subject: m68k/mac: Mark Mac IIsi ADB driver BROKEN

As reported by Finn Thain, the Mac IIsi ADB driver should be disabled
because it will crash.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/drivers/macintosh/Kconfig b/drivers/macintosh/Kconfig
index d26a312..3067d56 100644
--- a/drivers/macintosh/Kconfig
+++ b/drivers/macintosh/Kconfig
@@ -32,7 +32,7 @@ config ADB_MACII
 
 config ADB_MACIISI
 	bool "Include Mac IIsi ADB driver"
-	depends on ADB && MAC
+	depends on ADB && MAC && BROKEN
 	help
 	  Say Y here if want your kernel to support Macintosh systems that use
 	  the Mac IIsi style ADB.  This includes the IIsi, IIvi, IIvx, Classic
-- 
cgit v0.10.2


From 7d5f5fa276efbbe45f0ed270b3f4e4a2816398c2 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Tue, 20 Aug 2013 22:51:47 +0200
Subject: m68k: Add kexec support

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 75f25a8..178dffa 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -87,6 +87,23 @@ config MMU_SUN3
 	bool
 	depends on MMU && !MMU_MOTOROLA && !MMU_COLDFIRE
 
+config KEXEC
+	bool "kexec system call"
+	depends on M68KCLASSIC
+	help
+	  kexec is a system call that implements the ability to shutdown your
+	  current kernel, and to start another kernel.  It is like a reboot
+	  but it is independent of the system firmware.   And like a reboot
+	  you can start any kernel with it, not just Linux.
+
+	  The name comes from the similarity to the exec system call.
+
+	  It is an ongoing process to be certain the hardware in a machine
+	  is properly shutdown, so do not be surprised if this code does not
+	  initially work for you.  As of this writing the exact hardware
+	  interface is strongly in flux, so no good recommendation can be
+	  made.
+
 menu "Platform setup"
 
 source arch/m68k/Kconfig.cpu
diff --git a/arch/m68k/include/asm/kexec.h b/arch/m68k/include/asm/kexec.h
new file mode 100644
index 0000000..3df97ab
--- /dev/null
+++ b/arch/m68k/include/asm/kexec.h
@@ -0,0 +1,29 @@
+#ifndef _ASM_M68K_KEXEC_H
+#define _ASM_M68K_KEXEC_H
+
+#ifdef CONFIG_KEXEC
+
+/* Maximum physical address we can use pages from */
+#define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
+/* Maximum address we can reach in physical address mode */
+#define KEXEC_DESTINATION_MEMORY_LIMIT (-1UL)
+/* Maximum address we can use for the control code buffer */
+#define KEXEC_CONTROL_MEMORY_LIMIT (-1UL)
+
+#define KEXEC_CONTROL_PAGE_SIZE	4096
+
+#define KEXEC_ARCH KEXEC_ARCH_68K
+
+#ifndef __ASSEMBLY__
+
+static inline void crash_setup_regs(struct pt_regs *newregs,
+				    struct pt_regs *oldregs)
+{
+	/* Dummy implementation for now */
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* CONFIG_KEXEC */
+
+#endif /* _ASM_M68K_KEXEC_H */
diff --git a/arch/m68k/kernel/Makefile b/arch/m68k/kernel/Makefile
index 655347d..7ee5f00 100644
--- a/arch/m68k/kernel/Makefile
+++ b/arch/m68k/kernel/Makefile
@@ -22,3 +22,5 @@ obj-$(CONFIG_PCI) += pcibios.o
 
 obj-$(CONFIG_HAS_DMA)	+= dma.o
 
+obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
+
diff --git a/arch/m68k/kernel/asm-offsets.c b/arch/m68k/kernel/asm-offsets.c
index 8b7b228..3a38634 100644
--- a/arch/m68k/kernel/asm-offsets.c
+++ b/arch/m68k/kernel/asm-offsets.c
@@ -98,6 +98,9 @@ int main(void)
 	DEFINE(CIABBASE, &ciab);
 	DEFINE(C_PRA, offsetof(struct CIA, pra));
 	DEFINE(ZTWOBASE, zTwoBase);
+
+	/* enum m68k_fixup_type */
+	DEFINE(M68K_FIXUP_MEMOFFSET, m68k_fixup_memoffset);
 #endif
 
 	return 0;
diff --git a/arch/m68k/kernel/machine_kexec.c b/arch/m68k/kernel/machine_kexec.c
new file mode 100644
index 0000000..d4affc9
--- /dev/null
+++ b/arch/m68k/kernel/machine_kexec.c
@@ -0,0 +1,58 @@
+/*
+ * machine_kexec.c - handle transition of Linux booting another kernel
+ */
+#include <linux/compiler.h>
+#include <linux/kexec.h>
+#include <linux/mm.h>
+#include <linux/delay.h>
+
+#include <asm/cacheflush.h>
+#include <asm/page.h>
+#include <asm/setup.h>
+
+extern const unsigned char relocate_new_kernel[];
+extern const size_t relocate_new_kernel_size;
+
+int machine_kexec_prepare(struct kimage *kimage)
+{
+	return 0;
+}
+
+void machine_kexec_cleanup(struct kimage *kimage)
+{
+}
+
+void machine_shutdown(void)
+{
+}
+
+void machine_crash_shutdown(struct pt_regs *regs)
+{
+}
+
+typedef void (*relocate_kernel_t)(unsigned long ptr,
+				  unsigned long start,
+				  unsigned long cpu_mmu_flags) __noreturn;
+
+void machine_kexec(struct kimage *image)
+{
+	void *reboot_code_buffer;
+	unsigned long cpu_mmu_flags;
+
+	reboot_code_buffer = page_address(image->control_code_page);
+
+	memcpy(reboot_code_buffer, relocate_new_kernel,
+	       relocate_new_kernel_size);
+
+	/*
+	 * we do not want to be bothered.
+	 */
+	local_irq_disable();
+
+	pr_info("Will call new kernel at 0x%08lx. Bye...\n", image->start);
+	__flush_cache_all();
+	cpu_mmu_flags = m68k_cputype | m68k_mmutype << 8;
+	((relocate_kernel_t) reboot_code_buffer)(image->head & PAGE_MASK,
+						 image->start,
+						 cpu_mmu_flags);
+}
diff --git a/arch/m68k/kernel/relocate_kernel.S b/arch/m68k/kernel/relocate_kernel.S
new file mode 100644
index 0000000..3e09a89
--- /dev/null
+++ b/arch/m68k/kernel/relocate_kernel.S
@@ -0,0 +1,159 @@
+#include <linux/linkage.h>
+
+#include <asm/asm-offsets.h>
+#include <asm/page.h>
+#include <asm/setup.h>
+
+
+#define MMU_BASE	8		/* MMU flags base in cpu_mmu_flags */
+
+.text
+
+ENTRY(relocate_new_kernel)
+	movel %sp@(4),%a0		/* a0 = ptr */
+	movel %sp@(8),%a1		/* a1 = start */
+	movel %sp@(12),%d1		/* d1 = cpu_mmu_flags */
+	movew #PAGE_MASK,%d2		/* d2 = PAGE_MASK */
+
+	/* Disable MMU */
+
+	btst #MMU_BASE + MMUB_68851,%d1
+	jeq 3f
+
+1:	/* 68851 or 68030 */
+
+	lea %pc@(.Lcopy),%a4
+2:	addl #0x00000000,%a4		/* virt_to_phys() */
+
+	.section ".m68k_fixup","aw"
+	.long M68K_FIXUP_MEMOFFSET, 2b+2
+	.previous
+
+	.chip 68030
+	pmove %tc,%d0			/* Disable MMU */
+	bclr #7,%d0
+	pmove %d0,%tc
+	jmp %a4@			/* Jump to physical .Lcopy */
+	.chip 68k
+
+3:
+	btst #MMU_BASE + MMUB_68030,%d1
+	jne 1b
+
+	btst #MMU_BASE + MMUB_68040,%d1
+	jeq 6f
+
+4:	/* 68040 or 68060 */
+
+	lea %pc@(.Lcont040),%a4
+5:	addl #0x00000000,%a4		/* virt_to_phys() */
+
+	.section ".m68k_fixup","aw"
+	.long M68K_FIXUP_MEMOFFSET, 5b+2
+	.previous
+
+	movel %a4,%d0
+	andl #0xff000000,%d0
+	orw #0xe020,%d0			/* Map 16 MiB, enable, cacheable */
+	.chip 68040
+	movec %d0,%itt0
+	movec %d0,%dtt0
+	.chip 68k
+	jmp %a4@			/* Jump to physical .Lcont040 */
+
+.Lcont040:
+	moveq #0,%d0
+	.chip 68040
+	movec %d0,%tc			/* Disable MMU */
+	movec %d0,%itt0
+	movec %d0,%itt1
+	movec %d0,%dtt0
+	movec %d0,%dtt1
+	.chip 68k
+	jra .Lcopy
+
+6:
+	btst #MMU_BASE + MMUB_68060,%d1
+	jne 4b
+
+.Lcopy:
+	movel %a0@+,%d0			/* d0 = entry = *ptr */
+	jeq .Lflush
+
+	btst #2,%d0			/* entry & IND_DONE? */
+	jne .Lflush
+
+	btst #1,%d0			/* entry & IND_INDIRECTION? */
+	jeq 1f
+	andw %d2,%d0
+	movel %d0,%a0			/* ptr = entry & PAGE_MASK */
+	jra .Lcopy
+
+1:
+	btst #0,%d0			/* entry & IND_DESTINATION? */
+	jeq 2f
+	andw %d2,%d0
+	movel %d0,%a2			/* a2 = dst = entry & PAGE_MASK */
+	jra .Lcopy
+
+2:
+	btst #3,%d0			/* entry & IND_SOURCE? */
+	jeq .Lcopy
+
+	andw %d2,%d0
+	movel %d0,%a3			/* a3 = src = entry & PAGE_MASK */
+	movew #PAGE_SIZE/32 - 1,%d0	/* d0 = PAGE_SIZE/32 - 1 */
+3:
+	movel %a3@+,%a2@+		/* *dst++ = *src++ */
+	movel %a3@+,%a2@+		/* *dst++ = *src++ */
+	movel %a3@+,%a2@+		/* *dst++ = *src++ */
+	movel %a3@+,%a2@+		/* *dst++ = *src++ */
+	movel %a3@+,%a2@+		/* *dst++ = *src++ */
+	movel %a3@+,%a2@+		/* *dst++ = *src++ */
+	movel %a3@+,%a2@+		/* *dst++ = *src++ */
+	movel %a3@+,%a2@+		/* *dst++ = *src++ */
+	dbf %d0, 3b
+	jra .Lcopy
+
+.Lflush:
+	/* Flush all caches */
+
+	btst #CPUB_68020,%d1
+	jeq 2f
+
+1:	/* 68020 or 68030 */
+	.chip 68030
+	movec %cacr,%d0
+	orw #0x808,%d0
+	movec %d0,%cacr
+	.chip 68k
+	jra .Lreincarnate
+
+2:
+	btst #CPUB_68030,%d1
+	jne 1b
+
+	btst #CPUB_68040,%d1
+	jeq 4f
+
+3:	/* 68040 or 68060 */
+	.chip 68040
+	nop
+	cpusha %bc
+	nop
+	cinva %bc
+	nop
+	.chip 68k
+	jra .Lreincarnate
+
+4:
+	btst #CPUB_68060,%d1
+	jne 3b
+
+.Lreincarnate:
+	jmp %a1@
+
+relocate_new_kernel_end:
+
+ENTRY(relocate_new_kernel_size)
+	.long relocate_new_kernel_end - relocate_new_kernel
diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h
index 104838f..d6629d4 100644
--- a/include/uapi/linux/kexec.h
+++ b/include/uapi/linux/kexec.h
@@ -18,6 +18,7 @@
  */
 #define KEXEC_ARCH_DEFAULT ( 0 << 16)
 #define KEXEC_ARCH_386     ( 3 << 16)
+#define KEXEC_ARCH_68K     ( 4 << 16)
 #define KEXEC_ARCH_X86_64  (62 << 16)
 #define KEXEC_ARCH_PPC     (20 << 16)
 #define KEXEC_ARCH_PPC64   (21 << 16)
-- 
cgit v0.10.2


From 7bc1e4d8d506462c7d40118196f79a709f3fecfd Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Wed, 21 Aug 2013 22:36:32 +0200
Subject: m68k: Add support to export bootinfo in procfs

Add optional support to export the bootinfo used to boot the kernel in a
"bootinfo" file in procfs.  This is useful with kexec.

This is based on the similar feature for ATAGS on ARM.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 178dffa..dbdd223 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -104,6 +104,13 @@ config KEXEC
 	  interface is strongly in flux, so no good recommendation can be
 	  made.
 
+config BOOTINFO_PROC
+	bool "Export bootinfo in procfs"
+	depends on KEXEC && M68KCLASSIC
+	help
+	  Say Y to export the bootinfo used to boot the kernel in a
+	  "bootinfo" file in procfs.  This is useful with kexec.
+
 menu "Platform setup"
 
 source arch/m68k/Kconfig.cpu
diff --git a/arch/m68k/include/asm/bootinfo.h b/arch/m68k/include/asm/bootinfo.h
index 9edc318..8e21326 100644
--- a/arch/m68k/include/asm/bootinfo.h
+++ b/arch/m68k/include/asm/bootinfo.h
@@ -13,4 +13,16 @@
 
 #include <uapi/asm/bootinfo.h>
 
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_BOOTINFO_PROC
+extern void save_bootinfo(const struct bi_record *bi);
+#else
+static inline void save_bootinfo(const struct bi_record *bi) {}
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+
 #endif /* _M68K_BOOTINFO_H */
diff --git a/arch/m68k/kernel/Makefile b/arch/m68k/kernel/Makefile
index 7ee5f00..2d5d9be 100644
--- a/arch/m68k/kernel/Makefile
+++ b/arch/m68k/kernel/Makefile
@@ -23,4 +23,5 @@ obj-$(CONFIG_PCI) += pcibios.o
 obj-$(CONFIG_HAS_DMA)	+= dma.o
 
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
+obj-$(CONFIG_BOOTINFO_PROC)	+= bootinfo_proc.o
 
diff --git a/arch/m68k/kernel/bootinfo_proc.c b/arch/m68k/kernel/bootinfo_proc.c
new file mode 100644
index 0000000..7ee853e
--- /dev/null
+++ b/arch/m68k/kernel/bootinfo_proc.c
@@ -0,0 +1,80 @@
+/*
+ * Based on arch/arm/kernel/atags_proc.c
+ */
+
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/printk.h>
+#include <linux/proc_fs.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+
+#include <asm/bootinfo.h>
+#include <asm/byteorder.h>
+
+
+static char bootinfo_tmp[1536] __initdata;
+
+static void *bootinfo_copy;
+static size_t bootinfo_size;
+
+static ssize_t bootinfo_read(struct file *file, char __user *buf,
+			  size_t count, loff_t *ppos)
+{
+	return simple_read_from_buffer(buf, count, ppos, bootinfo_copy,
+				       bootinfo_size);
+}
+
+static const struct file_operations bootinfo_fops = {
+	.read = bootinfo_read,
+	.llseek = default_llseek,
+};
+
+void __init save_bootinfo(const struct bi_record *bi)
+{
+	const void *start = bi;
+	size_t size = sizeof(bi->tag);
+
+	while (be16_to_cpu(bi->tag) != BI_LAST) {
+		uint16_t n = be16_to_cpu(bi->size);
+		size += n;
+		bi = (struct bi_record *)((unsigned long)bi + n);
+	}
+
+	if (size > sizeof(bootinfo_tmp)) {
+		pr_err("Cannot save %zu bytes of bootinfo\n", size);
+		return;
+	}
+
+	pr_info("Saving %zu bytes of bootinfo\n", size);
+	memcpy(bootinfo_tmp, start, size);
+	bootinfo_size = size;
+}
+
+static int __init init_bootinfo_procfs(void)
+{
+	/*
+	 * This cannot go into save_bootinfo() because kmalloc and proc don't
+	 * work yet when it is called.
+	 */
+	struct proc_dir_entry *pde;
+
+	if (!bootinfo_size)
+		return -EINVAL;
+
+	bootinfo_copy = kmalloc(bootinfo_size, GFP_KERNEL);
+	if (!bootinfo_copy)
+		return -ENOMEM;
+
+	memcpy(bootinfo_copy, bootinfo_tmp, bootinfo_size);
+
+	pde = proc_create_data("bootinfo", 0400, NULL, &bootinfo_fops, NULL);
+	if (!pde) {
+		kfree(bootinfo_copy);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+arch_initcall(init_bootinfo_procfs);
diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c
index 28abca4..5b8ec4d 100644
--- a/arch/m68k/kernel/setup_mm.c
+++ b/arch/m68k/kernel/setup_mm.c
@@ -146,6 +146,8 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record)
 {
 	uint16_t tag;
 
+	save_bootinfo(record);
+
 	while ((tag = be16_to_cpu(record->tag)) != BI_LAST) {
 		int unknown = 0;
 		const void *data = record->data;
-- 
cgit v0.10.2


From c6188d0f5756e3b20c216483cc7982d097c7b9de Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Thu, 28 Nov 2013 13:57:24 +0100
Subject: m68k/defconfig: Use ext4 for ext2/ext3 file systems

This reduces the kernel image size by ca. 160 KiB.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 04432b7..1f87c07 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -345,10 +345,6 @@ CONFIG_HEARTBEAT=y
 CONFIG_PROC_HARDWARE=y
 CONFIG_AMIGA_BUILTIN_SERIAL=y
 CONFIG_SERIAL_CONSOLE=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index a018fd7..ea5b647 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -302,10 +302,6 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_HEARTBEAT=y
 CONFIG_PROC_HARDWARE=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index fa33639..0c3d280 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -320,10 +320,6 @@ CONFIG_NFBLOCK=y
 CONFIG_NFCON=y
 CONFIG_NFETH=y
 CONFIG_ATARI_DSP56K=m
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index ca310d5..9b6b515 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -294,10 +294,6 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_PROC_HARDWARE=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index aa98958..efffa68 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -304,10 +304,6 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_PROC_HARDWARE=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index ac2c153..73a8565 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -327,10 +327,6 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_PROC_HARDWARE=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 61cdb09..19c7939 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -405,10 +405,6 @@ CONFIG_NFETH=y
 CONFIG_ATARI_DSP56K=m
 CONFIG_AMIGA_BUILTIN_SERIAL=y
 CONFIG_SERIAL_CONSOLE=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index f89613f..81fab00 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -294,10 +294,6 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_PROC_HARDWARE=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index d086acd..df07837 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -294,10 +294,6 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_PROC_HARDWARE=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 3662899..f64c896 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -318,10 +318,6 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_HEARTBEAT=y
 CONFIG_PROC_HARDWARE=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index bb87f17..99bcc60 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -296,10 +296,6 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_PROC_HARDWARE=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index b75a0b1..2023a91 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -296,10 +296,6 @@ CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_PROC_HARDWARE=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
-- 
cgit v0.10.2


From 8a09cec25fa19a3a7e9f21b4186fecc69085a60f Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Sun, 1 Dec 2013 11:14:51 +0100
Subject: m68k/amiga,atari: Fix specifying multiple debug= parameters

Since commit d6713b4091a99fa2af2fabdcd2f3fb97f32ecf2e ("m68k: early
parameter support"), the user can specify multiple debug consoles using the
"debug=" kernel command line parameter.
However, as there's only a single struct console object, which is reused,
it would actually register the same console object multiple times, causing
the following warning:

WARNING: CPU: 0 PID: 0 at kernel/printk/printk.c:2233 register_console+0x36/
console 'debug0' already registered

Make sure to register the console object only once, to avoid the warning.

Note that still only one console (the one corresponding to the last
"debug=" parameter) will be active at the same time, as the .write() method
of the already registered console object is overwritten by a subsequent
"debug=" parameter.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c
index c425fa6..9625b71 100644
--- a/arch/m68k/amiga/config.c
+++ b/arch/m68k/amiga/config.c
@@ -620,6 +620,8 @@ static void amiga_mem_console_write(struct console *co, const char *s,
 
 static int __init amiga_savekmsg_setup(char *arg)
 {
+	bool registered;
+
 	if (!MACH_IS_AMIGA || strcmp(arg, "mem"))
 		return 0;
 
@@ -636,8 +638,10 @@ static int __init amiga_savekmsg_setup(char *arg)
 	savekmsg->magicptr = ZTWO_PADDR(savekmsg);
 	savekmsg->size = 0;
 
+	registered = !!amiga_console_driver.write;
 	amiga_console_driver.write = amiga_mem_console_write;
-	register_console(&amiga_console_driver);
+	if (!registered)
+		register_console(&amiga_console_driver);
 	return 0;
 }
 
@@ -719,11 +723,16 @@ void amiga_serial_gets(struct console *co, char *s, int len)
 
 static int __init amiga_debug_setup(char *arg)
 {
-	if (MACH_IS_AMIGA && !strcmp(arg, "ser")) {
-		/* no initialization required (?) */
-		amiga_console_driver.write = amiga_serial_console_write;
+	bool registered;
+
+	if (!MACH_IS_AMIGA || strcmp(arg, "ser"))
+		return 0;
+
+	/* no initialization required (?) */
+	registered = !!amiga_console_driver.write;
+	amiga_console_driver.write = amiga_serial_console_write;
+	if (!registered)
 		register_console(&amiga_console_driver);
-	}
 	return 0;
 }
 
diff --git a/arch/m68k/atari/debug.c b/arch/m68k/atari/debug.c
index a547ba9..03cb5e0 100644
--- a/arch/m68k/atari/debug.c
+++ b/arch/m68k/atari/debug.c
@@ -287,6 +287,8 @@ static void __init atari_init_midi_port(int cflag)
 
 static int __init atari_debug_setup(char *arg)
 {
+	bool registered;
+
 	if (!MACH_IS_ATARI)
 		return 0;
 
@@ -294,6 +296,7 @@ static int __init atari_debug_setup(char *arg)
 		/* defaults to ser2 for a Falcon and ser1 otherwise */
 		arg = MACH_IS_FALCON ? "ser2" : "ser1";
 
+	registered = !!atari_console_driver.write;
 	if (!strcmp(arg, "ser1")) {
 		/* ST-MFP Modem1 serial port */
 		atari_init_mfp_port(B9600|CS8);
@@ -317,7 +320,7 @@ static int __init atari_debug_setup(char *arg)
 		sound_ym.wd_data = sound_ym.rd_data_reg_sel | 0x20; /* strobe H */
 		atari_console_driver.write = atari_par_console_write;
 	}
-	if (atari_console_driver.write)
+	if (atari_console_driver.write && !registered)
 		register_console(&atari_console_driver);
 
 	return 0;
-- 
cgit v0.10.2


From 27d632d27c4f4f0e9201b38f4ae70bd3050de843 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Mon, 2 Dec 2013 11:08:13 +0100
Subject: m68k/atari: Hide RTC_PORT() macro from rtc-cmos

Rename RTC_PORT() to ATARI_RTC_PORT(), as the rtc-cmos RTC driver uses the
presence of this macro to enable support for the second NVRAM bank, which
Atari doesn't have ("Unable to handle kernel access at virtual address
00ff8965").

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/include/asm/mc146818rtc.h b/arch/m68k/include/asm/mc146818rtc.h
index 9f70a01..05b43bf 100644
--- a/arch/m68k/include/asm/mc146818rtc.h
+++ b/arch/m68k/include/asm/mc146818rtc.h
@@ -10,16 +10,16 @@
 
 #include <asm/atarihw.h>
 
-#define RTC_PORT(x)	(TT_RTC_BAS + 2*(x))
+#define ATARI_RTC_PORT(x)	(TT_RTC_BAS + 2*(x))
 #define RTC_ALWAYS_BCD	0
 
 #define CMOS_READ(addr) ({ \
-atari_outb_p((addr),RTC_PORT(0)); \
-atari_inb_p(RTC_PORT(1)); \
+atari_outb_p((addr), ATARI_RTC_PORT(0)); \
+atari_inb_p(ATARI_RTC_PORT(1)); \
 })
 #define CMOS_WRITE(val, addr) ({ \
-atari_outb_p((addr),RTC_PORT(0)); \
-atari_outb_p((val),RTC_PORT(1)); \
+atari_outb_p((addr), ATARI_RTC_PORT(0)); \
+atari_outb_p((val), ATARI_RTC_PORT(1)); \
 })
 #endif /* CONFIG_ATARI */
 
-- 
cgit v0.10.2


From 545104dd2ba0feb62544284ee1d6c98fe6ef8245 Mon Sep 17 00:00:00 2001
From: Rui Wang <ruiv.wang@gmail.com>
Date: Sun, 8 Dec 2013 12:17:53 +0800
Subject: PCI, AER: Fix severity usage in aer trace event

There's inconsistency between dmesg and the trace event output.
When dmesg says "severity=Corrected", the trace event says
"severity=Fatal". What happens is that HW_EVENT_ERR_CORRECTED is
defined in edac.h:

enum hw_event_mc_err_type {
        HW_EVENT_ERR_CORRECTED,
        HW_EVENT_ERR_UNCORRECTED,
        HW_EVENT_ERR_FATAL,
        HW_EVENT_ERR_INFO,
};

while aer_print_error() uses aer_error_severity_string[] defined as:

static const char *aer_error_severity_string[] = {
        "Uncorrected (Non-Fatal)",
        "Uncorrected (Fatal)",
        "Corrected"
};

In this case dmesg is correct because info->severity is assigned in
aer_isr_one_error() using the definitions in include/linux/ras.h:

Signed-off-by: Rui Wang <rui.y.wang@intel.com>
Acked-by: Ethan Zhao <ethan.kernel@gmail.com>
Link: http://lkml.kernel.org/r/CANVTcTaP18CiGOSEcX5Ch_wPw9mEhkgokfp+d+ZOMFD+Ce4juA@mail.gmail.com
Signed-off-by: Borislav Petkov <bp@suse.de>

diff --git a/include/trace/events/ras.h b/include/trace/events/ras.h
index 88b8783..1c875ad 100644
--- a/include/trace/events/ras.h
+++ b/include/trace/events/ras.h
@@ -5,7 +5,7 @@
 #define _TRACE_AER_H
 
 #include <linux/tracepoint.h>
-#include <linux/edac.h>
+#include <linux/aer.h>
 
 
 /*
@@ -63,10 +63,10 @@ TRACE_EVENT(aer_event,
 
 	TP_printk("%s PCIe Bus Error: severity=%s, %s\n",
 		__get_str(dev_name),
-		__entry->severity == HW_EVENT_ERR_CORRECTED ? "Corrected" :
-			__entry->severity == HW_EVENT_ERR_FATAL ?
-			"Fatal" : "Uncorrected",
-		__entry->severity == HW_EVENT_ERR_CORRECTED ?
+		__entry->severity == AER_CORRECTABLE ? "Corrected" :
+			__entry->severity == AER_FATAL ?
+			"Fatal" : "Uncorrected, non-fatal",
+		__entry->severity == AER_CORRECTABLE ?
 		__print_flags(__entry->status, "|", aer_correctable_errors) :
 		__print_flags(__entry->status, "|", aer_uncorrectable_errors))
 );
-- 
cgit v0.10.2


From a4eb24a49566db77ee999b46603f602a0302f481 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Dec 2013 09:42:56 +0200
Subject: perf script: Fix symoff printing in callchains

The address being used to calculate the offset was the memory address
but the address needed is the address mapped to the dso. i.e. the 'addr'
member of 'struct addr_location'

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1386315778-11633-2-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8a7da6f..c236b38 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1515,6 +1515,8 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
 			node_al = *al;
 
 		while (stack_depth) {
+			u64 addr = 0;
+
 			node = callchain_cursor_current(&callchain_cursor);
 			if (!node)
 				break;
@@ -1525,10 +1527,13 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
 			if (print_ip)
 				printf("%c%16" PRIx64, s, node->ip);
 
+			if (node->map)
+				addr = node->map->map_ip(node->map, node->ip);
+
 			if (print_sym) {
 				printf(" ");
 				if (print_symoffset) {
-					node_al.addr = node->ip;
+					node_al.addr = addr;
 					node_al.map  = node->map;
 					symbol__fprintf_symname_offs(node->sym, &node_al, stdout);
 				} else
-- 
cgit v0.10.2


From 724a371396e8162cc883a40cd8e525dfc7e5f3ff Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Thu, 10 Oct 2013 16:55:57 +0200
Subject: posix-timers: Remove dead thread posix cpu timers caching

When a task is exiting or has exited, its posix cpu timers
don't tick anymore and won't elapse further. It's too late
for them to expire.

So any further call to timer_gettime() on these timers will
return the same remaining expiry time.

The current code optimize this by caching the remaining delta
and storing it where we use to save the absolute expiration time.
This way, the future calls to timer_gettime() won't need to
compute the difference between the absolute expiration time and
the current time anymore.

Now this optimization doesn't seem to bring much value. Computing
the timer remaining delta is not very costly. Fetching the timer
value OTOH can be costly in two ways:

* CPUCLOCK_SCHED read requires to lock the target's rq. But some
optimizations are on the way to make task_sched_runtime() not holding
the rq lock of a non-running target.

* CPUCLOCK_VIRT/CPUCLOCK_PROF read simply consist in fetching
current->utime/current->stime except when the system uses full
dynticks cputime accounting. The latter requires a per task lock
in order to correctly compute user and system time. But once the
target is dead, this lock shouldn't be contended anyway.

All in one this caching doesn't seem to be justified.
Given that it complicates the code significantly for
few wins, let's remove it on single thread timers.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>

diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 79747b7..3b7df86 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -788,7 +788,6 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 {
 	unsigned long long now;
 	struct task_struct *p = timer->it.cpu.task;
-	int clear_dead;
 
 	/*
 	 * Easy part: convert the reload time.
@@ -802,6 +801,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 	}
 
 	if (unlikely(p == NULL)) {
+		WARN_ON_ONCE(CPUCLOCK_PERTHREAD(timer->it_clock));
 		/*
 		 * This task already died and the timer will never fire.
 		 * In this case, expires is actually the dead value.
@@ -817,7 +817,6 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 	 */
 	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
 		cpu_clock_sample(timer->it_clock, p, &now);
-		clear_dead = p->exit_state;
 	} else {
 		read_lock(&tasklist_lock);
 		if (unlikely(p->sighand == NULL)) {
@@ -833,22 +832,20 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 			goto dead;
 		} else {
 			cpu_timer_sample_group(timer->it_clock, p, &now);
-			clear_dead = (unlikely(p->exit_state) &&
-				      thread_group_empty(p));
+			if (unlikely(p->exit_state) && thread_group_empty(p)) {
+				read_unlock(&tasklist_lock);
+				/*
+				 * We've noticed that the thread is dead, but
+				 * not yet reaped.  Take this opportunity to
+				 * drop our task ref.
+				 */
+				clear_dead_task(timer, now);
+				goto dead;
+			}
 		}
 		read_unlock(&tasklist_lock);
 	}
 
-	if (unlikely(clear_dead)) {
-		/*
-		 * We've noticed that the thread is dead, but
-		 * not yet reaped.  Take this opportunity to
-		 * drop our task ref.
-		 */
-		clear_dead_task(timer, now);
-		goto dead;
-	}
-
 	if (now < timer->it.cpu.expires) {
 		sample_to_timespec(timer->it_clock,
 				   timer->it.cpu.expires - now,
@@ -1063,11 +1060,13 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 	struct task_struct *p = timer->it.cpu.task;
 	unsigned long long now;
 
-	if (unlikely(p == NULL))
+	if (unlikely(p == NULL)) {
+		WARN_ON_ONCE(CPUCLOCK_PERTHREAD(timer->it_clock));
 		/*
 		 * The task was cleaned up already, no future firings.
 		 */
 		goto out;
+	}
 
 	/*
 	 * Fetch the current sample and update the timer's expiry time.
@@ -1075,10 +1074,9 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
 		cpu_clock_sample(timer->it_clock, p, &now);
 		bump_cpu_timer(timer, now);
-		if (unlikely(p->exit_state)) {
-			clear_dead_task(timer, now);
+		if (unlikely(p->exit_state))
 			goto out;
-		}
+
 		read_lock(&tasklist_lock); /* arm_timer needs it.  */
 		spin_lock(&p->sighand->siglock);
 	} else {
-- 
cgit v0.10.2


From d430b9173a9a50a83e10d1c70baead3e625b522f Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Thu, 10 Oct 2013 16:55:57 +0200
Subject: posix-timers: Remove dead process posix cpu timers caching

Now that we removed dead thread posix cpu timers caching,
lets remove the dead process wide version. This caching
is similar to the per thread version but it should be even
more rare:

* If the process id dead, we are not reading its timers
status from a thread belonging to its group since they
are all dead. So this caching only concern remote process
timers reads. Now posix cpu timers using itimers or timer_settime()
can't do remote process timers anyway so it's not even clear if there
is actually a user for this caching.

* Unlike per thread timers caching, this only applies to
zombies targets. Buried targets' process wide timers return
0 values. But then again, timer_gettime() can't read remote
process timers, so if the process is dead, there can't be
any reader left anyway.

Then again this caching seem to complicate the code for
corner cases that are probably not worth it. So lets get
rid of it.

Also remove the sample snapshot on dying process timer
that is now useless, as suggested by Kosaki.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>

diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 3b7df86..c5d1ef5 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -453,23 +453,6 @@ void posix_cpu_timers_exit_group(struct task_struct *tsk)
 		       tsk->se.sum_exec_runtime + sig->sum_sched_runtime);
 }
 
-static void clear_dead_task(struct k_itimer *itimer, unsigned long long now)
-{
-	struct cpu_timer_list *timer = &itimer->it.cpu;
-
-	/*
-	 * That's all for this thread or process.
-	 * We leave our residual in expires to be reported.
-	 */
-	put_task_struct(timer->task);
-	timer->task = NULL;
-	if (timer->expires < now) {
-		timer->expires = 0;
-	} else {
-		timer->expires -= now;
-	}
-}
-
 static inline int expires_gt(cputime_t expires, cputime_t new_exp)
 {
 	return expires == 0 || expires > new_exp;
@@ -832,16 +815,6 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 			goto dead;
 		} else {
 			cpu_timer_sample_group(timer->it_clock, p, &now);
-			if (unlikely(p->exit_state) && thread_group_empty(p)) {
-				read_unlock(&tasklist_lock);
-				/*
-				 * We've noticed that the thread is dead, but
-				 * not yet reaped.  Take this opportunity to
-				 * drop our task ref.
-				 */
-				clear_dead_task(timer, now);
-				goto dead;
-			}
 		}
 		read_unlock(&tasklist_lock);
 	}
@@ -1092,14 +1065,8 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 			read_unlock(&tasklist_lock);
 			goto out;
 		} else if (unlikely(p->exit_state) && thread_group_empty(p)) {
-			/*
-			 * We've noticed that the thread is dead, but
-			 * not yet reaped.  Take this opportunity to
-			 * drop our task ref.
-			 */
-			cpu_timer_sample_group(timer->it_clock, p, &now);
-			clear_dead_task(timer, now);
 			read_unlock(&tasklist_lock);
+			/* Optimizations: if the process is dying, no need to rearm */
 			goto out;
 		}
 		spin_lock(&p->sighand->siglock);
-- 
cgit v0.10.2


From e26d70d271ee1a68a925796b411cb0239394c7a1 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Fri, 11 Oct 2013 00:27:19 +0200
Subject: posix-timers: Cleanup reaped target handling

When a timer's target is seen to be buried, for example on calls
to timer_gettime(), the posix cpu timers code behaves a bit
like a garbage collector and releases early the reference to the
task.

Then again, this optimization complicates the code for no much
value: it's up to the user to release the timer and its associated
ressources by calling timer_delete() after it buries the target
tasks.

Remove this to simplify the code.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>

diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index c5d1ef5..dc4355b 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -639,8 +639,6 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	 */
 	if (unlikely(p->sighand == NULL)) {
 		read_unlock(&tasklist_lock);
-		put_task_struct(p);
-		timer->it.cpu.task = NULL;
 		return -ESRCH;
 	}
 
@@ -808,8 +806,6 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 			 * We can't even collect a sample any more.
 			 * Call the timer disarmed, nothing else to do.
 			 */
-			put_task_struct(p);
-			timer->it.cpu.task = NULL;
 			timer->it.cpu.expires = 0;
 			read_unlock(&tasklist_lock);
 			goto dead;
@@ -1059,8 +1055,6 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 			 * The process has been reaped.
 			 * We can't even collect a sample any more.
 			 */
-			put_task_struct(p);
-			timer->it.cpu.task = p = NULL;
 			timer->it.cpu.expires = 0;
 			read_unlock(&tasklist_lock);
 			goto out;
-- 
cgit v0.10.2


From a3222f88fa4f2ebec4632aef527dd2c9a41b997d Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Fri, 11 Oct 2013 00:37:39 +0200
Subject: posix-timers: Remove dead task special case

Now that we've removed all the optimizations that could
result in NULL timer's targets, we can remove all the
associated special case handling.

Also add some warnings on NULL targets to spot any possible
leftover.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>

diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index dc4355b..ab9911b 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -374,27 +374,27 @@ static int posix_cpu_timer_del(struct k_itimer *timer)
 	struct task_struct *p = timer->it.cpu.task;
 	int ret = 0;
 
-	if (likely(p != NULL)) {
-		read_lock(&tasklist_lock);
-		if (unlikely(p->sighand == NULL)) {
-			/*
-			 * We raced with the reaping of the task.
-			 * The deletion should have cleared us off the list.
-			 */
-			BUG_ON(!list_empty(&timer->it.cpu.entry));
-		} else {
-			spin_lock(&p->sighand->siglock);
-			if (timer->it.cpu.firing)
-				ret = TIMER_RETRY;
-			else
-				list_del(&timer->it.cpu.entry);
-			spin_unlock(&p->sighand->siglock);
-		}
-		read_unlock(&tasklist_lock);
+	WARN_ON_ONCE(p == NULL);
 
-		if (!ret)
-			put_task_struct(p);
+	read_lock(&tasklist_lock);
+	if (unlikely(p->sighand == NULL)) {
+		/*
+		 * We raced with the reaping of the task.
+		 * The deletion should have cleared us off the list.
+		 */
+		BUG_ON(!list_empty(&timer->it.cpu.entry));
+	} else {
+		spin_lock(&p->sighand->siglock);
+		if (timer->it.cpu.firing)
+			ret = TIMER_RETRY;
+		else
+			list_del(&timer->it.cpu.entry);
+		spin_unlock(&p->sighand->siglock);
 	}
+	read_unlock(&tasklist_lock);
+
+	if (!ret)
+		put_task_struct(p);
 
 	return ret;
 }
@@ -622,12 +622,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 	unsigned long long old_expires, new_expires, old_incr, val;
 	int ret;
 
-	if (unlikely(p == NULL)) {
-		/*
-		 * Timer refers to a dead task's clock.
-		 */
-		return -ESRCH;
-	}
+	WARN_ON_ONCE(p == NULL);
 
 	new_expires = timespec_to_sample(timer->it_clock, &new->it_value);
 
@@ -770,6 +765,8 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 	unsigned long long now;
 	struct task_struct *p = timer->it.cpu.task;
 
+	WARN_ON_ONCE(p == NULL);
+
 	/*
 	 * Easy part: convert the reload time.
 	 */
@@ -781,18 +778,6 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 		return;
 	}
 
-	if (unlikely(p == NULL)) {
-		WARN_ON_ONCE(CPUCLOCK_PERTHREAD(timer->it_clock));
-		/*
-		 * This task already died and the timer will never fire.
-		 * In this case, expires is actually the dead value.
-		 */
-	dead:
-		sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
-				   &itp->it_value);
-		return;
-	}
-
 	/*
 	 * Sample the clock to take the difference with the expiry time.
 	 */
@@ -807,8 +792,9 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 			 * Call the timer disarmed, nothing else to do.
 			 */
 			timer->it.cpu.expires = 0;
+			sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
+					   &itp->it_value);
 			read_unlock(&tasklist_lock);
-			goto dead;
 		} else {
 			cpu_timer_sample_group(timer->it_clock, p, &now);
 		}
@@ -1029,13 +1015,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 	struct task_struct *p = timer->it.cpu.task;
 	unsigned long long now;
 
-	if (unlikely(p == NULL)) {
-		WARN_ON_ONCE(CPUCLOCK_PERTHREAD(timer->it_clock));
-		/*
-		 * The task was cleaned up already, no future firings.
-		 */
-		goto out;
-	}
+	WARN_ON_ONCE(p == NULL);
 
 	/*
 	 * Fetch the current sample and update the timer's expiry time.
-- 
cgit v0.10.2


From af82eb3c3068877a6b1989796a06b846b1e9e1c3 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Fri, 11 Oct 2013 16:11:43 +0200
Subject: posix-timers: Remove useless clock sample on timers cleanup

a0b2062b0904ef07944c4a6e4d0f88ee44f1e9f2
("posix_timers: fix racy timer delta caching on task exit") forgot
to remove the arguments used for timer caching.

Fix this leftover.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>

diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index ab9911b..e6389f9 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -399,8 +399,7 @@ static int posix_cpu_timer_del(struct k_itimer *timer)
 	return ret;
 }
 
-static void cleanup_timers_list(struct list_head *head,
-				unsigned long long curr)
+static void cleanup_timers_list(struct list_head *head)
 {
 	struct cpu_timer_list *timer, *next;
 
@@ -414,16 +413,11 @@ static void cleanup_timers_list(struct list_head *head,
  * time for later timer_gettime calls to return.
  * This must be called with the siglock held.
  */
-static void cleanup_timers(struct list_head *head,
-			   cputime_t utime, cputime_t stime,
-			   unsigned long long sum_exec_runtime)
+static void cleanup_timers(struct list_head *head)
 {
-
-	cputime_t ptime = utime + stime;
-
-	cleanup_timers_list(head, cputime_to_expires(ptime));
-	cleanup_timers_list(++head, cputime_to_expires(utime));
-	cleanup_timers_list(++head, sum_exec_runtime);
+	cleanup_timers_list(head);
+	cleanup_timers_list(++head);
+	cleanup_timers_list(++head);
 }
 
 /*
@@ -433,24 +427,14 @@ static void cleanup_timers(struct list_head *head,
  */
 void posix_cpu_timers_exit(struct task_struct *tsk)
 {
-	cputime_t utime, stime;
-
 	add_device_randomness((const void*) &tsk->se.sum_exec_runtime,
 						sizeof(unsigned long long));
-	task_cputime(tsk, &utime, &stime);
-	cleanup_timers(tsk->cpu_timers,
-		       utime, stime, tsk->se.sum_exec_runtime);
+	cleanup_timers(tsk->cpu_timers);
 
 }
 void posix_cpu_timers_exit_group(struct task_struct *tsk)
 {
-	struct signal_struct *const sig = tsk->signal;
-	cputime_t utime, stime;
-
-	task_cputime(tsk, &utime, &stime);
-	cleanup_timers(tsk->signal->cpu_timers,
-		       utime + sig->utime, stime + sig->stime,
-		       tsk->se.sum_exec_runtime + sig->sum_sched_runtime);
+	cleanup_timers(tsk->signal->cpu_timers);
 }
 
 static inline int expires_gt(cputime_t expires, cputime_t new_exp)
-- 
cgit v0.10.2


From 33ab0fec33527e8b5ab124cff6aefd4746508e04 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Fri, 11 Oct 2013 17:41:11 +0200
Subject: posix-timers: Consolidate posix_cpu_clock_get()

Consolidate the clock sampling common code used for both local
and remote targets.

Note that this introduces a tiny user ABI change: if a
PID is passed to clock_gettime() along the clockid,
we used to forbid a process wide clock sample when that
PID doesn't belong to a group leader. Now after this patch
we allow process wide clock samples if that PID belongs to
the current task, even if the current task is not the
group leader.

But local process wide clock samples are allowed if PID == 0
(current task) even if the current task is not the group leader.
So in the end this should be no big deal as this actually harmonize
the behaviour when the remote sample is actually a local one.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>

diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index e6389f9..03c5d6c3 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -260,30 +260,43 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
 	return 0;
 }
 
+static int posix_cpu_clock_get_task(struct task_struct *tsk,
+				    const clockid_t which_clock,
+				    struct timespec *tp)
+{
+	int err = -EINVAL;
+	unsigned long long rtn;
+
+	if (CPUCLOCK_PERTHREAD(which_clock)) {
+		if (same_thread_group(tsk, current))
+			err = cpu_clock_sample(which_clock, tsk, &rtn);
+	} else {
+		read_lock(&tasklist_lock);
+
+		if (tsk->sighand && (tsk == current || thread_group_leader(tsk)))
+			err = cpu_clock_sample_group(which_clock, tsk, &rtn);
+
+		read_unlock(&tasklist_lock);
+	}
+
+	if (!err)
+		sample_to_timespec(which_clock, rtn, tp);
+
+	return err;
+}
+
 
 static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
 {
 	const pid_t pid = CPUCLOCK_PID(which_clock);
-	int error = -EINVAL;
-	unsigned long long rtn;
+	int err = -EINVAL;
 
 	if (pid == 0) {
 		/*
 		 * Special case constant value for our own clocks.
 		 * We don't have to do any lookup to find ourselves.
 		 */
-		if (CPUCLOCK_PERTHREAD(which_clock)) {
-			/*
-			 * Sampling just ourselves we can do with no locking.
-			 */
-			error = cpu_clock_sample(which_clock,
-						 current, &rtn);
-		} else {
-			read_lock(&tasklist_lock);
-			error = cpu_clock_sample_group(which_clock,
-						       current, &rtn);
-			read_unlock(&tasklist_lock);
-		}
+		err = posix_cpu_clock_get_task(current, which_clock, tp);
 	} else {
 		/*
 		 * Find the given PID, and validate that the caller
@@ -292,29 +305,12 @@ static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
 		struct task_struct *p;
 		rcu_read_lock();
 		p = find_task_by_vpid(pid);
-		if (p) {
-			if (CPUCLOCK_PERTHREAD(which_clock)) {
-				if (same_thread_group(p, current)) {
-					error = cpu_clock_sample(which_clock,
-								 p, &rtn);
-				}
-			} else {
-				read_lock(&tasklist_lock);
-				if (thread_group_leader(p) && p->sighand) {
-					error =
-					    cpu_clock_sample_group(which_clock,
-							           p, &rtn);
-				}
-				read_unlock(&tasklist_lock);
-			}
-		}
+		if (p)
+			err = posix_cpu_clock_get_task(p, which_clock, tp);
 		rcu_read_unlock();
 	}
 
-	if (error)
-		return error;
-	sample_to_timespec(which_clock, rtn, tp);
-	return 0;
+	return err;
 }
 
 
-- 
cgit v0.10.2


From 50875788a1d4a3f662a27ed13cd05282d835939a Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Fri, 11 Oct 2013 17:41:11 +0200
Subject: posix-timers: Use sighand lock instead of tasklist_lock for task
 clock sample

There is no need for the tasklist_lock just to take a process
wide clock sample.

All we need is to get a coherent sample that doesn't race with
exit() and exec():

* exit() may be concurrently reaping a task and flushing its time

* sighand is unstable under exit() and exec(), and the latter also
  result in group leader that can change

To protect against these, locking the target's sighand is enough.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>

diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 03c5d6c3..71a07699 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -271,12 +271,22 @@ static int posix_cpu_clock_get_task(struct task_struct *tsk,
 		if (same_thread_group(tsk, current))
 			err = cpu_clock_sample(which_clock, tsk, &rtn);
 	} else {
-		read_lock(&tasklist_lock);
+		unsigned long flags;
+		struct sighand_struct *sighand;
 
-		if (tsk->sighand && (tsk == current || thread_group_leader(tsk)))
+		/*
+		 * while_each_thread() is not yet entirely RCU safe,
+		 * keep locking the group while sampling process
+		 * clock for now.
+		 */
+		sighand = lock_task_sighand(tsk, &flags);
+		if (!sighand)
+			return err;
+
+		if (tsk == current || thread_group_leader(tsk))
 			err = cpu_clock_sample_group(which_clock, tsk, &rtn);
 
-		read_unlock(&tasklist_lock);
+		unlock_task_sighand(tsk, &flags);
 	}
 
 	if (!err)
-- 
cgit v0.10.2


From 3d7a1427e4ce545e949e9bccb75d0ca8d941d93c Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Fri, 11 Oct 2013 17:41:11 +0200
Subject: posix-timers: Use sighand lock instead of tasklist_lock on timer
 deletion

Timer deletion doesn't need the tasklist lock.
We need to protect against:

* concurrent access to the lists p->cputime_expires and
  p->sighand->cputime_expires

* task reaping that may also delete the timer list entry

* timer firing

We already hold the timer lock which protects us against concurrent
timer firing.

The rest only need the targets sighand to be locked.
So hold it and drop the use of tasklist_lock there.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>

diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 71a07699..9641958 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -377,27 +377,32 @@ static int posix_cpu_timer_create(struct k_itimer *new_timer)
  */
 static int posix_cpu_timer_del(struct k_itimer *timer)
 {
-	struct task_struct *p = timer->it.cpu.task;
 	int ret = 0;
+	unsigned long flags;
+	struct sighand_struct *sighand;
+	struct task_struct *p = timer->it.cpu.task;
 
 	WARN_ON_ONCE(p == NULL);
 
-	read_lock(&tasklist_lock);
-	if (unlikely(p->sighand == NULL)) {
+	/*
+	 * Protect against sighand release/switch in exit/exec and process/
+	 * thread timer list entry concurrent read/writes.
+	 */
+	sighand = lock_task_sighand(p, &flags);
+	if (unlikely(sighand == NULL)) {
 		/*
 		 * We raced with the reaping of the task.
 		 * The deletion should have cleared us off the list.
 		 */
 		BUG_ON(!list_empty(&timer->it.cpu.entry));
 	} else {
-		spin_lock(&p->sighand->siglock);
 		if (timer->it.cpu.firing)
 			ret = TIMER_RETRY;
 		else
 			list_del(&timer->it.cpu.entry);
-		spin_unlock(&p->sighand->siglock);
+
+		unlock_task_sighand(p, &flags);
 	}
-	read_unlock(&tasklist_lock);
 
 	if (!ret)
 		put_task_struct(p);
-- 
cgit v0.10.2


From e73d84e33f15c099ed1df60437700093cb14e46e Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Fri, 11 Oct 2013 18:56:49 +0200
Subject: posix-timers: Remove remaining uses of tasklist_lock

The remaining uses of tasklist_lock were mostly about synchronizing
against sighand modifications, getting coherent and safe group samples
and also thread/process wide timers list handling.

All of this is already safely synchronizable with the target's
sighand lock. Let's use it on these places instead.

Also update the comments about locking.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>

diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 9641958..d9dc5ed 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -233,7 +233,8 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
 
 /*
  * Sample a process (thread group) clock for the given group_leader task.
- * Must be called with tasklist_lock held for reading.
+ * Must be called with task sighand lock held for safe while_each_thread()
+ * traversal.
  */
 static int cpu_clock_sample_group(const clockid_t which_clock,
 				  struct task_struct *p,
@@ -455,8 +456,7 @@ static inline int expires_gt(cputime_t expires, cputime_t new_exp)
 
 /*
  * Insert the timer on the appropriate list before any timers that
- * expire later.  This must be called with the tasklist_lock held
- * for reading, interrupts disabled and p->sighand->siglock taken.
+ * expire later.  This must be called with the sighand lock held.
  */
 static void arm_timer(struct k_itimer *timer)
 {
@@ -547,7 +547,8 @@ static void cpu_timer_fire(struct k_itimer *timer)
 
 /*
  * Sample a process (thread group) timer for the given group_leader task.
- * Must be called with tasklist_lock held for reading.
+ * Must be called with task sighand lock held for safe while_each_thread()
+ * traversal.
  */
 static int cpu_timer_sample_group(const clockid_t which_clock,
 				  struct task_struct *p,
@@ -610,9 +611,11 @@ static inline void posix_cpu_timer_kick_nohz(void) { }
  * If we return TIMER_RETRY, it's necessary to release the timer's lock
  * and try again.  (This happens when the timer is in the middle of firing.)
  */
-static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
+static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 			       struct itimerspec *new, struct itimerspec *old)
 {
+	unsigned long flags;
+	struct sighand_struct *sighand;
 	struct task_struct *p = timer->it.cpu.task;
 	unsigned long long old_expires, new_expires, old_incr, val;
 	int ret;
@@ -621,14 +624,16 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 
 	new_expires = timespec_to_sample(timer->it_clock, &new->it_value);
 
-	read_lock(&tasklist_lock);
 	/*
-	 * We need the tasklist_lock to protect against reaping that
-	 * clears p->sighand.  If p has just been reaped, we can no
+	 * Protect against sighand release/switch in exit/exec and p->cpu_timers
+	 * and p->signal->cpu_timers read/write in arm_timer()
+	 */
+	sighand = lock_task_sighand(p, &flags);
+	/*
+	 * If p has just been reaped, we can no
 	 * longer get any information about it at all.
 	 */
-	if (unlikely(p->sighand == NULL)) {
-		read_unlock(&tasklist_lock);
+	if (unlikely(sighand == NULL)) {
 		return -ESRCH;
 	}
 
@@ -639,7 +644,6 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 
 	ret = 0;
 	old_incr = timer->it.cpu.incr;
-	spin_lock(&p->sighand->siglock);
 	old_expires = timer->it.cpu.expires;
 	if (unlikely(timer->it.cpu.firing)) {
 		timer->it.cpu.firing = -1;
@@ -696,12 +700,11 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 		 * disable this firing since we are already reporting
 		 * it as an overrun (thanks to bump_cpu_timer above).
 		 */
-		spin_unlock(&p->sighand->siglock);
-		read_unlock(&tasklist_lock);
+		unlock_task_sighand(p, &flags);
 		goto out;
 	}
 
-	if (new_expires != 0 && !(flags & TIMER_ABSTIME)) {
+	if (new_expires != 0 && !(timer_flags & TIMER_ABSTIME)) {
 		new_expires += val;
 	}
 
@@ -715,9 +718,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags,
 		arm_timer(timer);
 	}
 
-	spin_unlock(&p->sighand->siglock);
-	read_unlock(&tasklist_lock);
-
+	unlock_task_sighand(p, &flags);
 	/*
 	 * Install the new reload setting, and
 	 * set up the signal and overrun bookkeeping.
@@ -779,8 +780,16 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
 		cpu_clock_sample(timer->it_clock, p, &now);
 	} else {
-		read_lock(&tasklist_lock);
-		if (unlikely(p->sighand == NULL)) {
+		struct sighand_struct *sighand;
+		unsigned long flags;
+
+		/*
+		 * Protect against sighand release/switch in exit/exec and
+		 * also make timer sampling safe if it ends up calling
+		 * thread_group_cputime().
+		 */
+		sighand = lock_task_sighand(p, &flags);
+		if (unlikely(sighand == NULL)) {
 			/*
 			 * The process has been reaped.
 			 * We can't even collect a sample any more.
@@ -789,11 +798,10 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 			timer->it.cpu.expires = 0;
 			sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
 					   &itp->it_value);
-			read_unlock(&tasklist_lock);
 		} else {
 			cpu_timer_sample_group(timer->it_clock, p, &now);
+			unlock_task_sighand(p, &flags);
 		}
-		read_unlock(&tasklist_lock);
 	}
 
 	if (now < timer->it.cpu.expires) {
@@ -1007,6 +1015,8 @@ static void check_process_timers(struct task_struct *tsk,
  */
 void posix_cpu_timer_schedule(struct k_itimer *timer)
 {
+	struct sighand_struct *sighand;
+	unsigned long flags;
 	struct task_struct *p = timer->it.cpu.task;
 	unsigned long long now;
 
@@ -1021,27 +1031,31 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 		if (unlikely(p->exit_state))
 			goto out;
 
-		read_lock(&tasklist_lock); /* arm_timer needs it.  */
-		spin_lock(&p->sighand->siglock);
+		/* Protect timer list r/w in arm_timer() */
+		sighand = lock_task_sighand(p, &flags);
+		if (!sighand)
+			goto out;
 	} else {
-		read_lock(&tasklist_lock);
-		if (unlikely(p->sighand == NULL)) {
+		/*
+		 * Protect arm_timer() and timer sampling in case of call to
+		 * thread_group_cputime().
+		 */
+		sighand = lock_task_sighand(p, &flags);
+		if (unlikely(sighand == NULL)) {
 			/*
 			 * The process has been reaped.
 			 * We can't even collect a sample any more.
 			 */
 			timer->it.cpu.expires = 0;
-			read_unlock(&tasklist_lock);
 			goto out;
 		} else if (unlikely(p->exit_state) && thread_group_empty(p)) {
-			read_unlock(&tasklist_lock);
+			unlock_task_sighand(p, &flags);
 			/* Optimizations: if the process is dying, no need to rearm */
 			goto out;
 		}
-		spin_lock(&p->sighand->siglock);
 		cpu_timer_sample_group(timer->it_clock, p, &now);
 		bump_cpu_timer(timer, now);
-		/* Leave the tasklist_lock locked for the call below.  */
+		/* Leave the sighand locked for the call below.  */
 	}
 
 	/*
@@ -1049,12 +1063,10 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 	 */
 	BUG_ON(!irqs_disabled());
 	arm_timer(timer);
-	spin_unlock(&p->sighand->siglock);
-	read_unlock(&tasklist_lock);
+	unlock_task_sighand(p, &flags);
 
 	/* Kick full dynticks CPUs in case they need to tick on the new timer */
 	posix_cpu_timer_kick_nohz();
-
 out:
 	timer->it_overrun_last = timer->it_overrun;
 	timer->it_overrun = -1;
-- 
cgit v0.10.2


From 531f64fd6f46a3f2a3edb1b97ecc827c775932c5 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Fri, 11 Oct 2013 17:58:08 +0200
Subject: posix-timers: Convert abuses of BUG_ON to WARN_ON

The posix cpu timers code makes a heavy use of BUG_ON()
but none of these concern fatal issues that require
to stop the machine. So let's just warn the user when
some internal state slips out of our hands.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>

diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index d9dc5ed..3b89464 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -395,7 +395,7 @@ static int posix_cpu_timer_del(struct k_itimer *timer)
 		 * We raced with the reaping of the task.
 		 * The deletion should have cleared us off the list.
 		 */
-		BUG_ON(!list_empty(&timer->it.cpu.entry));
+		WARN_ON_ONCE(!list_empty(&timer->it.cpu.entry));
 	} else {
 		if (timer->it.cpu.firing)
 			ret = TIMER_RETRY;
@@ -640,7 +640,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 	/*
 	 * Disarm any old timer after extracting its expiry time.
 	 */
-	BUG_ON(!irqs_disabled());
+	WARN_ON_ONCE(!irqs_disabled());
 
 	ret = 0;
 	old_incr = timer->it.cpu.incr;
@@ -1061,7 +1061,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 	/*
 	 * Now re-arm for the new expiry time.
 	 */
-	BUG_ON(!irqs_disabled());
+	WARN_ON_ONCE(!irqs_disabled());
 	arm_timer(timer);
 	unlock_task_sighand(p, &flags);
 
@@ -1150,7 +1150,7 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 	struct k_itimer *timer, *next;
 	unsigned long flags;
 
-	BUG_ON(!irqs_disabled());
+	WARN_ON_ONCE(!irqs_disabled());
 
 	/*
 	 * The fast path checks that there are no expired thread or thread
@@ -1217,7 +1217,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 {
 	unsigned long long now;
 
-	BUG_ON(clock_idx == CPUCLOCK_SCHED);
+	WARN_ON_ONCE(clock_idx == CPUCLOCK_SCHED);
 	cpu_timer_sample_group(clock_idx, tsk, &now);
 
 	if (oldval) {
-- 
cgit v0.10.2


From cc8fae1d81648e85587f5d18b4f93e0b771fb02d Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 6 Dec 2013 09:42:57 +0200
Subject: perf script: Add an option to print the source line number

Add field 'srcline' that displays the source file name and line number
associated with the sample ip.  The information displayed is the same as
from addr2line.

 $ perf script -f comm,tid,pid,time,ip,sym,dso,symoff,srcline
            grep 10701/10701 2497321.421013:  ffffffff81043ffa native_write_msr_safe+0xa ([kernel.kallsyms])
  /usr/src/debug/kernel-3.9.fc17/linux-3.9.10-100.fc17.x86_64/arch/x86/include/asm/msr.h:95
            grep 10701/10701 2497321.421984:  ffffffff8165b6b3 _raw_spin_lock+0x13 ([kernel.kallsyms])
  /usr/src/debug/kernel-3.9.fc17/linux-3.9.10-100.fc17.x86_64/arch/x86/include/asm/spinlock.h:54
            grep 10701/10701 2497321.421990:  ffffffff810b64b3 tick_sched_timer+0x53 ([kernel.kallsyms])
  /usr/src/debug/kernel-3.9.fc17/linux-3.9.10-100.fc17.x86_64/kernel/time/tick-sched.c:840
            grep 10701/10701 2497321.421992:  ffffffff8106f63f run_timer_softirq+0x2f ([kernel.kallsyms])
  /usr/src/debug/kernel-3.9.fc17/linux-3.9.10-100.fc17.x86_64/kernel/timer.c:1372

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1386315778-11633-3-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index cfdbb1e..c2a5071 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -115,7 +115,7 @@ OPTIONS
 -f::
 --fields::
         Comma separated list of fields to print. Options are:
-        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff.
+        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -f sw:comm,tid,time,ip,sym  and -f trace:time,cpu,trace
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 4484886..7a571fb 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -43,6 +43,7 @@ enum perf_output_field {
 	PERF_OUTPUT_DSO             = 1U << 9,
 	PERF_OUTPUT_ADDR            = 1U << 10,
 	PERF_OUTPUT_SYMOFFSET       = 1U << 11,
+	PERF_OUTPUT_SRCLINE         = 1U << 12,
 };
 
 struct output_option {
@@ -61,6 +62,7 @@ struct output_option {
 	{.str = "dso",   .field = PERF_OUTPUT_DSO},
 	{.str = "addr",  .field = PERF_OUTPUT_ADDR},
 	{.str = "symoff", .field = PERF_OUTPUT_SYMOFFSET},
+	{.str = "srcline", .field = PERF_OUTPUT_SRCLINE},
 };
 
 /* default set to maintain compatibility with current format */
@@ -210,6 +212,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		       "to DSO.\n");
 		return -EINVAL;
 	}
+	if (PRINT_FIELD(SRCLINE) && !PRINT_FIELD(IP)) {
+		pr_err("Display of source line number requested but sample IP is not\n"
+		       "selected. Hence, no address to lookup the source line number.\n");
+		return -EINVAL;
+	}
 
 	if ((PRINT_FIELD(PID) || PRINT_FIELD(TID)) &&
 		perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID",
@@ -245,6 +252,9 @@ static void set_print_ip_opts(struct perf_event_attr *attr)
 
 	if (PRINT_FIELD(SYMOFFSET))
 		output[type].print_ip_opts |= PRINT_IP_OPT_SYMOFFSET;
+
+	if (PRINT_FIELD(SRCLINE))
+		output[type].print_ip_opts |= PRINT_IP_OPT_SRCLINE;
 }
 
 /*
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index ef5bc91..9b9bd71 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -11,6 +11,7 @@
 #include "strlist.h"
 #include "vdso.h"
 #include "build-id.h"
+#include "util.h"
 #include <linux/string.h>
 
 const char *map_type__name[MAP__NR_TYPES] = {
@@ -252,6 +253,22 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp)
 	return fprintf(fp, "%s", dsoname);
 }
 
+int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
+			 FILE *fp)
+{
+	char *srcline;
+	int ret = 0;
+
+	if (map && map->dso) {
+		srcline = get_srcline(map->dso,
+				      map__rip_2objdump(map, addr));
+		if (srcline != SRCLINE_UNKNOWN)
+			ret = fprintf(fp, "%s%s", prefix, srcline);
+		free_srcline(srcline);
+	}
+	return ret;
+}
+
 /**
  * map__rip_2objdump - convert symbol start address to objdump address.
  * @map: memory map
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index e4e259c..18068c6 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -103,6 +103,8 @@ struct map *map__clone(struct map *map);
 int map__overlap(struct map *l, struct map *r);
 size_t map__fprintf(struct map *map, FILE *fp);
 size_t map__fprintf_dsoname(struct map *map, FILE *fp);
+int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
+			 FILE *fp);
 
 int map__load(struct map *map, symbol_filter_t filter);
 struct symbol *map__find_symbol(struct map *map,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index c236b38..e748f29 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1497,6 +1497,7 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
 	int print_dso = print_opts & PRINT_IP_OPT_DSO;
 	int print_symoffset = print_opts & PRINT_IP_OPT_SYMOFFSET;
 	int print_oneline = print_opts & PRINT_IP_OPT_ONELINE;
+	int print_srcline = print_opts & PRINT_IP_OPT_SRCLINE;
 	char s = print_oneline ? ' ' : '\t';
 
 	if (symbol_conf.use_callchain && sample->callchain) {
@@ -1546,6 +1547,10 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
 				printf(")");
 			}
 
+			if (print_srcline)
+				map__fprintf_srcline(node->map, addr, "\n  ",
+						     stdout);
+
 			if (!print_oneline)
 				printf("\n");
 
@@ -1575,6 +1580,9 @@ next:
 			map__fprintf_dsoname(al->map, stdout);
 			printf(")");
 		}
+
+		if (print_srcline)
+			map__fprintf_srcline(al->map, al->addr, "\n  ", stdout);
 	}
 }
 
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 004d3e8..2a3955e 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -45,6 +45,7 @@ struct perf_session {
 #define PRINT_IP_OPT_DSO		(1<<2)
 #define PRINT_IP_OPT_SYMOFFSET	(1<<3)
 #define PRINT_IP_OPT_ONELINE	(1<<4)
+#define PRINT_IP_OPT_SRCLINE	(1<<5)
 
 struct perf_tool;
 
-- 
cgit v0.10.2


From 53653d70a0784a997748cc9e315ddf19d310e812 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 9 Dec 2013 15:18:40 +0200
Subject: perf record: Fix display of incorrect mmap pages

'mmap_pages' is 'unsigned int' not 'int' e.g.

  perf record -m2147483648 uname
  Permission error mapping pages.
  Consider increasing /proc/sys/kernel/perf_event_mlock_kb,
  or try again with a smaller value of -m/--mmap_pages.
  (current value: -2147483648)

Fixed:

  perf record -m2147483648 uname
  Permission error mapping pages.
  Consider increasing /proc/sys/kernel/perf_event_mlock_kb,
  or try again with a smaller value of -m/--mmap_pages.
  (current value: 2147483648)

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1386595120-22978-5-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index d93e2ee..c1c1200 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -224,7 +224,7 @@ try_again:
 			       "Consider increasing "
 			       "/proc/sys/kernel/perf_event_mlock_kb,\n"
 			       "or try again with a smaller value of -m/--mmap_pages.\n"
-			       "(current value: %d)\n", opts->mmap_pages);
+			       "(current value: %u)\n", opts->mmap_pages);
 			rc = -errno;
 		} else {
 			pr_err("failed to mmap with %d (%s)\n", errno, strerror(errno));
-- 
cgit v0.10.2


From 2bcab6c146fde0d0286b132068111f98b6217460 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 9 Dec 2013 15:18:37 +0200
Subject: perf evlist: Remove unnecessary parentheses

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1386595120-22978-2-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 7bb6ee1..4d0945c 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -732,7 +732,7 @@ static long parse_pages_arg(const char *str, unsigned long min,
 			return -EINVAL;
 	}
 
-	if ((pages == 0) && (min == 0)) {
+	if (pages == 0 && min == 0) {
 		/* leave number of pages at 0 */
 	} else if (pages < (1UL << 31) && !is_power_of_2(pages)) {
 		/* round pages up to next power of 2 */
-- 
cgit v0.10.2


From f5ae9c424e4c80c44e9ab7e5ff4a6b79490c23be Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 9 Dec 2013 15:18:38 +0200
Subject: perf evlist: Fix max mmap_pages

'SIZE_MAX / page_size' is an upper limit for the maximum number of mmap
pages, not a lower limit.  Change the condition accordingly.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1386595120-22978-3-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 4d0945c..98ec96b 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -754,7 +754,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
 	unsigned long max = UINT_MAX;
 	long pages;
 
-	if (max < SIZE_MAX / page_size)
+	if (max > SIZE_MAX / page_size)
 		max = SIZE_MAX / page_size;
 
 	pages = parse_pages_arg(str, 1, max);
-- 
cgit v0.10.2


From 1dbfa9387b397f2c4b8c65411b3e3fdf9284d2b1 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 9 Dec 2013 15:18:39 +0200
Subject: perf evlist: Fix mmap pages rounding to power of 2

'next_pow2()' only works for 'unsigned int' but the argument is
'unsigned long'.  Checking for values less than (1 << 31) ensures that
'next_pow2()' is not passed a value out of range but lets anything else
go through unvalidated.

As a result mmap_pages of zero is used e.g.

  perf record -v -m2147483649 uname
  mmap size 0B
  failed to mmap with 22 (Invalid argument)

Fixed:

  perf record -m2147483649 uname
  rounding mmap pages size to 17592186044416 bytes (4294967296 pages)
  Invalid argument for --mmap_pages/-m

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1386595120-22978-4-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 98ec96b..af25055 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -734,9 +734,11 @@ static long parse_pages_arg(const char *str, unsigned long min,
 
 	if (pages == 0 && min == 0) {
 		/* leave number of pages at 0 */
-	} else if (pages < (1UL << 31) && !is_power_of_2(pages)) {
+	} else if (!is_power_of_2(pages)) {
 		/* round pages up to next power of 2 */
-		pages = next_pow2(pages);
+		pages = next_pow2_l(pages);
+		if (!pages)
+			return -EINVAL;
 		pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n",
 			pages * page_size, pages);
 	}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index adb39f2..659abf3 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -73,6 +73,7 @@
 #include <sys/ttydefaults.h>
 #include <lk/debugfs.h>
 #include <termios.h>
+#include <linux/bitops.h>
 
 extern const char *graph_line;
 extern const char *graph_dotted_line;
@@ -281,6 +282,17 @@ static inline unsigned next_pow2(unsigned x)
 	return 1ULL << (32 - __builtin_clz(x - 1));
 }
 
+static inline unsigned long next_pow2_l(unsigned long x)
+{
+#if BITS_PER_LONG == 64
+	if (x <= (1UL << 31))
+		return next_pow2(x);
+	return (unsigned long)next_pow2(x >> 32) << 32;
+#else
+	return next_pow2(x);
+#endif
+}
+
 size_t hex_width(u64 v);
 int hex2u64(const char *ptr, u64 *val);
 
-- 
cgit v0.10.2


From 100b907350c87aa1f3b5dbd95bac3ad5aad3e108 Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Mon, 9 Dec 2013 12:15:11 -0500
Subject: perf kvm: Introduce option -v for perf kvm command.

As there is no -v option for perf kvm, the all debug message for perf
kvm will nerver be printed out to user.

Example:
	# perf kvm --guestmount /tmp/guestmount/ record -a
	Not enough memory for reading perf file header

It is confusing message for newbies such as me. With this patch applied,
we can use -v option to get the detail.

Example:
	# perf kvm --guestmount /tmp/guestmount/ record -a -v
	Can't access file /tmp/guestmount//15069/proc/kallsyms
	Not enough memory for reading perf file header

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Cc: David Ahern <dsahern@gmail.com>
Link: http://lkml.kernel.org/r/1386609311-23889-1-git-send-email-yangds.fnst@cn.fujitsu.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index 96a9a1d..52276a6 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -10,9 +10,9 @@ SYNOPSIS
 [verse]
 'perf kvm' [--host] [--guest] [--guestmount=<path>
 	[--guestkallsyms=<path> --guestmodules=<path> | --guestvmlinux=<path>]]
-	{top|record|report|diff|buildid-list}
+	{top|record|report|diff|buildid-list} [<options>]
 'perf kvm' [--host] [--guest] [--guestkallsyms=<path> --guestmodules=<path>
-	| --guestvmlinux=<path>] {top|record|report|diff|buildid-list|stat}
+	| --guestvmlinux=<path>] {top|record|report|diff|buildid-list|stat} [<options>]
 'perf kvm stat [record|report|live] [<options>]
 
 DESCRIPTION
@@ -93,6 +93,9 @@ OPTIONS
 	kernel module information. Users copy it out from guest os.
 --guestvmlinux=<path>::
 	Guest os kernel vmlinux.
+-v::
+--verbose::
+	Be more verbose (show counter open errors, etc).
 
 STAT REPORT OPTIONS
 -------------------
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index f8bf5f2..d9cc0e3 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1690,6 +1690,8 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
 			   "file", "file saving guest os /proc/kallsyms"),
 		OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules,
 			   "file", "file saving guest os /proc/modules"),
+		OPT_INCR('v', "verbose", &verbose,
+			    "be more verbose (show counter open errors, etc)"),
 		OPT_END()
 	};
 
-- 
cgit v0.10.2


From 476b3a865f8a3734f74cf659cfa510856a105b1a Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Mon, 9 Dec 2013 18:47:03 -0500
Subject: perf kvm: Fix bug in 'stat report'

When we use perf kvm record-report, there is a bug in report subcommand.

Example:
	# perf kvm stat record -a sleep 1
	[ perf record: Woken up 1 times to write data ]
	[ perf record: Captured and wrote 0.678 MB perf.data.guest (~29641 samples) ]
	# perf kvm stat report
	failed to open perf.data: No such file or directory  (try 'perf record' first)
	Initializing perf session failed

This bug was introduced by f5fc14124.

+       struct perf_data_file file = {
+               .path = input_name,
+               .mode = PERF_DATA_MODE_READ,
+       };

        kvm->tool = eops;
-       kvm->session = perf_session__new(kvm->file_name, O_RDONLY, 0, false,
-                                        &kvm->tool);
+       kvm->session = perf_session__new(&file, false, &kvm->tool);

It changed the path from kvm->file_name to input_name, this patch change the path back to
'kvm->file_name', then it works well.

Verification:
	# perf kvm stat record -a sleep 1
	[ perf record: Woken up 1 times to write data ]
	[ perf record: Captured and wrote 0.807 MB perf.data.guest (~35264 samples) ]
	# perf kvm stat report

	Analyze events for all VCPUs:

		     VM-EXIT    Samples  Samples%     Time%   Min Time   Max Time         Avg time

	       EPT_VIOLATION        200    32.79%     1.25%        0us    12064us     62.35us ( +-  96.74% )
	       EPT_MISCONFIG        134    21.97%     0.21%        0us       35us     15.25us ( +-   4.14% )
	       EXCEPTION_NMI         96    15.74%     0.02%        0us       11us      1.95us ( +-   9.81% )
		 APIC_ACCESS         79    12.95%     0.02%        0us       13us      2.94us ( +-  11.20% )
			 HLT         65    10.66%    98.47%        0us    16706us  15084.86us ( +-   1.89% )
	      IO_INSTRUCTION         27     4.43%     0.02%        0us       29us      6.42us ( +-  15.53% )
	  EXTERNAL_INTERRUPT          5     0.82%     0.01%        0us       77us     23.65us ( +-  57.90% )
	 TPR_BELOW_THRESHOLD          4     0.66%     0.00%        0us        1us      1.22us ( +-   4.36% )

	Total Samples:610, Total events handled time:995745.54us.

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Link: http://lkml.kernel.org/r/1386632823-17539-1-git-send-email-yangds.fnst@cn.fujitsu.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index d9cc0e3..c2e5d56 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1232,7 +1232,7 @@ static int read_events(struct perf_kvm_stat *kvm)
 		.ordered_samples	= true,
 	};
 	struct perf_data_file file = {
-		.path = input_name,
+		.path = kvm->file_name,
 		.mode = PERF_DATA_MODE_READ,
 	};
 
-- 
cgit v0.10.2


From f113bee01956d4a2efde461443b09ab1020f4b17 Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Mon, 9 Dec 2013 17:47:47 -0500
Subject: perf archive: Remove duplicated 'runs' in man page

Two 'runs' here breaks the sentence in Description of 'perf archive'
command.

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Link: http://lkml.kernel.org/r/78a15a9f4f500b6074a1e25917d6e8251f894628.1386629050.git.yangds.fnst@cn.fujitsu.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-archive.txt b/tools/perf/Documentation/perf-archive.txt
index 5032a14..ac6ecbb 100644
--- a/tools/perf/Documentation/perf-archive.txt
+++ b/tools/perf/Documentation/perf-archive.txt
@@ -12,9 +12,9 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-This command runs runs perf-buildid-list --with-hits, and collects the files
-with the buildids found so that analysis of perf.data contents can be possible
-on another machine.
+This command runs perf-buildid-list --with-hits, and collects the files with the
+buildids found so that analysis of perf.data contents can be possible on another
+machine.
 
 
 SEE ALSO
-- 
cgit v0.10.2


From 6f1d0c866261ec1e42850b2bf760484c100b6dd6 Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Mon, 9 Dec 2013 17:47:48 -0500
Subject: perf annotate: Fix typo

A typo in comment of builtin-annotate.c about 'that'.

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Link: http://lkml.kernel.org/r/46cb069a4ce21141057a07c0b50baa9968e3228c.1386629050.git.yangds.fnst@cn.fujitsu.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 4087ab1..6fd52c8 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -373,7 +373,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	if (argc) {
 		/*
-		 * Special case: if there's an argument left then assume tha
+		 * Special case: if there's an argument left then assume that
 		 * it's a symbol filter:
 		 */
 		if (argc > 1)
-- 
cgit v0.10.2


From e1a2b174dbbe08dce12bde9f05f64dbbae652bed Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Fri, 6 Dec 2013 17:25:51 -0500
Subject: perf kvm: Move code to generate filename for perf-kvm to function.

The code in builtin-kvm.c to generate filename for perf-kvm is useful to
other command such as builtin-diff.

This patch move the related code form builtin-kvm.c to util/util.c and
wrap them in a function named get_filename_for_perf_kvm.

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Link: http://lkml.kernel.org/r/5e09a5c47e8a495e888cbdc65a6fafb2c950f529.1386368672.git.yangds.fnst@cn.fujitsu.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index c2e5d56..c6fa3cb 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1713,12 +1713,7 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
 		perf_guest = 1;
 
 	if (!file_name) {
-		if (perf_host && !perf_guest)
-			file_name = strdup("perf.data.host");
-		else if (!perf_host && perf_guest)
-			file_name = strdup("perf.data.guest");
-		else
-			file_name = strdup("perf.data.kvm");
+		file_name = get_filename_for_perf_kvm();
 
 		if (!file_name) {
 			pr_err("Failed to allocate memory for filename\n");
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index bae8756..4a57609 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -482,3 +482,17 @@ int filename__read_str(const char *filename, char **buf, size_t *sizep)
 	close(fd);
 	return err;
 }
+
+const char *get_filename_for_perf_kvm(void)
+{
+	const char *filename;
+
+	if (perf_host && !perf_guest)
+		filename = strdup("perf.data.host");
+	else if (!perf_host && perf_guest)
+		filename = strdup("perf.data.guest");
+	else
+		filename = strdup("perf.data.kvm");
+
+	return filename;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 659abf3..0171213 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -321,4 +321,6 @@ void free_srcline(char *srcline);
 
 int filename__read_int(const char *filename, int *value);
 int filename__read_str(const char *filename, char **buf, size_t *sizep);
+
+const char *get_filename_for_perf_kvm(void);
 #endif /* GIT_COMPAT_UTIL_H */
-- 
cgit v0.10.2


From d8d9608fdd19f85a524db0a41bc2def5c88cbdd0 Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Fri, 6 Dec 2013 17:25:52 -0500
Subject: perf kvm: Make perf kvm diff support --guestmount.

In manpage of perf-kvm, --guestmount is supported by diff command, but
it does not work well.

This patch change the extend the checking in buildid-diff from
guestkallsyms or guestmodules to perf_guest. Then this checking can
cover the all cases perf kvm is used for.

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Link: http://lkml.kernel.org/r/72857ed89642e0633f5e88f7e7abbc9645359e8e.1386368672.git.yangds.fnst@cn.fujitsu.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 3b67ea2..2a85cc9 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -1000,8 +1000,7 @@ static int data_init(int argc, const char **argv)
 			data__files_cnt = argc;
 			use_default = false;
 		}
-	} else if (symbol_conf.default_guest_vmlinux_name ||
-		   symbol_conf.default_guest_kallsyms) {
+	} else if (perf_guest) {
 		defaults[0] = "perf.data.host";
 		defaults[1] = "perf.data.guest";
 	}
-- 
cgit v0.10.2


From 4f24416331e9a507e953e90d4534e9a9802cbc12 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 9 Dec 2013 14:34:00 +0900
Subject: tools lib traceevent: Get rid of malloc_or_die() in
 pevent_filter_alloc()

It returns NULL when allocation fails so the users should check the
return value from now on.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386567251-22751-4-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 2500e75..b3a61d4 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -182,7 +182,10 @@ struct event_filter *pevent_filter_alloc(struct pevent *pevent)
 {
 	struct event_filter *filter;
 
-	filter = malloc_or_die(sizeof(*filter));
+	filter = malloc(sizeof(*filter));
+	if (filter == NULL)
+		return NULL;
+
 	memset(filter, 0, sizeof(*filter));
 	filter->pevent = pevent;
 	pevent_ref(pevent);
-- 
cgit v0.10.2


From 234520d3fbe43ef72268c4959f85ae326459378c Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 9 Dec 2013 14:34:04 +0900
Subject: tools lib traceevent: Get rid of malloc_or_die() in add_event()

Make it return error value since its only caller find_event() now can
handle allocation error properly.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386567251-22751-8-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index b3a61d4..2b73abf 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -245,15 +245,19 @@ static void free_arg(struct filter_arg *arg)
 	free(arg);
 }
 
-static void add_event(struct event_list **events,
+static int add_event(struct event_list **events,
 		      struct event_format *event)
 {
 	struct event_list *list;
 
-	list = malloc_or_die(sizeof(*list));
+	list = malloc(sizeof(*list));
+	if (list == NULL)
+		return -1;
+
 	list->next = *events;
 	*events = list;
 	list->event = event;
+	return 0;
 }
 
 static int event_match(struct event_format *event,
@@ -276,6 +280,7 @@ find_event(struct pevent *pevent, struct event_list **events,
 	regex_t ereg;
 	regex_t sreg;
 	int match = 0;
+	int fail = 0;
 	char *reg;
 	int ret;
 	int i;
@@ -310,7 +315,10 @@ find_event(struct pevent *pevent, struct event_list **events,
 		event = pevent->events[i];
 		if (event_match(event, sys_name ? &sreg : NULL, &ereg)) {
 			match = 1;
-			add_event(events, event);
+			if (add_event(events, event) < 0) {
+				fail = 1;
+				break;
+			}
 		}
 	}
 
@@ -320,6 +328,8 @@ find_event(struct pevent *pevent, struct event_list **events,
 
 	if (!match)
 		return -1;
+	if (fail)
+		return -2;
 
 	return 0;
 }
-- 
cgit v0.10.2


From 2036fcd1c7ce455424c11bdb1c8a2ac906430e2f Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 9 Dec 2013 14:34:05 +0900
Subject: tools lib traceevent: Get rid of die() in create_arg_item()

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386567251-22751-9-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 2b73abf..53e48eb 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -362,8 +362,11 @@ create_arg_item(struct event_format *event, const char *token,
 		arg->value.type =
 			type == EVENT_DQUOTE ? FILTER_STRING : FILTER_CHAR;
 		arg->value.str = strdup(token);
-		if (!arg->value.str)
-			die("malloc string");
+		if (!arg->value.str) {
+			free_arg(arg);
+			show_error(error_str, "failed to allocate string filter arg");
+			return NULL;
+		}
 		break;
 	case EVENT_ITEM:
 		/* if it is a number, then convert it */
-- 
cgit v0.10.2


From 28942c87e5e907f591d77547203e86ad1089b499 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 9 Dec 2013 14:34:08 +0900
Subject: tools lib traceevent: Get rid of malloc_or_die() in
 pevent_filter_add_filter_str()

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386567251-22751-12-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 53e48eb..a4d5bb2 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -1226,7 +1226,13 @@ int pevent_filter_add_filter_str(struct event_filter *filter,
 		else
 			len = strlen(filter_str);
 
-		this_event = malloc_or_die(len + 1);
+		this_event = malloc(len + 1);
+		if (this_event == NULL) {
+			show_error(error_str, "Memory allocation failure");
+			/* This can only happen when events is NULL, but still */
+			free_events(events);
+			return -1;
+		}
 		memcpy(this_event, filter_str, len);
 		this_event[len] = 0;
 
-- 
cgit v0.10.2


From 7ef2e813476273ac9c9138f002d8f4cb28e5adad Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 9 Dec 2013 14:34:09 +0900
Subject: tools lib traceevent: Get rid of die() in
 pevent_filter_clear_trivial()

Change the function signature to return error code and not call die()
anymore.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386567251-22751-13-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 620c27a..6e23f19 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -860,7 +860,7 @@ int pevent_event_filtered(struct event_filter *filter,
 
 void pevent_filter_reset(struct event_filter *filter);
 
-void pevent_filter_clear_trivial(struct event_filter *filter,
+int pevent_filter_clear_trivial(struct event_filter *filter,
 				 enum filter_trivial_type type);
 
 void pevent_filter_free(struct event_filter *filter);
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index a4d5bb2..ab402fb 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -1504,8 +1504,10 @@ int pevent_update_trivial(struct event_filter *dest, struct event_filter *source
  * @type: remove only true, false, or both
  *
  * Removes filters that only contain a TRUE or FALES boolean arg.
+ *
+ * Returns 0 on success and -1 if there was a problem.
  */
-void pevent_filter_clear_trivial(struct event_filter *filter,
+int pevent_filter_clear_trivial(struct event_filter *filter,
 				 enum filter_trivial_type type)
 {
 	struct filter_type *filter_type;
@@ -1514,13 +1516,15 @@ void pevent_filter_clear_trivial(struct event_filter *filter,
 	int i;
 
 	if (!filter->filters)
-		return;
+		return 0;
 
 	/*
 	 * Two steps, first get all ids with trivial filters.
 	 *  then remove those ids.
 	 */
 	for (i = 0; i < filter->filters; i++) {
+		int *new_ids;
+
 		filter_type = &filter->event_filters[i];
 		if (filter_type->filter->type != FILTER_ARG_BOOLEAN)
 			continue;
@@ -1535,19 +1539,24 @@ void pevent_filter_clear_trivial(struct event_filter *filter,
 			break;
 		}
 
-		ids = realloc(ids, sizeof(*ids) * (count + 1));
-		if (!ids)
-			die("Can't allocate ids");
+		new_ids = realloc(ids, sizeof(*ids) * (count + 1));
+		if (!new_ids) {
+			free(ids);
+			return -1;
+		}
+
+		ids = new_ids;
 		ids[count++] = filter_type->event_id;
 	}
 
 	if (!count)
-		return;
+		return 0;
 
 	for (i = 0; i < count; i++)
 		pevent_filter_remove_event(filter, ids[i]);
 
 	free(ids);
+	return 0;
 }
 
 /**
-- 
cgit v0.10.2


From f6f7ee9af7554e4d167ccd0ffe7cb8da0aa954f9 Mon Sep 17 00:00:00 2001
From: Fengguang Wu <fengguang.wu@intel.com>
Date: Thu, 10 Oct 2013 11:08:33 -0700
Subject: rcu: Fix coccinelle warnings

This commit fixes the following coccinelle warning:

kernel/rcu/tree.c:712:9-10: WARNING: return of 0/1 in function
'rcu_lockdep_current_cpu_online' with return type bool

Return statements in functions returning bool should use
 true/false instead of 1/0.
 Generated by: coccinelle/misc/boolreturn.cocci

Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 3049950..f8c0299 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -725,7 +725,7 @@ bool rcu_lockdep_current_cpu_online(void)
 	bool ret;
 
 	if (in_nmi())
-		return 1;
+		return true;
 	preempt_disable();
 	rdp = this_cpu_ptr(&rcu_sched_data);
 	rnp = rdp->mynode;
-- 
cgit v0.10.2


From 04f34650ca5e8445aae0ab3e0ff6704f141150a8 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 16 Oct 2013 08:39:10 -0700
Subject: rcu: Fix CONFIG_RCU_FANOUT_EXACT for odd fanout/leaf values

Each element of the rcu_state structure's ->levelspread[] array
is intended to contain the per-level fanout, where the zero-th
element corresponds to the root of the rcu_node tree, and the last
element corresponds to the leaves.  In the CONFIG_RCU_FANOUT_EXACT
case, this means that the last element should be filled in
from CONFIG_RCU_FANOUT_LEAF (or from the rcu_fanout_leaf boot
parameter, if provided) and that the remaining elements should
be filled in from CONFIG_RCU_FANOUT.  Unfortunately, the current
code in rcu_init_levelspread() takes the opposite approach, placing
CONFIG_RCU_FANOUT_LEAF in the zero-th element and CONFIG_RCU_FANOUT in
the remaining elements.

For typical power-of-two values, this generates odd but functional
rcu_node trees.  However, other values, for example CONFIG_RCU_FANOUT=3
and CONFIG_RCU_FANOUT_LEAF=2, generate trees that can leave some CPUs
out of the grace-period computation, resulting in too-short grace periods
and therefore a broken RCU implementation.

This commit therefore fixes rcu_init_levelspread() to set the last
->levelspread[] array element from CONFIG_RCU_FANOUT_LEAF and the
remaining elements from CONFIG_RCU_FANOUT, thus generating the
intended rcu_node trees.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index f8c0299..db1a9fd 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3259,9 +3259,9 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp)
 {
 	int i;
 
-	for (i = rcu_num_lvls - 1; i > 0; i--)
+	rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
+	for (i = rcu_num_lvls - 2; i >= 0; i--)
 		rsp->levelspread[i] = CONFIG_RCU_FANOUT;
-	rsp->levelspread[0] = rcu_fanout_leaf;
 }
 #else /* #ifdef CONFIG_RCU_FANOUT_EXACT */
 static void __init rcu_init_levelspread(struct rcu_state *rsp)
-- 
cgit v0.10.2


From bc72d962d6a0ba8d9d5314d04fd1775261a9ec79 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sat, 26 Oct 2013 04:43:36 -0700
Subject: rcu: Improve SRCU's grace-period comments

This commit documents the memory-barrier guarantees provided by
synchronize_srcu() and call_srcu().

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index 0f0c631..3318d82 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -363,6 +363,29 @@ static void srcu_flip(struct srcu_struct *sp)
 /*
  * Enqueue an SRCU callback on the specified srcu_struct structure,
  * initiating grace-period processing if it is not already running.
+ *
+ * Note that all CPUs must agree that the grace period extended beyond
+ * all pre-existing SRCU read-side critical section.  On systems with
+ * more than one CPU, this means that when "func()" is invoked, each CPU
+ * is guaranteed to have executed a full memory barrier since the end of
+ * its last corresponding SRCU read-side critical section whose beginning
+ * preceded the call to call_rcu().  It also means that each CPU executing
+ * an SRCU read-side critical section that continues beyond the start of
+ * "func()" must have executed a memory barrier after the call_rcu()
+ * but before the beginning of that SRCU read-side critical section.
+ * Note that these guarantees include CPUs that are offline, idle, or
+ * executing in user mode, as well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
+ * resulting SRCU callback function "func()", then both CPU A and CPU
+ * B are guaranteed to execute a full memory barrier during the time
+ * interval between the call to call_rcu() and the invocation of "func()".
+ * This guarantee applies even if CPU A and CPU B are the same CPU (but
+ * again only if the system has more than one CPU).
+ *
+ * Of course, these guarantees apply only for invocations of call_srcu(),
+ * srcu_read_lock(), and srcu_read_unlock() that are all passed the same
+ * srcu_struct structure.
  */
 void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
 		void (*func)(struct rcu_head *head))
@@ -459,7 +482,30 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
  * Note that it is illegal to call synchronize_srcu() from the corresponding
  * SRCU read-side critical section; doing so will result in deadlock.
  * However, it is perfectly legal to call synchronize_srcu() on one
- * srcu_struct from some other srcu_struct's read-side critical section.
+ * srcu_struct from some other srcu_struct's read-side critical section,
+ * as long as the resulting graph of srcu_structs is acyclic.
+ *
+ * There are memory-ordering constraints implied by synchronize_srcu().
+ * On systems with more than one CPU, when synchronize_srcu() returns,
+ * each CPU is guaranteed to have executed a full memory barrier since
+ * the end of its last corresponding SRCU-sched read-side critical section
+ * whose beginning preceded the call to synchronize_srcu().  In addition,
+ * each CPU having an SRCU read-side critical section that extends beyond
+ * the return from synchronize_srcu() is guaranteed to have executed a
+ * full memory barrier after the beginning of synchronize_srcu() and before
+ * the beginning of that SRCU read-side critical section.  Note that these
+ * guarantees include CPUs that are offline, idle, or executing in user mode,
+ * as well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked synchronize_srcu(), which returned
+ * to its caller on CPU B, then both CPU A and CPU B are guaranteed
+ * to have executed a full memory barrier during the execution of
+ * synchronize_srcu().  This guarantee applies even if CPU A and CPU B
+ * are the same CPU, but again only if the system has more than one CPU.
+ *
+ * Of course, these memory-ordering guarantees apply only when
+ * synchronize_srcu(), srcu_read_lock(), and srcu_read_unlock() are
+ * passed the same srcu_struct structure.
  */
 void synchronize_srcu(struct srcu_struct *sp)
 {
@@ -476,12 +522,8 @@ EXPORT_SYMBOL_GPL(synchronize_srcu);
  * Wait for an SRCU grace period to elapse, but be more aggressive about
  * spinning rather than blocking when waiting.
  *
- * Note that it is also illegal to call synchronize_srcu_expedited()
- * from the corresponding SRCU read-side critical section;
- * doing so will result in deadlock.  However, it is perfectly legal
- * to call synchronize_srcu_expedited() on one srcu_struct from some
- * other srcu_struct's read-side critical section, as long as
- * the resulting graph of srcu_structs is acyclic.
+ * Note that synchronize_srcu_expedited() has the same deadlock and
+ * memory-ordering properties as does synchronize_srcu().
  */
 void synchronize_srcu_expedited(struct srcu_struct *sp)
 {
-- 
cgit v0.10.2


From 24ef659a857c3cba40b64ea51ea4fce8d2fb7bbc Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 28 Oct 2013 09:22:24 -0700
Subject: rcu: Provide better diagnostics for blocking in RCU callback
 functions

Currently blocking in an RCU callback function will result in
"scheduling while atomic", which could be triggered for any number
of reasons.  To aid debugging, this patch introduces a rcu_callback_map
that is used to tie the inappropriate voluntary context switch back
to the fact that the function is being invoked from within a callback.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 39cbb88..a94a580 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -325,6 +325,7 @@ static inline void rcu_lock_release(struct lockdep_map *map)
 extern struct lockdep_map rcu_lock_map;
 extern struct lockdep_map rcu_bh_lock_map;
 extern struct lockdep_map rcu_sched_lock_map;
+extern struct lockdep_map rcu_callback_map;
 extern int debug_lockdep_rcu_enabled(void);
 
 /**
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 7859a0a..a8f981a 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -102,13 +102,16 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
 {
 	unsigned long offset = (unsigned long)head->func;
 
+	rcu_lock_acquire(&rcu_callback_map);
 	if (__is_kfree_rcu_offset(offset)) {
 		RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset));
 		kfree((void *)head - offset);
+		rcu_lock_release(&rcu_callback_map);
 		return 1;
 	} else {
 		RCU_TRACE(trace_rcu_invoke_callback(rn, head));
 		head->func(head);
+		rcu_lock_release(&rcu_callback_map);
 		return 0;
 	}
 }
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 6cb3dff..802365c 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -128,6 +128,11 @@ struct lockdep_map rcu_sched_lock_map =
 	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key);
 EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
 
+static struct lock_class_key rcu_callback_key;
+struct lockdep_map rcu_callback_map =
+	STATIC_LOCKDEP_MAP_INIT("rcu_callback", &rcu_callback_key);
+EXPORT_SYMBOL_GPL(rcu_callback_map);
+
 int notrace debug_lockdep_rcu_enabled(void)
 {
 	return rcu_scheduler_active && debug_locks &&
-- 
cgit v0.10.2


From 73beb63d290f961c299526852884846b0d868840 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 2 Dec 2013 12:20:36 +0100
Subject: mfd: rtsx_pcr: Disable interrupts before cancelling delayed works

This fixes a kernel panic when resuming from suspend to RAM.
Without this fix an interrupt hits after the delayed work is canceled
and thus requeues it. So we end up freeing an armed timer.

Cc: stable@vger.kernel.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>

diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c
index 11e20af..705698f 100644
--- a/drivers/mfd/rtsx_pcr.c
+++ b/drivers/mfd/rtsx_pcr.c
@@ -1228,8 +1228,14 @@ static void rtsx_pci_remove(struct pci_dev *pcidev)
 
 	pcr->remove_pci = true;
 
-	cancel_delayed_work(&pcr->carddet_work);
-	cancel_delayed_work(&pcr->idle_work);
+	/* Disable interrupts at the pcr level */
+	spin_lock_irq(&pcr->lock);
+	rtsx_pci_writel(pcr, RTSX_BIER, 0);
+	pcr->bier = 0;
+	spin_unlock_irq(&pcr->lock);
+
+	cancel_delayed_work_sync(&pcr->carddet_work);
+	cancel_delayed_work_sync(&pcr->idle_work);
 
 	mfd_remove_devices(&pcidev->dev);
 
-- 
cgit v0.10.2


From 5cfe2c82f3eb6876cf4b55e99decea0bd015d6b8 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Mon, 9 Dec 2013 11:02:49 +0100
Subject: perf report: Add --header/--header-only options

Currently the perf.data header is always displayed for stdio output,
which is no always useful.

Disabling header information by default and adding following options to
control header output:

  --header      - display header information (old default)
  --header-only - display header information only w/o further
                  processing, forces stdio output

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1386583370-1699-2-git-send-email-jolsa@redhat.com
[ Added single line explaining talking about the new --header* options,
  to address David Ahern comment; better man page entry for the new options,
  from Namhyung Kim ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 10a2798..8eab8a4 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -237,6 +237,15 @@ OPTIONS
 	Do not show entries which have an overhead under that percent.
 	(Default: 0).
 
+--header::
+	Show header information in the perf.data file.  This includes
+	various information like hostname, OS and perf version, cpu/mem
+	info, perf command line, event list and so on.  Currently only
+	--stdio output supports this feature.
+
+--header-only::
+	Show only perf.data header (forces --stdio).
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-annotate[1]
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8cf8e66..3a14dbe 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -49,6 +49,8 @@ struct perf_report {
 	bool			show_threads;
 	bool			inverted_callchain;
 	bool			mem_mode;
+	bool			header;
+	bool			header_only;
 	int			max_stack;
 	struct perf_read_values	show_threads_values;
 	const char		*pretty_printing_style;
@@ -514,9 +516,6 @@ static int __cmd_report(struct perf_report *rep)
 			return ret;
 	}
 
-	if (use_browser <= 0)
-		perf_session__fprintf_info(session, stdout, rep->show_full_info);
-
 	if (rep->show_threads)
 		perf_read_values_init(&rep->show_threads_values);
 
@@ -820,6 +819,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN(0, "gtk", &report.use_gtk, "Use the GTK2 interface"),
 	OPT_BOOLEAN(0, "stdio", &report.use_stdio,
 		    "Use the stdio interface"),
+	OPT_BOOLEAN(0, "header", &report.header, "Show data header."),
+	OPT_BOOLEAN(0, "header-only", &report.header_only,
+		    "Show only data header."),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
 		   "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline,"
 		   " dso_to, dso_from, symbol_to, symbol_from, mispredict,"
@@ -963,6 +965,10 @@ repeat:
 			goto error;
 	}
 
+	/* Force tty output for header output. */
+	if (report.header || report.header_only)
+		use_browser = 0;
+
 	if (strcmp(input_name, "-") != 0)
 		setup_browser(true);
 	else {
@@ -970,6 +976,16 @@ repeat:
 		perf_hpp__init();
 	}
 
+	if (report.header || report.header_only) {
+		perf_session__fprintf_info(session, stdout,
+					   report.show_full_info);
+		if (report.header_only)
+			return 0;
+	} else if (use_browser == 0) {
+		fputs("# To display the perf.data header info, please use --header/--header-only options.\n#\n",
+		      stdout);
+	}
+
 	/*
 	 * Only in the TUI browser we are doing integrated annotation,
 	 * so don't allocate extra space that won't be used in the stdio
-- 
cgit v0.10.2


From e90debddf8f26094cd90162b9af2a8ed37ed57cb Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Mon, 9 Dec 2013 11:02:50 +0100
Subject: perf script: Add --header/--header-only options

Currently the perf.data header is always displayed for stdio output,
which is no always useful.

Disabling header information by default and adding following options to
control header output:

  --header      - display header information
  --header-only - display header information only w/o further
                  processing

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/n/tip-0ehaawv5xc83w6ag03c5hi10@git.kernel.org
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1386583370-1699-3-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index c2a5071..05f9a0a 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -209,6 +209,12 @@ OPTIONS
 --show-mmap-events
 	Display mmap related events (e.g. MMAP, MMAP2).
 
+--header
+	Show perf.data header.
+
+--header-only
+	Show only perf.data header.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 7a571fb..f8ab125 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1494,6 +1494,8 @@ static int have_cmd(int argc, const char **argv)
 int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	bool show_full_info = false;
+	bool header = false;
+	bool header_only = false;
 	char *rec_script_path = NULL;
 	char *rep_script_path = NULL;
 	struct perf_session *session;
@@ -1532,6 +1534,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_STRING('i', "input", &input_name, "file", "input file name"),
 	OPT_BOOLEAN('d', "debug-mode", &debug_mode,
 		   "do various checks like samples ordering and lost events"),
+	OPT_BOOLEAN(0, "header", &header, "Show data header."),
+	OPT_BOOLEAN(0, "header-only", &header_only, "Show only data header."),
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
 	OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
@@ -1748,6 +1752,12 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (session == NULL)
 		return -ENOMEM;
 
+	if (header || header_only) {
+		perf_session__fprintf_info(session, stdout, show_full_info);
+		if (header_only)
+			return 0;
+	}
+
 	script.session = session;
 
 	if (cpu_list) {
@@ -1755,9 +1765,6 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 			return -1;
 	}
 
-	if (!script_name && !generate_script_lang)
-		perf_session__fprintf_info(session, stdout, show_full_info);
-
 	if (!no_callchain)
 		symbol_conf.use_callchain = true;
 	else
-- 
cgit v0.10.2


From c7282f2efff9f115378b450b7aea51210fabb6ef Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 10 Dec 2013 10:44:37 -0300
Subject: perf symbols: Rename [sl]name_alloc to match the members they refer
 to

So we now have:

   dso->short_name
   dso->short_name_len
   dso->short_name_allocated

Ditto for the 'long  variants. To more quickly grasp what they refer to.

Suggested-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-nu228f8vlp9w0lr7c0q77dqi@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index a0c7c59..55c9835 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -465,9 +465,9 @@ void dso__delete(struct dso *dso)
 	int i;
 	for (i = 0; i < MAP__NR_TYPES; ++i)
 		symbols__delete(&dso->symbols[i]);
-	if (dso->sname_alloc)
+	if (dso->short_name_allocated)
 		free((char *)dso->short_name);
-	if (dso->lname_alloc)
+	if (dso->long_name_allocated)
 		free(dso->long_name);
 	dso_cache__free(&dso->cache);
 	dso__free_a2l(dso);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 384f2d9..00a232d 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -89,8 +89,8 @@ struct dso {
 	u8		 has_srcline:1;
 	u8		 hit:1;
 	u8		 annotate_warned:1;
-	u8		 sname_alloc:1;
-	u8		 lname_alloc:1;
+	u8		 short_name_allocated:1;
+	u8		 long_name_allocated:1;
 	u8		 sorted_by_name;
 	u8		 loaded;
 	u8		 rel;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index bac817a..f66f309 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -764,7 +764,7 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg,
 				goto out;
 			}
 			dso__set_long_name(map->dso, long_name);
-			map->dso->lname_alloc = 1;
+			map->dso->long_name_allocated = 1;
 			dso__kernel_module_get_build_id(map->dso, "");
 		}
 	}
@@ -936,7 +936,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 			goto out_problem;
 
 		map->dso->short_name = name;
-		map->dso->sname_alloc = 1;
+		map->dso->short_name_allocated = 1;
 		map->end = map->start + event->mmap.len;
 	} else if (is_kernel_mmap) {
 		const char *symbol_name = (event->mmap.filename +
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index de87dba..265a149 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1458,7 +1458,7 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 	if (filename != NULL) {
 		err = dso__load_vmlinux(dso, map, filename, filter);
 		if (err > 0) {
-			dso->lname_alloc = 1;
+			dso->long_name_allocated = 1;
 			goto out;
 		}
 		free(filename);
@@ -1468,7 +1468,7 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 		err = dso__load_vmlinux(dso, map, vmlinux_path[i], filter);
 		if (err > 0) {
 			dso__set_long_name(dso, strdup(vmlinux_path[i]));
-			dso->lname_alloc = 1;
+			dso->long_name_allocated = 1;
 			break;
 		}
 	}
@@ -1612,7 +1612,7 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map,
 		if (err > 0) {
 			dso__set_long_name(dso,
 					   strdup(symbol_conf.vmlinux_name));
-			dso->lname_alloc = 1;
+			dso->long_name_allocated = 1;
 			return err;
 		}
 		return err;
-- 
cgit v0.10.2


From 7521ab592550d9e6542a496bcea11b40900690da Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 10 Dec 2013 10:58:47 -0300
Subject: perf machine: Don't open code assign dso->short_name

Use dso__set_short_name instead, as it will release any previously,
possibly allocated, short name.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-1v39elw7v6nxczpntpp7ljwr@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index f66f309..f85da9a 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -935,7 +935,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		if (name == NULL)
 			goto out_problem;
 
-		map->dso->short_name = name;
+		dso__set_short_name(map->dso, name);
 		map->dso->short_name_allocated = 1;
 		map->end = map->start + event->mmap.len;
 	} else if (is_kernel_mmap) {
-- 
cgit v0.10.2


From 58a98c9cc583435784a93f23754128363b4cca94 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 10 Dec 2013 11:11:46 -0300
Subject: perf symbols: Remove open coded management of  short_name_allocated
 member

Instead of expecting callers to set this member accodingly so that later
at dso destruction it can, if needed, be correctly free()d, make it a
requirement by passing it as a parameter to dso__set_short_name.

Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
CC: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Link: http://lkml.kernel.org/r/52A707A2.5020802@intel.com
[ Renamed the 'allocated' parameter to clearly indicate to which variable it refers to. ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 55c9835..f8c8497 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -379,7 +379,7 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
 	 * processing we had no idea this was the kernel dso.
 	 */
 	if (dso != NULL) {
-		dso__set_short_name(dso, short_name);
+		dso__set_short_name(dso, short_name, false);
 		dso->kernel = dso_type;
 	}
 
@@ -394,17 +394,22 @@ void dso__set_long_name(struct dso *dso, char *name)
 	dso->long_name_len = strlen(name);
 }
 
-void dso__set_short_name(struct dso *dso, const char *name)
+void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
 {
 	if (name == NULL)
 		return;
-	dso->short_name = name;
-	dso->short_name_len = strlen(name);
+
+	if (dso->short_name_allocated)
+		free((char *)dso->short_name);
+
+	dso->short_name		  = name;
+	dso->short_name_len	  = strlen(name);
+	dso->short_name_allocated = name_allocated;
 }
 
 static void dso__set_basename(struct dso *dso)
 {
-	dso__set_short_name(dso, basename(dso->long_name));
+	dso__set_short_name(dso, basename(dso->long_name), false);
 }
 
 int dso__name_len(const struct dso *dso)
@@ -440,7 +445,7 @@ struct dso *dso__new(const char *name)
 		int i;
 		strcpy(dso->name, name);
 		dso__set_long_name(dso, dso->name);
-		dso__set_short_name(dso, dso->name);
+		dso__set_short_name(dso, dso->name, false);
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
 		dso->cache = RB_ROOT;
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 00a232d..8eceab7 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -110,7 +110,7 @@ static inline void dso__set_loaded(struct dso *dso, enum map_type type)
 struct dso *dso__new(const char *name);
 void dso__delete(struct dso *dso);
 
-void dso__set_short_name(struct dso *dso, const char *name);
+void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated);
 void dso__set_long_name(struct dso *dso, char *name);
 
 int dso__name_len(const struct dso *dso);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index f85da9a..09d5c66 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -935,8 +935,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		if (name == NULL)
 			goto out_problem;
 
-		dso__set_short_name(map->dso, name);
-		map->dso->short_name_allocated = 1;
+		dso__set_short_name(map->dso, name, true);
 		map->end = map->start + event->mmap.len;
 	} else if (is_kernel_mmap) {
 		const char *symbol_name = (event->mmap.filename +
-- 
cgit v0.10.2


From 5230fb7db42914e47786a6e920d2624739b0f896 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 10 Dec 2013 11:58:52 -0300
Subject: perf symbols: Set alloc flag close to setting the long_name

This is a preparatory patch to do with dso__set_long_name what was done
with the short name variant.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-mb7eqhkyejq1qcf3p22wz2x7@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 9c6989c..d7cff57 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -154,7 +154,7 @@ static struct dso *kernel_get_module_dso(const char *module)
 
 	vmlinux_name = symbol_conf.vmlinux_name;
 	if (vmlinux_name) {
-		if (dso__load_vmlinux(dso, map, vmlinux_name, NULL) <= 0)
+		if (dso__load_vmlinux(dso, map, vmlinux_name, false, NULL) <= 0)
 			return NULL;
 	} else {
 		if (dso__load_vmlinux_path(dso, map, NULL) <= 0) {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 265a149..9a5de88 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1408,7 +1408,8 @@ struct map *map_groups__find_by_name(struct map_groups *mg,
 }
 
 int dso__load_vmlinux(struct dso *dso, struct map *map,
-		      const char *vmlinux, symbol_filter_t filter)
+		      const char *vmlinux, bool vmlinux_allocated,
+		      symbol_filter_t filter)
 {
 	int err = -1;
 	struct symsrc ss;
@@ -1438,6 +1439,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 		else
 			dso->data_type = DSO_BINARY_TYPE__VMLINUX;
 		dso__set_long_name(dso, (char *)vmlinux);
+		dso->long_name_allocated = vmlinux_allocated;
 		dso__set_loaded(dso, map->type);
 		pr_debug("Using %s for symbols\n", symfs_vmlinux);
 	}
@@ -1456,21 +1458,16 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 
 	filename = dso__build_id_filename(dso, NULL, 0);
 	if (filename != NULL) {
-		err = dso__load_vmlinux(dso, map, filename, filter);
-		if (err > 0) {
-			dso->long_name_allocated = 1;
+		err = dso__load_vmlinux(dso, map, filename, true, filter);
+		if (err > 0)
 			goto out;
-		}
 		free(filename);
 	}
 
 	for (i = 0; i < vmlinux_path__nr_entries; ++i) {
-		err = dso__load_vmlinux(dso, map, vmlinux_path[i], filter);
-		if (err > 0) {
-			dso__set_long_name(dso, strdup(vmlinux_path[i]));
-			dso->long_name_allocated = 1;
+		err = dso__load_vmlinux(dso, map, vmlinux_path[i], false, filter);
+		if (err > 0)
 			break;
-		}
 	}
 out:
 	return err;
@@ -1607,15 +1604,8 @@ static int dso__load_kernel_sym(struct dso *dso, struct map *map,
 	}
 
 	if (!symbol_conf.ignore_vmlinux && symbol_conf.vmlinux_name != NULL) {
-		err = dso__load_vmlinux(dso, map,
-					symbol_conf.vmlinux_name, filter);
-		if (err > 0) {
-			dso__set_long_name(dso,
-					   strdup(symbol_conf.vmlinux_name));
-			dso->long_name_allocated = 1;
-			return err;
-		}
-		return err;
+		return dso__load_vmlinux(dso, map, symbol_conf.vmlinux_name,
+					 false, filter);
 	}
 
 	if (!symbol_conf.ignore_vmlinux && vmlinux_path != NULL) {
@@ -1671,7 +1661,8 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
 		 */
 		if (symbol_conf.default_guest_vmlinux_name != NULL) {
 			err = dso__load_vmlinux(dso, map,
-				symbol_conf.default_guest_vmlinux_name, filter);
+						symbol_conf.default_guest_vmlinux_name,
+						false, filter);
 			return err;
 		}
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index f1031a1..6de9c2b 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -206,7 +206,8 @@ bool symsrc__possibly_runtime(struct symsrc *ss);
 
 int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter);
 int dso__load_vmlinux(struct dso *dso, struct map *map,
-		      const char *vmlinux, symbol_filter_t filter);
+		      const char *vmlinux, bool vmlinux_allocated,
+		      symbol_filter_t filter);
 int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 			   symbol_filter_t filter);
 int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
-- 
cgit v0.10.2


From 7e155d4d5e2912f75443c18c02dd6f1dbd4eef84 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 10 Dec 2013 15:08:44 -0300
Subject: perf symbols: Remove open coded management of  long_name_allocated
 member

Instead of expecting callers to set this member accodingly so that later
at dso destruction it can, if needed, be correctly free()d, make it a
requirement by passing it as a parameter to dso__set_long_name.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-na7t1tqim22vuqkt4zq5n4ri@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index f8c8497..ecb37d6 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -386,12 +386,17 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
 	return dso;
 }
 
-void dso__set_long_name(struct dso *dso, char *name)
+void dso__set_long_name(struct dso *dso, char *name, bool name_allocated)
 {
 	if (name == NULL)
 		return;
-	dso->long_name = name;
-	dso->long_name_len = strlen(name);
+
+	if (dso->long_name_allocated)
+		free(dso->long_name);
+
+	dso->long_name		 = name;
+	dso->long_name_len	 = strlen(name);
+	dso->long_name_allocated = name_allocated;
 }
 
 void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
@@ -444,7 +449,7 @@ struct dso *dso__new(const char *name)
 	if (dso != NULL) {
 		int i;
 		strcpy(dso->name, name);
-		dso__set_long_name(dso, dso->name);
+		dso__set_long_name(dso, dso->name, false);
 		dso__set_short_name(dso, dso->name, false);
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 8eceab7..7b43469 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -111,7 +111,7 @@ struct dso *dso__new(const char *name);
 void dso__delete(struct dso *dso);
 
 void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated);
-void dso__set_long_name(struct dso *dso, char *name);
+void dso__set_long_name(struct dso *dso, char *name, bool name_allocated);
 
 int dso__name_len(const struct dso *dso);
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 09d5c66..751454b 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -763,8 +763,7 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg,
 				ret = -1;
 				goto out;
 			}
-			dso__set_long_name(map->dso, long_name);
-			map->dso->long_name_allocated = 1;
+			dso__set_long_name(map->dso, long_name, true);
 			dso__kernel_module_get_build_id(map->dso, "");
 		}
 	}
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 9a5de88..5029ee1 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1159,7 +1159,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 		dso->data_type = DSO_BINARY_TYPE__GUEST_KCORE;
 	else
 		dso->data_type = DSO_BINARY_TYPE__KCORE;
-	dso__set_long_name(dso, strdup(kcore_filename));
+	dso__set_long_name(dso, strdup(kcore_filename), true);
 
 	close(fd);
 
@@ -1438,8 +1438,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 			dso->data_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
 		else
 			dso->data_type = DSO_BINARY_TYPE__VMLINUX;
-		dso__set_long_name(dso, (char *)vmlinux);
-		dso->long_name_allocated = vmlinux_allocated;
+		dso__set_long_name(dso, (char *)vmlinux, vmlinux_allocated);
 		dso__set_loaded(dso, map->type);
 		pr_debug("Using %s for symbols\n", symfs_vmlinux);
 	}
@@ -1631,7 +1630,7 @@ do_kallsyms:
 	free(kallsyms_allocated_filename);
 
 	if (err > 0 && !dso__is_kcore(dso)) {
-		dso__set_long_name(dso, strdup("[kernel.kallsyms]"));
+		dso__set_long_name(dso, strdup("[kernel.kallsyms]"), true);
 		map__fixup_start(map);
 		map__fixup_end(map);
 	}
@@ -1679,7 +1678,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
 		pr_debug("Using %s for symbols\n", kallsyms_filename);
 	if (err > 0 && !dso__is_kcore(dso)) {
 		machine__mmap_name(machine, path, sizeof(path));
-		dso__set_long_name(dso, strdup(path));
+		dso__set_long_name(dso, strdup(path), true);
 		map__fixup_start(map);
 		map__fixup_end(map);
 	}
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 3915982..0ddb3b8 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -103,7 +103,7 @@ struct dso *vdso__dso_findnew(struct list_head *head)
 		dso = dso__new(VDSO__MAP_NAME);
 		if (dso != NULL) {
 			dsos__add(head, dso);
-			dso__set_long_name(dso, file);
+			dso__set_long_name(dso, file, false);
 		}
 	}
 
-- 
cgit v0.10.2


From bf4414ae7b86cddca60a5b510954a37d30583a1f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 10 Dec 2013 15:19:23 -0300
Subject: perf symbols: Constify dso->long_name

Same reason as for dso->short_name, it may point to a const string, and
in most places it is treated as const, i.e. it is just accessed for
using its contents as a key or to show it on reports.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-nf7mxf33zt5qw207pbxxryot@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index cf6242c..0fcd81e 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -900,7 +900,7 @@ fallback:
 		 * cache, or is just a kallsyms file, well, lets hope that this
 		 * DSO is the same as when 'perf record' ran.
 		 */
-		filename = dso->long_name;
+		filename = (char *)dso->long_name;
 		snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
 			 symbol_conf.symfs, filename);
 		free_filename = false;
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index ecb37d6..2c7e189 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -67,7 +67,7 @@ int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
 
 	case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
 	{
-		char *last_slash;
+		const char *last_slash;
 		size_t len;
 		size_t dir_size;
 
@@ -386,13 +386,13 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
 	return dso;
 }
 
-void dso__set_long_name(struct dso *dso, char *name, bool name_allocated)
+void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
 {
 	if (name == NULL)
 		return;
 
 	if (dso->long_name_allocated)
-		free(dso->long_name);
+		free((char *)dso->long_name);
 
 	dso->long_name		 = name;
 	dso->long_name_len	 = strlen(name);
@@ -414,7 +414,7 @@ void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
 
 static void dso__set_basename(struct dso *dso)
 {
-	dso__set_short_name(dso, basename(dso->long_name), false);
+	dso__set_short_name(dso, basename((char *)dso->long_name), false);
 }
 
 int dso__name_len(const struct dso *dso)
@@ -478,7 +478,7 @@ void dso__delete(struct dso *dso)
 	if (dso->short_name_allocated)
 		free((char *)dso->short_name);
 	if (dso->long_name_allocated)
-		free(dso->long_name);
+		free((char *)dso->long_name);
 	dso_cache__free(&dso->cache);
 	dso__free_a2l(dso);
 	free(dso->symsrc_filename);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 7b43469..a2d7129 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -96,7 +96,7 @@ struct dso {
 	u8		 rel;
 	u8		 build_id[BUILD_ID_SIZE];
 	const char	 *short_name;
-	char		 *long_name;
+	const char	 *long_name;
 	u16		 long_name_len;
 	u16		 short_name_len;
 	char		 name[0];
@@ -111,7 +111,7 @@ struct dso *dso__new(const char *name);
 void dso__delete(struct dso *dso);
 
 void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated);
-void dso__set_long_name(struct dso *dso, char *name, bool name_allocated);
+void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated);
 
 int dso__name_len(const struct dso *dso);
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 125cdc9..0bb830f 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -177,7 +177,7 @@ perf_header__set_cmdline(int argc, const char **argv)
 			continue;		\
 		else
 
-static int write_buildid(char *name, size_t name_len, u8 *build_id,
+static int write_buildid(const char *name, size_t name_len, u8 *build_id,
 			 pid_t pid, u16 misc, int fd)
 {
 	int err;
@@ -209,7 +209,7 @@ static int __dsos__write_buildid_table(struct list_head *head,
 
 	dsos__for_each_with_build_id(pos, head) {
 		int err;
-		char  *name;
+		const char *name;
 		size_t name_len;
 
 		if (!pos->hit)
@@ -387,7 +387,7 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine,
 {
 	bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
 	bool is_vdso = is_vdso_map(dso->short_name);
-	char *name = dso->long_name;
+	const char *name = dso->long_name;
 	char nm[PATH_MAX];
 
 	if (dso__is_kcore(dso)) {
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 0c07556..58b2bd8 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -255,7 +255,7 @@ char *get_srcline(struct dso *dso, unsigned long addr)
 	char *file = NULL;
 	unsigned line = 0;
 	char *srcline;
-	char *dso_name;
+	const char *dso_name;
 
 	if (!dso->has_srcline)
 		return SRCLINE_UNKNOWN;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 5029ee1..e377c2e 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1438,7 +1438,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 			dso->data_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
 		else
 			dso->data_type = DSO_BINARY_TYPE__VMLINUX;
-		dso__set_long_name(dso, (char *)vmlinux, vmlinux_allocated);
+		dso__set_long_name(dso, vmlinux, vmlinux_allocated);
 		dso__set_loaded(dso, map->type);
 		pr_debug("Using %s for symbols\n", symfs_vmlinux);
 	}
@@ -1630,7 +1630,7 @@ do_kallsyms:
 	free(kallsyms_allocated_filename);
 
 	if (err > 0 && !dso__is_kcore(dso)) {
-		dso__set_long_name(dso, strdup("[kernel.kallsyms]"), true);
+		dso__set_long_name(dso, "[kernel.kallsyms]", false);
 		map__fixup_start(map);
 		map__fixup_end(map);
 	}
-- 
cgit v0.10.2


From ee021d42238daadc7ba49274bb0ba7dff219c6ab Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 10 Dec 2013 15:26:55 -0300
Subject: perf symbols: Set freed members to NULL in dso destructor

To help in debugging use after free bugs.

Reported-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-3ckwsob2g1q23s77nuhexrq7@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 2c7e189..19babb0 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -475,13 +475,23 @@ void dso__delete(struct dso *dso)
 	int i;
 	for (i = 0; i < MAP__NR_TYPES; ++i)
 		symbols__delete(&dso->symbols[i]);
-	if (dso->short_name_allocated)
+
+	if (dso->short_name_allocated) {
 		free((char *)dso->short_name);
-	if (dso->long_name_allocated)
+		dso->short_name		  = NULL;
+		dso->short_name_allocated = false;
+	}
+
+	if (dso->long_name_allocated) {
 		free((char *)dso->long_name);
+		dso->long_name		 = NULL;
+		dso->long_name_allocated = false;
+	}
+
 	dso_cache__free(&dso->cache);
 	dso__free_a2l(dso);
 	free(dso->symsrc_filename);
+	dso->symsrc_filename = NULL;
 	free(dso);
 }
 
-- 
cgit v0.10.2


From 3344996e4f2980be568ecf0cd59cb85e646da029 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 10 Dec 2013 15:46:29 -0300
Subject: perf symbols: Constify some DSO methods parameters

Those methods are not supposed to change the data structures they
manipulate, so make that clearer by using the const qualifier in the
function signature and in some variables.

Suggested-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-j7oyakex7zy3r82h33rdw25x@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index a92770c..6baabe6 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -89,7 +89,7 @@ int build_id__sprintf(const u8 *build_id, int len, char *bf)
 	return raw - build_id;
 }
 
-char *dso__build_id_filename(struct dso *dso, char *bf, size_t size)
+char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
 {
 	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
 
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 929f28a..845ef86 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -10,7 +10,7 @@ extern struct perf_tool build_id__mark_dso_hit_ops;
 struct dso;
 
 int build_id__sprintf(const u8 *build_id, int len, char *bf);
-char *dso__build_id_filename(struct dso *dso, char *bf, size_t size);
+char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
 
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
 			   struct perf_sample *sample, struct perf_evsel *evsel,
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 19babb0..fbc66fd 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -28,7 +28,7 @@ char dso__symtab_origin(const struct dso *dso)
 	return origin[dso->symtab_type];
 }
 
-int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
+int dso__binary_type_file(const struct dso *dso, enum dso_binary_type type,
 			  char *root_dir, char *file, size_t size)
 {
 	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
@@ -200,11 +200,10 @@ dso_cache__free(struct rb_root *root)
 	}
 }
 
-static struct dso_cache*
-dso_cache__find(struct rb_root *root, u64 offset)
+static struct dso_cache *dso_cache__find(const struct rb_root *root, u64 offset)
 {
-	struct rb_node **p = &root->rb_node;
-	struct rb_node *parent = NULL;
+	struct rb_node * const *p = &root->rb_node;
+	const struct rb_node *parent = NULL;
 	struct dso_cache *cache;
 
 	while (*p != NULL) {
@@ -566,7 +565,7 @@ void dsos__add(struct list_head *head, struct dso *dso)
 	list_add_tail(&dso->node, head);
 }
 
-struct dso *dsos__find(struct list_head *head, const char *name, bool cmp_short)
+struct dso *dsos__find(const struct list_head *head, const char *name, bool cmp_short)
 {
 	struct dso *pos;
 
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index a2d7129..99f3c64 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -128,7 +128,7 @@ void dso__read_running_kernel_build_id(struct dso *dso,
 int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir);
 
 char dso__symtab_origin(const struct dso *dso);
-int dso__binary_type_file(struct dso *dso, enum dso_binary_type type,
+int dso__binary_type_file(const struct dso *dso, enum dso_binary_type type,
 			  char *root_dir, char *file, size_t size);
 
 int dso__data_fd(struct dso *dso, struct machine *machine);
@@ -143,7 +143,7 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
 				const char *short_name, int dso_type);
 
 void dsos__add(struct list_head *head, struct dso *dso);
-struct dso *dsos__find(struct list_head *head, const char *name,
+struct dso *dsos__find(const struct list_head *head, const char *name,
 		       bool cmp_short);
 struct dso *__dsos__findnew(struct list_head *head, const char *name);
 bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
-- 
cgit v0.10.2


From 7d2a5122ca973cdf3c1469187811ae01dc07f67a Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 10 Dec 2013 16:02:50 -0300
Subject: perf symbols: Rename filename argument

The 'file' is more commonly associated with a file descriptor of
some sort, rename it to 'filename' as this is the more common idiom
for a file name argument.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-0ehaawv5xc83w6ag03c5hi10@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index fbc66fd..582b5d3 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -29,7 +29,7 @@ char dso__symtab_origin(const struct dso *dso)
 }
 
 int dso__binary_type_file(const struct dso *dso, enum dso_binary_type type,
-			  char *root_dir, char *file, size_t size)
+			  char *root_dir, char *filename, size_t size)
 {
 	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
 	int ret = 0;
@@ -38,30 +38,30 @@ int dso__binary_type_file(const struct dso *dso, enum dso_binary_type type,
 	case DSO_BINARY_TYPE__DEBUGLINK: {
 		char *debuglink;
 
-		strncpy(file, dso->long_name, size);
-		debuglink = file + dso->long_name_len;
-		while (debuglink != file && *debuglink != '/')
+		strncpy(filename, dso->long_name, size);
+		debuglink = filename + dso->long_name_len;
+		while (debuglink != filename && *debuglink != '/')
 			debuglink--;
 		if (*debuglink == '/')
 			debuglink++;
 		filename__read_debuglink(dso->long_name, debuglink,
-					 size - (debuglink - file));
+					 size - (debuglink - filename));
 		}
 		break;
 	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
 		/* skip the locally configured cache if a symfs is given */
 		if (symbol_conf.symfs[0] ||
-		    (dso__build_id_filename(dso, file, size) == NULL))
+		    (dso__build_id_filename(dso, filename, size) == NULL))
 			ret = -1;
 		break;
 
 	case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
-		snprintf(file, size, "%s/usr/lib/debug%s.debug",
+		snprintf(filename, size, "%s/usr/lib/debug%s.debug",
 			 symbol_conf.symfs, dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
-		snprintf(file, size, "%s/usr/lib/debug%s",
+		snprintf(filename, size, "%s/usr/lib/debug%s",
 			 symbol_conf.symfs, dso->long_name);
 		break;
 
@@ -75,14 +75,14 @@ int dso__binary_type_file(const struct dso *dso, enum dso_binary_type type,
 		while (last_slash != dso->long_name && *last_slash != '/')
 			last_slash--;
 
-		len = scnprintf(file, size, "%s", symbol_conf.symfs);
+		len = scnprintf(filename, size, "%s", symbol_conf.symfs);
 		dir_size = last_slash - dso->long_name + 2;
 		if (dir_size > (size - len)) {
 			ret = -1;
 			break;
 		}
-		len += scnprintf(file + len, dir_size, "%s",  dso->long_name);
-		len += scnprintf(file + len , size - len, ".debug%s",
+		len += scnprintf(filename + len, dir_size, "%s",  dso->long_name);
+		len += scnprintf(filename + len , size - len, ".debug%s",
 								last_slash);
 		break;
 	}
@@ -96,7 +96,7 @@ int dso__binary_type_file(const struct dso *dso, enum dso_binary_type type,
 		build_id__sprintf(dso->build_id,
 				  sizeof(dso->build_id),
 				  build_id_hex);
-		snprintf(file, size,
+		snprintf(filename, size,
 			 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
 			 symbol_conf.symfs, build_id_hex, build_id_hex + 2);
 		break;
@@ -104,23 +104,23 @@ int dso__binary_type_file(const struct dso *dso, enum dso_binary_type type,
 	case DSO_BINARY_TYPE__VMLINUX:
 	case DSO_BINARY_TYPE__GUEST_VMLINUX:
 	case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
-		snprintf(file, size, "%s%s",
+		snprintf(filename, size, "%s%s",
 			 symbol_conf.symfs, dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__GUEST_KMODULE:
-		snprintf(file, size, "%s%s%s", symbol_conf.symfs,
+		snprintf(filename, size, "%s%s%s", symbol_conf.symfs,
 			 root_dir, dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
-		snprintf(file, size, "%s%s", symbol_conf.symfs,
+		snprintf(filename, size, "%s%s", symbol_conf.symfs,
 			 dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__KCORE:
 	case DSO_BINARY_TYPE__GUEST_KCORE:
-		snprintf(file, size, "%s", dso->long_name);
+		snprintf(filename, size, "%s", dso->long_name);
 		break;
 
 	default:
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 99f3c64..e1cc506 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -129,7 +129,7 @@ int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir);
 
 char dso__symtab_origin(const struct dso *dso);
 int dso__binary_type_file(const struct dso *dso, enum dso_binary_type type,
-			  char *root_dir, char *file, size_t size);
+			  char *root_dir, char *filename, size_t size);
 
 int dso__data_fd(struct dso *dso, struct machine *machine);
 ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
-- 
cgit v0.10.2


From ac5e7f84c0e050fe19146d9bf51f69890beabcef Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Thu, 5 Dec 2013 19:26:42 +0100
Subject: perf symbols: Fix bug in usage of the basename() function

The basename() implementation varies a lot between systems.

The Linux man page says: "basename may modify the content of the path,
so it may be desirable to pass a copy when calling the function".

On some other systems, the returned address may come from an internal
buffer which can be reused in subsequent calls, thus the results should
also be copied.

The dso__set_basename() function was not doing this causing problems
on some systems with wrong library names being shown by perf report,
such as on Android systems.

This patch fixes the problem.
The patch is relative to tip.git.

In v2, we clean up the comments based on Ingo's feedback.

Reported-by: Ben Cheng <bccheng@google.com>
Signed-off-by: Stephane Eranian <eranian@google.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: Ben Cheng <bccheng@google.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131205182642.GA14614@quad
[ v3: Fixed up wrt allocated flag now being set in dso__set_short_name ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 582b5d3..436922f 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -413,7 +413,28 @@ void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
 
 static void dso__set_basename(struct dso *dso)
 {
-	dso__set_short_name(dso, basename((char *)dso->long_name), false);
+       /*
+        * basename() may modify path buffer, so we must pass
+        * a copy.
+        */
+       char *base, *lname = strdup(dso->long_name);
+
+       if (!lname)
+               return;
+
+       /*
+        * basename() may return a pointer to internal
+        * storage which is reused in subsequent calls
+        * so copy the result.
+        */
+       base = strdup(basename(lname));
+
+       free(lname);
+
+       if (!base)
+               return;
+
+       dso__set_short_name(dso, base, true);
 }
 
 int dso__name_len(const struct dso *dso)
-- 
cgit v0.10.2


From ef517c6bee5d16404b06bee1d07f00ffb74fc21a Mon Sep 17 00:00:00 2001
From: Jean Pihet <jean.pihet@linaro.org>
Date: Tue, 10 Dec 2013 13:24:03 +0100
Subject: perf tools: Add per-feature check flags

Add CFLAGS and LDFLAGS for each feature to be checked. This allows to
pass flags and parameters to the feature checks compilation.  Also
simplifies the feature check makefile, to come in a subsequent patch.

Signed-off-by: Jean Pihet <jean.pihet@linaro.org>
Acked-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linaro-kernel@lists.linaro.org
Cc: patches@linaro.org
Link: http://lkml.kernel.org/r/1386678244-13535-2-git-send-email-jean.pihet@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index bae1072..2afb132 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -102,7 +102,7 @@ endif
 
 feature_check = $(eval $(feature_check_code))
 define feature_check_code
-  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS)" LDFLAGS="$(LDFLAGS)" LIBUNWIND_LIBS="$(LIBUNWIND_LIBS)" -C config/feature-checks test-$1 >/dev/null 2>/dev/null && echo 1 || echo 0)
+  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" LIBUNWIND_LIBS="$(LIBUNWIND_LIBS)" -C config/feature-checks test-$1 >/dev/null 2>/dev/null && echo 1 || echo 0)
 endef
 
 feature_set = $(eval $(feature_set_code))
-- 
cgit v0.10.2


From 1448fef40af6079de38380c3a81bcf9994a1037d Mon Sep 17 00:00:00 2001
From: Jean Pihet <jean.pihet@linaro.org>
Date: Tue, 10 Dec 2013 13:24:04 +0100
Subject: perf unwinding: Use the per-feature check flags

Use the per-feature check flags for the unwinding feature in order to
correctly compile the test-all, libunwind and libunwind-debug-frame
feature checks.

Tested on x86_64, ARMv7 and ARMv8 with and without LIBUNWIND_DIR set in
'make -C tools/perf'

Signed-off-by: Jean Pihet <jean.pihet@linaro.org>
Acked-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linaro-kernel@lists.linaro.org
Cc: patches@linaro.org
Link: http://lkml.kernel.org/r/1386678244-13535-3-git-send-email-jean.pihet@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 2afb132..5a1f4df 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -36,6 +36,30 @@ ifeq ($(ARCH),arm)
   LIBUNWIND_LIBS = -lunwind -lunwind-arm
 endif
 
+ifeq ($(LIBUNWIND_LIBS),)
+  NO_LIBUNWIND := 1
+else
+  #
+  # For linking with debug library, run like:
+  #
+  #   make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
+  #
+  ifdef LIBUNWIND_DIR
+    LIBUNWIND_CFLAGS  = -I$(LIBUNWIND_DIR)/include
+    LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib
+  endif
+  LIBUNWIND_LDFLAGS += $(LIBUNWIND_LIBS)
+
+  # Set per-feature check compilation flags
+  FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS)
+  FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS)
+  FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS)
+  FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS)
+  #  and the flags for the test-all case
+  FEATURE_CHECK_CFLAGS-all += $(LIBUNWIND_CFLAGS)
+  FEATURE_CHECK_LDFLAGS-all += $(LIBUNWIND_LDFLAGS)
+endif
+
 ifeq ($(NO_PERF_REGS),0)
   CFLAGS += -DHAVE_PERF_REGS_SUPPORT
 endif
@@ -102,7 +126,7 @@ endif
 
 feature_check = $(eval $(feature_check_code))
 define feature_check_code
-  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" LIBUNWIND_LIBS="$(LIBUNWIND_LIBS)" -C config/feature-checks test-$1 >/dev/null 2>/dev/null && echo 1 || echo 0)
+  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C config/feature-checks test-$1 >/dev/null 2>/dev/null && echo 1 || echo 0)
 endef
 
 feature_set = $(eval $(feature_set_code))
@@ -305,21 +329,7 @@ ifndef NO_LIBELF
   endif # NO_DWARF
 endif # NO_LIBELF
 
-ifeq ($(LIBUNWIND_LIBS),)
-  NO_LIBUNWIND := 1
-endif
-
 ifndef NO_LIBUNWIND
-  #
-  # For linking with debug library, run like:
-  #
-  #   make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
-  #
-  ifdef LIBUNWIND_DIR
-    LIBUNWIND_CFLAGS  := -I$(LIBUNWIND_DIR)/include
-    LIBUNWIND_LDFLAGS := -L$(LIBUNWIND_DIR)/lib
-  endif
-
   ifneq ($(feature-libunwind), 1)
     msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 1.1);
     NO_LIBUNWIND := 1
@@ -334,14 +344,12 @@ ifndef NO_LIBUNWIND
       # non-ARM has no dwarf_find_debug_frame() function:
       CFLAGS += -DNO_LIBUNWIND_DEBUG_FRAME
     endif
-  endif
-endif
 
-ifndef NO_LIBUNWIND
-  CFLAGS += -DHAVE_LIBUNWIND_SUPPORT
-  EXTLIBS += $(LIBUNWIND_LIBS)
-  CFLAGS += $(LIBUNWIND_CFLAGS)
-  LDFLAGS += $(LIBUNWIND_LDFLAGS)
+    CFLAGS += -DHAVE_LIBUNWIND_SUPPORT
+    EXTLIBS += $(LIBUNWIND_LIBS)
+    CFLAGS += $(LIBUNWIND_CFLAGS)
+    LDFLAGS += $(LIBUNWIND_LDFLAGS)
+  endif # ifneq ($(feature-libunwind), 1)
 endif
 
 ifndef NO_LIBAUDIT
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index b8bb749..bc86462 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -32,12 +32,12 @@ CC := $(CC) -MD
 
 all: $(FILES)
 
-BUILD = $(CC) $(CFLAGS) $(LDFLAGS) -o $(OUTPUT)$@ $@.c
+BUILD = $(CC) $(CFLAGS) -o $(OUTPUT)$@ $@.c $(LDFLAGS)
 
 ###############################
 
 test-all:
-	$(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma $(LIBUNWIND_LIBS) -lelf -laudit -I/usr/include/slang -lslang $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl
+	$(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl
 
 test-hello:
 	$(BUILD)
@@ -70,10 +70,10 @@ test-libnuma:
 	$(BUILD) -lnuma
 
 test-libunwind:
-	$(BUILD) $(LIBUNWIND_LIBS) -lelf
+	$(BUILD) -lelf
 
 test-libunwind-debug-frame:
-	$(BUILD) $(LIBUNWIND_LIBS) -lelf
+	$(BUILD) -lelf
 
 test-libaudit:
 	$(BUILD) -laudit
-- 
cgit v0.10.2


From d52eefb47d4eb6fe40d4c92bc711dd34a8ce1747 Mon Sep 17 00:00:00 2001
From: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Date: Thu, 5 Dec 2013 13:47:27 -0500
Subject: ia64/xen: Remove Xen support for ia64

ia64 has not been supported by Xen since 4.2 so it's time to drop
Xen/ia64 from Linux as well.

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 4e4119b..a8c3a11 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -147,9 +147,6 @@ config PARAVIRT
 	  over full virtualization.  However, when run without a hypervisor
 	  the kernel is theoretically slower and slightly larger.
 
-
-source "arch/ia64/xen/Kconfig"
-
 endif
 
 choice
@@ -175,7 +172,6 @@ config IA64_GENERIC
 	  SGI-SN2		For SGI Altix systems
 	  SGI-UV		For SGI UV systems
 	  Ski-simulator		For the HP simulator <http://www.hpl.hp.com/research/linux/ski/>
-	  Xen-domU		For xen domU system
 
 	  If you don't know what to do, choose "generic".
 
@@ -231,14 +227,6 @@ config IA64_HP_SIM
 	bool "Ski-simulator"
 	select SWIOTLB
 
-config IA64_XEN_GUEST
-	bool "Xen guest"
-	select SWIOTLB
-	depends on XEN
-	help
-	  Build a kernel that runs on Xen guest domain. At this moment only
-	  16KB page size in supported.
-
 endchoice
 
 choice
diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile
index be7bfa1..f37238f 100644
--- a/arch/ia64/Makefile
+++ b/arch/ia64/Makefile
@@ -51,11 +51,9 @@ core-$(CONFIG_IA64_DIG_VTD) 	+= arch/ia64/dig/
 core-$(CONFIG_IA64_GENERIC) 	+= arch/ia64/dig/
 core-$(CONFIG_IA64_HP_ZX1)	+= arch/ia64/dig/
 core-$(CONFIG_IA64_HP_ZX1_SWIOTLB) += arch/ia64/dig/
-core-$(CONFIG_IA64_XEN_GUEST)	+= arch/ia64/dig/
 core-$(CONFIG_IA64_SGI_SN2)	+= arch/ia64/sn/
 core-$(CONFIG_IA64_SGI_UV)	+= arch/ia64/uv/
 core-$(CONFIG_KVM) 		+= arch/ia64/kvm/
-core-$(CONFIG_XEN)		+= arch/ia64/xen/
 
 drivers-$(CONFIG_PCI)		+= arch/ia64/pci/
 drivers-$(CONFIG_IA64_HP_SIM)	+= arch/ia64/hp/sim/
diff --git a/arch/ia64/configs/xen_domu_defconfig b/arch/ia64/configs/xen_domu_defconfig
deleted file mode 100644
index b025acf..0000000
--- a/arch/ia64/configs/xen_domu_defconfig
+++ /dev/null
@@ -1,199 +0,0 @@
-CONFIG_EXPERIMENTAL=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=20
-CONFIG_SYSFS_DEPRECATED_V2=y
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODVERSIONS=y
-CONFIG_MODULE_SRCVERSION_ALL=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_PARAVIRT_GUEST=y
-CONFIG_IA64_XEN_GUEST=y
-CONFIG_MCKINLEY=y
-CONFIG_IA64_CYCLONE=y
-CONFIG_SMP=y
-CONFIG_NR_CPUS=16
-CONFIG_HOTPLUG_CPU=y
-CONFIG_PERMIT_BSP_REMOVE=y
-CONFIG_FORCE_CPEI_RETARGET=y
-CONFIG_IA64_MCA_RECOVERY=y
-CONFIG_PERFMON=y
-CONFIG_IA64_PALINFO=y
-CONFIG_KEXEC=y
-CONFIG_EFI_VARS=y
-CONFIG_BINFMT_MISC=m
-CONFIG_ACPI_PROCFS=y
-CONFIG_ACPI_BUTTON=m
-CONFIG_ACPI_FAN=m
-CONFIG_ACPI_PROCESSOR=m
-CONFIG_ACPI_CONTAINER=m
-CONFIG_HOTPLUG_PCI=y
-CONFIG_HOTPLUG_PCI_ACPI=m
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_ARPD=y
-CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
-# CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_BLK_DEV_LOOP=m
-CONFIG_BLK_DEV_CRYPTOLOOP=m
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=y
-CONFIG_IDE=y
-CONFIG_BLK_DEV_IDECD=y
-CONFIG_BLK_DEV_GENERIC=y
-CONFIG_BLK_DEV_CMD64X=y
-CONFIG_BLK_DEV_PIIX=y
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_ST=m
-CONFIG_BLK_DEV_SR=m
-CONFIG_CHR_DEV_SG=m
-CONFIG_SCSI_SYM53C8XX_2=y
-CONFIG_SCSI_QLOGIC_1280=y
-CONFIG_MD=y
-CONFIG_BLK_DEV_MD=m
-CONFIG_MD_LINEAR=m
-CONFIG_MD_RAID0=m
-CONFIG_MD_RAID1=m
-CONFIG_MD_MULTIPATH=m
-CONFIG_BLK_DEV_DM=m
-CONFIG_DM_CRYPT=m
-CONFIG_DM_SNAPSHOT=m
-CONFIG_DM_MIRROR=m
-CONFIG_DM_ZERO=m
-CONFIG_FUSION=y
-CONFIG_FUSION_SPI=y
-CONFIG_FUSION_FC=y
-CONFIG_FUSION_CTL=y
-CONFIG_NETDEVICES=y
-CONFIG_DUMMY=m
-CONFIG_NET_ETHERNET=y
-CONFIG_NET_TULIP=y
-CONFIG_TULIP=m
-CONFIG_NET_PCI=y
-CONFIG_NET_VENDOR_INTEL=y
-CONFIG_E100=m
-CONFIG_E1000=y
-CONFIG_TIGON3=y
-CONFIG_NETCONSOLE=y
-# CONFIG_SERIO_SERPORT is not set
-CONFIG_GAMEPORT=m
-CONFIG_SERIAL_NONSTANDARD=y
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_NR_UARTS=6
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-# CONFIG_HW_RANDOM is not set
-CONFIG_EFI_RTC=y
-CONFIG_RAW_DRIVER=m
-CONFIG_HPET=y
-CONFIG_AGP=m
-CONFIG_DRM=m
-CONFIG_DRM_TDFX=m
-CONFIG_DRM_R128=m
-CONFIG_DRM_RADEON=m
-CONFIG_DRM_MGA=m
-CONFIG_DRM_SIS=m
-CONFIG_HID_GYRATION=y
-CONFIG_HID_NTRIG=y
-CONFIG_HID_PANTHERLORD=y
-CONFIG_HID_PETALYNX=y
-CONFIG_HID_SAMSUNG=y
-CONFIG_HID_SONY=y
-CONFIG_HID_SUNPLUS=y
-CONFIG_HID_TOPSEED=y
-CONFIG_USB=y
-CONFIG_USB_DEVICEFS=y
-CONFIG_USB_EHCI_HCD=m
-CONFIG_USB_OHCI_HCD=m
-CONFIG_USB_UHCI_HCD=y
-CONFIG_USB_STORAGE=m
-CONFIG_EXT2_FS=y
-CONFIG_EXT2_FS_XATTR=y
-CONFIG_EXT2_FS_POSIX_ACL=y
-CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
-CONFIG_REISERFS_FS=y
-CONFIG_REISERFS_FS_XATTR=y
-CONFIG_REISERFS_FS_POSIX_ACL=y
-CONFIG_REISERFS_FS_SECURITY=y
-CONFIG_XFS_FS=y
-CONFIG_AUTOFS_FS=y
-CONFIG_AUTOFS4_FS=y
-CONFIG_ISO9660_FS=m
-CONFIG_JOLIET=y
-CONFIG_UDF_FS=m
-CONFIG_VFAT_FS=y
-CONFIG_NTFS_FS=m
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_HUGETLBFS=y
-CONFIG_NFS_FS=m
-CONFIG_NFS_V3=y
-CONFIG_NFS_V4=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V4=y
-CONFIG_SMB_FS=m
-CONFIG_SMB_NLS_DEFAULT=y
-CONFIG_CIFS=m
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_SGI_PARTITION=y
-CONFIG_EFI_PARTITION=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_CODEPAGE_737=m
-CONFIG_NLS_CODEPAGE_775=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_CODEPAGE_852=m
-CONFIG_NLS_CODEPAGE_855=m
-CONFIG_NLS_CODEPAGE_857=m
-CONFIG_NLS_CODEPAGE_860=m
-CONFIG_NLS_CODEPAGE_861=m
-CONFIG_NLS_CODEPAGE_862=m
-CONFIG_NLS_CODEPAGE_863=m
-CONFIG_NLS_CODEPAGE_864=m
-CONFIG_NLS_CODEPAGE_865=m
-CONFIG_NLS_CODEPAGE_866=m
-CONFIG_NLS_CODEPAGE_869=m
-CONFIG_NLS_CODEPAGE_936=m
-CONFIG_NLS_CODEPAGE_950=m
-CONFIG_NLS_CODEPAGE_932=m
-CONFIG_NLS_CODEPAGE_949=m
-CONFIG_NLS_CODEPAGE_874=m
-CONFIG_NLS_ISO8859_8=m
-CONFIG_NLS_CODEPAGE_1250=m
-CONFIG_NLS_CODEPAGE_1251=m
-CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_ISO8859_2=m
-CONFIG_NLS_ISO8859_3=m
-CONFIG_NLS_ISO8859_4=m
-CONFIG_NLS_ISO8859_5=m
-CONFIG_NLS_ISO8859_6=m
-CONFIG_NLS_ISO8859_7=m
-CONFIG_NLS_ISO8859_9=m
-CONFIG_NLS_ISO8859_13=m
-CONFIG_NLS_ISO8859_14=m
-CONFIG_NLS_ISO8859_15=m
-CONFIG_NLS_KOI8_R=m
-CONFIG_NLS_KOI8_U=m
-CONFIG_NLS_UTF8=m
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_MUTEXES=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_IA64_GRANULE_16MB=y
-CONFIG_CRYPTO_ECB=m
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_MD5=y
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
diff --git a/arch/ia64/include/asm/acpi.h b/arch/ia64/include/asm/acpi.h
index faa1bf0..d651102 100644
--- a/arch/ia64/include/asm/acpi.h
+++ b/arch/ia64/include/asm/acpi.h
@@ -111,8 +111,6 @@ static inline const char *acpi_get_sysname (void)
 	return "uv";
 # elif defined (CONFIG_IA64_DIG)
 	return "dig";
-# elif defined (CONFIG_IA64_XEN_GUEST)
-	return "xen";
 # elif defined(CONFIG_IA64_DIG_VTD)
 	return "dig_vtd";
 # else
diff --git a/arch/ia64/include/asm/machvec.h b/arch/ia64/include/asm/machvec.h
index 2d1ad4b1..9c39bdf 100644
--- a/arch/ia64/include/asm/machvec.h
+++ b/arch/ia64/include/asm/machvec.h
@@ -113,8 +113,6 @@ extern void machvec_tlb_migrate_finish (struct mm_struct *);
 #  include <asm/machvec_sn2.h>
 # elif defined (CONFIG_IA64_SGI_UV)
 #  include <asm/machvec_uv.h>
-# elif defined (CONFIG_IA64_XEN_GUEST)
-#  include <asm/machvec_xen.h>
 # elif defined (CONFIG_IA64_GENERIC)
 
 # ifdef MACHVEC_PLATFORM_HEADER
diff --git a/arch/ia64/include/asm/machvec_xen.h b/arch/ia64/include/asm/machvec_xen.h
deleted file mode 100644
index 8b8bd0e..0000000
--- a/arch/ia64/include/asm/machvec_xen.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef _ASM_IA64_MACHVEC_XEN_h
-#define _ASM_IA64_MACHVEC_XEN_h
-
-extern ia64_mv_setup_t			dig_setup;
-extern ia64_mv_cpu_init_t		xen_cpu_init;
-extern ia64_mv_irq_init_t		xen_irq_init;
-extern ia64_mv_send_ipi_t		xen_platform_send_ipi;
-
-/*
- * This stuff has dual use!
- *
- * For a generic kernel, the macros are used to initialize the
- * platform's machvec structure.  When compiling a non-generic kernel,
- * the macros are used directly.
- */
-#define ia64_platform_name			"xen"
-#define platform_setup				dig_setup
-#define platform_cpu_init			xen_cpu_init
-#define platform_irq_init			xen_irq_init
-#define platform_send_ipi			xen_platform_send_ipi
-
-#endif /* _ASM_IA64_MACHVEC_XEN_h */
diff --git a/arch/ia64/include/asm/meminit.h b/arch/ia64/include/asm/meminit.h
index 61c7b17..092f1c9 100644
--- a/arch/ia64/include/asm/meminit.h
+++ b/arch/ia64/include/asm/meminit.h
@@ -18,7 +18,6 @@
  * 	- crash dumping code reserved region
  * 	- Kernel memory map built from EFI memory map
  * 	- ELF core header
- *	- xen start info if CONFIG_XEN
  *
  * More could be added if necessary
  */
diff --git a/arch/ia64/include/asm/paravirt.h b/arch/ia64/include/asm/paravirt.h
index b149b88..b53518a 100644
--- a/arch/ia64/include/asm/paravirt.h
+++ b/arch/ia64/include/asm/paravirt.h
@@ -75,7 +75,6 @@ void *paravirt_get_gate_section(void);
 #ifdef CONFIG_PARAVIRT_GUEST
 
 #define PARAVIRT_HYPERVISOR_TYPE_DEFAULT	0
-#define PARAVIRT_HYPERVISOR_TYPE_XEN		1
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/ia64/include/asm/pvclock-abi.h b/arch/ia64/include/asm/pvclock-abi.h
index 44ef9ef..42b233b 100644
--- a/arch/ia64/include/asm/pvclock-abi.h
+++ b/arch/ia64/include/asm/pvclock-abi.h
@@ -11,7 +11,7 @@
 /*
  * These structs MUST NOT be changed.
  * They are the ABI between hypervisor and guest OS.
- * Both Xen and KVM are using this.
+ * KVM is using this.
  *
  * pvclock_vcpu_time_info holds the system time and the tsc timestamp
  * of the last update. So the guest can use the tsc delta to get a
diff --git a/arch/ia64/include/asm/sync_bitops.h b/arch/ia64/include/asm/sync_bitops.h
deleted file mode 100644
index 593c12e..0000000
--- a/arch/ia64/include/asm/sync_bitops.h
+++ /dev/null
@@ -1,51 +0,0 @@
-#ifndef _ASM_IA64_SYNC_BITOPS_H
-#define _ASM_IA64_SYNC_BITOPS_H
-
-/*
- * Copyright (C) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *
- * Based on synch_bitops.h which Dan Magenhaimer wrote.
- *
- * bit operations which provide guaranteed strong synchronisation
- * when communicating with Xen or other guest OSes running on other CPUs.
- */
-
-static inline void sync_set_bit(int nr, volatile void *addr)
-{
-	set_bit(nr, addr);
-}
-
-static inline void sync_clear_bit(int nr, volatile void *addr)
-{
-	clear_bit(nr, addr);
-}
-
-static inline void sync_change_bit(int nr, volatile void *addr)
-{
-	change_bit(nr, addr);
-}
-
-static inline int sync_test_and_set_bit(int nr, volatile void *addr)
-{
-	return test_and_set_bit(nr, addr);
-}
-
-static inline int sync_test_and_clear_bit(int nr, volatile void *addr)
-{
-	return test_and_clear_bit(nr, addr);
-}
-
-static inline int sync_test_and_change_bit(int nr, volatile void *addr)
-{
-	return test_and_change_bit(nr, addr);
-}
-
-static inline int sync_test_bit(int nr, const volatile void *addr)
-{
-	return test_bit(nr, addr);
-}
-
-#define sync_cmpxchg(ptr, old, new)				\
-	((__typeof__(*(ptr)))cmpxchg_acq((ptr), (old), (new)))
-
-#endif /* _ASM_IA64_SYNC_BITOPS_H */
diff --git a/arch/ia64/include/asm/xen/events.h b/arch/ia64/include/asm/xen/events.h
deleted file mode 100644
index baa74c8..0000000
--- a/arch/ia64/include/asm/xen/events.h
+++ /dev/null
@@ -1,41 +0,0 @@
-/******************************************************************************
- * arch/ia64/include/asm/xen/events.h
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-#ifndef _ASM_IA64_XEN_EVENTS_H
-#define _ASM_IA64_XEN_EVENTS_H
-
-enum ipi_vector {
-	XEN_RESCHEDULE_VECTOR,
-	XEN_IPI_VECTOR,
-	XEN_CMCP_VECTOR,
-	XEN_CPEP_VECTOR,
-
-	XEN_NR_IPIS,
-};
-
-static inline int xen_irqs_disabled(struct pt_regs *regs)
-{
-	return !(ia64_psr(regs)->i);
-}
-
-#define irq_ctx_init(cpu)	do { } while (0)
-
-#endif /* _ASM_IA64_XEN_EVENTS_H */
diff --git a/arch/ia64/include/asm/xen/hypercall.h b/arch/ia64/include/asm/xen/hypercall.h
deleted file mode 100644
index ed28bcd..0000000
--- a/arch/ia64/include/asm/xen/hypercall.h
+++ /dev/null
@@ -1,265 +0,0 @@
-/******************************************************************************
- * hypercall.h
- *
- * Linux-specific hypervisor handling.
- *
- * Copyright (c) 2002-2004, K A Fraser
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation; or, when distributed
- * separately from the Linux kernel or incorporated into other
- * software packages, subject to the following license:
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this source file (the "Software"), to deal in the Software without
- * restriction, including without limitation the rights to use, copy, modify,
- * merge, publish, distribute, sublicense, and/or sell copies of the Software,
- * and to permit persons to whom the Software is furnished to do so, subject to
- * the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
- */
-
-#ifndef _ASM_IA64_XEN_HYPERCALL_H
-#define _ASM_IA64_XEN_HYPERCALL_H
-
-#include <xen/interface/xen.h>
-#include <xen/interface/physdev.h>
-#include <xen/interface/sched.h>
-#include <asm/xen/xcom_hcall.h>
-struct xencomm_handle;
-extern unsigned long __hypercall(unsigned long a1, unsigned long a2,
-				 unsigned long a3, unsigned long a4,
-				 unsigned long a5, unsigned long cmd);
-
-/*
- * Assembler stubs for hyper-calls.
- */
-
-#define _hypercall0(type, name)					\
-({								\
-	long __res;						\
-	__res = __hypercall(0, 0, 0, 0, 0, __HYPERVISOR_##name);\
-	(type)__res;						\
-})
-
-#define _hypercall1(type, name, a1)				\
-({								\
-	long __res;						\
-	__res = __hypercall((unsigned long)a1,			\
-			     0, 0, 0, 0, __HYPERVISOR_##name);	\
-	(type)__res;						\
-})
-
-#define _hypercall2(type, name, a1, a2)				\
-({								\
-	long __res;						\
-	__res = __hypercall((unsigned long)a1,			\
-			    (unsigned long)a2,			\
-			    0, 0, 0, __HYPERVISOR_##name);	\
-	(type)__res;						\
-})
-
-#define _hypercall3(type, name, a1, a2, a3)			\
-({								\
-	long __res;						\
-	__res = __hypercall((unsigned long)a1,			\
-			    (unsigned long)a2,			\
-			    (unsigned long)a3,			\
-			    0, 0, __HYPERVISOR_##name);		\
-	(type)__res;						\
-})
-
-#define _hypercall4(type, name, a1, a2, a3, a4)			\
-({								\
-	long __res;						\
-	__res = __hypercall((unsigned long)a1,			\
-			    (unsigned long)a2,			\
-			    (unsigned long)a3,			\
-			    (unsigned long)a4,			\
-			    0, __HYPERVISOR_##name);		\
-	(type)__res;						\
-})
-
-#define _hypercall5(type, name, a1, a2, a3, a4, a5)		\
-({								\
-	long __res;						\
-	__res = __hypercall((unsigned long)a1,			\
-			    (unsigned long)a2,			\
-			    (unsigned long)a3,			\
-			    (unsigned long)a4,			\
-			    (unsigned long)a5,			\
-			    __HYPERVISOR_##name);		\
-	(type)__res;						\
-})
-
-
-static inline int
-xencomm_arch_hypercall_sched_op(int cmd, struct xencomm_handle *arg)
-{
-	return _hypercall2(int, sched_op, cmd, arg);
-}
-
-static inline long
-HYPERVISOR_set_timer_op(u64 timeout)
-{
-	unsigned long timeout_hi = (unsigned long)(timeout >> 32);
-	unsigned long timeout_lo = (unsigned long)timeout;
-	return _hypercall2(long, set_timer_op, timeout_lo, timeout_hi);
-}
-
-static inline int
-xencomm_arch_hypercall_multicall(struct xencomm_handle *call_list,
-				 int nr_calls)
-{
-	return _hypercall2(int, multicall, call_list, nr_calls);
-}
-
-static inline int
-xencomm_arch_hypercall_memory_op(unsigned int cmd, struct xencomm_handle *arg)
-{
-	return _hypercall2(int, memory_op, cmd, arg);
-}
-
-static inline int
-xencomm_arch_hypercall_event_channel_op(int cmd, struct xencomm_handle *arg)
-{
-	return _hypercall2(int, event_channel_op, cmd, arg);
-}
-
-static inline int
-xencomm_arch_hypercall_xen_version(int cmd, struct xencomm_handle *arg)
-{
-	return _hypercall2(int, xen_version, cmd, arg);
-}
-
-static inline int
-xencomm_arch_hypercall_console_io(int cmd, int count,
-				  struct xencomm_handle *str)
-{
-	return _hypercall3(int, console_io, cmd, count, str);
-}
-
-static inline int
-xencomm_arch_hypercall_physdev_op(int cmd, struct xencomm_handle *arg)
-{
-	return _hypercall2(int, physdev_op, cmd, arg);
-}
-
-static inline int
-xencomm_arch_hypercall_grant_table_op(unsigned int cmd,
-				      struct xencomm_handle *uop,
-				      unsigned int count)
-{
-	return _hypercall3(int, grant_table_op, cmd, uop, count);
-}
-
-int HYPERVISOR_grant_table_op(unsigned int cmd, void *uop, unsigned int count);
-
-extern int xencomm_arch_hypercall_suspend(struct xencomm_handle *arg);
-
-static inline int
-xencomm_arch_hypercall_callback_op(int cmd, struct xencomm_handle *arg)
-{
-	return _hypercall2(int, callback_op, cmd, arg);
-}
-
-static inline long
-xencomm_arch_hypercall_vcpu_op(int cmd, int cpu, void *arg)
-{
-	return _hypercall3(long, vcpu_op, cmd, cpu, arg);
-}
-
-static inline int
-HYPERVISOR_physdev_op(int cmd, void *arg)
-{
-	switch (cmd) {
-	case PHYSDEVOP_eoi:
-		return _hypercall1(int, ia64_fast_eoi,
-				   ((struct physdev_eoi *)arg)->irq);
-	default:
-		return xencomm_hypercall_physdev_op(cmd, arg);
-	}
-}
-
-static inline long
-xencomm_arch_hypercall_opt_feature(struct xencomm_handle *arg)
-{
-	return _hypercall1(long, opt_feature, arg);
-}
-
-/* for balloon driver */
-#define HYPERVISOR_update_va_mapping(va, new_val, flags) (0)
-
-/* Use xencomm to do hypercalls.  */
-#define HYPERVISOR_sched_op xencomm_hypercall_sched_op
-#define HYPERVISOR_event_channel_op xencomm_hypercall_event_channel_op
-#define HYPERVISOR_callback_op xencomm_hypercall_callback_op
-#define HYPERVISOR_multicall xencomm_hypercall_multicall
-#define HYPERVISOR_xen_version xencomm_hypercall_xen_version
-#define HYPERVISOR_console_io xencomm_hypercall_console_io
-#define HYPERVISOR_memory_op xencomm_hypercall_memory_op
-#define HYPERVISOR_suspend xencomm_hypercall_suspend
-#define HYPERVISOR_vcpu_op xencomm_hypercall_vcpu_op
-#define HYPERVISOR_opt_feature xencomm_hypercall_opt_feature
-
-/* to compile gnttab_copy_grant_page() in drivers/xen/core/gnttab.c */
-#define HYPERVISOR_mmu_update(req, count, success_count, domid) ({ BUG(); 0; })
-
-static inline int
-HYPERVISOR_shutdown(
-	unsigned int reason)
-{
-	struct sched_shutdown sched_shutdown = {
-		.reason = reason
-	};
-
-	int rc = HYPERVISOR_sched_op(SCHEDOP_shutdown, &sched_shutdown);
-
-	return rc;
-}
-
-/* for netfront.c, netback.c */
-#define MULTI_UVMFLAGS_INDEX 0 /* XXX any value */
-
-static inline void
-MULTI_update_va_mapping(
-	struct multicall_entry *mcl, unsigned long va,
-	pte_t new_val, unsigned long flags)
-{
-	mcl->op = __HYPERVISOR_update_va_mapping;
-	mcl->result = 0;
-}
-
-static inline void
-MULTI_grant_table_op(struct multicall_entry *mcl, unsigned int cmd,
-	void *uop, unsigned int count)
-{
-	mcl->op = __HYPERVISOR_grant_table_op;
-	mcl->args[0] = cmd;
-	mcl->args[1] = (unsigned long)uop;
-	mcl->args[2] = count;
-}
-
-static inline void
-MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req,
-		 int count, int *success_count, domid_t domid)
-{
-	mcl->op = __HYPERVISOR_mmu_update;
-	mcl->args[0] = (unsigned long)req;
-	mcl->args[1] = count;
-	mcl->args[2] = (unsigned long)success_count;
-	mcl->args[3] = domid;
-}
-
-#endif /* _ASM_IA64_XEN_HYPERCALL_H */
diff --git a/arch/ia64/include/asm/xen/hypervisor.h b/arch/ia64/include/asm/xen/hypervisor.h
deleted file mode 100644
index 67455c2..0000000
--- a/arch/ia64/include/asm/xen/hypervisor.h
+++ /dev/null
@@ -1,61 +0,0 @@
-/******************************************************************************
- * hypervisor.h
- *
- * Linux-specific hypervisor handling.
- *
- * Copyright (c) 2002-2004, K A Fraser
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation; or, when distributed
- * separately from the Linux kernel or incorporated into other
- * software packages, subject to the following license:
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this source file (the "Software"), to deal in the Software without
- * restriction, including without limitation the rights to use, copy, modify,
- * merge, publish, distribute, sublicense, and/or sell copies of the Software,
- * and to permit persons to whom the Software is furnished to do so, subject to
- * the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
- */
-
-#ifndef _ASM_IA64_XEN_HYPERVISOR_H
-#define _ASM_IA64_XEN_HYPERVISOR_H
-
-#include <linux/err.h>
-#include <xen/interface/xen.h>
-#include <xen/interface/version.h>	/* to compile feature.c */
-#include <xen/features.h>		/* to comiple xen-netfront.c */
-#include <xen/xen.h>
-#include <asm/xen/hypercall.h>
-
-#ifdef CONFIG_XEN
-extern struct shared_info *HYPERVISOR_shared_info;
-extern struct start_info *xen_start_info;
-
-void __init xen_setup_vcpu_info_placement(void);
-void force_evtchn_callback(void);
-
-/* for drivers/xen/balloon/balloon.c */
-#ifdef CONFIG_XEN_SCRUB_PAGES
-#define scrub_pages(_p, _n) memset((void *)(_p), 0, (_n) << PAGE_SHIFT)
-#else
-#define scrub_pages(_p, _n) ((void)0)
-#endif
-
-/* For setup_arch() in arch/ia64/kernel/setup.c */
-void xen_ia64_enable_opt_feature(void);
-#endif
-
-#endif /* _ASM_IA64_XEN_HYPERVISOR_H */
diff --git a/arch/ia64/include/asm/xen/inst.h b/arch/ia64/include/asm/xen/inst.h
deleted file mode 100644
index c53a476..0000000
--- a/arch/ia64/include/asm/xen/inst.h
+++ /dev/null
@@ -1,486 +0,0 @@
-/******************************************************************************
- * arch/ia64/include/asm/xen/inst.h
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#include <asm/xen/privop.h>
-
-#define ia64_ivt				xen_ivt
-#define DO_SAVE_MIN				XEN_DO_SAVE_MIN
-
-#define __paravirt_switch_to			xen_switch_to
-#define __paravirt_leave_syscall		xen_leave_syscall
-#define __paravirt_work_processed_syscall	xen_work_processed_syscall
-#define __paravirt_leave_kernel			xen_leave_kernel
-#define __paravirt_pending_syscall_end		xen_work_pending_syscall_end
-#define __paravirt_work_processed_syscall_target \
-						xen_work_processed_syscall
-
-#define paravirt_fsyscall_table			xen_fsyscall_table
-#define paravirt_fsys_bubble_down		xen_fsys_bubble_down
-
-#define MOV_FROM_IFA(reg)	\
-	movl reg = XSI_IFA;	\
-	;;			\
-	ld8 reg = [reg]
-
-#define MOV_FROM_ITIR(reg)	\
-	movl reg = XSI_ITIR;	\
-	;;			\
-	ld8 reg = [reg]
-
-#define MOV_FROM_ISR(reg)	\
-	movl reg = XSI_ISR;	\
-	;;			\
-	ld8 reg = [reg]
-
-#define MOV_FROM_IHA(reg)	\
-	movl reg = XSI_IHA;	\
-	;;			\
-	ld8 reg = [reg]
-
-#define MOV_FROM_IPSR(pred, reg)	\
-(pred)	movl reg = XSI_IPSR;		\
-	;;				\
-(pred)	ld8 reg = [reg]
-
-#define MOV_FROM_IIM(reg)	\
-	movl reg = XSI_IIM;	\
-	;;			\
-	ld8 reg = [reg]
-
-#define MOV_FROM_IIP(reg)	\
-	movl reg = XSI_IIP;	\
-	;;			\
-	ld8 reg = [reg]
-
-.macro __MOV_FROM_IVR reg, clob
-	.ifc "\reg", "r8"
-		XEN_HYPER_GET_IVR
-		.exitm
-	.endif
-	.ifc "\clob", "r8"
-		XEN_HYPER_GET_IVR
-		;;
-		mov \reg = r8
-		.exitm
-	.endif
-
-	mov \clob = r8
-	;;
-	XEN_HYPER_GET_IVR
-	;;
-	mov \reg = r8
-	;;
-	mov r8 = \clob
-.endm
-#define MOV_FROM_IVR(reg, clob)	__MOV_FROM_IVR reg, clob
-
-.macro __MOV_FROM_PSR pred, reg, clob
-	.ifc "\reg", "r8"
-		(\pred)	XEN_HYPER_GET_PSR;
-		.exitm
-	.endif
-	.ifc "\clob", "r8"
-		(\pred)	XEN_HYPER_GET_PSR
-		;;
-		(\pred)	mov \reg = r8
-		.exitm
-	.endif
-
-	(\pred)	mov \clob = r8
-	(\pred)	XEN_HYPER_GET_PSR
-	;;
-	(\pred)	mov \reg = r8
-	(\pred)	mov r8 = \clob
-.endm
-#define MOV_FROM_PSR(pred, reg, clob)	__MOV_FROM_PSR pred, reg, clob
-
-/* assuming ar.itc is read with interrupt disabled. */
-#define MOV_FROM_ITC(pred, pred_clob, reg, clob)		\
-(pred)	movl clob = XSI_ITC_OFFSET;				\
-	;;							\
-(pred)	ld8 clob = [clob];					\
-(pred)	mov reg = ar.itc;					\
-	;;							\
-(pred)	add reg = reg, clob;					\
-	;;							\
-(pred)	movl clob = XSI_ITC_LAST;				\
-	;;							\
-(pred)	ld8 clob = [clob];					\
-	;;							\
-(pred)	cmp.geu.unc pred_clob, p0 = clob, reg;			\
-	;;							\
-(pred_clob)	add reg = 1, clob;				\
-	;;							\
-(pred)	movl clob = XSI_ITC_LAST;				\
-	;;							\
-(pred)	st8 [clob] = reg
-
-
-#define MOV_TO_IFA(reg, clob)	\
-	movl clob = XSI_IFA;	\
-	;;			\
-	st8 [clob] = reg	\
-
-#define MOV_TO_ITIR(pred, reg, clob)	\
-(pred)	movl clob = XSI_ITIR;		\
-	;;				\
-(pred)	st8 [clob] = reg
-
-#define MOV_TO_IHA(pred, reg, clob)	\
-(pred)	movl clob = XSI_IHA;		\
-	;;				\
-(pred)	st8 [clob] = reg
-
-#define MOV_TO_IPSR(pred, reg, clob)	\
-(pred)	movl clob = XSI_IPSR;		\
-	;;				\
-(pred)	st8 [clob] = reg;		\
-	;;
-
-#define MOV_TO_IFS(pred, reg, clob)	\
-(pred)	movl clob = XSI_IFS;		\
-	;;				\
-(pred)	st8 [clob] = reg;		\
-	;;
-
-#define MOV_TO_IIP(reg, clob)	\
-	movl clob = XSI_IIP;	\
-	;;			\
-	st8 [clob] = reg
-
-.macro ____MOV_TO_KR kr, reg, clob0, clob1
-	.ifc "\clob0", "r9"
-		.error "clob0 \clob0 must not be r9"
-	.endif
-	.ifc "\clob1", "r8"
-		.error "clob1 \clob1 must not be r8"
-	.endif
-
-	.ifnc "\reg", "r9"
-		.ifnc "\clob1", "r9"
-			mov \clob1 = r9
-		.endif
-		mov r9 = \reg
-	.endif
-	.ifnc "\clob0", "r8"
-		mov \clob0 = r8
-	.endif
-	mov r8 = \kr
-	;;
-	XEN_HYPER_SET_KR
-
-	.ifnc "\reg", "r9"
-		.ifnc "\clob1", "r9"
-			mov r9 = \clob1
-		.endif
-	.endif
-	.ifnc "\clob0", "r8"
-		mov r8 = \clob0
-	.endif
-.endm
-
-.macro __MOV_TO_KR kr, reg, clob0, clob1
-	.ifc "\clob0", "r9"
-		____MOV_TO_KR \kr, \reg, \clob1, \clob0
-		.exitm
-	.endif
-	.ifc "\clob1", "r8"
-		____MOV_TO_KR \kr, \reg, \clob1, \clob0
-		.exitm
-	.endif
-
-	____MOV_TO_KR \kr, \reg, \clob0, \clob1
-.endm
-
-#define MOV_TO_KR(kr, reg, clob0, clob1) \
-	__MOV_TO_KR IA64_KR_ ## kr, reg, clob0, clob1
-
-
-.macro __ITC_I pred, reg, clob
-	.ifc "\reg", "r8"
-		(\pred)	XEN_HYPER_ITC_I
-		.exitm
-	.endif
-	.ifc "\clob", "r8"
-		(\pred)	mov r8 = \reg
-		;;
-		(\pred)	XEN_HYPER_ITC_I
-		.exitm
-	.endif
-
-	(\pred)	mov \clob = r8
-	(\pred)	mov r8 = \reg
-	;;
-	(\pred)	XEN_HYPER_ITC_I
-	;;
-	(\pred)	mov r8 = \clob
-	;;
-.endm
-#define ITC_I(pred, reg, clob)	__ITC_I pred, reg, clob
-
-.macro __ITC_D pred, reg, clob
-	.ifc "\reg", "r8"
-		(\pred)	XEN_HYPER_ITC_D
-		;;
-		.exitm
-	.endif
-	.ifc "\clob", "r8"
-		(\pred)	mov r8 = \reg
-		;;
-		(\pred)	XEN_HYPER_ITC_D
-		;;
-		.exitm
-	.endif
-
-	(\pred)	mov \clob = r8
-	(\pred)	mov r8 = \reg
-	;;
-	(\pred)	XEN_HYPER_ITC_D
-	;;
-	(\pred)	mov r8 = \clob
-	;;
-.endm
-#define ITC_D(pred, reg, clob)	__ITC_D pred, reg, clob
-
-.macro __ITC_I_AND_D pred_i, pred_d, reg, clob
-	.ifc "\reg", "r8"
-		(\pred_i)XEN_HYPER_ITC_I
-		;;
-		(\pred_d)XEN_HYPER_ITC_D
-		;;
-		.exitm
-	.endif
-	.ifc "\clob", "r8"
-		mov r8 = \reg
-		;;
-		(\pred_i)XEN_HYPER_ITC_I
-		;;
-		(\pred_d)XEN_HYPER_ITC_D
-		;;
-		.exitm
-	.endif
-
-	mov \clob = r8
-	mov r8 = \reg
-	;;
-	(\pred_i)XEN_HYPER_ITC_I
-	;;
-	(\pred_d)XEN_HYPER_ITC_D
-	;;
-	mov r8 = \clob
-	;;
-.endm
-#define ITC_I_AND_D(pred_i, pred_d, reg, clob) \
-	__ITC_I_AND_D pred_i, pred_d, reg, clob
-
-.macro __THASH pred, reg0, reg1, clob
-	.ifc "\reg0", "r8"
-		(\pred)	mov r8 = \reg1
-		(\pred)	XEN_HYPER_THASH
-		.exitm
-	.endc
-	.ifc "\reg1", "r8"
-		(\pred)	XEN_HYPER_THASH
-		;;
-		(\pred)	mov \reg0 = r8
-		;;
-		.exitm
-	.endif
-	.ifc "\clob", "r8"
-		(\pred)	mov r8 = \reg1
-		(\pred)	XEN_HYPER_THASH
-		;;
-		(\pred)	mov \reg0 = r8
-		;;
-		.exitm
-	.endif
-
-	(\pred)	mov \clob = r8
-	(\pred)	mov r8 = \reg1
-	(\pred)	XEN_HYPER_THASH
-	;;
-	(\pred)	mov \reg0 = r8
-	(\pred)	mov r8 = \clob
-	;;
-.endm
-#define THASH(pred, reg0, reg1, clob) __THASH pred, reg0, reg1, clob
-
-#define SSM_PSR_IC_AND_DEFAULT_BITS_AND_SRLZ_I(clob0, clob1)	\
-	mov clob0 = 1;						\
-	movl clob1 = XSI_PSR_IC;				\
-	;;							\
-	st4 [clob1] = clob0					\
-	;;
-
-#define SSM_PSR_IC_AND_SRLZ_D(clob0, clob1)	\
-	;;					\
-	srlz.d;					\
-	mov clob1 = 1;				\
-	movl clob0 = XSI_PSR_IC;		\
-	;;					\
-	st4 [clob0] = clob1
-
-#define RSM_PSR_IC(clob)	\
-	movl clob = XSI_PSR_IC;	\
-	;;			\
-	st4 [clob] = r0;	\
-	;;
-
-/* pred will be clobbered */
-#define MASK_TO_PEND_OFS    (-1)
-#define SSM_PSR_I(pred, pred_clob, clob)				\
-(pred)	movl clob = XSI_PSR_I_ADDR					\
-	;;								\
-(pred)	ld8 clob = [clob]						\
-	;;								\
-	/* if (pred) vpsr.i = 1 */					\
-	/* if (pred) (vcpu->vcpu_info->evtchn_upcall_mask)=0 */		\
-(pred)	st1 [clob] = r0, MASK_TO_PEND_OFS				\
-	;;								\
-	/* if (vcpu->vcpu_info->evtchn_upcall_pending) */		\
-(pred)	ld1 clob = [clob]						\
-	;;								\
-(pred)	cmp.ne.unc pred_clob, p0 = clob, r0				\
-	;;								\
-(pred_clob)XEN_HYPER_SSM_I	/* do areal ssm psr.i */
-
-#define RSM_PSR_I(pred, clob0, clob1)	\
-	movl clob0 = XSI_PSR_I_ADDR;	\
-	mov clob1 = 1;			\
-	;;				\
-	ld8 clob0 = [clob0];		\
-	;;				\
-(pred)	st1 [clob0] = clob1
-
-#define RSM_PSR_I_IC(clob0, clob1, clob2)		\
-	movl clob0 = XSI_PSR_I_ADDR;			\
-	movl clob1 = XSI_PSR_IC;			\
-	;;						\
-	ld8 clob0 = [clob0];				\
-	mov clob2 = 1;					\
-	;;						\
-	/* note: clears both vpsr.i and vpsr.ic! */	\
-	st1 [clob0] = clob2;				\
-	st4 [clob1] = r0;				\
-	;;
-
-#define RSM_PSR_DT		\
-	XEN_HYPER_RSM_PSR_DT
-
-#define RSM_PSR_BE_I(clob0, clob1)	\
-	RSM_PSR_I(p0, clob0, clob1);	\
-	rum psr.be
-
-#define SSM_PSR_DT_AND_SRLZ_I	\
-	XEN_HYPER_SSM_PSR_DT
-
-#define BSW_0(clob0, clob1, clob2)			\
-	;;						\
-	/* r16-r31 all now hold bank1 values */		\
-	mov clob2 = ar.unat;				\
-	movl clob0 = XSI_BANK1_R16;			\
-	movl clob1 = XSI_BANK1_R16 + 8;			\
-	;;						\
-.mem.offset 0, 0; st8.spill [clob0] = r16, 16;		\
-.mem.offset 8, 0; st8.spill [clob1] = r17, 16;		\
-	;;						\
-.mem.offset 0, 0; st8.spill [clob0] = r18, 16;		\
-.mem.offset 8, 0; st8.spill [clob1] = r19, 16;		\
-	;;						\
-.mem.offset 0, 0; st8.spill [clob0] = r20, 16;		\
-.mem.offset 8, 0; st8.spill [clob1] = r21, 16;		\
-	;;						\
-.mem.offset 0, 0; st8.spill [clob0] = r22, 16;		\
-.mem.offset 8, 0; st8.spill [clob1] = r23, 16;		\
-	;;						\
-.mem.offset 0, 0; st8.spill [clob0] = r24, 16;		\
-.mem.offset 8, 0; st8.spill [clob1] = r25, 16;		\
-	;;						\
-.mem.offset 0, 0; st8.spill [clob0] = r26, 16;		\
-.mem.offset 8, 0; st8.spill [clob1] = r27, 16;		\
-	;;						\
-.mem.offset 0, 0; st8.spill [clob0] = r28, 16;		\
-.mem.offset 8, 0; st8.spill [clob1] = r29, 16;		\
-	;;						\
-.mem.offset 0, 0; st8.spill [clob0] = r30, 16;		\
-.mem.offset 8, 0; st8.spill [clob1] = r31, 16;		\
-	;;						\
-	mov clob1 = ar.unat;				\
-	movl clob0 = XSI_B1NAT;				\
-	;;						\
-	st8 [clob0] = clob1;				\
-	mov ar.unat = clob2;				\
-	movl clob0 = XSI_BANKNUM;			\
-	;;						\
-	st4 [clob0] = r0
-
-
-	/* FIXME: THIS CODE IS NOT NaT SAFE! */
-#define XEN_BSW_1(clob)			\
-	mov clob = ar.unat;		\
-	movl r30 = XSI_B1NAT;		\
-	;;				\
-	ld8 r30 = [r30];		\
-	mov r31 = 1;			\
-	;;				\
-	mov ar.unat = r30;		\
-	movl r30 = XSI_BANKNUM;		\
-	;;				\
-	st4 [r30] = r31;		\
-	movl r30 = XSI_BANK1_R16;	\
-	movl r31 = XSI_BANK1_R16+8;	\
-	;;				\
-	ld8.fill r16 = [r30], 16;	\
-	ld8.fill r17 = [r31], 16;	\
-	;;				\
-	ld8.fill r18 = [r30], 16;	\
-	ld8.fill r19 = [r31], 16;	\
-	;;				\
-	ld8.fill r20 = [r30], 16;	\
-	ld8.fill r21 = [r31], 16;	\
-	;;				\
-	ld8.fill r22 = [r30], 16;	\
-	ld8.fill r23 = [r31], 16;	\
-	;;				\
-	ld8.fill r24 = [r30], 16;	\
-	ld8.fill r25 = [r31], 16;	\
-	;;				\
-	ld8.fill r26 = [r30], 16;	\
-	ld8.fill r27 = [r31], 16;	\
-	;;				\
-	ld8.fill r28 = [r30], 16;	\
-	ld8.fill r29 = [r31], 16;	\
-	;;				\
-	ld8.fill r30 = [r30];		\
-	ld8.fill r31 = [r31];		\
-	;;				\
-	mov ar.unat = clob
-
-#define BSW_1(clob0, clob1)	XEN_BSW_1(clob1)
-
-
-#define COVER	\
-	XEN_HYPER_COVER
-
-#define RFI			\
-	XEN_HYPER_RFI;		\
-	dv_serialize_data
diff --git a/arch/ia64/include/asm/xen/interface.h b/arch/ia64/include/asm/xen/interface.h
deleted file mode 100644
index e88c5de..0000000
--- a/arch/ia64/include/asm/xen/interface.h
+++ /dev/null
@@ -1,363 +0,0 @@
-/******************************************************************************
- * arch-ia64/hypervisor-if.h
- *
- * Guest OS interface to IA64 Xen.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to
- * deal in the Software without restriction, including without limitation the
- * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
- * sell copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- *
- * Copyright by those who contributed. (in alphabetical order)
- *
- * Anthony Xu <anthony.xu@intel.com>
- * Eddie Dong <eddie.dong@intel.com>
- * Fred Yang <fred.yang@intel.com>
- * Kevin Tian <kevin.tian@intel.com>
- * Alex Williamson <alex.williamson@hp.com>
- * Chris Wright <chrisw@sous-sol.org>
- * Christian Limpach <Christian.Limpach@cl.cam.ac.uk>
- * Dietmar Hahn <dietmar.hahn@fujitsu-siemens.com>
- * Hollis Blanchard <hollisb@us.ibm.com>
- * Isaku Yamahata <yamahata@valinux.co.jp>
- * Jan Beulich <jbeulich@novell.com>
- * John Levon <john.levon@sun.com>
- * Kazuhiro Suzuki <kaz@jp.fujitsu.com>
- * Keir Fraser <keir.fraser@citrix.com>
- * Kouya Shimura <kouya@jp.fujitsu.com>
- * Masaki Kanno <kanno.masaki@jp.fujitsu.com>
- * Matt Chapman <matthewc@hp.com>
- * Matthew Chapman <matthewc@hp.com>
- * Samuel Thibault <samuel.thibault@eu.citrix.com>
- * Tomonari Horikoshi <t.horikoshi@jp.fujitsu.com>
- * Tristan Gingold <tgingold@free.fr>
- * Tsunehisa Doi <Doi.Tsunehisa@jp.fujitsu.com>
- * Yutaka Ezaki <yutaka.ezaki@jp.fujitsu.com>
- * Zhang Xin <xing.z.zhang@intel.com>
- * Zhang xiantao <xiantao.zhang@intel.com>
- * dan.magenheimer@hp.com
- * ian.pratt@cl.cam.ac.uk
- * michael.fetterman@cl.cam.ac.uk
- */
-
-#ifndef _ASM_IA64_XEN_INTERFACE_H
-#define _ASM_IA64_XEN_INTERFACE_H
-
-#define __DEFINE_GUEST_HANDLE(name, type)	\
-	typedef struct { type *p; } __guest_handle_ ## name
-
-#define DEFINE_GUEST_HANDLE_STRUCT(name)	\
-	__DEFINE_GUEST_HANDLE(name, struct name)
-#define DEFINE_GUEST_HANDLE(name)	__DEFINE_GUEST_HANDLE(name, name)
-#define GUEST_HANDLE(name)		__guest_handle_ ## name
-#define GUEST_HANDLE_64(name)		GUEST_HANDLE(name)
-#define set_xen_guest_handle(hnd, val)	do { (hnd).p = val; } while (0)
-
-#ifndef __ASSEMBLY__
-/* Explicitly size integers that represent pfns in the public interface
- * with Xen so that we could have one ABI that works for 32 and 64 bit
- * guests. */
-typedef unsigned long xen_pfn_t;
-typedef unsigned long xen_ulong_t;
-/* Guest handles for primitive C types. */
-__DEFINE_GUEST_HANDLE(uchar, unsigned char);
-__DEFINE_GUEST_HANDLE(uint, unsigned int);
-__DEFINE_GUEST_HANDLE(ulong, unsigned long);
-
-DEFINE_GUEST_HANDLE(char);
-DEFINE_GUEST_HANDLE(int);
-DEFINE_GUEST_HANDLE(long);
-DEFINE_GUEST_HANDLE(void);
-DEFINE_GUEST_HANDLE(uint64_t);
-DEFINE_GUEST_HANDLE(uint32_t);
-
-DEFINE_GUEST_HANDLE(xen_pfn_t);
-#define PRI_xen_pfn	"lx"
-#endif
-
-/* Arch specific VIRQs definition */
-#define VIRQ_ITC	VIRQ_ARCH_0	/* V. Virtual itc timer */
-#define VIRQ_MCA_CMC	VIRQ_ARCH_1	/* MCA cmc interrupt */
-#define VIRQ_MCA_CPE	VIRQ_ARCH_2	/* MCA cpe interrupt */
-
-/* Maximum number of virtual CPUs in multi-processor guests. */
-/* keep sizeof(struct shared_page) <= PAGE_SIZE.
- * this is checked in arch/ia64/xen/hypervisor.c. */
-#define MAX_VIRT_CPUS	64
-
-#ifndef __ASSEMBLY__
-
-#define INVALID_MFN	(~0UL)
-
-union vac {
-	unsigned long value;
-	struct {
-		int a_int:1;
-		int a_from_int_cr:1;
-		int a_to_int_cr:1;
-		int a_from_psr:1;
-		int a_from_cpuid:1;
-		int a_cover:1;
-		int a_bsw:1;
-		long reserved:57;
-	};
-};
-
-union vdc {
-	unsigned long value;
-	struct {
-		int d_vmsw:1;
-		int d_extint:1;
-		int d_ibr_dbr:1;
-		int d_pmc:1;
-		int d_to_pmd:1;
-		int d_itm:1;
-		long reserved:58;
-	};
-};
-
-struct mapped_regs {
-	union vac vac;
-	union vdc vdc;
-	unsigned long virt_env_vaddr;
-	unsigned long reserved1[29];
-	unsigned long vhpi;
-	unsigned long reserved2[95];
-	union {
-		unsigned long vgr[16];
-		unsigned long bank1_regs[16];	/* bank1 regs (r16-r31)
-						   when bank0 active */
-	};
-	union {
-		unsigned long vbgr[16];
-		unsigned long bank0_regs[16];	/* bank0 regs (r16-r31)
-						   when bank1 active */
-	};
-	unsigned long vnat;
-	unsigned long vbnat;
-	unsigned long vcpuid[5];
-	unsigned long reserved3[11];
-	unsigned long vpsr;
-	unsigned long vpr;
-	unsigned long reserved4[76];
-	union {
-		unsigned long vcr[128];
-		struct {
-			unsigned long dcr;	/* CR0 */
-			unsigned long itm;
-			unsigned long iva;
-			unsigned long rsv1[5];
-			unsigned long pta;	/* CR8 */
-			unsigned long rsv2[7];
-			unsigned long ipsr;	/* CR16 */
-			unsigned long isr;
-			unsigned long rsv3;
-			unsigned long iip;
-			unsigned long ifa;
-			unsigned long itir;
-			unsigned long iipa;
-			unsigned long ifs;
-			unsigned long iim;	/* CR24 */
-			unsigned long iha;
-			unsigned long rsv4[38];
-			unsigned long lid;	/* CR64 */
-			unsigned long ivr;
-			unsigned long tpr;
-			unsigned long eoi;
-			unsigned long irr[4];
-			unsigned long itv;	/* CR72 */
-			unsigned long pmv;
-			unsigned long cmcv;
-			unsigned long rsv5[5];
-			unsigned long lrr0;	/* CR80 */
-			unsigned long lrr1;
-			unsigned long rsv6[46];
-		};
-	};
-	union {
-		unsigned long reserved5[128];
-		struct {
-			unsigned long precover_ifs;
-			unsigned long unat;	/* not sure if this is needed
-						   until NaT arch is done */
-			int interrupt_collection_enabled; /* virtual psr.ic */
-
-			/* virtual interrupt deliverable flag is
-			 * evtchn_upcall_mask in shared info area now.
-			 * interrupt_mask_addr is the address
-			 * of evtchn_upcall_mask for current vcpu
-			 */
-			unsigned char *interrupt_mask_addr;
-			int pending_interruption;
-			unsigned char vpsr_pp;
-			unsigned char vpsr_dfh;
-			unsigned char hpsr_dfh;
-			unsigned char hpsr_mfh;
-			unsigned long reserved5_1[4];
-			int metaphysical_mode;	/* 1 = use metaphys mapping
-						   0 = use virtual */
-			int banknum;		/* 0 or 1, which virtual
-						   register bank is active */
-			unsigned long rrs[8];	/* region registers */
-			unsigned long krs[8];	/* kernel registers */
-			unsigned long tmp[16];	/* temp registers
-						   (e.g. for hyperprivops) */
-
-			/* itc paravirtualization
-			 * vAR.ITC = mAR.ITC + itc_offset
-			 * itc_last is one which was lastly passed to
-			 * the guest OS in order to prevent it from
-			 * going backwords.
-			 */
-			unsigned long itc_offset;
-			unsigned long itc_last;
-		};
-	};
-};
-
-struct arch_vcpu_info {
-	/* nothing */
-};
-
-/*
- * This structure is used for magic page in domain pseudo physical address
- * space and the result of XENMEM_machine_memory_map.
- * As the XENMEM_machine_memory_map result,
- * xen_memory_map::nr_entries indicates the size in bytes
- * including struct xen_ia64_memmap_info. Not the number of entries.
- */
-struct xen_ia64_memmap_info {
-	uint64_t efi_memmap_size;	/* size of EFI memory map */
-	uint64_t efi_memdesc_size;	/* size of an EFI memory map
-					 * descriptor */
-	uint32_t efi_memdesc_version;	/* memory descriptor version */
-	void *memdesc[0];		/* array of efi_memory_desc_t */
-};
-
-struct arch_shared_info {
-	/* PFN of the start_info page.	*/
-	unsigned long start_info_pfn;
-
-	/* Interrupt vector for event channel.	*/
-	int evtchn_vector;
-
-	/* PFN of memmap_info page */
-	unsigned int memmap_info_num_pages;	/* currently only = 1 case is
-						   supported. */
-	unsigned long memmap_info_pfn;
-
-	uint64_t pad[31];
-};
-
-struct xen_callback {
-	unsigned long ip;
-};
-typedef struct xen_callback xen_callback_t;
-
-#endif /* !__ASSEMBLY__ */
-
-#include <asm/pvclock-abi.h>
-
-/* Size of the shared_info area (this is not related to page size).  */
-#define XSI_SHIFT			14
-#define XSI_SIZE			(1 << XSI_SHIFT)
-/* Log size of mapped_regs area (64 KB - only 4KB is used).  */
-#define XMAPPEDREGS_SHIFT		12
-#define XMAPPEDREGS_SIZE		(1 << XMAPPEDREGS_SHIFT)
-/* Offset of XASI (Xen arch shared info) wrt XSI_BASE.	*/
-#define XMAPPEDREGS_OFS			XSI_SIZE
-
-/* Hyperprivops.  */
-#define HYPERPRIVOP_START		0x1
-#define HYPERPRIVOP_RFI			(HYPERPRIVOP_START + 0x0)
-#define HYPERPRIVOP_RSM_DT		(HYPERPRIVOP_START + 0x1)
-#define HYPERPRIVOP_SSM_DT		(HYPERPRIVOP_START + 0x2)
-#define HYPERPRIVOP_COVER		(HYPERPRIVOP_START + 0x3)
-#define HYPERPRIVOP_ITC_D		(HYPERPRIVOP_START + 0x4)
-#define HYPERPRIVOP_ITC_I		(HYPERPRIVOP_START + 0x5)
-#define HYPERPRIVOP_SSM_I		(HYPERPRIVOP_START + 0x6)
-#define HYPERPRIVOP_GET_IVR		(HYPERPRIVOP_START + 0x7)
-#define HYPERPRIVOP_GET_TPR		(HYPERPRIVOP_START + 0x8)
-#define HYPERPRIVOP_SET_TPR		(HYPERPRIVOP_START + 0x9)
-#define HYPERPRIVOP_EOI			(HYPERPRIVOP_START + 0xa)
-#define HYPERPRIVOP_SET_ITM		(HYPERPRIVOP_START + 0xb)
-#define HYPERPRIVOP_THASH		(HYPERPRIVOP_START + 0xc)
-#define HYPERPRIVOP_PTC_GA		(HYPERPRIVOP_START + 0xd)
-#define HYPERPRIVOP_ITR_D		(HYPERPRIVOP_START + 0xe)
-#define HYPERPRIVOP_GET_RR		(HYPERPRIVOP_START + 0xf)
-#define HYPERPRIVOP_SET_RR		(HYPERPRIVOP_START + 0x10)
-#define HYPERPRIVOP_SET_KR		(HYPERPRIVOP_START + 0x11)
-#define HYPERPRIVOP_FC			(HYPERPRIVOP_START + 0x12)
-#define HYPERPRIVOP_GET_CPUID		(HYPERPRIVOP_START + 0x13)
-#define HYPERPRIVOP_GET_PMD		(HYPERPRIVOP_START + 0x14)
-#define HYPERPRIVOP_GET_EFLAG		(HYPERPRIVOP_START + 0x15)
-#define HYPERPRIVOP_SET_EFLAG		(HYPERPRIVOP_START + 0x16)
-#define HYPERPRIVOP_RSM_BE		(HYPERPRIVOP_START + 0x17)
-#define HYPERPRIVOP_GET_PSR		(HYPERPRIVOP_START + 0x18)
-#define HYPERPRIVOP_SET_RR0_TO_RR4	(HYPERPRIVOP_START + 0x19)
-#define HYPERPRIVOP_MAX			(0x1a)
-
-/* Fast and light hypercalls.  */
-#define __HYPERVISOR_ia64_fast_eoi	__HYPERVISOR_arch_1
-
-/* Xencomm macros.  */
-#define XENCOMM_INLINE_MASK		0xf800000000000000UL
-#define XENCOMM_INLINE_FLAG		0x8000000000000000UL
-
-#ifndef __ASSEMBLY__
-
-/*
- * Optimization features.
- * The hypervisor may do some special optimizations for guests. This hypercall
- * can be used to switch on/of these special optimizations.
- */
-#define __HYPERVISOR_opt_feature	0x700UL
-
-#define XEN_IA64_OPTF_OFF		0x0
-#define XEN_IA64_OPTF_ON		0x1
-
-/*
- * If this feature is switched on, the hypervisor inserts the
- * tlb entries without calling the guests traphandler.
- * This is useful in guests using region 7 for identity mapping
- * like the linux kernel does.
- */
-#define XEN_IA64_OPTF_IDENT_MAP_REG7	1
-
-/* Identity mapping of region 4 addresses in HVM. */
-#define XEN_IA64_OPTF_IDENT_MAP_REG4	2
-
-/* Identity mapping of region 5 addresses in HVM. */
-#define XEN_IA64_OPTF_IDENT_MAP_REG5	3
-
-#define XEN_IA64_OPTF_IDENT_MAP_NOT_SET	 (0)
-
-struct xen_ia64_opt_feature {
-	unsigned long cmd;	/* Which feature */
-	unsigned char on;	/* Switch feature on/off */
-	union {
-		struct {
-			/* The page protection bit mask of the pte.
-			 * This will be or'ed with the pte. */
-			unsigned long pgprot;
-			unsigned long key;	/* A protection key for itir.*/
-		};
-	};
-};
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* _ASM_IA64_XEN_INTERFACE_H */
diff --git a/arch/ia64/include/asm/xen/irq.h b/arch/ia64/include/asm/xen/irq.h
deleted file mode 100644
index a904509..0000000
--- a/arch/ia64/include/asm/xen/irq.h
+++ /dev/null
@@ -1,44 +0,0 @@
-/******************************************************************************
- * arch/ia64/include/asm/xen/irq.h
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#ifndef _ASM_IA64_XEN_IRQ_H
-#define _ASM_IA64_XEN_IRQ_H
-
-/*
- * The flat IRQ space is divided into two regions:
- *  1. A one-to-one mapping of real physical IRQs. This space is only used
- *     if we have physical device-access privilege. This region is at the
- *     start of the IRQ space so that existing device drivers do not need
- *     to be modified to translate physical IRQ numbers into our IRQ space.
- *  3. A dynamic mapping of inter-domain and Xen-sourced virtual IRQs. These
- *     are bound using the provided bind/unbind functions.
- */
-
-#define XEN_PIRQ_BASE		0
-#define XEN_NR_PIRQS		256
-
-#define XEN_DYNIRQ_BASE		(XEN_PIRQ_BASE + XEN_NR_PIRQS)
-#define XEN_NR_DYNIRQS		(NR_CPUS * 8)
-
-#define XEN_NR_IRQS		(XEN_NR_PIRQS + XEN_NR_DYNIRQS)
-
-#endif /* _ASM_IA64_XEN_IRQ_H */
diff --git a/arch/ia64/include/asm/xen/minstate.h b/arch/ia64/include/asm/xen/minstate.h
deleted file mode 100644
index 00cf03e..0000000
--- a/arch/ia64/include/asm/xen/minstate.h
+++ /dev/null
@@ -1,143 +0,0 @@
-
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-/* read ar.itc in advance, and use it before leaving bank 0 */
-#define XEN_ACCOUNT_GET_STAMP		\
-	MOV_FROM_ITC(pUStk, p6, r20, r2);
-#else
-#define XEN_ACCOUNT_GET_STAMP
-#endif
-
-/*
- * DO_SAVE_MIN switches to the kernel stacks (if necessary) and saves
- * the minimum state necessary that allows us to turn psr.ic back
- * on.
- *
- * Assumed state upon entry:
- *	psr.ic: off
- *	r31:	contains saved predicates (pr)
- *
- * Upon exit, the state is as follows:
- *	psr.ic: off
- *	 r2 = points to &pt_regs.r16
- *	 r8 = contents of ar.ccv
- *	 r9 = contents of ar.csd
- *	r10 = contents of ar.ssd
- *	r11 = FPSR_DEFAULT
- *	r12 = kernel sp (kernel virtual address)
- *	r13 = points to current task_struct (kernel virtual address)
- *	p15 = TRUE if psr.i is set in cr.ipsr
- *	predicate registers (other than p2, p3, and p15), b6, r3, r14, r15:
- *		preserved
- * CONFIG_XEN note: p6/p7 are not preserved
- *
- * Note that psr.ic is NOT turned on by this macro.  This is so that
- * we can pass interruption state as arguments to a handler.
- */
-#define XEN_DO_SAVE_MIN(__COVER,SAVE_IFS,EXTRA,WORKAROUND)					\
-	mov r16=IA64_KR(CURRENT);	/* M */							\
-	mov r27=ar.rsc;			/* M */							\
-	mov r20=r1;			/* A */							\
-	mov r25=ar.unat;		/* M */							\
-	MOV_FROM_IPSR(p0,r29);		/* M */							\
-	MOV_FROM_IIP(r28);		/* M */							\
-	mov r21=ar.fpsr;		/* M */							\
-	mov r26=ar.pfs;			/* I */							\
-	__COVER;			/* B;; (or nothing) */					\
-	adds r16=IA64_TASK_THREAD_ON_USTACK_OFFSET,r16;						\
-	;;											\
-	ld1 r17=[r16];				/* load current->thread.on_ustack flag */	\
-	st1 [r16]=r0;				/* clear current->thread.on_ustack flag */	\
-	adds r1=-IA64_TASK_THREAD_ON_USTACK_OFFSET,r16						\
-	/* switch from user to kernel RBS: */							\
-	;;											\
-	invala;				/* M */							\
-	/* SAVE_IFS;*/ /* see xen special handling below */					\
-	cmp.eq pKStk,pUStk=r0,r17;		/* are we in kernel mode already? */		\
-	;;											\
-(pUStk)	mov ar.rsc=0;		/* set enforced lazy mode, pl 0, little-endian, loadrs=0 */	\
-	;;											\
-(pUStk)	mov.m r24=ar.rnat;									\
-(pUStk)	addl r22=IA64_RBS_OFFSET,r1;			/* compute base of RBS */		\
-(pKStk) mov r1=sp;					/* get sp  */				\
-	;;											\
-(pUStk) lfetch.fault.excl.nt1 [r22];								\
-(pUStk)	addl r1=IA64_STK_OFFSET-IA64_PT_REGS_SIZE,r1;	/* compute base of memory stack */	\
-(pUStk)	mov r23=ar.bspstore;				/* save ar.bspstore */			\
-	;;											\
-(pUStk)	mov ar.bspstore=r22;				/* switch to kernel RBS */		\
-(pKStk) addl r1=-IA64_PT_REGS_SIZE,r1;			/* if in kernel mode, use sp (r12) */	\
-	;;											\
-(pUStk)	mov r18=ar.bsp;										\
-(pUStk)	mov ar.rsc=0x3;		/* set eager mode, pl 0, little-endian, loadrs=0 */		\
-	adds r17=2*L1_CACHE_BYTES,r1;		/* really: biggest cache-line size */		\
-	adds r16=PT(CR_IPSR),r1;								\
-	;;											\
-	lfetch.fault.excl.nt1 [r17],L1_CACHE_BYTES;						\
-	st8 [r16]=r29;		/* save cr.ipsr */						\
-	;;											\
-	lfetch.fault.excl.nt1 [r17];								\
-	tbit.nz p15,p0=r29,IA64_PSR_I_BIT;							\
-	mov r29=b0										\
-	;;											\
-	WORKAROUND;										\
-	adds r16=PT(R8),r1;	/* initialize first base pointer */				\
-	adds r17=PT(R9),r1;	/* initialize second base pointer */				\
-(pKStk)	mov r18=r0;		/* make sure r18 isn't NaT */					\
-	;;											\
-.mem.offset 0,0; st8.spill [r16]=r8,16;								\
-.mem.offset 8,0; st8.spill [r17]=r9,16;								\
-        ;;											\
-.mem.offset 0,0; st8.spill [r16]=r10,24;							\
-	movl r8=XSI_PRECOVER_IFS;								\
-.mem.offset 8,0; st8.spill [r17]=r11,24;							\
-        ;;											\
-	/* xen special handling for possibly lazy cover */					\
-	/* SAVE_MIN case in dispatch_ia32_handler: mov r30=r0 */				\
-	ld8 r30=[r8];										\
-(pUStk)	sub r18=r18,r22;	/* r18=RSE.ndirty*8 */						\
-	st8 [r16]=r28,16;	/* save cr.iip */						\
-	;;											\
-	st8 [r17]=r30,16;	/* save cr.ifs */						\
-	mov r8=ar.ccv;										\
-	mov r9=ar.csd;										\
-	mov r10=ar.ssd;										\
-	movl r11=FPSR_DEFAULT;   /* L-unit */							\
-	;;											\
-	st8 [r16]=r25,16;	/* save ar.unat */						\
-	st8 [r17]=r26,16;	/* save ar.pfs */						\
-	shl r18=r18,16;		/* compute ar.rsc to be used for "loadrs" */			\
-	;;											\
-	st8 [r16]=r27,16;	/* save ar.rsc */						\
-(pUStk)	st8 [r17]=r24,16;	/* save ar.rnat */						\
-(pKStk)	adds r17=16,r17;	/* skip over ar_rnat field */					\
-	;;			/* avoid RAW on r16 & r17 */					\
-(pUStk)	st8 [r16]=r23,16;	/* save ar.bspstore */						\
-	st8 [r17]=r31,16;	/* save predicates */						\
-(pKStk)	adds r16=16,r16;	/* skip over ar_bspstore field */				\
-	;;											\
-	st8 [r16]=r29,16;	/* save b0 */							\
-	st8 [r17]=r18,16;	/* save ar.rsc value for "loadrs" */				\
-	cmp.eq pNonSys,pSys=r0,r0	/* initialize pSys=0, pNonSys=1 */			\
-	;;											\
-.mem.offset 0,0; st8.spill [r16]=r20,16;	/* save original r1 */				\
-.mem.offset 8,0; st8.spill [r17]=r12,16;							\
-	adds r12=-16,r1;	/* switch to kernel memory stack (with 16 bytes of scratch) */	\
-	;;											\
-.mem.offset 0,0; st8.spill [r16]=r13,16;							\
-.mem.offset 8,0; st8.spill [r17]=r21,16;	/* save ar.fpsr */				\
-	mov r13=IA64_KR(CURRENT);	/* establish `current' */				\
-	;;											\
-.mem.offset 0,0; st8.spill [r16]=r15,16;							\
-.mem.offset 8,0; st8.spill [r17]=r14,16;							\
-	;;											\
-.mem.offset 0,0; st8.spill [r16]=r2,16;								\
-.mem.offset 8,0; st8.spill [r17]=r3,16;								\
-	XEN_ACCOUNT_GET_STAMP									\
-	adds r2=IA64_PT_REGS_R16_OFFSET,r1;							\
-	;;											\
-	EXTRA;											\
-	movl r1=__gp;		/* establish kernel global pointer */				\
-	;;											\
-	ACCOUNT_SYS_ENTER									\
-	BSW_1(r3,r14);	/* switch back to bank 1 (must be last in insn group) */		\
-	;;
diff --git a/arch/ia64/include/asm/xen/page-coherent.h b/arch/ia64/include/asm/xen/page-coherent.h
deleted file mode 100644
index 96e42f9..0000000
--- a/arch/ia64/include/asm/xen/page-coherent.h
+++ /dev/null
@@ -1,38 +0,0 @@
-#ifndef _ASM_IA64_XEN_PAGE_COHERENT_H
-#define _ASM_IA64_XEN_PAGE_COHERENT_H
-
-#include <asm/page.h>
-#include <linux/dma-attrs.h>
-#include <linux/dma-mapping.h>
-
-static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
-		dma_addr_t *dma_handle, gfp_t flags,
-		struct dma_attrs *attrs)
-{
-	void *vstart = (void*)__get_free_pages(flags, get_order(size));
-	*dma_handle = virt_to_phys(vstart);
-	return vstart;
-}
-
-static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
-		void *cpu_addr, dma_addr_t dma_handle,
-		struct dma_attrs *attrs)
-{
-	free_pages((unsigned long) cpu_addr, get_order(size));
-}
-
-static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
-	     unsigned long offset, size_t size, enum dma_data_direction dir,
-	     struct dma_attrs *attrs) { }
-
-static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir,
-		struct dma_attrs *attrs) { }
-
-static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir) { }
-
-static inline void xen_dma_sync_single_for_device(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir) { }
-
-#endif /* _ASM_IA64_XEN_PAGE_COHERENT_H */
diff --git a/arch/ia64/include/asm/xen/page.h b/arch/ia64/include/asm/xen/page.h
deleted file mode 100644
index 03441a78..0000000
--- a/arch/ia64/include/asm/xen/page.h
+++ /dev/null
@@ -1,65 +0,0 @@
-/******************************************************************************
- * arch/ia64/include/asm/xen/page.h
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#ifndef _ASM_IA64_XEN_PAGE_H
-#define _ASM_IA64_XEN_PAGE_H
-
-#define INVALID_P2M_ENTRY	(~0UL)
-
-static inline unsigned long mfn_to_pfn(unsigned long mfn)
-{
-	return mfn;
-}
-
-static inline unsigned long pfn_to_mfn(unsigned long pfn)
-{
-	return pfn;
-}
-
-#define phys_to_machine_mapping_valid(_x)	(1)
-
-static inline void *mfn_to_virt(unsigned long mfn)
-{
-	return __va(mfn << PAGE_SHIFT);
-}
-
-static inline unsigned long virt_to_mfn(void *virt)
-{
-	return __pa(virt) >> PAGE_SHIFT;
-}
-
-/* for tpmfront.c */
-static inline unsigned long virt_to_machine(void *virt)
-{
-	return __pa(virt);
-}
-
-static inline void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
-{
-	/* nothing */
-}
-
-#define pte_mfn(_x)	pte_pfn(_x)
-#define mfn_pte(_x, _y)	__pte_ma(0)		/* unmodified use */
-#define __pte_ma(_x)	((pte_t) {(_x)})        /* unmodified use */
-
-#endif /* _ASM_IA64_XEN_PAGE_H */
diff --git a/arch/ia64/include/asm/xen/patchlist.h b/arch/ia64/include/asm/xen/patchlist.h
deleted file mode 100644
index eae944e..0000000
--- a/arch/ia64/include/asm/xen/patchlist.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/******************************************************************************
- * arch/ia64/include/asm/xen/patchlist.h
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#define __paravirt_start_gate_fsyscall_patchlist		\
-	__xen_start_gate_fsyscall_patchlist
-#define __paravirt_end_gate_fsyscall_patchlist			\
-	__xen_end_gate_fsyscall_patchlist
-#define __paravirt_start_gate_brl_fsys_bubble_down_patchlist	\
-	__xen_start_gate_brl_fsys_bubble_down_patchlist
-#define __paravirt_end_gate_brl_fsys_bubble_down_patchlist	\
-	__xen_end_gate_brl_fsys_bubble_down_patchlist
-#define __paravirt_start_gate_vtop_patchlist			\
-	__xen_start_gate_vtop_patchlist
-#define __paravirt_end_gate_vtop_patchlist			\
-	__xen_end_gate_vtop_patchlist
-#define __paravirt_start_gate_mckinley_e9_patchlist		\
-	__xen_start_gate_mckinley_e9_patchlist
-#define __paravirt_end_gate_mckinley_e9_patchlist		\
-	__xen_end_gate_mckinley_e9_patchlist
diff --git a/arch/ia64/include/asm/xen/privop.h b/arch/ia64/include/asm/xen/privop.h
deleted file mode 100644
index fb4ec5e..0000000
--- a/arch/ia64/include/asm/xen/privop.h
+++ /dev/null
@@ -1,135 +0,0 @@
-#ifndef _ASM_IA64_XEN_PRIVOP_H
-#define _ASM_IA64_XEN_PRIVOP_H
-
-/*
- * Copyright (C) 2005 Hewlett-Packard Co
- *	Dan Magenheimer <dan.magenheimer@hp.com>
- *
- * Paravirtualizations of privileged operations for Xen/ia64
- *
- *
- * inline privop and paravirt_alt support
- * Copyright (c) 2007 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- */
-
-#ifndef __ASSEMBLY__
-#include <linux/types.h>		/* arch-ia64.h requires uint64_t */
-#endif
-#include <asm/xen/interface.h>
-
-/* At 1 MB, before per-cpu space but still addressable using addl instead
-   of movl. */
-#define XSI_BASE			0xfffffffffff00000
-
-/* Address of mapped regs.  */
-#define XMAPPEDREGS_BASE		(XSI_BASE + XSI_SIZE)
-
-#ifdef __ASSEMBLY__
-#define XEN_HYPER_RFI			break HYPERPRIVOP_RFI
-#define XEN_HYPER_RSM_PSR_DT		break HYPERPRIVOP_RSM_DT
-#define XEN_HYPER_SSM_PSR_DT		break HYPERPRIVOP_SSM_DT
-#define XEN_HYPER_COVER			break HYPERPRIVOP_COVER
-#define XEN_HYPER_ITC_D			break HYPERPRIVOP_ITC_D
-#define XEN_HYPER_ITC_I			break HYPERPRIVOP_ITC_I
-#define XEN_HYPER_SSM_I			break HYPERPRIVOP_SSM_I
-#define XEN_HYPER_GET_IVR		break HYPERPRIVOP_GET_IVR
-#define XEN_HYPER_THASH			break HYPERPRIVOP_THASH
-#define XEN_HYPER_ITR_D			break HYPERPRIVOP_ITR_D
-#define XEN_HYPER_SET_KR		break HYPERPRIVOP_SET_KR
-#define XEN_HYPER_GET_PSR		break HYPERPRIVOP_GET_PSR
-#define XEN_HYPER_SET_RR0_TO_RR4	break HYPERPRIVOP_SET_RR0_TO_RR4
-
-#define XSI_IFS				(XSI_BASE + XSI_IFS_OFS)
-#define XSI_PRECOVER_IFS		(XSI_BASE + XSI_PRECOVER_IFS_OFS)
-#define XSI_IFA				(XSI_BASE + XSI_IFA_OFS)
-#define XSI_ISR				(XSI_BASE + XSI_ISR_OFS)
-#define XSI_IIM				(XSI_BASE + XSI_IIM_OFS)
-#define XSI_ITIR			(XSI_BASE + XSI_ITIR_OFS)
-#define XSI_PSR_I_ADDR			(XSI_BASE + XSI_PSR_I_ADDR_OFS)
-#define XSI_PSR_IC			(XSI_BASE + XSI_PSR_IC_OFS)
-#define XSI_IPSR			(XSI_BASE + XSI_IPSR_OFS)
-#define XSI_IIP				(XSI_BASE + XSI_IIP_OFS)
-#define XSI_B1NAT			(XSI_BASE + XSI_B1NATS_OFS)
-#define XSI_BANK1_R16			(XSI_BASE + XSI_BANK1_R16_OFS)
-#define XSI_BANKNUM			(XSI_BASE + XSI_BANKNUM_OFS)
-#define XSI_IHA				(XSI_BASE + XSI_IHA_OFS)
-#define XSI_ITC_OFFSET			(XSI_BASE + XSI_ITC_OFFSET_OFS)
-#define XSI_ITC_LAST			(XSI_BASE + XSI_ITC_LAST_OFS)
-#endif
-
-#ifndef __ASSEMBLY__
-
-/************************************************/
-/* Instructions paravirtualized for correctness */
-/************************************************/
-
-/* "fc" and "thash" are privilege-sensitive instructions, meaning they
- *  may have different semantics depending on whether they are executed
- *  at PL0 vs PL!=0.  When paravirtualized, these instructions mustn't
- *  be allowed to execute directly, lest incorrect semantics result. */
-extern void xen_fc(void *addr);
-extern unsigned long xen_thash(unsigned long addr);
-
-/* Note that "ttag" and "cover" are also privilege-sensitive; "ttag"
- * is not currently used (though it may be in a long-format VHPT system!)
- * and the semantics of cover only change if psr.ic is off which is very
- * rare (and currently non-existent outside of assembly code */
-
-/* There are also privilege-sensitive registers.  These registers are
- * readable at any privilege level but only writable at PL0. */
-extern unsigned long xen_get_cpuid(int index);
-extern unsigned long xen_get_pmd(int index);
-
-#ifndef ASM_SUPPORTED
-extern unsigned long xen_get_eflag(void);	/* see xen_ia64_getreg */
-extern void xen_set_eflag(unsigned long);	/* see xen_ia64_setreg */
-#endif
-
-/************************************************/
-/* Instructions paravirtualized for performance */
-/************************************************/
-
-/* Xen uses memory-mapped virtual privileged registers for access to many
- * performance-sensitive privileged registers.  Some, like the processor
- * status register (psr), are broken up into multiple memory locations.
- * Others, like "pend", are abstractions based on privileged registers.
- * "Pend" is guaranteed to be set if reading cr.ivr would return a
- * (non-spurious) interrupt. */
-#define XEN_MAPPEDREGS ((struct mapped_regs *)XMAPPEDREGS_BASE)
-
-#define XSI_PSR_I			\
-	(*XEN_MAPPEDREGS->interrupt_mask_addr)
-#define xen_get_virtual_psr_i()		\
-	(!XSI_PSR_I)
-#define xen_set_virtual_psr_i(_val)	\
-	({ XSI_PSR_I = (uint8_t)(_val) ? 0 : 1; })
-#define xen_set_virtual_psr_ic(_val)	\
-	({ XEN_MAPPEDREGS->interrupt_collection_enabled = _val ? 1 : 0; })
-#define xen_get_virtual_pend()		\
-	(*(((uint8_t *)XEN_MAPPEDREGS->interrupt_mask_addr) - 1))
-
-#ifndef ASM_SUPPORTED
-/* Although all privileged operations can be left to trap and will
- * be properly handled by Xen, some are frequent enough that we use
- * hyperprivops for performance. */
-extern unsigned long xen_get_psr(void);
-extern unsigned long xen_get_ivr(void);
-extern unsigned long xen_get_tpr(void);
-extern void xen_hyper_ssm_i(void);
-extern void xen_set_itm(unsigned long);
-extern void xen_set_tpr(unsigned long);
-extern void xen_eoi(unsigned long);
-extern unsigned long xen_get_rr(unsigned long index);
-extern void xen_set_rr(unsigned long index, unsigned long val);
-extern void xen_set_rr0_to_rr4(unsigned long val0, unsigned long val1,
-			       unsigned long val2, unsigned long val3,
-			       unsigned long val4);
-extern void xen_set_kr(unsigned long index, unsigned long val);
-extern void xen_ptcga(unsigned long addr, unsigned long size);
-#endif /* !ASM_SUPPORTED */
-
-#endif /* !__ASSEMBLY__ */
-
-#endif /* _ASM_IA64_XEN_PRIVOP_H */
diff --git a/arch/ia64/include/asm/xen/xcom_hcall.h b/arch/ia64/include/asm/xen/xcom_hcall.h
deleted file mode 100644
index 20b2950..0000000
--- a/arch/ia64/include/asm/xen/xcom_hcall.h
+++ /dev/null
@@ -1,51 +0,0 @@
-/*
- * Copyright (C) 2006 Tristan Gingold <tristan.gingold@bull.net>, Bull SAS
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-
-#ifndef _ASM_IA64_XEN_XCOM_HCALL_H
-#define _ASM_IA64_XEN_XCOM_HCALL_H
-
-/* These function creates inline or mini descriptor for the parameters and
-   calls the corresponding xencomm_arch_hypercall_X.
-   Architectures should defines HYPERVISOR_xxx as xencomm_hypercall_xxx unless
-   they want to use their own wrapper.  */
-extern int xencomm_hypercall_console_io(int cmd, int count, char *str);
-
-extern int xencomm_hypercall_event_channel_op(int cmd, void *op);
-
-extern int xencomm_hypercall_xen_version(int cmd, void *arg);
-
-extern int xencomm_hypercall_physdev_op(int cmd, void *op);
-
-extern int xencomm_hypercall_grant_table_op(unsigned int cmd, void *op,
-					    unsigned int count);
-
-extern int xencomm_hypercall_sched_op(int cmd, void *arg);
-
-extern int xencomm_hypercall_multicall(void *call_list, int nr_calls);
-
-extern int xencomm_hypercall_callback_op(int cmd, void *arg);
-
-extern int xencomm_hypercall_memory_op(unsigned int cmd, void *arg);
-
-extern int xencomm_hypercall_suspend(unsigned long srec);
-
-extern long xencomm_hypercall_vcpu_op(int cmd, int cpu, void *arg);
-
-extern long xencomm_hypercall_opt_feature(void *arg);
-
-#endif /* _ASM_IA64_XEN_XCOM_HCALL_H */
diff --git a/arch/ia64/include/asm/xen/xencomm.h b/arch/ia64/include/asm/xen/xencomm.h
deleted file mode 100644
index cded677..0000000
--- a/arch/ia64/include/asm/xen/xencomm.h
+++ /dev/null
@@ -1,42 +0,0 @@
-/*
- * Copyright (C) 2006 Hollis Blanchard <hollisb@us.ibm.com>, IBM Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-
-#ifndef _ASM_IA64_XEN_XENCOMM_H
-#define _ASM_IA64_XEN_XENCOMM_H
-
-#include <xen/xencomm.h>
-#include <asm/pgtable.h>
-
-/* Must be called before any hypercall.  */
-extern void xencomm_initialize(void);
-extern int xencomm_is_initialized(void);
-
-/* Check if virtual contiguity means physical contiguity
- * where the passed address is a pointer value in virtual address.
- * On ia64, identity mapping area in region 7 or the piece of region 5
- * that is mapped by itr[IA64_TR_KERNEL]/dtr[IA64_TR_KERNEL]
- */
-static inline int xencomm_is_phys_contiguous(unsigned long addr)
-{
-	return (PAGE_OFFSET <= addr &&
-		addr < (PAGE_OFFSET + (1UL << IA64_MAX_PHYS_BITS))) ||
-		(KERNEL_START <= addr &&
-		 addr < KERNEL_START + KERNEL_TR_PAGE_SIZE);
-}
-
-#endif /* _ASM_IA64_XEN_XENCOMM_H */
diff --git a/arch/ia64/include/uapi/asm/break.h b/arch/ia64/include/uapi/asm/break.h
index e90c40e..f034020 100644
--- a/arch/ia64/include/uapi/asm/break.h
+++ b/arch/ia64/include/uapi/asm/break.h
@@ -20,13 +20,4 @@
  */
 #define __IA64_BREAK_SYSCALL		0x100000
 
-/*
- * Xen specific break numbers:
- */
-#define __IA64_XEN_HYPERCALL		0x1000
-/* [__IA64_XEN_HYPERPRIVOP_START, __IA64_XEN_HYPERPRIVOP_MAX] is used
-   for xen hyperprivops */
-#define __IA64_XEN_HYPERPRIVOP_START	0x1
-#define __IA64_XEN_HYPERPRIVOP_MAX	0x1a
-
 #endif /* _ASM_IA64_BREAK_H */
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 59d52e3..bfa1931 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -53,7 +53,6 @@
 #include <asm/numa.h>
 #include <asm/sal.h>
 #include <asm/cyclone.h>
-#include <asm/xen/hypervisor.h>
 
 #define BAD_MADT_ENTRY(entry, end) (                                        \
 		(!entry) || (unsigned long)entry + sizeof(*entry) > end ||  \
@@ -120,8 +119,6 @@ acpi_get_sysname(void)
 			return "uv";
 		else
 			return "sn2";
-	} else if (xen_pv_domain() && !strcmp(hdr->oem_id, "XEN")) {
-		return "xen";
 	}
 
 #ifdef CONFIG_INTEL_IOMMU
diff --git a/arch/ia64/kernel/asm-offsets.c b/arch/ia64/kernel/asm-offsets.c
index 46c9e30..60ef83e 100644
--- a/arch/ia64/kernel/asm-offsets.c
+++ b/arch/ia64/kernel/asm-offsets.c
@@ -16,9 +16,6 @@
 #include <asm/sigcontext.h>
 #include <asm/mca.h>
 
-#include <asm/xen/interface.h>
-#include <asm/xen/hypervisor.h>
-
 #include "../kernel/sigframe.h"
 #include "../kernel/fsyscall_gtod_data.h"
 
@@ -290,33 +287,4 @@ void foo(void)
 	DEFINE(IA64_ITC_LASTCYCLE_OFFSET,
 		offsetof (struct itc_jitter_data_t, itc_lastcycle));
 
-#ifdef CONFIG_XEN
-	BLANK();
-
-	DEFINE(XEN_NATIVE_ASM, XEN_NATIVE);
-	DEFINE(XEN_PV_DOMAIN_ASM, XEN_PV_DOMAIN);
-
-#define DEFINE_MAPPED_REG_OFS(sym, field) \
-	DEFINE(sym, (XMAPPEDREGS_OFS + offsetof(struct mapped_regs, field)))
-
-	DEFINE_MAPPED_REG_OFS(XSI_PSR_I_ADDR_OFS, interrupt_mask_addr);
-	DEFINE_MAPPED_REG_OFS(XSI_IPSR_OFS, ipsr);
-	DEFINE_MAPPED_REG_OFS(XSI_IIP_OFS, iip);
-	DEFINE_MAPPED_REG_OFS(XSI_IFS_OFS, ifs);
-	DEFINE_MAPPED_REG_OFS(XSI_PRECOVER_IFS_OFS, precover_ifs);
-	DEFINE_MAPPED_REG_OFS(XSI_ISR_OFS, isr);
-	DEFINE_MAPPED_REG_OFS(XSI_IFA_OFS, ifa);
-	DEFINE_MAPPED_REG_OFS(XSI_IIPA_OFS, iipa);
-	DEFINE_MAPPED_REG_OFS(XSI_IIM_OFS, iim);
-	DEFINE_MAPPED_REG_OFS(XSI_IHA_OFS, iha);
-	DEFINE_MAPPED_REG_OFS(XSI_ITIR_OFS, itir);
-	DEFINE_MAPPED_REG_OFS(XSI_PSR_IC_OFS, interrupt_collection_enabled);
-	DEFINE_MAPPED_REG_OFS(XSI_BANKNUM_OFS, banknum);
-	DEFINE_MAPPED_REG_OFS(XSI_BANK0_R16_OFS, bank0_regs[0]);
-	DEFINE_MAPPED_REG_OFS(XSI_BANK1_R16_OFS, bank1_regs[0]);
-	DEFINE_MAPPED_REG_OFS(XSI_B0NATS_OFS, vbnat);
-	DEFINE_MAPPED_REG_OFS(XSI_B1NATS_OFS, vnat);
-	DEFINE_MAPPED_REG_OFS(XSI_ITC_OFFSET_OFS, itc_offset);
-	DEFINE_MAPPED_REG_OFS(XSI_ITC_LAST_OFS, itc_last);
-#endif /* CONFIG_XEN */
 }
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index 991ca33..e6f80fc 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -416,8 +416,6 @@ start_ap:
 
 default_setup_hook = 0		// Currently nothing needs to be done.
 
-	.weak xen_setup_hook
-
 	.global hypervisor_type
 hypervisor_type:
 	data8		PARAVIRT_HYPERVISOR_TYPE_DEFAULT
@@ -426,7 +424,6 @@ hypervisor_type:
 
 hypervisor_setup_hooks:
 	data8		default_setup_hook
-	data8		xen_setup_hook
 num_hypervisor_hooks = (. - hypervisor_setup_hooks) / 8
 	.previous
 
diff --git a/arch/ia64/kernel/nr-irqs.c b/arch/ia64/kernel/nr-irqs.c
index ee56457..f6769cd 100644
--- a/arch/ia64/kernel/nr-irqs.c
+++ b/arch/ia64/kernel/nr-irqs.c
@@ -10,15 +10,11 @@
 #include <linux/kbuild.h>
 #include <linux/threads.h>
 #include <asm/native/irq.h>
-#include <asm/xen/irq.h>
 
 void foo(void)
 {
 	union paravirt_nr_irqs_max {
 		char ia64_native_nr_irqs[IA64_NATIVE_NR_IRQS];
-#ifdef CONFIG_XEN
-		char xen_nr_irqs[XEN_NR_IRQS];
-#endif
 	};
 
 	DEFINE(NR_IRQS, sizeof (union paravirt_nr_irqs_max));
diff --git a/arch/ia64/kernel/paravirt_inst.h b/arch/ia64/kernel/paravirt_inst.h
index 64d6d81..1ad7512 100644
--- a/arch/ia64/kernel/paravirt_inst.h
+++ b/arch/ia64/kernel/paravirt_inst.h
@@ -22,9 +22,6 @@
 
 #ifdef __IA64_ASM_PARAVIRTUALIZED_PVCHECK
 #include <asm/native/pvchk_inst.h>
-#elif defined(__IA64_ASM_PARAVIRTUALIZED_XEN)
-#include <asm/xen/inst.h>
-#include <asm/xen/minstate.h>
 #else
 #include <asm/native/inst.h>
 #endif
diff --git a/arch/ia64/kernel/paravirt_patchlist.h b/arch/ia64/kernel/paravirt_patchlist.h
index 0684aa6..67cffc36 100644
--- a/arch/ia64/kernel/paravirt_patchlist.h
+++ b/arch/ia64/kernel/paravirt_patchlist.h
@@ -20,9 +20,5 @@
  *
  */
 
-#if defined(__IA64_GATE_PARAVIRTUALIZED_XEN)
-#include <asm/xen/patchlist.h>
-#else
 #include <asm/native/patchlist.h>
-#endif
 
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 0ccb28f..84f8a52 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -182,12 +182,6 @@ SECTIONS {
 		__start_gate_section = .;
 		*(.data..gate)
 		__stop_gate_section = .;
-#ifdef CONFIG_XEN
-		. = ALIGN(PAGE_SIZE);
-		__xen_start_gate_section = .;
-		*(.data..gate.xen)
-		__xen_stop_gate_section = .;
-#endif
 	}
 	/*
 	 * make sure the gate page doesn't expose
diff --git a/arch/ia64/xen/Kconfig b/arch/ia64/xen/Kconfig
deleted file mode 100644
index 5d8a06b..0000000
--- a/arch/ia64/xen/Kconfig
+++ /dev/null
@@ -1,25 +0,0 @@
-#
-# This Kconfig describes xen/ia64 options
-#
-
-config XEN
-	bool "Xen hypervisor support"
-	default y
-	depends on PARAVIRT && MCKINLEY && IA64_PAGE_SIZE_16KB
-	select XEN_XENCOMM
-	select NO_IDLE_HZ
-	# followings are required to save/restore.
-	select ARCH_SUSPEND_POSSIBLE
-	select SUSPEND
-	select PM_SLEEP
-	help
-	  Enable Xen hypervisor support.  Resulting kernel runs
-	  both as a guest OS on Xen and natively on hardware.
-
-config XEN_XENCOMM
-	depends on XEN
-	bool
-
-config NO_IDLE_HZ
-	depends on XEN
-	bool
diff --git a/arch/ia64/xen/Makefile b/arch/ia64/xen/Makefile
deleted file mode 100644
index e6f4a0a..0000000
--- a/arch/ia64/xen/Makefile
+++ /dev/null
@@ -1,37 +0,0 @@
-#
-# Makefile for Xen components
-#
-
-obj-y := hypercall.o xenivt.o xensetup.o xen_pv_ops.o irq_xen.o \
-	 hypervisor.o xencomm.o xcom_hcall.o grant-table.o time.o suspend.o \
-	 gate-data.o
-
-obj-$(CONFIG_IA64_GENERIC) += machvec.o
-
-# The gate DSO image is built using a special linker script.
-include $(srctree)/arch/ia64/kernel/Makefile.gate
-
-# tell compiled for xen
-CPPFLAGS_gate.lds += -D__IA64_GATE_PARAVIRTUALIZED_XEN
-AFLAGS_gate.o += -D__IA64_ASM_PARAVIRTUALIZED_XEN -D__IA64_GATE_PARAVIRTUALIZED_XEN
-
-# use same file of native.
-$(obj)/gate.o: $(src)/../kernel/gate.S FORCE
-	$(call if_changed_dep,as_o_S)
-$(obj)/gate.lds: $(src)/../kernel/gate.lds.S FORCE
-	$(call if_changed_dep,cpp_lds_S)
-
-
-AFLAGS_xenivt.o += -D__IA64_ASM_PARAVIRTUALIZED_XEN
-
-# xen multi compile
-ASM_PARAVIRT_MULTI_COMPILE_SRCS = ivt.S entry.S fsys.S
-ASM_PARAVIRT_OBJS = $(addprefix xen-,$(ASM_PARAVIRT_MULTI_COMPILE_SRCS:.S=.o))
-obj-y += $(ASM_PARAVIRT_OBJS)
-define paravirtualized_xen
-AFLAGS_$(1) += -D__IA64_ASM_PARAVIRTUALIZED_XEN
-endef
-$(foreach o,$(ASM_PARAVIRT_OBJS),$(eval $(call paravirtualized_xen,$(o))))
-
-$(obj)/xen-%.o: $(src)/../kernel/%.S FORCE
-	$(call if_changed_dep,as_o_S)
diff --git a/arch/ia64/xen/gate-data.S b/arch/ia64/xen/gate-data.S
deleted file mode 100644
index 6f95b6b..0000000
--- a/arch/ia64/xen/gate-data.S
+++ /dev/null
@@ -1,3 +0,0 @@
-	.section .data..gate.xen, "aw"
-
-	.incbin "arch/ia64/xen/gate.so"
diff --git a/arch/ia64/xen/grant-table.c b/arch/ia64/xen/grant-table.c
deleted file mode 100644
index c182813..0000000
--- a/arch/ia64/xen/grant-table.c
+++ /dev/null
@@ -1,94 +0,0 @@
-/******************************************************************************
- * arch/ia64/xen/grant-table.c
- *
- * Copyright (c) 2006 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#include <linux/module.h>
-#include <linux/vmalloc.h>
-#include <linux/slab.h>
-#include <linux/mm.h>
-
-#include <xen/interface/xen.h>
-#include <xen/interface/memory.h>
-#include <xen/grant_table.h>
-
-#include <asm/xen/hypervisor.h>
-
-/****************************************************************************
- * grant table hack
- * cmd: GNTTABOP_xxx
- */
-
-int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
-			   unsigned long max_nr_gframes,
-			   struct grant_entry **__shared)
-{
-	*__shared = __va(frames[0] << PAGE_SHIFT);
-	return 0;
-}
-
-void arch_gnttab_unmap_shared(struct grant_entry *shared,
-			      unsigned long nr_gframes)
-{
-	/* nothing */
-}
-
-static void
-gnttab_map_grant_ref_pre(struct gnttab_map_grant_ref *uop)
-{
-	uint32_t flags;
-
-	flags = uop->flags;
-
-	if (flags & GNTMAP_host_map) {
-		if (flags & GNTMAP_application_map) {
-			printk(KERN_DEBUG
-			       "GNTMAP_application_map is not supported yet: "
-			       "flags 0x%x\n", flags);
-			BUG();
-		}
-		if (flags & GNTMAP_contains_pte) {
-			printk(KERN_DEBUG
-			       "GNTMAP_contains_pte is not supported yet: "
-			       "flags 0x%x\n", flags);
-			BUG();
-		}
-	} else if (flags & GNTMAP_device_map) {
-		printk("GNTMAP_device_map is not supported yet 0x%x\n", flags);
-		BUG();	/* not yet. actually this flag is not used. */
-	} else {
-		BUG();
-	}
-}
-
-int
-HYPERVISOR_grant_table_op(unsigned int cmd, void *uop, unsigned int count)
-{
-	if (cmd == GNTTABOP_map_grant_ref) {
-		unsigned int i;
-		for (i = 0; i < count; i++) {
-			gnttab_map_grant_ref_pre(
-				(struct gnttab_map_grant_ref *)uop + i);
-		}
-	}
-	return xencomm_hypercall_grant_table_op(cmd, uop, count);
-}
-
-EXPORT_SYMBOL(HYPERVISOR_grant_table_op);
diff --git a/arch/ia64/xen/hypercall.S b/arch/ia64/xen/hypercall.S
deleted file mode 100644
index 08847aa..0000000
--- a/arch/ia64/xen/hypercall.S
+++ /dev/null
@@ -1,88 +0,0 @@
-/*
- * Support routines for Xen hypercalls
- *
- * Copyright (C) 2005 Dan Magenheimer <dan.magenheimer@hp.com>
- * Copyright (C) 2008 Yaozu (Eddie) Dong <eddie.dong@intel.com>
- */
-
-#include <asm/asmmacro.h>
-#include <asm/intrinsics.h>
-#include <asm/xen/privop.h>
-
-#ifdef __INTEL_COMPILER
-/*
- * Hypercalls without parameter.
- */
-#define __HCALL0(name,hcall)		\
-	GLOBAL_ENTRY(name);		\
-	break	hcall;			\
-	br.ret.sptk.many rp;		\
-	END(name)
-
-/*
- * Hypercalls with 1 parameter.
- */
-#define __HCALL1(name,hcall)		\
-	GLOBAL_ENTRY(name);		\
-	mov r8=r32;			\
-	break	hcall;			\
-	br.ret.sptk.many rp;		\
-	END(name)
-
-/*
- * Hypercalls with 2 parameters.
- */
-#define __HCALL2(name,hcall)		\
-	GLOBAL_ENTRY(name);		\
-	mov r8=r32;			\
-	mov r9=r33;			\
-	break	hcall;			\
-	br.ret.sptk.many rp;		\
-	END(name)
-
-__HCALL0(xen_get_psr, HYPERPRIVOP_GET_PSR)
-__HCALL0(xen_get_ivr, HYPERPRIVOP_GET_IVR)
-__HCALL0(xen_get_tpr, HYPERPRIVOP_GET_TPR)
-__HCALL0(xen_hyper_ssm_i, HYPERPRIVOP_SSM_I)
-
-__HCALL1(xen_set_tpr, HYPERPRIVOP_SET_TPR)
-__HCALL1(xen_eoi, HYPERPRIVOP_EOI)
-__HCALL1(xen_thash, HYPERPRIVOP_THASH)
-__HCALL1(xen_set_itm, HYPERPRIVOP_SET_ITM)
-__HCALL1(xen_get_rr, HYPERPRIVOP_GET_RR)
-__HCALL1(xen_fc, HYPERPRIVOP_FC)
-__HCALL1(xen_get_cpuid, HYPERPRIVOP_GET_CPUID)
-__HCALL1(xen_get_pmd, HYPERPRIVOP_GET_PMD)
-
-__HCALL2(xen_ptcga, HYPERPRIVOP_PTC_GA)
-__HCALL2(xen_set_rr, HYPERPRIVOP_SET_RR)
-__HCALL2(xen_set_kr, HYPERPRIVOP_SET_KR)
-
-GLOBAL_ENTRY(xen_set_rr0_to_rr4)
-	mov r8=r32
-	mov r9=r33
-	mov r10=r34
-	mov r11=r35
-	mov r14=r36
-	XEN_HYPER_SET_RR0_TO_RR4
-	br.ret.sptk.many rp
-	;;
-END(xen_set_rr0_to_rr4)
-#endif
-
-GLOBAL_ENTRY(xen_send_ipi)
-	mov r14=r32
-	mov r15=r33
-	mov r2=0x400
-	break 0x1000
-	;;
-	br.ret.sptk.many rp
-	;;
-END(xen_send_ipi)
-
-GLOBAL_ENTRY(__hypercall)
-	mov r2=r37
-	break 0x1000
-	br.ret.sptk.many b0
-	;;
-END(__hypercall)
diff --git a/arch/ia64/xen/hypervisor.c b/arch/ia64/xen/hypervisor.c
deleted file mode 100644
index fab6252..0000000
--- a/arch/ia64/xen/hypervisor.c
+++ /dev/null
@@ -1,97 +0,0 @@
-/******************************************************************************
- * arch/ia64/xen/hypervisor.c
- *
- * Copyright (c) 2006 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#include <linux/efi.h>
-#include <linux/export.h>
-#include <asm/xen/hypervisor.h>
-#include <asm/xen/privop.h>
-
-#include "irq_xen.h"
-
-struct shared_info *HYPERVISOR_shared_info __read_mostly =
-	(struct shared_info *)XSI_BASE;
-EXPORT_SYMBOL(HYPERVISOR_shared_info);
-
-DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
-
-struct start_info *xen_start_info;
-EXPORT_SYMBOL(xen_start_info);
-
-EXPORT_SYMBOL(xen_domain_type);
-
-EXPORT_SYMBOL(__hypercall);
-
-/* Stolen from arch/x86/xen/enlighten.c */
-/*
- * Flag to determine whether vcpu info placement is available on all
- * VCPUs.  We assume it is to start with, and then set it to zero on
- * the first failure.  This is because it can succeed on some VCPUs
- * and not others, since it can involve hypervisor memory allocation,
- * or because the guest failed to guarantee all the appropriate
- * constraints on all VCPUs (ie buffer can't cross a page boundary).
- *
- * Note that any particular CPU may be using a placed vcpu structure,
- * but we can only optimise if the all are.
- *
- * 0: not available, 1: available
- */
-
-static void __init xen_vcpu_setup(int cpu)
-{
-	/*
-	 * WARNING:
-	 * before changing MAX_VIRT_CPUS,
-	 * check that shared_info fits on a page
-	 */
-	BUILD_BUG_ON(sizeof(struct shared_info) > PAGE_SIZE);
-	per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
-}
-
-void __init xen_setup_vcpu_info_placement(void)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		xen_vcpu_setup(cpu);
-}
-
-void
-xen_cpu_init(void)
-{
-	xen_smp_intr_init();
-}
-
-/**************************************************************************
- * opt feature
- */
-void
-xen_ia64_enable_opt_feature(void)
-{
-	/* Enable region 7 identity map optimizations in Xen */
-	struct xen_ia64_opt_feature optf;
-
-	optf.cmd = XEN_IA64_OPTF_IDENT_MAP_REG7;
-	optf.on = XEN_IA64_OPTF_ON;
-	optf.pgprot = pgprot_val(PAGE_KERNEL);
-	optf.key = 0;	/* No key on linux. */
-	HYPERVISOR_opt_feature(&optf);
-}
diff --git a/arch/ia64/xen/irq_xen.c b/arch/ia64/xen/irq_xen.c
deleted file mode 100644
index efb74da..0000000
--- a/arch/ia64/xen/irq_xen.c
+++ /dev/null
@@ -1,443 +0,0 @@
-/******************************************************************************
- * arch/ia64/xen/irq_xen.c
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#include <linux/cpu.h>
-
-#include <xen/interface/xen.h>
-#include <xen/interface/callback.h>
-#include <xen/events.h>
-
-#include <asm/xen/privop.h>
-
-#include "irq_xen.h"
-
-/***************************************************************************
- * pv_irq_ops
- * irq operations
- */
-
-static int
-xen_assign_irq_vector(int irq)
-{
-	struct physdev_irq irq_op;
-
-	irq_op.irq = irq;
-	if (HYPERVISOR_physdev_op(PHYSDEVOP_alloc_irq_vector, &irq_op))
-		return -ENOSPC;
-
-	return irq_op.vector;
-}
-
-static void
-xen_free_irq_vector(int vector)
-{
-	struct physdev_irq irq_op;
-
-	if (vector < IA64_FIRST_DEVICE_VECTOR ||
-	    vector > IA64_LAST_DEVICE_VECTOR)
-		return;
-
-	irq_op.vector = vector;
-	if (HYPERVISOR_physdev_op(PHYSDEVOP_free_irq_vector, &irq_op))
-		printk(KERN_WARNING "%s: xen_free_irq_vector fail vector=%d\n",
-		       __func__, vector);
-}
-
-
-static DEFINE_PER_CPU(int, xen_timer_irq) = -1;
-static DEFINE_PER_CPU(int, xen_ipi_irq) = -1;
-static DEFINE_PER_CPU(int, xen_resched_irq) = -1;
-static DEFINE_PER_CPU(int, xen_cmc_irq) = -1;
-static DEFINE_PER_CPU(int, xen_cmcp_irq) = -1;
-static DEFINE_PER_CPU(int, xen_cpep_irq) = -1;
-#define NAME_SIZE	15
-static DEFINE_PER_CPU(char[NAME_SIZE], xen_timer_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], xen_ipi_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], xen_resched_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], xen_cmc_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], xen_cmcp_name);
-static DEFINE_PER_CPU(char[NAME_SIZE], xen_cpep_name);
-#undef NAME_SIZE
-
-struct saved_irq {
-	unsigned int irq;
-	struct irqaction *action;
-};
-/* 16 should be far optimistic value, since only several percpu irqs
- * are registered early.
- */
-#define MAX_LATE_IRQ	16
-static struct saved_irq saved_percpu_irqs[MAX_LATE_IRQ];
-static unsigned short late_irq_cnt;
-static unsigned short saved_irq_cnt;
-static int xen_slab_ready;
-
-#ifdef CONFIG_SMP
-#include <linux/sched.h>
-
-/* Dummy stub. Though we may check XEN_RESCHEDULE_VECTOR before __do_IRQ,
- * it ends up to issue several memory accesses upon percpu data and
- * thus adds unnecessary traffic to other paths.
- */
-static irqreturn_t
-xen_dummy_handler(int irq, void *dev_id)
-{
-	return IRQ_HANDLED;
-}
-
-static irqreturn_t
-xen_resched_handler(int irq, void *dev_id)
-{
-	scheduler_ipi();
-	return IRQ_HANDLED;
-}
-
-static struct irqaction xen_ipi_irqaction = {
-	.handler =	handle_IPI,
-	.flags =	IRQF_DISABLED,
-	.name =		"IPI"
-};
-
-static struct irqaction xen_resched_irqaction = {
-	.handler =	xen_resched_handler,
-	.flags =	IRQF_DISABLED,
-	.name =		"resched"
-};
-
-static struct irqaction xen_tlb_irqaction = {
-	.handler =	xen_dummy_handler,
-	.flags =	IRQF_DISABLED,
-	.name =		"tlb_flush"
-};
-#endif
-
-/*
- * This is xen version percpu irq registration, which needs bind
- * to xen specific evtchn sub-system. One trick here is that xen
- * evtchn binding interface depends on kmalloc because related
- * port needs to be freed at device/cpu down. So we cache the
- * registration on BSP before slab is ready and then deal them
- * at later point. For rest instances happening after slab ready,
- * we hook them to xen evtchn immediately.
- *
- * FIXME: MCA is not supported by far, and thus "nomca" boot param is
- * required.
- */
-static void
-__xen_register_percpu_irq(unsigned int cpu, unsigned int vec,
-			struct irqaction *action, int save)
-{
-	int irq = 0;
-
-	if (xen_slab_ready) {
-		switch (vec) {
-		case IA64_TIMER_VECTOR:
-			snprintf(per_cpu(xen_timer_name, cpu),
-				 sizeof(per_cpu(xen_timer_name, cpu)),
-				 "%s%d", action->name, cpu);
-			irq = bind_virq_to_irqhandler(VIRQ_ITC, cpu,
-				action->handler, action->flags,
-				per_cpu(xen_timer_name, cpu), action->dev_id);
-			per_cpu(xen_timer_irq, cpu) = irq;
-			break;
-		case IA64_IPI_RESCHEDULE:
-			snprintf(per_cpu(xen_resched_name, cpu),
-				 sizeof(per_cpu(xen_resched_name, cpu)),
-				 "%s%d", action->name, cpu);
-			irq = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR, cpu,
-				action->handler, action->flags,
-				per_cpu(xen_resched_name, cpu), action->dev_id);
-			per_cpu(xen_resched_irq, cpu) = irq;
-			break;
-		case IA64_IPI_VECTOR:
-			snprintf(per_cpu(xen_ipi_name, cpu),
-				 sizeof(per_cpu(xen_ipi_name, cpu)),
-				 "%s%d", action->name, cpu);
-			irq = bind_ipi_to_irqhandler(XEN_IPI_VECTOR, cpu,
-				action->handler, action->flags,
-				per_cpu(xen_ipi_name, cpu), action->dev_id);
-			per_cpu(xen_ipi_irq, cpu) = irq;
-			break;
-		case IA64_CMC_VECTOR:
-			snprintf(per_cpu(xen_cmc_name, cpu),
-				 sizeof(per_cpu(xen_cmc_name, cpu)),
-				 "%s%d", action->name, cpu);
-			irq = bind_virq_to_irqhandler(VIRQ_MCA_CMC, cpu,
-						action->handler,
-						action->flags,
-						per_cpu(xen_cmc_name, cpu),
-						action->dev_id);
-			per_cpu(xen_cmc_irq, cpu) = irq;
-			break;
-		case IA64_CMCP_VECTOR:
-			snprintf(per_cpu(xen_cmcp_name, cpu),
-				 sizeof(per_cpu(xen_cmcp_name, cpu)),
-				 "%s%d", action->name, cpu);
-			irq = bind_ipi_to_irqhandler(XEN_CMCP_VECTOR, cpu,
-						action->handler,
-						action->flags,
-						per_cpu(xen_cmcp_name, cpu),
-						action->dev_id);
-			per_cpu(xen_cmcp_irq, cpu) = irq;
-			break;
-		case IA64_CPEP_VECTOR:
-			snprintf(per_cpu(xen_cpep_name, cpu),
-				 sizeof(per_cpu(xen_cpep_name, cpu)),
-				 "%s%d", action->name, cpu);
-			irq = bind_ipi_to_irqhandler(XEN_CPEP_VECTOR, cpu,
-						action->handler,
-						action->flags,
-						per_cpu(xen_cpep_name, cpu),
-						action->dev_id);
-			per_cpu(xen_cpep_irq, cpu) = irq;
-			break;
-		case IA64_CPE_VECTOR:
-		case IA64_MCA_RENDEZ_VECTOR:
-		case IA64_PERFMON_VECTOR:
-		case IA64_MCA_WAKEUP_VECTOR:
-		case IA64_SPURIOUS_INT_VECTOR:
-			/* No need to complain, these aren't supported. */
-			break;
-		default:
-			printk(KERN_WARNING "Percpu irq %d is unsupported "
-			       "by xen!\n", vec);
-			break;
-		}
-		BUG_ON(irq < 0);
-
-		if (irq > 0) {
-			/*
-			 * Mark percpu.  Without this, migrate_irqs() will
-			 * mark the interrupt for migrations and trigger it
-			 * on cpu hotplug.
-			 */
-			irq_set_status_flags(irq, IRQ_PER_CPU);
-		}
-	}
-
-	/* For BSP, we cache registered percpu irqs, and then re-walk
-	 * them when initializing APs
-	 */
-	if (!cpu && save) {
-		BUG_ON(saved_irq_cnt == MAX_LATE_IRQ);
-		saved_percpu_irqs[saved_irq_cnt].irq = vec;
-		saved_percpu_irqs[saved_irq_cnt].action = action;
-		saved_irq_cnt++;
-		if (!xen_slab_ready)
-			late_irq_cnt++;
-	}
-}
-
-static void
-xen_register_percpu_irq(ia64_vector vec, struct irqaction *action)
-{
-	__xen_register_percpu_irq(smp_processor_id(), vec, action, 1);
-}
-
-static void
-xen_bind_early_percpu_irq(void)
-{
-	int i;
-
-	xen_slab_ready = 1;
-	/* There's no race when accessing this cached array, since only
-	 * BSP will face with such step shortly
-	 */
-	for (i = 0; i < late_irq_cnt; i++)
-		__xen_register_percpu_irq(smp_processor_id(),
-					  saved_percpu_irqs[i].irq,
-					  saved_percpu_irqs[i].action, 0);
-}
-
-/* FIXME: There's no obvious point to check whether slab is ready. So
- * a hack is used here by utilizing a late time hook.
- */
-
-#ifdef CONFIG_HOTPLUG_CPU
-static int unbind_evtchn_callback(struct notifier_block *nfb,
-				  unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (unsigned long)hcpu;
-
-	if (action == CPU_DEAD) {
-		/* Unregister evtchn.  */
-		if (per_cpu(xen_cpep_irq, cpu) >= 0) {
-			unbind_from_irqhandler(per_cpu(xen_cpep_irq, cpu),
-					       NULL);
-			per_cpu(xen_cpep_irq, cpu) = -1;
-		}
-		if (per_cpu(xen_cmcp_irq, cpu) >= 0) {
-			unbind_from_irqhandler(per_cpu(xen_cmcp_irq, cpu),
-					       NULL);
-			per_cpu(xen_cmcp_irq, cpu) = -1;
-		}
-		if (per_cpu(xen_cmc_irq, cpu) >= 0) {
-			unbind_from_irqhandler(per_cpu(xen_cmc_irq, cpu), NULL);
-			per_cpu(xen_cmc_irq, cpu) = -1;
-		}
-		if (per_cpu(xen_ipi_irq, cpu) >= 0) {
-			unbind_from_irqhandler(per_cpu(xen_ipi_irq, cpu), NULL);
-			per_cpu(xen_ipi_irq, cpu) = -1;
-		}
-		if (per_cpu(xen_resched_irq, cpu) >= 0) {
-			unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu),
-					       NULL);
-			per_cpu(xen_resched_irq, cpu) = -1;
-		}
-		if (per_cpu(xen_timer_irq, cpu) >= 0) {
-			unbind_from_irqhandler(per_cpu(xen_timer_irq, cpu),
-					       NULL);
-			per_cpu(xen_timer_irq, cpu) = -1;
-		}
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block unbind_evtchn_notifier = {
-	.notifier_call = unbind_evtchn_callback,
-	.priority = 0
-};
-#endif
-
-void xen_smp_intr_init_early(unsigned int cpu)
-{
-#ifdef CONFIG_SMP
-	unsigned int i;
-
-	for (i = 0; i < saved_irq_cnt; i++)
-		__xen_register_percpu_irq(cpu, saved_percpu_irqs[i].irq,
-					  saved_percpu_irqs[i].action, 0);
-#endif
-}
-
-void xen_smp_intr_init(void)
-{
-#ifdef CONFIG_SMP
-	unsigned int cpu = smp_processor_id();
-	struct callback_register event = {
-		.type = CALLBACKTYPE_event,
-		.address = { .ip = (unsigned long)&xen_event_callback },
-	};
-
-	if (cpu == 0) {
-		/* Initialization was already done for boot cpu.  */
-#ifdef CONFIG_HOTPLUG_CPU
-		/* Register the notifier only once.  */
-		register_cpu_notifier(&unbind_evtchn_notifier);
-#endif
-		return;
-	}
-
-	/* This should be piggyback when setup vcpu guest context */
-	BUG_ON(HYPERVISOR_callback_op(CALLBACKOP_register, &event));
-#endif /* CONFIG_SMP */
-}
-
-void __init
-xen_irq_init(void)
-{
-	struct callback_register event = {
-		.type = CALLBACKTYPE_event,
-		.address = { .ip = (unsigned long)&xen_event_callback },
-	};
-
-	xen_init_IRQ();
-	BUG_ON(HYPERVISOR_callback_op(CALLBACKOP_register, &event));
-	late_time_init = xen_bind_early_percpu_irq;
-}
-
-void
-xen_platform_send_ipi(int cpu, int vector, int delivery_mode, int redirect)
-{
-#ifdef CONFIG_SMP
-	/* TODO: we need to call vcpu_up here */
-	if (unlikely(vector == ap_wakeup_vector)) {
-		/* XXX
-		 * This should be in __cpu_up(cpu) in ia64 smpboot.c
-		 * like x86. But don't want to modify it,
-		 * keep it untouched.
-		 */
-		xen_smp_intr_init_early(cpu);
-
-		xen_send_ipi(cpu, vector);
-		/* vcpu_prepare_and_up(cpu); */
-		return;
-	}
-#endif
-
-	switch (vector) {
-	case IA64_IPI_VECTOR:
-		xen_send_IPI_one(cpu, XEN_IPI_VECTOR);
-		break;
-	case IA64_IPI_RESCHEDULE:
-		xen_send_IPI_one(cpu, XEN_RESCHEDULE_VECTOR);
-		break;
-	case IA64_CMCP_VECTOR:
-		xen_send_IPI_one(cpu, XEN_CMCP_VECTOR);
-		break;
-	case IA64_CPEP_VECTOR:
-		xen_send_IPI_one(cpu, XEN_CPEP_VECTOR);
-		break;
-	case IA64_TIMER_VECTOR: {
-		/* this is used only once by check_sal_cache_flush()
-		   at boot time */
-		static int used = 0;
-		if (!used) {
-			xen_send_ipi(cpu, IA64_TIMER_VECTOR);
-			used = 1;
-			break;
-		}
-		/* fallthrough */
-	}
-	default:
-		printk(KERN_WARNING "Unsupported IPI type 0x%x\n",
-		       vector);
-		notify_remote_via_irq(0); /* defaults to 0 irq */
-		break;
-	}
-}
-
-static void __init
-xen_register_ipi(void)
-{
-#ifdef CONFIG_SMP
-	register_percpu_irq(IA64_IPI_VECTOR, &xen_ipi_irqaction);
-	register_percpu_irq(IA64_IPI_RESCHEDULE, &xen_resched_irqaction);
-	register_percpu_irq(IA64_IPI_LOCAL_TLB_FLUSH, &xen_tlb_irqaction);
-#endif
-}
-
-static void
-xen_resend_irq(unsigned int vector)
-{
-	(void)resend_irq_on_evtchn(vector);
-}
-
-const struct pv_irq_ops xen_irq_ops __initconst = {
-	.register_ipi = xen_register_ipi,
-
-	.assign_irq_vector = xen_assign_irq_vector,
-	.free_irq_vector = xen_free_irq_vector,
-	.register_percpu_irq = xen_register_percpu_irq,
-
-	.resend_irq = xen_resend_irq,
-};
diff --git a/arch/ia64/xen/irq_xen.h b/arch/ia64/xen/irq_xen.h
deleted file mode 100644
index 1778517..0000000
--- a/arch/ia64/xen/irq_xen.h
+++ /dev/null
@@ -1,34 +0,0 @@
-/******************************************************************************
- * arch/ia64/xen/irq_xen.h
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#ifndef IRQ_XEN_H
-#define IRQ_XEN_H
-
-extern void (*late_time_init)(void);
-extern char xen_event_callback;
-void __init xen_init_IRQ(void);
-
-extern const struct pv_irq_ops xen_irq_ops __initconst;
-extern void xen_smp_intr_init(void);
-extern void xen_send_ipi(int cpu, int vec);
-
-#endif /* IRQ_XEN_H */
diff --git a/arch/ia64/xen/machvec.c b/arch/ia64/xen/machvec.c
deleted file mode 100644
index 4ad588a..0000000
--- a/arch/ia64/xen/machvec.c
+++ /dev/null
@@ -1,4 +0,0 @@
-#define MACHVEC_PLATFORM_NAME           xen
-#define MACHVEC_PLATFORM_HEADER         <asm/machvec_xen.h>
-#include <asm/machvec_init.h>
-
diff --git a/arch/ia64/xen/suspend.c b/arch/ia64/xen/suspend.c
deleted file mode 100644
index 419c862..0000000
--- a/arch/ia64/xen/suspend.c
+++ /dev/null
@@ -1,59 +0,0 @@
-/******************************************************************************
- * arch/ia64/xen/suspend.c
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- * suspend/resume
- */
-
-#include <xen/xen-ops.h>
-#include <asm/xen/hypervisor.h>
-#include "time.h"
-
-void
-xen_mm_pin_all(void)
-{
-	/* nothing */
-}
-
-void
-xen_mm_unpin_all(void)
-{
-	/* nothing */
-}
-
-void
-xen_arch_pre_suspend()
-{
-	/* nothing */
-}
-
-void
-xen_arch_post_suspend(int suspend_cancelled)
-{
-	if (suspend_cancelled)
-		return;
-
-	xen_ia64_enable_opt_feature();
-	/* add more if necessary */
-}
-
-void xen_arch_resume(void)
-{
-	xen_timer_resume_on_aps();
-}
diff --git a/arch/ia64/xen/time.c b/arch/ia64/xen/time.c
deleted file mode 100644
index 1f8244a..0000000
--- a/arch/ia64/xen/time.c
+++ /dev/null
@@ -1,257 +0,0 @@
-/******************************************************************************
- * arch/ia64/xen/time.c
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#include <linux/delay.h>
-#include <linux/kernel_stat.h>
-#include <linux/posix-timers.h>
-#include <linux/irq.h>
-#include <linux/clocksource.h>
-
-#include <asm/timex.h>
-
-#include <asm/xen/hypervisor.h>
-
-#include <xen/interface/vcpu.h>
-
-#include "../kernel/fsyscall_gtod_data.h"
-
-static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate);
-static DEFINE_PER_CPU(unsigned long, xen_stolen_time);
-static DEFINE_PER_CPU(unsigned long, xen_blocked_time);
-
-/* taken from i386/kernel/time-xen.c */
-static void xen_init_missing_ticks_accounting(int cpu)
-{
-	struct vcpu_register_runstate_memory_area area;
-	struct vcpu_runstate_info *runstate = &per_cpu(xen_runstate, cpu);
-	int rc;
-
-	memset(runstate, 0, sizeof(*runstate));
-
-	area.addr.v = runstate;
-	rc = HYPERVISOR_vcpu_op(VCPUOP_register_runstate_memory_area, cpu,
-				&area);
-	WARN_ON(rc && rc != -ENOSYS);
-
-	per_cpu(xen_blocked_time, cpu) = runstate->time[RUNSTATE_blocked];
-	per_cpu(xen_stolen_time, cpu) = runstate->time[RUNSTATE_runnable]
-					    + runstate->time[RUNSTATE_offline];
-}
-
-/*
- * Runstate accounting
- */
-/* stolen from arch/x86/xen/time.c */
-static void get_runstate_snapshot(struct vcpu_runstate_info *res)
-{
-	u64 state_time;
-	struct vcpu_runstate_info *state;
-
-	BUG_ON(preemptible());
-
-	state = &__get_cpu_var(xen_runstate);
-
-	/*
-	 * The runstate info is always updated by the hypervisor on
-	 * the current CPU, so there's no need to use anything
-	 * stronger than a compiler barrier when fetching it.
-	 */
-	do {
-		state_time = state->state_entry_time;
-		rmb();
-		*res = *state;
-		rmb();
-	} while (state->state_entry_time != state_time);
-}
-
-#define NS_PER_TICK (1000000000LL/HZ)
-
-static unsigned long
-consider_steal_time(unsigned long new_itm)
-{
-	unsigned long stolen, blocked;
-	unsigned long delta_itm = 0, stolentick = 0;
-	int cpu = smp_processor_id();
-	struct vcpu_runstate_info runstate;
-	struct task_struct *p = current;
-
-	get_runstate_snapshot(&runstate);
-
-	/*
-	 * Check for vcpu migration effect
-	 * In this case, itc value is reversed.
-	 * This causes huge stolen value.
-	 * This function just checks and reject this effect.
-	 */
-	if (!time_after_eq(runstate.time[RUNSTATE_blocked],
-			   per_cpu(xen_blocked_time, cpu)))
-		blocked = 0;
-
-	if (!time_after_eq(runstate.time[RUNSTATE_runnable] +
-			   runstate.time[RUNSTATE_offline],
-			   per_cpu(xen_stolen_time, cpu)))
-		stolen = 0;
-
-	if (!time_after(delta_itm + new_itm, ia64_get_itc()))
-		stolentick = ia64_get_itc() - new_itm;
-
-	do_div(stolentick, NS_PER_TICK);
-	stolentick++;
-
-	do_div(stolen, NS_PER_TICK);
-
-	if (stolen > stolentick)
-		stolen = stolentick;
-
-	stolentick -= stolen;
-	do_div(blocked, NS_PER_TICK);
-
-	if (blocked > stolentick)
-		blocked = stolentick;
-
-	if (stolen > 0 || blocked > 0) {
-		account_steal_ticks(stolen);
-		account_idle_ticks(blocked);
-		run_local_timers();
-
-		rcu_check_callbacks(cpu, user_mode(get_irq_regs()));
-
-		scheduler_tick();
-		run_posix_cpu_timers(p);
-		delta_itm += local_cpu_data->itm_delta * (stolen + blocked);
-
-		if (cpu == time_keeper_id)
-			xtime_update(stolen + blocked);
-
-		local_cpu_data->itm_next = delta_itm + new_itm;
-
-		per_cpu(xen_stolen_time, cpu) += NS_PER_TICK * stolen;
-		per_cpu(xen_blocked_time, cpu) += NS_PER_TICK * blocked;
-	}
-	return delta_itm;
-}
-
-static int xen_do_steal_accounting(unsigned long *new_itm)
-{
-	unsigned long delta_itm;
-	delta_itm = consider_steal_time(*new_itm);
-	*new_itm += delta_itm;
-	if (time_after(*new_itm, ia64_get_itc()) && delta_itm)
-		return 1;
-
-	return 0;
-}
-
-static void xen_itc_jitter_data_reset(void)
-{
-	u64 lcycle, ret;
-
-	do {
-		lcycle = itc_jitter_data.itc_lastcycle;
-		ret = cmpxchg(&itc_jitter_data.itc_lastcycle, lcycle, 0);
-	} while (unlikely(ret != lcycle));
-}
-
-/* based on xen_sched_clock() in arch/x86/xen/time.c. */
-/*
- * This relies on HAVE_UNSTABLE_SCHED_CLOCK. If it can't be defined,
- * something similar logic should be implemented here.
- */
-/*
- * Xen sched_clock implementation.  Returns the number of unstolen
- * nanoseconds, which is nanoseconds the VCPU spent in RUNNING+BLOCKED
- * states.
- */
-static unsigned long long xen_sched_clock(void)
-{
-	struct vcpu_runstate_info runstate;
-
-	unsigned long long now;
-	unsigned long long offset;
-	unsigned long long ret;
-
-	/*
-	 * Ideally sched_clock should be called on a per-cpu basis
-	 * anyway, so preempt should already be disabled, but that's
-	 * not current practice at the moment.
-	 */
-	preempt_disable();
-
-	/*
-	 * both ia64_native_sched_clock() and xen's runstate are
-	 * based on mAR.ITC. So difference of them makes sense.
-	 */
-	now = ia64_native_sched_clock();
-
-	get_runstate_snapshot(&runstate);
-
-	WARN_ON(runstate.state != RUNSTATE_running);
-
-	offset = 0;
-	if (now > runstate.state_entry_time)
-		offset = now - runstate.state_entry_time;
-	ret = runstate.time[RUNSTATE_blocked] +
-		runstate.time[RUNSTATE_running] +
-		offset;
-
-	preempt_enable();
-
-	return ret;
-}
-
-struct pv_time_ops xen_time_ops __initdata = {
-	.init_missing_ticks_accounting	= xen_init_missing_ticks_accounting,
-	.do_steal_accounting		= xen_do_steal_accounting,
-	.clocksource_resume		= xen_itc_jitter_data_reset,
-	.sched_clock			= xen_sched_clock,
-};
-
-/* Called after suspend, to resume time.  */
-static void xen_local_tick_resume(void)
-{
-	/* Just trigger a tick.  */
-	ia64_cpu_local_tick();
-	touch_softlockup_watchdog();
-}
-
-void
-xen_timer_resume(void)
-{
-	unsigned int cpu;
-
-	xen_local_tick_resume();
-
-	for_each_online_cpu(cpu)
-		xen_init_missing_ticks_accounting(cpu);
-}
-
-static void ia64_cpu_local_tick_fn(void *unused)
-{
-	xen_local_tick_resume();
-	xen_init_missing_ticks_accounting(smp_processor_id());
-}
-
-void
-xen_timer_resume_on_aps(void)
-{
-	smp_call_function(&ia64_cpu_local_tick_fn, NULL, 1);
-}
diff --git a/arch/ia64/xen/time.h b/arch/ia64/xen/time.h
deleted file mode 100644
index f98d7e1..0000000
--- a/arch/ia64/xen/time.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/******************************************************************************
- * arch/ia64/xen/time.h
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-extern struct pv_time_ops xen_time_ops __initdata;
-void xen_timer_resume_on_aps(void);
diff --git a/arch/ia64/xen/xcom_hcall.c b/arch/ia64/xen/xcom_hcall.c
deleted file mode 100644
index ccaf743..0000000
--- a/arch/ia64/xen/xcom_hcall.c
+++ /dev/null
@@ -1,441 +0,0 @@
-/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
- *
- *          Tristan Gingold <tristan.gingold@bull.net>
- *
- *          Copyright (c) 2007
- *          Isaku Yamahata <yamahata at valinux co jp>
- *                          VA Linux Systems Japan K.K.
- *          consolidate mini and inline version.
- */
-
-#include <linux/module.h>
-#include <xen/interface/xen.h>
-#include <xen/interface/memory.h>
-#include <xen/interface/grant_table.h>
-#include <xen/interface/callback.h>
-#include <xen/interface/vcpu.h>
-#include <asm/xen/hypervisor.h>
-#include <asm/xen/xencomm.h>
-
-/* Xencomm notes:
- * This file defines hypercalls to be used by xencomm.  The hypercalls simply
- * create inlines or mini descriptors for pointers and then call the raw arch
- * hypercall xencomm_arch_hypercall_XXX
- *
- * If the arch wants to directly use these hypercalls, simply define macros
- * in asm/xen/hypercall.h, eg:
- *  #define HYPERVISOR_sched_op xencomm_hypercall_sched_op
- *
- * The arch may also define HYPERVISOR_xxx as a function and do more operations
- * before/after doing the hypercall.
- *
- * Note: because only inline or mini descriptors are created these functions
- * must only be called with in kernel memory parameters.
- */
-
-int
-xencomm_hypercall_console_io(int cmd, int count, char *str)
-{
-	/* xen early printk uses console io hypercall before
-	 * xencomm initialization. In that case, we just ignore it.
-	 */
-	if (!xencomm_is_initialized())
-		return 0;
-
-	return xencomm_arch_hypercall_console_io
-		(cmd, count, xencomm_map_no_alloc(str, count));
-}
-EXPORT_SYMBOL_GPL(xencomm_hypercall_console_io);
-
-int
-xencomm_hypercall_event_channel_op(int cmd, void *op)
-{
-	struct xencomm_handle *desc;
-	desc = xencomm_map_no_alloc(op, sizeof(struct evtchn_op));
-	if (desc == NULL)
-		return -EINVAL;
-
-	return xencomm_arch_hypercall_event_channel_op(cmd, desc);
-}
-EXPORT_SYMBOL_GPL(xencomm_hypercall_event_channel_op);
-
-int
-xencomm_hypercall_xen_version(int cmd, void *arg)
-{
-	struct xencomm_handle *desc;
-	unsigned int argsize;
-
-	switch (cmd) {
-	case XENVER_version:
-		/* do not actually pass an argument */
-		return xencomm_arch_hypercall_xen_version(cmd, 0);
-	case XENVER_extraversion:
-		argsize = sizeof(struct xen_extraversion);
-		break;
-	case XENVER_compile_info:
-		argsize = sizeof(struct xen_compile_info);
-		break;
-	case XENVER_capabilities:
-		argsize = sizeof(struct xen_capabilities_info);
-		break;
-	case XENVER_changeset:
-		argsize = sizeof(struct xen_changeset_info);
-		break;
-	case XENVER_platform_parameters:
-		argsize = sizeof(struct xen_platform_parameters);
-		break;
-	case XENVER_get_features:
-		argsize = (arg == NULL) ? 0 : sizeof(struct xen_feature_info);
-		break;
-
-	default:
-		printk(KERN_DEBUG
-		       "%s: unknown version op %d\n", __func__, cmd);
-		return -ENOSYS;
-	}
-
-	desc = xencomm_map_no_alloc(arg, argsize);
-	if (desc == NULL)
-		return -EINVAL;
-
-	return xencomm_arch_hypercall_xen_version(cmd, desc);
-}
-EXPORT_SYMBOL_GPL(xencomm_hypercall_xen_version);
-
-int
-xencomm_hypercall_physdev_op(int cmd, void *op)
-{
-	unsigned int argsize;
-
-	switch (cmd) {
-	case PHYSDEVOP_apic_read:
-	case PHYSDEVOP_apic_write:
-		argsize = sizeof(struct physdev_apic);
-		break;
-	case PHYSDEVOP_alloc_irq_vector:
-	case PHYSDEVOP_free_irq_vector:
-		argsize = sizeof(struct physdev_irq);
-		break;
-	case PHYSDEVOP_irq_status_query:
-		argsize = sizeof(struct physdev_irq_status_query);
-		break;
-
-	default:
-		printk(KERN_DEBUG
-		       "%s: unknown physdev op %d\n", __func__, cmd);
-		return -ENOSYS;
-	}
-
-	return xencomm_arch_hypercall_physdev_op
-		(cmd, xencomm_map_no_alloc(op, argsize));
-}
-
-static int
-xencommize_grant_table_op(struct xencomm_mini **xc_area,
-			  unsigned int cmd, void *op, unsigned int count,
-			  struct xencomm_handle **desc)
-{
-	struct xencomm_handle *desc1;
-	unsigned int argsize;
-
-	switch (cmd) {
-	case GNTTABOP_map_grant_ref:
-		argsize = sizeof(struct gnttab_map_grant_ref);
-		break;
-	case GNTTABOP_unmap_grant_ref:
-		argsize = sizeof(struct gnttab_unmap_grant_ref);
-		break;
-	case GNTTABOP_setup_table:
-	{
-		struct gnttab_setup_table *setup = op;
-
-		argsize = sizeof(*setup);
-
-		if (count != 1)
-			return -EINVAL;
-		desc1 = __xencomm_map_no_alloc
-			(xen_guest_handle(setup->frame_list),
-			 setup->nr_frames *
-			 sizeof(*xen_guest_handle(setup->frame_list)),
-			 *xc_area);
-		if (desc1 == NULL)
-			return -EINVAL;
-		(*xc_area)++;
-		set_xen_guest_handle(setup->frame_list, (void *)desc1);
-		break;
-	}
-	case GNTTABOP_dump_table:
-		argsize = sizeof(struct gnttab_dump_table);
-		break;
-	case GNTTABOP_transfer:
-		argsize = sizeof(struct gnttab_transfer);
-		break;
-	case GNTTABOP_copy:
-		argsize = sizeof(struct gnttab_copy);
-		break;
-	case GNTTABOP_query_size:
-		argsize = sizeof(struct gnttab_query_size);
-		break;
-	default:
-		printk(KERN_DEBUG "%s: unknown hypercall grant table op %d\n",
-		       __func__, cmd);
-		BUG();
-	}
-
-	*desc = __xencomm_map_no_alloc(op, count * argsize, *xc_area);
-	if (*desc == NULL)
-		return -EINVAL;
-	(*xc_area)++;
-
-	return 0;
-}
-
-int
-xencomm_hypercall_grant_table_op(unsigned int cmd, void *op,
-				 unsigned int count)
-{
-	int rc;
-	struct xencomm_handle *desc;
-	XENCOMM_MINI_ALIGNED(xc_area, 2);
-
-	rc = xencommize_grant_table_op(&xc_area, cmd, op, count, &desc);
-	if (rc)
-		return rc;
-
-	return xencomm_arch_hypercall_grant_table_op(cmd, desc, count);
-}
-EXPORT_SYMBOL_GPL(xencomm_hypercall_grant_table_op);
-
-int
-xencomm_hypercall_sched_op(int cmd, void *arg)
-{
-	struct xencomm_handle *desc;
-	unsigned int argsize;
-
-	switch (cmd) {
-	case SCHEDOP_yield:
-	case SCHEDOP_block:
-		argsize = 0;
-		break;
-	case SCHEDOP_shutdown:
-		argsize = sizeof(struct sched_shutdown);
-		break;
-	case SCHEDOP_poll:
-	{
-		struct sched_poll *poll = arg;
-		struct xencomm_handle *ports;
-
-		argsize = sizeof(struct sched_poll);
-		ports = xencomm_map_no_alloc(xen_guest_handle(poll->ports),
-				     sizeof(*xen_guest_handle(poll->ports)));
-
-		set_xen_guest_handle(poll->ports, (void *)ports);
-		break;
-	}
-	default:
-		printk(KERN_DEBUG "%s: unknown sched op %d\n", __func__, cmd);
-		return -ENOSYS;
-	}
-
-	desc = xencomm_map_no_alloc(arg, argsize);
-	if (desc == NULL)
-		return -EINVAL;
-
-	return xencomm_arch_hypercall_sched_op(cmd, desc);
-}
-EXPORT_SYMBOL_GPL(xencomm_hypercall_sched_op);
-
-int
-xencomm_hypercall_multicall(void *call_list, int nr_calls)
-{
-	int rc;
-	int i;
-	struct multicall_entry *mce;
-	struct xencomm_handle *desc;
-	XENCOMM_MINI_ALIGNED(xc_area, nr_calls * 2);
-
-	for (i = 0; i < nr_calls; i++) {
-		mce = (struct multicall_entry *)call_list + i;
-
-		switch (mce->op) {
-		case __HYPERVISOR_update_va_mapping:
-		case __HYPERVISOR_mmu_update:
-			/* No-op on ia64.  */
-			break;
-		case __HYPERVISOR_grant_table_op:
-			rc = xencommize_grant_table_op
-				(&xc_area,
-				 mce->args[0], (void *)mce->args[1],
-				 mce->args[2], &desc);
-			if (rc)
-				return rc;
-			mce->args[1] = (unsigned long)desc;
-			break;
-		case __HYPERVISOR_memory_op:
-		default:
-			printk(KERN_DEBUG
-			       "%s: unhandled multicall op entry op %lu\n",
-			       __func__, mce->op);
-			return -ENOSYS;
-		}
-	}
-
-	desc = xencomm_map_no_alloc(call_list,
-				    nr_calls * sizeof(struct multicall_entry));
-	if (desc == NULL)
-		return -EINVAL;
-
-	return xencomm_arch_hypercall_multicall(desc, nr_calls);
-}
-EXPORT_SYMBOL_GPL(xencomm_hypercall_multicall);
-
-int
-xencomm_hypercall_callback_op(int cmd, void *arg)
-{
-	unsigned int argsize;
-	switch (cmd) {
-	case CALLBACKOP_register:
-		argsize = sizeof(struct callback_register);
-		break;
-	case CALLBACKOP_unregister:
-		argsize = sizeof(struct callback_unregister);
-		break;
-	default:
-		printk(KERN_DEBUG
-		       "%s: unknown callback op %d\n", __func__, cmd);
-		return -ENOSYS;
-	}
-
-	return xencomm_arch_hypercall_callback_op
-		(cmd, xencomm_map_no_alloc(arg, argsize));
-}
-
-static int
-xencommize_memory_reservation(struct xencomm_mini *xc_area,
-			      struct xen_memory_reservation *mop)
-{
-	struct xencomm_handle *desc;
-
-	desc = __xencomm_map_no_alloc(xen_guest_handle(mop->extent_start),
-			mop->nr_extents *
-			sizeof(*xen_guest_handle(mop->extent_start)),
-			xc_area);
-	if (desc == NULL)
-		return -EINVAL;
-
-	set_xen_guest_handle(mop->extent_start, (void *)desc);
-	return 0;
-}
-
-int
-xencomm_hypercall_memory_op(unsigned int cmd, void *arg)
-{
-	GUEST_HANDLE(xen_pfn_t) extent_start_va[2] = { {NULL}, {NULL} };
-	struct xen_memory_reservation *xmr = NULL;
-	int rc;
-	struct xencomm_handle *desc;
-	unsigned int argsize;
-	XENCOMM_MINI_ALIGNED(xc_area, 2);
-
-	switch (cmd) {
-	case XENMEM_increase_reservation:
-	case XENMEM_decrease_reservation:
-	case XENMEM_populate_physmap:
-		xmr = (struct xen_memory_reservation *)arg;
-		set_xen_guest_handle(extent_start_va[0],
-				     xen_guest_handle(xmr->extent_start));
-
-		argsize = sizeof(*xmr);
-		rc = xencommize_memory_reservation(xc_area, xmr);
-		if (rc)
-			return rc;
-		xc_area++;
-		break;
-
-	case XENMEM_maximum_ram_page:
-		argsize = 0;
-		break;
-
-	case XENMEM_add_to_physmap:
-		argsize = sizeof(struct xen_add_to_physmap);
-		break;
-
-	default:
-		printk(KERN_DEBUG "%s: unknown memory op %d\n", __func__, cmd);
-		return -ENOSYS;
-	}
-
-	desc = xencomm_map_no_alloc(arg, argsize);
-	if (desc == NULL)
-		return -EINVAL;
-
-	rc = xencomm_arch_hypercall_memory_op(cmd, desc);
-
-	switch (cmd) {
-	case XENMEM_increase_reservation:
-	case XENMEM_decrease_reservation:
-	case XENMEM_populate_physmap:
-		set_xen_guest_handle(xmr->extent_start,
-				     xen_guest_handle(extent_start_va[0]));
-		break;
-	}
-
-	return rc;
-}
-EXPORT_SYMBOL_GPL(xencomm_hypercall_memory_op);
-
-int
-xencomm_hypercall_suspend(unsigned long srec)
-{
-	struct sched_shutdown arg;
-
-	arg.reason = SHUTDOWN_suspend;
-
-	return xencomm_arch_hypercall_sched_op(
-		SCHEDOP_shutdown, xencomm_map_no_alloc(&arg, sizeof(arg)));
-}
-
-long
-xencomm_hypercall_vcpu_op(int cmd, int cpu, void *arg)
-{
-	unsigned int argsize;
-	switch (cmd) {
-	case VCPUOP_register_runstate_memory_area: {
-		struct vcpu_register_runstate_memory_area *area =
-			(struct vcpu_register_runstate_memory_area *)arg;
-		argsize = sizeof(*arg);
-		set_xen_guest_handle(area->addr.h,
-		     (void *)xencomm_map_no_alloc(area->addr.v,
-						  sizeof(area->addr.v)));
-		break;
-	}
-
-	default:
-		printk(KERN_DEBUG "%s: unknown vcpu op %d\n", __func__, cmd);
-		return -ENOSYS;
-	}
-
-	return xencomm_arch_hypercall_vcpu_op(cmd, cpu,
-					xencomm_map_no_alloc(arg, argsize));
-}
-
-long
-xencomm_hypercall_opt_feature(void *arg)
-{
-	return xencomm_arch_hypercall_opt_feature(
-		xencomm_map_no_alloc(arg,
-				     sizeof(struct xen_ia64_opt_feature)));
-}
diff --git a/arch/ia64/xen/xen_pv_ops.c b/arch/ia64/xen/xen_pv_ops.c
deleted file mode 100644
index 3e8d350..0000000
--- a/arch/ia64/xen/xen_pv_ops.c
+++ /dev/null
@@ -1,1141 +0,0 @@
-/******************************************************************************
- * arch/ia64/xen/xen_pv_ops.c
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- */
-
-#include <linux/console.h>
-#include <linux/irq.h>
-#include <linux/kernel.h>
-#include <linux/pm.h>
-#include <linux/unistd.h>
-
-#include <asm/xen/hypervisor.h>
-#include <asm/xen/xencomm.h>
-#include <asm/xen/privop.h>
-
-#include "irq_xen.h"
-#include "time.h"
-
-/***************************************************************************
- * general info
- */
-static struct pv_info xen_info __initdata = {
-	.kernel_rpl = 2,	/* or 1: determin at runtime */
-	.paravirt_enabled = 1,
-	.name = "Xen/ia64",
-};
-
-#define IA64_RSC_PL_SHIFT	2
-#define IA64_RSC_PL_BIT_SIZE	2
-#define IA64_RSC_PL_MASK	\
-	(((1UL << IA64_RSC_PL_BIT_SIZE) - 1) << IA64_RSC_PL_SHIFT)
-
-static void __init
-xen_info_init(void)
-{
-	/* Xenified Linux/ia64 may run on pl = 1 or 2.
-	 * determin at run time. */
-	unsigned long rsc = ia64_getreg(_IA64_REG_AR_RSC);
-	unsigned int rpl = (rsc & IA64_RSC_PL_MASK) >> IA64_RSC_PL_SHIFT;
-	xen_info.kernel_rpl = rpl;
-}
-
-/***************************************************************************
- * pv_init_ops
- * initialization hooks.
- */
-
-static void
-xen_panic_hypercall(struct unw_frame_info *info, void *arg)
-{
-	current->thread.ksp = (__u64)info->sw - 16;
-	HYPERVISOR_shutdown(SHUTDOWN_crash);
-	/* we're never actually going to get here... */
-}
-
-static int
-xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr)
-{
-	unw_init_running(xen_panic_hypercall, NULL);
-	/* we're never actually going to get here... */
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block xen_panic_block = {
-	xen_panic_event, NULL, 0 /* try to go last */
-};
-
-static void xen_pm_power_off(void)
-{
-	local_irq_disable();
-	HYPERVISOR_shutdown(SHUTDOWN_poweroff);
-}
-
-static void __init
-xen_banner(void)
-{
-	printk(KERN_INFO
-	       "Running on Xen! pl = %d start_info_pfn=0x%lx nr_pages=%ld "
-	       "flags=0x%x\n",
-	       xen_info.kernel_rpl,
-	       HYPERVISOR_shared_info->arch.start_info_pfn,
-	       xen_start_info->nr_pages, xen_start_info->flags);
-}
-
-static int __init
-xen_reserve_memory(struct rsvd_region *region)
-{
-	region->start = (unsigned long)__va(
-		(HYPERVISOR_shared_info->arch.start_info_pfn << PAGE_SHIFT));
-	region->end   = region->start + PAGE_SIZE;
-	return 1;
-}
-
-static void __init
-xen_arch_setup_early(void)
-{
-	struct shared_info *s;
-	BUG_ON(!xen_pv_domain());
-
-	s = HYPERVISOR_shared_info;
-	xen_start_info = __va(s->arch.start_info_pfn << PAGE_SHIFT);
-
-	/* Must be done before any hypercall.  */
-	xencomm_initialize();
-
-	xen_setup_features();
-	/* Register a call for panic conditions. */
-	atomic_notifier_chain_register(&panic_notifier_list,
-				       &xen_panic_block);
-	pm_power_off = xen_pm_power_off;
-
-	xen_ia64_enable_opt_feature();
-}
-
-static void __init
-xen_arch_setup_console(char **cmdline_p)
-{
-	add_preferred_console("xenboot", 0, NULL);
-	add_preferred_console("tty", 0, NULL);
-	/* use hvc_xen */
-	add_preferred_console("hvc", 0, NULL);
-
-#if !defined(CONFIG_VT) || !defined(CONFIG_DUMMY_CONSOLE)
-	conswitchp = NULL;
-#endif
-}
-
-static int __init
-xen_arch_setup_nomca(void)
-{
-	return 1;
-}
-
-static void __init
-xen_post_smp_prepare_boot_cpu(void)
-{
-	xen_setup_vcpu_info_placement();
-}
-
-#ifdef ASM_SUPPORTED
-static unsigned long __init_or_module
-xen_patch_bundle(void *sbundle, void *ebundle, unsigned long type);
-#endif
-static void __init
-xen_patch_branch(unsigned long tag, unsigned long type);
-
-static const struct pv_init_ops xen_init_ops __initconst = {
-	.banner = xen_banner,
-
-	.reserve_memory = xen_reserve_memory,
-
-	.arch_setup_early = xen_arch_setup_early,
-	.arch_setup_console = xen_arch_setup_console,
-	.arch_setup_nomca = xen_arch_setup_nomca,
-
-	.post_smp_prepare_boot_cpu = xen_post_smp_prepare_boot_cpu,
-#ifdef ASM_SUPPORTED
-	.patch_bundle = xen_patch_bundle,
-#endif
-	.patch_branch = xen_patch_branch,
-};
-
-/***************************************************************************
- * pv_fsys_data
- * addresses for fsys
- */
-
-extern unsigned long xen_fsyscall_table[NR_syscalls];
-extern char xen_fsys_bubble_down[];
-struct pv_fsys_data xen_fsys_data __initdata = {
-	.fsyscall_table = (unsigned long *)xen_fsyscall_table,
-	.fsys_bubble_down = (void *)xen_fsys_bubble_down,
-};
-
-/***************************************************************************
- * pv_patchdata
- * patchdata addresses
- */
-
-#define DECLARE(name)							\
-	extern unsigned long __xen_start_gate_##name##_patchlist[];	\
-	extern unsigned long __xen_end_gate_##name##_patchlist[]
-
-DECLARE(fsyscall);
-DECLARE(brl_fsys_bubble_down);
-DECLARE(vtop);
-DECLARE(mckinley_e9);
-
-extern unsigned long __xen_start_gate_section[];
-
-#define ASSIGN(name)							\
-	.start_##name##_patchlist =					\
-		(unsigned long)__xen_start_gate_##name##_patchlist,	\
-	.end_##name##_patchlist =					\
-		(unsigned long)__xen_end_gate_##name##_patchlist
-
-static struct pv_patchdata xen_patchdata __initdata = {
-	ASSIGN(fsyscall),
-	ASSIGN(brl_fsys_bubble_down),
-	ASSIGN(vtop),
-	ASSIGN(mckinley_e9),
-
-	.gate_section = (void*)__xen_start_gate_section,
-};
-
-/***************************************************************************
- * pv_cpu_ops
- * intrinsics hooks.
- */
-
-#ifndef ASM_SUPPORTED
-static void
-xen_set_itm_with_offset(unsigned long val)
-{
-	/* ia64_cpu_local_tick() calls this with interrupt enabled. */
-	/* WARN_ON(!irqs_disabled()); */
-	xen_set_itm(val - XEN_MAPPEDREGS->itc_offset);
-}
-
-static unsigned long
-xen_get_itm_with_offset(void)
-{
-	/* unused at this moment */
-	printk(KERN_DEBUG "%s is called.\n", __func__);
-
-	WARN_ON(!irqs_disabled());
-	return ia64_native_getreg(_IA64_REG_CR_ITM) +
-		XEN_MAPPEDREGS->itc_offset;
-}
-
-/* ia64_set_itc() is only called by
- * cpu_init() with ia64_set_itc(0) and ia64_sync_itc().
- * So XEN_MAPPEDRESG->itc_offset cal be considered as almost constant.
- */
-static void
-xen_set_itc(unsigned long val)
-{
-	unsigned long mitc;
-
-	WARN_ON(!irqs_disabled());
-	mitc = ia64_native_getreg(_IA64_REG_AR_ITC);
-	XEN_MAPPEDREGS->itc_offset = val - mitc;
-	XEN_MAPPEDREGS->itc_last = val;
-}
-
-static unsigned long
-xen_get_itc(void)
-{
-	unsigned long res;
-	unsigned long itc_offset;
-	unsigned long itc_last;
-	unsigned long ret_itc_last;
-
-	itc_offset = XEN_MAPPEDREGS->itc_offset;
-	do {
-		itc_last = XEN_MAPPEDREGS->itc_last;
-		res = ia64_native_getreg(_IA64_REG_AR_ITC);
-		res += itc_offset;
-		if (itc_last >= res)
-			res = itc_last + 1;
-		ret_itc_last = cmpxchg(&XEN_MAPPEDREGS->itc_last,
-				       itc_last, res);
-	} while (unlikely(ret_itc_last != itc_last));
-	return res;
-
-#if 0
-	/* ia64_itc_udelay() calls ia64_get_itc() with interrupt enabled.
-	   Should it be paravirtualized instead? */
-	WARN_ON(!irqs_disabled());
-	itc_offset = XEN_MAPPEDREGS->itc_offset;
-	itc_last = XEN_MAPPEDREGS->itc_last;
-	res = ia64_native_getreg(_IA64_REG_AR_ITC);
-	res += itc_offset;
-	if (itc_last >= res)
-		res = itc_last + 1;
-	XEN_MAPPEDREGS->itc_last = res;
-	return res;
-#endif
-}
-
-static void xen_setreg(int regnum, unsigned long val)
-{
-	switch (regnum) {
-	case _IA64_REG_AR_KR0 ... _IA64_REG_AR_KR7:
-		xen_set_kr(regnum - _IA64_REG_AR_KR0, val);
-		break;
-	case _IA64_REG_AR_ITC:
-		xen_set_itc(val);
-		break;
-	case _IA64_REG_CR_TPR:
-		xen_set_tpr(val);
-		break;
-	case _IA64_REG_CR_ITM:
-		xen_set_itm_with_offset(val);
-		break;
-	case _IA64_REG_CR_EOI:
-		xen_eoi(val);
-		break;
-	default:
-		ia64_native_setreg_func(regnum, val);
-		break;
-	}
-}
-
-static unsigned long xen_getreg(int regnum)
-{
-	unsigned long res;
-
-	switch (regnum) {
-	case _IA64_REG_PSR:
-		res = xen_get_psr();
-		break;
-	case _IA64_REG_AR_ITC:
-		res = xen_get_itc();
-		break;
-	case _IA64_REG_CR_ITM:
-		res = xen_get_itm_with_offset();
-		break;
-	case _IA64_REG_CR_IVR:
-		res = xen_get_ivr();
-		break;
-	case _IA64_REG_CR_TPR:
-		res = xen_get_tpr();
-		break;
-	default:
-		res = ia64_native_getreg_func(regnum);
-		break;
-	}
-	return res;
-}
-
-/* turning on interrupts is a bit more complicated.. write to the
- * memory-mapped virtual psr.i bit first (to avoid race condition),
- * then if any interrupts were pending, we have to execute a hyperprivop
- * to ensure the pending interrupt gets delivered; else we're done! */
-static void
-xen_ssm_i(void)
-{
-	int old = xen_get_virtual_psr_i();
-	xen_set_virtual_psr_i(1);
-	barrier();
-	if (!old && xen_get_virtual_pend())
-		xen_hyper_ssm_i();
-}
-
-/* turning off interrupts can be paravirtualized simply by writing
- * to a memory-mapped virtual psr.i bit (implemented as a 16-bit bool) */
-static void
-xen_rsm_i(void)
-{
-	xen_set_virtual_psr_i(0);
-	barrier();
-}
-
-static unsigned long
-xen_get_psr_i(void)
-{
-	return xen_get_virtual_psr_i() ? IA64_PSR_I : 0;
-}
-
-static void
-xen_intrin_local_irq_restore(unsigned long mask)
-{
-	if (mask & IA64_PSR_I)
-		xen_ssm_i();
-	else
-		xen_rsm_i();
-}
-#else
-#define __DEFINE_FUNC(name, code)					\
-	extern const char xen_ ## name ## _direct_start[];		\
-	extern const char xen_ ## name ## _direct_end[];		\
-	asm (".align 32\n"						\
-	     ".proc xen_" #name "\n"					\
-	     "xen_" #name ":\n"						\
-	     "xen_" #name "_direct_start:\n"				\
-	     code							\
-	     "xen_" #name "_direct_end:\n"				\
-	     "br.cond.sptk.many b6\n"					\
-	     ".endp xen_" #name "\n")
-
-#define DEFINE_VOID_FUNC0(name, code)		\
-	extern void				\
-	xen_ ## name (void);			\
-	__DEFINE_FUNC(name, code)
-
-#define DEFINE_VOID_FUNC1(name, code)		\
-	extern void				\
-	xen_ ## name (unsigned long arg);	\
-	__DEFINE_FUNC(name, code)
-
-#define DEFINE_VOID_FUNC1_VOID(name, code)	\
-	extern void				\
-	xen_ ## name (void *arg);		\
-	__DEFINE_FUNC(name, code)
-
-#define DEFINE_VOID_FUNC2(name, code)		\
-	extern void				\
-	xen_ ## name (unsigned long arg0,	\
-		      unsigned long arg1);	\
-	__DEFINE_FUNC(name, code)
-
-#define DEFINE_FUNC0(name, code)		\
-	extern unsigned long			\
-	xen_ ## name (void);			\
-	__DEFINE_FUNC(name, code)
-
-#define DEFINE_FUNC1(name, type, code)		\
-	extern unsigned long			\
-	xen_ ## name (type arg);		\
-	__DEFINE_FUNC(name, code)
-
-#define XEN_PSR_I_ADDR_ADDR     (XSI_BASE + XSI_PSR_I_ADDR_OFS)
-
-/*
- * static void xen_set_itm_with_offset(unsigned long val)
- *        xen_set_itm(val - XEN_MAPPEDREGS->itc_offset);
- */
-/* 2 bundles */
-DEFINE_VOID_FUNC1(set_itm_with_offset,
-		  "mov r2 = " __stringify(XSI_BASE) " + "
-		  __stringify(XSI_ITC_OFFSET_OFS) "\n"
-		  ";;\n"
-		  "ld8 r3 = [r2]\n"
-		  ";;\n"
-		  "sub r8 = r8, r3\n"
-		  "break " __stringify(HYPERPRIVOP_SET_ITM) "\n");
-
-/*
- * static unsigned long xen_get_itm_with_offset(void)
- *    return ia64_native_getreg(_IA64_REG_CR_ITM) + XEN_MAPPEDREGS->itc_offset;
- */
-/* 2 bundles */
-DEFINE_FUNC0(get_itm_with_offset,
-	     "mov r2 = " __stringify(XSI_BASE) " + "
-	     __stringify(XSI_ITC_OFFSET_OFS) "\n"
-	     ";;\n"
-	     "ld8 r3 = [r2]\n"
-	     "mov r8 = cr.itm\n"
-	     ";;\n"
-	     "add r8 = r8, r2\n");
-
-/*
- * static void xen_set_itc(unsigned long val)
- *	unsigned long mitc;
- *
- *	WARN_ON(!irqs_disabled());
- *	mitc = ia64_native_getreg(_IA64_REG_AR_ITC);
- *	XEN_MAPPEDREGS->itc_offset = val - mitc;
- *	XEN_MAPPEDREGS->itc_last = val;
- */
-/* 2 bundles */
-DEFINE_VOID_FUNC1(set_itc,
-		  "mov r2 = " __stringify(XSI_BASE) " + "
-		  __stringify(XSI_ITC_LAST_OFS) "\n"
-		  "mov r3 = ar.itc\n"
-		  ";;\n"
-		  "sub r3 = r8, r3\n"
-		  "st8 [r2] = r8, "
-		  __stringify(XSI_ITC_LAST_OFS) " - "
-		  __stringify(XSI_ITC_OFFSET_OFS) "\n"
-		  ";;\n"
-		  "st8 [r2] = r3\n");
-
-/*
- * static unsigned long xen_get_itc(void)
- *	unsigned long res;
- *	unsigned long itc_offset;
- *	unsigned long itc_last;
- *	unsigned long ret_itc_last;
- *
- *	itc_offset = XEN_MAPPEDREGS->itc_offset;
- *	do {
- *		itc_last = XEN_MAPPEDREGS->itc_last;
- *		res = ia64_native_getreg(_IA64_REG_AR_ITC);
- *		res += itc_offset;
- *		if (itc_last >= res)
- *			res = itc_last + 1;
- *		ret_itc_last = cmpxchg(&XEN_MAPPEDREGS->itc_last,
- *				       itc_last, res);
- *	} while (unlikely(ret_itc_last != itc_last));
- *	return res;
- */
-/* 5 bundles */
-DEFINE_FUNC0(get_itc,
-	     "mov r2 = " __stringify(XSI_BASE) " + "
-	     __stringify(XSI_ITC_OFFSET_OFS) "\n"
-	     ";;\n"
-	     "ld8 r9 = [r2], " __stringify(XSI_ITC_LAST_OFS) " - "
-	     __stringify(XSI_ITC_OFFSET_OFS) "\n"
-					/* r9 = itc_offset */
-					/* r2 = XSI_ITC_OFFSET */
-	     "888:\n"
-	     "mov r8 = ar.itc\n"	/* res = ar.itc */
-	     ";;\n"
-	     "ld8 r3 = [r2]\n"		/* r3 = itc_last */
-	     "add r8 = r8, r9\n"	/* res = ar.itc + itc_offset */
-	     ";;\n"
-	     "cmp.gtu p6, p0 = r3, r8\n"
-	     ";;\n"
-	     "(p6) add r8 = 1, r3\n"	/* if (itc_last > res) itc_last + 1 */
-	     ";;\n"
-	     "mov ar.ccv = r8\n"
-	     ";;\n"
-	     "cmpxchg8.acq r10 = [r2], r8, ar.ccv\n"
-	     ";;\n"
-	     "cmp.ne p6, p0 = r10, r3\n"
-	     "(p6) hint @pause\n"
-	     "(p6) br.cond.spnt 888b\n");
-
-DEFINE_VOID_FUNC1_VOID(fc,
-		       "break " __stringify(HYPERPRIVOP_FC) "\n");
-
-/*
- * psr_i_addr_addr = XEN_PSR_I_ADDR_ADDR
- * masked_addr = *psr_i_addr_addr
- * pending_intr_addr = masked_addr - 1
- * if (val & IA64_PSR_I) {
- *   masked = *masked_addr
- *   *masked_addr = 0:xen_set_virtual_psr_i(1)
- *   compiler barrier
- *   if (masked) {
- *      uint8_t pending = *pending_intr_addr;
- *      if (pending)
- *              XEN_HYPER_SSM_I
- *   }
- * } else {
- *   *masked_addr = 1:xen_set_virtual_psr_i(0)
- * }
- */
-/* 6 bundles */
-DEFINE_VOID_FUNC1(intrin_local_irq_restore,
-		  /* r8 = input value: 0 or IA64_PSR_I
-		   * p6 =  (flags & IA64_PSR_I)
-		   *    = if clause
-		   * p7 = !(flags & IA64_PSR_I)
-		   *    = else clause
-		   */
-		  "cmp.ne p6, p7 = r8, r0\n"
-		  "mov r9 = " __stringify(XEN_PSR_I_ADDR_ADDR) "\n"
-		  ";;\n"
-		  /* r9 = XEN_PSR_I_ADDR */
-		  "ld8 r9 = [r9]\n"
-		  ";;\n"
-
-		  /* r10 = masked previous value */
-		  "(p6)	ld1.acq r10 = [r9]\n"
-		  ";;\n"
-
-		  /* p8 = !masked interrupt masked previously? */
-		  "(p6)	cmp.ne.unc p8, p0 = r10, r0\n"
-
-		  /* p7 = else clause */
-		  "(p7)	mov r11 = 1\n"
-		  ";;\n"
-		  /* masked = 1 */
-		  "(p7)	st1.rel [r9] = r11\n"
-
-		  /* p6 = if clause */
-		  /* masked = 0
-		   * r9 = masked_addr - 1
-		   *    = pending_intr_addr
-		   */
-		  "(p8)	st1.rel [r9] = r0, -1\n"
-		  ";;\n"
-		  /* r8 = pending_intr */
-		  "(p8)	ld1.acq r11 = [r9]\n"
-		  ";;\n"
-		  /* p9 = interrupt pending? */
-		  "(p8)	cmp.ne.unc p9, p10 = r11, r0\n"
-		  ";;\n"
-		  "(p10) mf\n"
-		  /* issue hypercall to trigger interrupt */
-		  "(p9)	break " __stringify(HYPERPRIVOP_SSM_I) "\n");
-
-DEFINE_VOID_FUNC2(ptcga,
-		  "break " __stringify(HYPERPRIVOP_PTC_GA) "\n");
-DEFINE_VOID_FUNC2(set_rr,
-		  "break " __stringify(HYPERPRIVOP_SET_RR) "\n");
-
-/*
- * tmp = XEN_MAPPEDREGS->interrupt_mask_addr = XEN_PSR_I_ADDR_ADDR;
- * tmp = *tmp
- * tmp = *tmp;
- * psr_i = tmp? 0: IA64_PSR_I;
- */
-/* 4 bundles */
-DEFINE_FUNC0(get_psr_i,
-	     "mov r9 = " __stringify(XEN_PSR_I_ADDR_ADDR) "\n"
-	     ";;\n"
-	     "ld8 r9 = [r9]\n"			/* r9 = XEN_PSR_I_ADDR */
-	     "mov r8 = 0\n"			/* psr_i = 0 */
-	     ";;\n"
-	     "ld1.acq r9 = [r9]\n"		/* r9 = XEN_PSR_I */
-	     ";;\n"
-	     "cmp.eq.unc p6, p0 = r9, r0\n"	/* p6 = (XEN_PSR_I != 0) */
-	     ";;\n"
-	     "(p6) mov r8 = " __stringify(1 << IA64_PSR_I_BIT) "\n");
-
-DEFINE_FUNC1(thash, unsigned long,
-	     "break " __stringify(HYPERPRIVOP_THASH) "\n");
-DEFINE_FUNC1(get_cpuid, int,
-	     "break " __stringify(HYPERPRIVOP_GET_CPUID) "\n");
-DEFINE_FUNC1(get_pmd, int,
-	     "break " __stringify(HYPERPRIVOP_GET_PMD) "\n");
-DEFINE_FUNC1(get_rr, unsigned long,
-	     "break " __stringify(HYPERPRIVOP_GET_RR) "\n");
-
-/*
- * void xen_privop_ssm_i(void)
- *
- * int masked = !xen_get_virtual_psr_i();
- *	// masked = *(*XEN_MAPPEDREGS->interrupt_mask_addr)
- * xen_set_virtual_psr_i(1)
- *	// *(*XEN_MAPPEDREGS->interrupt_mask_addr) = 0
- * // compiler barrier
- * if (masked) {
- *	uint8_t* pend_int_addr =
- *		(uint8_t*)(*XEN_MAPPEDREGS->interrupt_mask_addr) - 1;
- *	uint8_t pending = *pend_int_addr;
- *	if (pending)
- *		XEN_HYPER_SSM_I
- * }
- */
-/* 4 bundles */
-DEFINE_VOID_FUNC0(ssm_i,
-		  "mov r8 = " __stringify(XEN_PSR_I_ADDR_ADDR) "\n"
-		  ";;\n"
-		  "ld8 r8 = [r8]\n"		/* r8 = XEN_PSR_I_ADDR */
-		  ";;\n"
-		  "ld1.acq r9 = [r8]\n"		/* r9 = XEN_PSR_I */
-		  ";;\n"
-		  "st1.rel [r8] = r0, -1\n"	/* psr_i = 0. enable interrupt
-						 * r8 = XEN_PSR_I_ADDR - 1
-						 *    = pend_int_addr
-						 */
-		  "cmp.eq.unc p0, p6 = r9, r0\n"/* p6 = !XEN_PSR_I
-						 * previously interrupt
-						 * masked?
-						 */
-		  ";;\n"
-		  "(p6) ld1.acq r8 = [r8]\n"	/* r8 = xen_pend_int */
-		  ";;\n"
-		  "(p6) cmp.eq.unc p6, p7 = r8, r0\n"	/*interrupt pending?*/
-		  ";;\n"
-		  /* issue hypercall to get interrupt */
-		  "(p7) break " __stringify(HYPERPRIVOP_SSM_I) "\n"
-		  ";;\n");
-
-/*
- * psr_i_addr_addr = XEN_MAPPEDREGS->interrupt_mask_addr
- *		   = XEN_PSR_I_ADDR_ADDR;
- * psr_i_addr = *psr_i_addr_addr;
- * *psr_i_addr = 1;
- */
-/* 2 bundles */
-DEFINE_VOID_FUNC0(rsm_i,
-		  "mov r8 = " __stringify(XEN_PSR_I_ADDR_ADDR) "\n"
-						/* r8 = XEN_PSR_I_ADDR */
-		  "mov r9 = 1\n"
-		  ";;\n"
-		  "ld8 r8 = [r8]\n"		/* r8 = XEN_PSR_I */
-		  ";;\n"
-		  "st1.rel [r8] = r9\n");	/* XEN_PSR_I = 1 */
-
-extern void
-xen_set_rr0_to_rr4(unsigned long val0, unsigned long val1,
-		   unsigned long val2, unsigned long val3,
-		   unsigned long val4);
-__DEFINE_FUNC(set_rr0_to_rr4,
-	      "break " __stringify(HYPERPRIVOP_SET_RR0_TO_RR4) "\n");
-
-
-extern unsigned long xen_getreg(int regnum);
-#define __DEFINE_GET_REG(id, privop)					\
-	"mov r2 = " __stringify(_IA64_REG_ ## id) "\n"			\
-	";;\n"								\
-	"cmp.eq p6, p0 = r2, r8\n"					\
-	";;\n"								\
-	"(p6) break " __stringify(HYPERPRIVOP_GET_ ## privop) "\n"	\
-	"(p6) br.cond.sptk.many b6\n"					\
-	";;\n"
-
-__DEFINE_FUNC(getreg,
-	      __DEFINE_GET_REG(PSR, PSR)
-
-	      /* get_itc */
-	      "mov r2 = " __stringify(_IA64_REG_AR_ITC) "\n"
-	      ";;\n"
-	      "cmp.eq p6, p0 = r2, r8\n"
-	      ";;\n"
-	      "(p6) br.cond.spnt xen_get_itc\n"
-	      ";;\n"
-
-	      /* get itm */
-	      "mov r2 = " __stringify(_IA64_REG_CR_ITM) "\n"
-	      ";;\n"
-	      "cmp.eq p6, p0 = r2, r8\n"
-	      ";;\n"
-	      "(p6) br.cond.spnt xen_get_itm_with_offset\n"
-	      ";;\n"
-
-	      __DEFINE_GET_REG(CR_IVR, IVR)
-	      __DEFINE_GET_REG(CR_TPR, TPR)
-
-	      /* fall back */
-	      "movl r2 = ia64_native_getreg_func\n"
-	      ";;\n"
-	      "mov b7 = r2\n"
-	      ";;\n"
-	      "br.cond.sptk.many b7\n");
-
-extern void xen_setreg(int regnum, unsigned long val);
-#define __DEFINE_SET_REG(id, privop)					\
-	"mov r2 = " __stringify(_IA64_REG_ ## id) "\n"			\
-	";;\n"								\
-	"cmp.eq p6, p0 = r2, r9\n"					\
-	";;\n"								\
-	"(p6) break " __stringify(HYPERPRIVOP_ ## privop) "\n"		\
-	"(p6) br.cond.sptk.many b6\n"					\
-	";;\n"
-
-__DEFINE_FUNC(setreg,
-	      /* kr0 .. kr 7*/
-	      /*
-	       * if (_IA64_REG_AR_KR0 <= regnum &&
-	       *     regnum <= _IA64_REG_AR_KR7) {
-	       *     register __index asm ("r8") = regnum - _IA64_REG_AR_KR0
-	       *     register __val asm ("r9") = val
-	       *    "break HYPERPRIVOP_SET_KR"
-	       * }
-	       */
-	      "mov r17 = r9\n"
-	      "mov r2 = " __stringify(_IA64_REG_AR_KR0) "\n"
-	      ";;\n"
-	      "cmp.ge p6, p0 = r9, r2\n"
-	      "sub r17 = r17, r2\n"
-	      ";;\n"
-	      "(p6) cmp.ge.unc p7, p0 = "
-	      __stringify(_IA64_REG_AR_KR7) " - " __stringify(_IA64_REG_AR_KR0)
-	      ", r17\n"
-	      ";;\n"
-	      "(p7) mov r9 = r8\n"
-	      ";;\n"
-	      "(p7) mov r8 = r17\n"
-	      "(p7) break " __stringify(HYPERPRIVOP_SET_KR) "\n"
-
-	      /* set itm */
-	      "mov r2 = " __stringify(_IA64_REG_CR_ITM) "\n"
-	      ";;\n"
-	      "cmp.eq p6, p0 = r2, r8\n"
-	      ";;\n"
-	      "(p6) br.cond.spnt xen_set_itm_with_offset\n"
-
-	      /* set itc */
-	      "mov r2 = " __stringify(_IA64_REG_AR_ITC) "\n"
-	      ";;\n"
-	      "cmp.eq p6, p0 = r2, r8\n"
-	      ";;\n"
-	      "(p6) br.cond.spnt xen_set_itc\n"
-
-	      __DEFINE_SET_REG(CR_TPR, SET_TPR)
-	      __DEFINE_SET_REG(CR_EOI, EOI)
-
-	      /* fall back */
-	      "movl r2 = ia64_native_setreg_func\n"
-	      ";;\n"
-	      "mov b7 = r2\n"
-	      ";;\n"
-	      "br.cond.sptk.many b7\n");
-#endif
-
-static const struct pv_cpu_ops xen_cpu_ops __initconst = {
-	.fc		= xen_fc,
-	.thash		= xen_thash,
-	.get_cpuid	= xen_get_cpuid,
-	.get_pmd	= xen_get_pmd,
-	.getreg		= xen_getreg,
-	.setreg		= xen_setreg,
-	.ptcga		= xen_ptcga,
-	.get_rr		= xen_get_rr,
-	.set_rr		= xen_set_rr,
-	.set_rr0_to_rr4	= xen_set_rr0_to_rr4,
-	.ssm_i		= xen_ssm_i,
-	.rsm_i		= xen_rsm_i,
-	.get_psr_i	= xen_get_psr_i,
-	.intrin_local_irq_restore
-			= xen_intrin_local_irq_restore,
-};
-
-/******************************************************************************
- * replacement of hand written assembly codes.
- */
-
-extern char xen_switch_to;
-extern char xen_leave_syscall;
-extern char xen_work_processed_syscall;
-extern char xen_leave_kernel;
-
-const struct pv_cpu_asm_switch xen_cpu_asm_switch = {
-	.switch_to		= (unsigned long)&xen_switch_to,
-	.leave_syscall		= (unsigned long)&xen_leave_syscall,
-	.work_processed_syscall	= (unsigned long)&xen_work_processed_syscall,
-	.leave_kernel		= (unsigned long)&xen_leave_kernel,
-};
-
-/***************************************************************************
- * pv_iosapic_ops
- * iosapic read/write hooks.
- */
-static void
-xen_pcat_compat_init(void)
-{
-	/* nothing */
-}
-
-static struct irq_chip*
-xen_iosapic_get_irq_chip(unsigned long trigger)
-{
-	return NULL;
-}
-
-static unsigned int
-xen_iosapic_read(char __iomem *iosapic, unsigned int reg)
-{
-	struct physdev_apic apic_op;
-	int ret;
-
-	apic_op.apic_physbase = (unsigned long)iosapic -
-					__IA64_UNCACHED_OFFSET;
-	apic_op.reg = reg;
-	ret = HYPERVISOR_physdev_op(PHYSDEVOP_apic_read, &apic_op);
-	if (ret)
-		return ret;
-	return apic_op.value;
-}
-
-static void
-xen_iosapic_write(char __iomem *iosapic, unsigned int reg, u32 val)
-{
-	struct physdev_apic apic_op;
-
-	apic_op.apic_physbase = (unsigned long)iosapic -
-					__IA64_UNCACHED_OFFSET;
-	apic_op.reg = reg;
-	apic_op.value = val;
-	HYPERVISOR_physdev_op(PHYSDEVOP_apic_write, &apic_op);
-}
-
-static struct pv_iosapic_ops xen_iosapic_ops __initdata = {
-	.pcat_compat_init = xen_pcat_compat_init,
-	.__get_irq_chip = xen_iosapic_get_irq_chip,
-
-	.__read = xen_iosapic_read,
-	.__write = xen_iosapic_write,
-};
-
-/***************************************************************************
- * pv_ops initialization
- */
-
-void __init
-xen_setup_pv_ops(void)
-{
-	xen_info_init();
-	pv_info = xen_info;
-	pv_init_ops = xen_init_ops;
-	pv_fsys_data = xen_fsys_data;
-	pv_patchdata = xen_patchdata;
-	pv_cpu_ops = xen_cpu_ops;
-	pv_iosapic_ops = xen_iosapic_ops;
-	pv_irq_ops = xen_irq_ops;
-	pv_time_ops = xen_time_ops;
-
-	paravirt_cpu_asm_init(&xen_cpu_asm_switch);
-}
-
-#ifdef ASM_SUPPORTED
-/***************************************************************************
- * binary pacthing
- * pv_init_ops.patch_bundle
- */
-
-#define DEFINE_FUNC_GETREG(name, privop)				\
-	DEFINE_FUNC0(get_ ## name,					\
-		     "break "__stringify(HYPERPRIVOP_GET_ ## privop) "\n")
-
-DEFINE_FUNC_GETREG(psr, PSR);
-DEFINE_FUNC_GETREG(eflag, EFLAG);
-DEFINE_FUNC_GETREG(ivr, IVR);
-DEFINE_FUNC_GETREG(tpr, TPR);
-
-#define DEFINE_FUNC_SET_KR(n)						\
-	DEFINE_VOID_FUNC0(set_kr ## n,					\
-			  ";;\n"					\
-			  "mov r9 = r8\n"				\
-			  "mov r8 = " #n "\n"				\
-			  "break " __stringify(HYPERPRIVOP_SET_KR) "\n")
-
-DEFINE_FUNC_SET_KR(0);
-DEFINE_FUNC_SET_KR(1);
-DEFINE_FUNC_SET_KR(2);
-DEFINE_FUNC_SET_KR(3);
-DEFINE_FUNC_SET_KR(4);
-DEFINE_FUNC_SET_KR(5);
-DEFINE_FUNC_SET_KR(6);
-DEFINE_FUNC_SET_KR(7);
-
-#define __DEFINE_FUNC_SETREG(name, privop)				\
-	DEFINE_VOID_FUNC0(name,						\
-			  "break "__stringify(HYPERPRIVOP_ ## privop) "\n")
-
-#define DEFINE_FUNC_SETREG(name, privop)			\
-	__DEFINE_FUNC_SETREG(set_ ## name, SET_ ## privop)
-
-DEFINE_FUNC_SETREG(eflag, EFLAG);
-DEFINE_FUNC_SETREG(tpr, TPR);
-__DEFINE_FUNC_SETREG(eoi, EOI);
-
-extern const char xen_check_events[];
-extern const char __xen_intrin_local_irq_restore_direct_start[];
-extern const char __xen_intrin_local_irq_restore_direct_end[];
-extern const unsigned long __xen_intrin_local_irq_restore_direct_reloc;
-
-asm (
-	".align 32\n"
-	".proc xen_check_events\n"
-	"xen_check_events:\n"
-	/* masked = 0
-	 * r9 = masked_addr - 1
-	 *    = pending_intr_addr
-	 */
-	"st1.rel [r9] = r0, -1\n"
-	";;\n"
-	/* r8 = pending_intr */
-	"ld1.acq r11 = [r9]\n"
-	";;\n"
-	/* p9 = interrupt pending? */
-	"cmp.ne p9, p10 = r11, r0\n"
-	";;\n"
-	"(p10) mf\n"
-	/* issue hypercall to trigger interrupt */
-	"(p9) break " __stringify(HYPERPRIVOP_SSM_I) "\n"
-	"br.cond.sptk.many b6\n"
-	".endp xen_check_events\n"
-	"\n"
-	".align 32\n"
-	".proc __xen_intrin_local_irq_restore_direct\n"
-	"__xen_intrin_local_irq_restore_direct:\n"
-	"__xen_intrin_local_irq_restore_direct_start:\n"
-	"1:\n"
-	"{\n"
-	"cmp.ne p6, p7 = r8, r0\n"
-	"mov r17 = ip\n" /* get ip to calc return address */
-	"mov r9 = "__stringify(XEN_PSR_I_ADDR_ADDR) "\n"
-	";;\n"
-	"}\n"
-	"{\n"
-	/* r9 = XEN_PSR_I_ADDR */
-	"ld8 r9 = [r9]\n"
-	";;\n"
-	/* r10 = masked previous value */
-	"(p6) ld1.acq r10 = [r9]\n"
-	"adds r17 =  1f - 1b, r17\n" /* calculate return address */
-	";;\n"
-	"}\n"
-	"{\n"
-	/* p8 = !masked interrupt masked previously? */
-	"(p6) cmp.ne.unc p8, p0 = r10, r0\n"
-	"\n"
-	/* p7 = else clause */
-	"(p7) mov r11 = 1\n"
-	";;\n"
-	"(p8) mov b6 = r17\n" /* set return address */
-	"}\n"
-	"{\n"
-	/* masked = 1 */
-	"(p7) st1.rel [r9] = r11\n"
-	"\n"
-	"[99:]\n"
-	"(p8) brl.cond.dptk.few xen_check_events\n"
-	"}\n"
-	/* pv calling stub is 5 bundles. fill nop to adjust return address */
-	"{\n"
-	"nop 0\n"
-	"nop 0\n"
-	"nop 0\n"
-	"}\n"
-	"1:\n"
-	"__xen_intrin_local_irq_restore_direct_end:\n"
-	".endp __xen_intrin_local_irq_restore_direct\n"
-	"\n"
-	".align 8\n"
-	"__xen_intrin_local_irq_restore_direct_reloc:\n"
-	"data8 99b\n"
-);
-
-static struct paravirt_patch_bundle_elem xen_patch_bundle_elems[]
-__initdata_or_module =
-{
-#define XEN_PATCH_BUNDLE_ELEM(name, type)		\
-	{						\
-		(void*)xen_ ## name ## _direct_start,	\
-		(void*)xen_ ## name ## _direct_end,	\
-		PARAVIRT_PATCH_TYPE_ ## type,		\
-	}
-
-	XEN_PATCH_BUNDLE_ELEM(fc, FC),
-	XEN_PATCH_BUNDLE_ELEM(thash, THASH),
-	XEN_PATCH_BUNDLE_ELEM(get_cpuid, GET_CPUID),
-	XEN_PATCH_BUNDLE_ELEM(get_pmd, GET_PMD),
-	XEN_PATCH_BUNDLE_ELEM(ptcga, PTCGA),
-	XEN_PATCH_BUNDLE_ELEM(get_rr, GET_RR),
-	XEN_PATCH_BUNDLE_ELEM(set_rr, SET_RR),
-	XEN_PATCH_BUNDLE_ELEM(set_rr0_to_rr4, SET_RR0_TO_RR4),
-	XEN_PATCH_BUNDLE_ELEM(ssm_i, SSM_I),
-	XEN_PATCH_BUNDLE_ELEM(rsm_i, RSM_I),
-	XEN_PATCH_BUNDLE_ELEM(get_psr_i, GET_PSR_I),
-	{
-		(void*)__xen_intrin_local_irq_restore_direct_start,
-		(void*)__xen_intrin_local_irq_restore_direct_end,
-		PARAVIRT_PATCH_TYPE_INTRIN_LOCAL_IRQ_RESTORE,
-	},
-
-#define XEN_PATCH_BUNDLE_ELEM_GETREG(name, reg)			\
-	{							\
-		xen_get_ ## name ## _direct_start,		\
-		xen_get_ ## name ## _direct_end,		\
-		PARAVIRT_PATCH_TYPE_GETREG + _IA64_REG_ ## reg, \
-	}
-
-	XEN_PATCH_BUNDLE_ELEM_GETREG(psr, PSR),
-	XEN_PATCH_BUNDLE_ELEM_GETREG(eflag, AR_EFLAG),
-
-	XEN_PATCH_BUNDLE_ELEM_GETREG(ivr, CR_IVR),
-	XEN_PATCH_BUNDLE_ELEM_GETREG(tpr, CR_TPR),
-
-	XEN_PATCH_BUNDLE_ELEM_GETREG(itc, AR_ITC),
-	XEN_PATCH_BUNDLE_ELEM_GETREG(itm_with_offset, CR_ITM),
-
-
-#define __XEN_PATCH_BUNDLE_ELEM_SETREG(name, reg)		\
-	{							\
-		xen_ ## name ## _direct_start,			\
-		xen_ ## name ## _direct_end,			\
-		PARAVIRT_PATCH_TYPE_SETREG + _IA64_REG_ ## reg, \
-	}
-
-#define XEN_PATCH_BUNDLE_ELEM_SETREG(name, reg)			\
-	__XEN_PATCH_BUNDLE_ELEM_SETREG(set_ ## name, reg)
-
-	XEN_PATCH_BUNDLE_ELEM_SETREG(kr0, AR_KR0),
-	XEN_PATCH_BUNDLE_ELEM_SETREG(kr1, AR_KR1),
-	XEN_PATCH_BUNDLE_ELEM_SETREG(kr2, AR_KR2),
-	XEN_PATCH_BUNDLE_ELEM_SETREG(kr3, AR_KR3),
-	XEN_PATCH_BUNDLE_ELEM_SETREG(kr4, AR_KR4),
-	XEN_PATCH_BUNDLE_ELEM_SETREG(kr5, AR_KR5),
-	XEN_PATCH_BUNDLE_ELEM_SETREG(kr6, AR_KR6),
-	XEN_PATCH_BUNDLE_ELEM_SETREG(kr7, AR_KR7),
-
-	XEN_PATCH_BUNDLE_ELEM_SETREG(eflag, AR_EFLAG),
-	XEN_PATCH_BUNDLE_ELEM_SETREG(tpr, CR_TPR),
-	__XEN_PATCH_BUNDLE_ELEM_SETREG(eoi, CR_EOI),
-
-	XEN_PATCH_BUNDLE_ELEM_SETREG(itc, AR_ITC),
-	XEN_PATCH_BUNDLE_ELEM_SETREG(itm_with_offset, CR_ITM),
-};
-
-static unsigned long __init_or_module
-xen_patch_bundle(void *sbundle, void *ebundle, unsigned long type)
-{
-	const unsigned long nelems = sizeof(xen_patch_bundle_elems) /
-		sizeof(xen_patch_bundle_elems[0]);
-	unsigned long used;
-	const struct paravirt_patch_bundle_elem *found;
-
-	used = __paravirt_patch_apply_bundle(sbundle, ebundle, type,
-					     xen_patch_bundle_elems, nelems,
-					     &found);
-
-	if (found == NULL)
-		/* fallback */
-		return ia64_native_patch_bundle(sbundle, ebundle, type);
-	if (used == 0)
-		return used;
-
-	/* relocation */
-	switch (type) {
-	case PARAVIRT_PATCH_TYPE_INTRIN_LOCAL_IRQ_RESTORE: {
-		unsigned long reloc =
-			__xen_intrin_local_irq_restore_direct_reloc;
-		unsigned long reloc_offset = reloc - (unsigned long)
-			__xen_intrin_local_irq_restore_direct_start;
-		unsigned long tag = (unsigned long)sbundle + reloc_offset;
-		paravirt_patch_reloc_brl(tag, xen_check_events);
-		break;
-	}
-	default:
-		/* nothing */
-		break;
-	}
-	return used;
-}
-#endif /* ASM_SUPPOTED */
-
-const struct paravirt_patch_branch_target xen_branch_target[]
-__initconst = {
-#define PARAVIRT_BR_TARGET(name, type)			\
-	{						\
-		&xen_ ## name,				\
-		PARAVIRT_PATCH_TYPE_BR_ ## type,	\
-	}
-	PARAVIRT_BR_TARGET(switch_to, SWITCH_TO),
-	PARAVIRT_BR_TARGET(leave_syscall, LEAVE_SYSCALL),
-	PARAVIRT_BR_TARGET(work_processed_syscall, WORK_PROCESSED_SYSCALL),
-	PARAVIRT_BR_TARGET(leave_kernel, LEAVE_KERNEL),
-};
-
-static void __init
-xen_patch_branch(unsigned long tag, unsigned long type)
-{
-	__paravirt_patch_apply_branch(tag, type, xen_branch_target,
-					ARRAY_SIZE(xen_branch_target));
-}
diff --git a/arch/ia64/xen/xencomm.c b/arch/ia64/xen/xencomm.c
deleted file mode 100644
index 73d903c..0000000
--- a/arch/ia64/xen/xencomm.c
+++ /dev/null
@@ -1,106 +0,0 @@
-/*
- * Copyright (C) 2006 Hollis Blanchard <hollisb@us.ibm.com>, IBM Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-
-#include <linux/mm.h>
-#include <linux/err.h>
-
-static unsigned long kernel_virtual_offset;
-static int is_xencomm_initialized;
-
-/* for xen early printk. It uses console io hypercall which uses xencomm.
- * However early printk may use it before xencomm initialization.
- */
-int
-xencomm_is_initialized(void)
-{
-	return is_xencomm_initialized;
-}
-
-void
-xencomm_initialize(void)
-{
-	kernel_virtual_offset = KERNEL_START - ia64_tpa(KERNEL_START);
-	is_xencomm_initialized = 1;
-}
-
-/* Translate virtual address to physical address.  */
-unsigned long
-xencomm_vtop(unsigned long vaddr)
-{
-	struct page *page;
-	struct vm_area_struct *vma;
-
-	if (vaddr == 0)
-		return 0UL;
-
-	if (REGION_NUMBER(vaddr) == 5) {
-		pgd_t *pgd;
-		pud_t *pud;
-		pmd_t *pmd;
-		pte_t *ptep;
-
-		/* On ia64, TASK_SIZE refers to current.  It is not initialized
-		   during boot.
-		   Furthermore the kernel is relocatable and __pa() doesn't
-		   work on  addresses.  */
-		if (vaddr >= KERNEL_START
-		    && vaddr < (KERNEL_START + KERNEL_TR_PAGE_SIZE))
-			return vaddr - kernel_virtual_offset;
-
-		/* In kernel area -- virtually mapped.  */
-		pgd = pgd_offset_k(vaddr);
-		if (pgd_none(*pgd) || pgd_bad(*pgd))
-			return ~0UL;
-
-		pud = pud_offset(pgd, vaddr);
-		if (pud_none(*pud) || pud_bad(*pud))
-			return ~0UL;
-
-		pmd = pmd_offset(pud, vaddr);
-		if (pmd_none(*pmd) || pmd_bad(*pmd))
-			return ~0UL;
-
-		ptep = pte_offset_kernel(pmd, vaddr);
-		if (!ptep)
-			return ~0UL;
-
-		return (pte_val(*ptep) & _PFN_MASK) | (vaddr & ~PAGE_MASK);
-	}
-
-	if (vaddr > TASK_SIZE) {
-		/* percpu variables */
-		if (REGION_NUMBER(vaddr) == 7 &&
-		    REGION_OFFSET(vaddr) >= (1ULL << IA64_MAX_PHYS_BITS))
-			ia64_tpa(vaddr);
-
-		/* kernel address */
-		return __pa(vaddr);
-	}
-
-	/* XXX double-check (lack of) locking */
-	vma = find_extend_vma(current->mm, vaddr);
-	if (!vma)
-		return ~0UL;
-
-	/* We assume the page is modified.  */
-	page = follow_page(vma, vaddr, FOLL_WRITE | FOLL_TOUCH);
-	if (IS_ERR_OR_NULL(page))
-		return ~0UL;
-
-	return (page_to_pfn(page) << PAGE_SHIFT) | (vaddr & ~PAGE_MASK);
-}
diff --git a/arch/ia64/xen/xenivt.S b/arch/ia64/xen/xenivt.S
deleted file mode 100644
index 3e71d50..0000000
--- a/arch/ia64/xen/xenivt.S
+++ /dev/null
@@ -1,52 +0,0 @@
-/*
- * arch/ia64/xen/ivt.S
- *
- * Copyright (C) 2005 Hewlett-Packard Co
- *	Dan Magenheimer <dan.magenheimer@hp.com>
- *
- * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
- *                    VA Linux Systems Japan K.K.
- *                    pv_ops.
- */
-
-#include <asm/asmmacro.h>
-#include <asm/kregs.h>
-#include <asm/pgtable.h>
-
-#include "../kernel/minstate.h"
-
-	.section .text,"ax"
-GLOBAL_ENTRY(xen_event_callback)
-	mov r31=pr		// prepare to save predicates
-	;;
-	SAVE_MIN_WITH_COVER	// uses r31; defines r2 and r3
-	;;
-	movl r3=XSI_PSR_IC
-	mov r14=1
-	;;
-	st4 [r3]=r14
-	;;
-	adds r3=8,r2		// set up second base pointer for SAVE_REST
-	srlz.i			// ensure everybody knows psr.ic is back on
-	;;
-	SAVE_REST
-	;;
-1:
-	alloc r14=ar.pfs,0,0,1,0 // must be first in an insn group
-	add out0=16,sp		// pass pointer to pt_regs as first arg
-	;;
-	br.call.sptk.many b0=xen_evtchn_do_upcall
-	;;
-	movl r20=XSI_PSR_I_ADDR
-	;;
-	ld8 r20=[r20]
-	;;
-	adds r20=-1,r20		// vcpu_info->evtchn_upcall_pending
-	;;
-	ld1 r20=[r20]
-	;;
-	cmp.ne p6,p0=r20,r0	// if there are pending events,
-	(p6) br.spnt.few 1b	// call evtchn_do_upcall again.
-	br.sptk.many xen_leave_kernel	// we know ia64_leave_kernel is
-					// paravirtualized as xen_leave_kernel
-END(xen_event_callback)
diff --git a/arch/ia64/xen/xensetup.S b/arch/ia64/xen/xensetup.S
deleted file mode 100644
index e29519e..0000000
--- a/arch/ia64/xen/xensetup.S
+++ /dev/null
@@ -1,80 +0,0 @@
-/*
- * Support routines for Xen
- *
- * Copyright (C) 2005 Dan Magenheimer <dan.magenheimer@hp.com>
- */
-
-#include <asm/processor.h>
-#include <asm/asmmacro.h>
-#include <asm/pgtable.h>
-#include <asm/paravirt.h>
-#include <asm/xen/privop.h>
-#include <linux/elfnote.h>
-#include <linux/init.h>
-#include <xen/interface/elfnote.h>
-
-	.section .data..read_mostly
-	.align 8
-	.global xen_domain_type
-xen_domain_type:
-	data4 XEN_NATIVE_ASM
-	.previous
-
-	__INIT
-ENTRY(startup_xen)
-	// Calculate load offset.
-	// The constant, LOAD_OFFSET, can't be used because the boot
-	// loader doesn't always load to the LMA specified by the vmlinux.lds.
-	mov r9=ip	// must be the first instruction to make sure
-			// that r9 = the physical address of startup_xen.
-			// Usually r9 = startup_xen - LOAD_OFFSET
-	movl r8=startup_xen
-	;;
-	sub r9=r9,r8	// Usually r9 = -LOAD_OFFSET.
-
-	mov r10=PARAVIRT_HYPERVISOR_TYPE_XEN
-	movl r11=_start
-	;;
-	add r11=r11,r9
-	movl r8=hypervisor_type
-	;;
-	add r8=r8,r9
-	mov b0=r11
-	;;
-	st8 [r8]=r10
-	br.cond.sptk.many b0
-	;;
-END(startup_xen)
-
-	ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS,	.asciz "linux")
-	ELFNOTE(Xen, XEN_ELFNOTE_GUEST_VERSION,	.asciz "2.6")
-	ELFNOTE(Xen, XEN_ELFNOTE_XEN_VERSION,	.asciz "xen-3.0")
-	ELFNOTE(Xen, XEN_ELFNOTE_ENTRY,		data8.ua startup_xen - LOAD_OFFSET)
-
-#define isBP	p3	// are we the Bootstrap Processor?
-
-GLOBAL_ENTRY(xen_setup_hook)
-	mov r8=XEN_PV_DOMAIN_ASM
-(isBP)	movl r9=xen_domain_type;;
-(isBP)	st4 [r9]=r8
-	movl r10=xen_ivt;;
-
-	mov cr.iva=r10
-
-	/* Set xsi base.  */
-#define FW_HYPERCALL_SET_SHARED_INFO_VA			0x600
-(isBP)	mov r2=FW_HYPERCALL_SET_SHARED_INFO_VA
-(isBP)	movl r28=XSI_BASE;;
-(isBP)	break 0x1000;;
-
-	/* setup pv_ops */
-(isBP)	mov r4=rp
-	;;
-(isBP)	br.call.sptk.many rp=xen_setup_pv_ops
-	;;
-(isBP)	mov rp=r4
-	;;
-
-	br.ret.sptk.many rp
-	;;
-END(xen_setup_hook)
diff --git a/include/xen/interface/callback.h b/include/xen/interface/callback.h
index 8c5fa0e..dc3193f 100644
--- a/include/xen/interface/callback.h
+++ b/include/xen/interface/callback.h
@@ -36,7 +36,7 @@
  * @extra_args == Operation-specific extra arguments (NULL if none).
  */
 
-/* ia64, x86: Callback for event delivery. */
+/* x86: Callback for event delivery. */
 #define CALLBACKTYPE_event                 0
 
 /* x86: Failsafe callback when guest state cannot be restored by Xen. */
diff --git a/include/xen/interface/io/protocols.h b/include/xen/interface/io/protocols.h
index 056744b..545a14b 100644
--- a/include/xen/interface/io/protocols.h
+++ b/include/xen/interface/io/protocols.h
@@ -3,7 +3,6 @@
 
 #define XEN_IO_PROTO_ABI_X86_32     "x86_32-abi"
 #define XEN_IO_PROTO_ABI_X86_64     "x86_64-abi"
-#define XEN_IO_PROTO_ABI_IA64       "ia64-abi"
 #define XEN_IO_PROTO_ABI_POWERPC64  "powerpc64-abi"
 #define XEN_IO_PROTO_ABI_ARM        "arm-abi"
 
@@ -11,8 +10,6 @@
 # define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_X86_32
 #elif defined(__x86_64__)
 # define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_X86_64
-#elif defined(__ia64__)
-# define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_IA64
 #elif defined(__powerpc64__)
 # define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_POWERPC64
 #elif defined(__arm__) || defined(__aarch64__)
-- 
cgit v0.10.2


From 247f325aaddb8b6117959f70c26ba735360c4160 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime.ripard@free-electrons.com>
Date: Fri, 25 Oct 2013 12:16:10 +0100
Subject: clockevent: sun4i: Fill the irq field in the clockevent structure

The clock event structure irq field was not filled previously to the
interrupt we're using.

This was resulting in the timer not being used at all when using a
configuration with SMP enabled on a system with several CPUs, and with
the cpumask set to the cpu_possible_mask.

Signed-off-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>

diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c
index 2fb4695..a7f492e 100644
--- a/drivers/clocksource/sun4i_timer.c
+++ b/drivers/clocksource/sun4i_timer.c
@@ -188,6 +188,7 @@ static void __init sun4i_timer_init(struct device_node *node)
 	writel(val | TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_EN_REG);
 
 	sun4i_clockevent.cpumask = cpumask_of(0);
+	sun4i_clockevent.irq = irq;
 
 	clockevents_config_and_register(&sun4i_clockevent, rate,
 					TIMER_SYNC_TICKS, 0xffffffff);
-- 
cgit v0.10.2


From 2c28f32ca4c98b41ad95f62fa27f59f3117931d4 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime.ripard@free-electrons.com>
Date: Fri, 25 Oct 2013 12:16:11 +0100
Subject: clocksource: sun4i: Change CPU mask to cpu_possible_mask

The interrupt for the timer is a shared processor interrupt, so any CPU
found in the system can handle it. Switch to our cpumask to
cpu_possible_mask instead of cpumask_of(0).

Signed-off-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>

diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c
index a7f492e..6a76b4e 100644
--- a/drivers/clocksource/sun4i_timer.c
+++ b/drivers/clocksource/sun4i_timer.c
@@ -187,7 +187,7 @@ static void __init sun4i_timer_init(struct device_node *node)
 	val = readl(timer_base + TIMER_IRQ_EN_REG);
 	writel(val | TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_EN_REG);
 
-	sun4i_clockevent.cpumask = cpumask_of(0);
+	sun4i_clockevent.cpumask = cpu_possible_mask;
 	sun4i_clockevent.irq = irq;
 
 	clockevents_config_and_register(&sun4i_clockevent, rate,
-- 
cgit v0.10.2


From 5df9affb50a09e0cb571c4fa3e2d577db85c7475 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime.ripard@free-electrons.com>
Date: Thu, 7 Nov 2013 12:01:48 +0100
Subject: clocksource: sun4i: Increase a bit the clock event and sources rating
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We want to keep this driver as the default provider of the clock events
and source, yet some other driver might fit in the "desired" category of
ratings. Hence, we need to increase a bit the rating so that we can have
more flexibility in the ratings we choose.

Signed-off-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Tested-by: Emilio López <emilio@elopez.com.ar>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c
index 6a76b4e..d7a1a1a 100644
--- a/drivers/clocksource/sun4i_timer.c
+++ b/drivers/clocksource/sun4i_timer.c
@@ -114,7 +114,7 @@ static int sun4i_clkevt_next_event(unsigned long evt,
 
 static struct clock_event_device sun4i_clockevent = {
 	.name = "sun4i_tick",
-	.rating = 300,
+	.rating = 350,
 	.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
 	.set_mode = sun4i_clkevt_mode,
 	.set_next_event = sun4i_clkevt_next_event,
@@ -172,7 +172,7 @@ static void __init sun4i_timer_init(struct device_node *node)
 
 	setup_sched_clock(sun4i_timer_sched_read, 32, rate);
 	clocksource_mmio_init(timer_base + TIMER_CNTVAL_REG(1), node->name,
-			      rate, 300, 32, clocksource_mmio_readl_down);
+			      rate, 350, 32, clocksource_mmio_readl_down);
 
 	ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
 
-- 
cgit v0.10.2


From 67905540e8b8eaf51e621cfd2ef15641d6d5b9a7 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime.ripard@free-electrons.com>
Date: Thu, 7 Nov 2013 12:01:48 +0100
Subject: clocksource: Add Allwinner SoCs HS timers driver
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Most of the Allwinner SoCs (at this time, all but the A10) also have a
High Speed timers that are not using the 24MHz oscillator as a source
but rather the AHB clock running much faster.

The IP is slightly different between the A10s/A13 and the one used in
the A20/A31, since the latter have 4 timers available, while the former
have only 2 of them.

[dlezcano] : Fixed conflict with b788beda "Order Kconfig options
		alphabetically"

Signed-off-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Tested-by: Emilio López <emilio@elopez.com.ar>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/Documentation/devicetree/bindings/timer/allwinner,sun5i-a13-hstimer.txt b/Documentation/devicetree/bindings/timer/allwinner,sun5i-a13-hstimer.txt
new file mode 100644
index 0000000..7c26154
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/allwinner,sun5i-a13-hstimer.txt
@@ -0,0 +1,22 @@
+Allwinner SoCs High Speed Timer Controller
+
+Required properties:
+
+- compatible :	should be "allwinner,sun5i-a13-hstimer" or
+		"allwinner,sun7i-a20-hstimer"
+- reg : Specifies base physical address and size of the registers.
+- interrupts :	The interrupts of these timers (2 for the sun5i IP, 4 for the sun7i
+		one)
+- clocks: phandle to the source clock (usually the AHB clock)
+
+Example:
+
+timer@01c60000 {
+	compatible = "allwinner,sun7i-a20-hstimer";
+	reg = <0x01c60000 0x1000>;
+	interrupts = <0 51 1>,
+		     <0 52 1>,
+		     <0 53 1>,
+		     <0 54 1>;
+	clocks = <&ahb1_gates 19>;
+};
diff --git a/arch/arm/mach-sunxi/Kconfig b/arch/arm/mach-sunxi/Kconfig
index c9e72c8..bce0d42 100644
--- a/arch/arm/mach-sunxi/Kconfig
+++ b/arch/arm/mach-sunxi/Kconfig
@@ -12,3 +12,4 @@ config ARCH_SUNXI
 	select PINCTRL_SUNXI
 	select SPARSE_IRQ
 	select SUN4I_TIMER
+	select SUN5I_HSTIMER
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index bdb953e..884eeff 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -37,6 +37,10 @@ config SUN4I_TIMER
 	select CLKSRC_MMIO
 	bool
 
+config SUN5I_HSTIMER
+	select CLKSRC_MMIO
+	bool
+
 config VT8500_TIMER
 	bool
 
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index 33621ef..358358d 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -22,6 +22,7 @@ obj-$(CONFIG_ARCH_MOXART)	+= moxart_timer.o
 obj-$(CONFIG_ARCH_MXS)		+= mxs_timer.o
 obj-$(CONFIG_ARCH_PRIMA2)	+= timer-prima2.o
 obj-$(CONFIG_SUN4I_TIMER)	+= sun4i_timer.o
+obj-$(CONFIG_SUN5I_HSTIMER)	+= timer-sun5i.o
 obj-$(CONFIG_ARCH_TEGRA)	+= tegra20_timer.o
 obj-$(CONFIG_VT8500_TIMER)	+= vt8500_timer.o
 obj-$(CONFIG_ARCH_NSPIRE)	+= zevio-timer.o
diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c
new file mode 100644
index 0000000..bddc522
--- /dev/null
+++ b/drivers/clocksource/timer-sun5i.c
@@ -0,0 +1,192 @@
+/*
+ * Allwinner SoCs hstimer driver.
+ *
+ * Copyright (C) 2013 Maxime Ripard
+ *
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqreturn.h>
+#include <linux/sched_clock.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#define TIMER_IRQ_EN_REG		0x00
+#define TIMER_IRQ_EN(val)			BIT(val)
+#define TIMER_IRQ_ST_REG		0x04
+#define TIMER_CTL_REG(val)		(0x20 * (val) + 0x10)
+#define TIMER_CTL_ENABLE			BIT(0)
+#define TIMER_CTL_RELOAD			BIT(1)
+#define TIMER_CTL_CLK_PRES(val)			(((val) & 0x7) << 4)
+#define TIMER_CTL_ONESHOT			BIT(7)
+#define TIMER_INTVAL_LO_REG(val)	(0x20 * (val) + 0x14)
+#define TIMER_INTVAL_HI_REG(val)	(0x20 * (val) + 0x18)
+#define TIMER_CNTVAL_LO_REG(val)	(0x20 * (val) + 0x1c)
+#define TIMER_CNTVAL_HI_REG(val)	(0x20 * (val) + 0x20)
+
+#define TIMER_SYNC_TICKS	3
+
+static void __iomem *timer_base;
+static u32 ticks_per_jiffy;
+
+/*
+ * When we disable a timer, we need to wait at least for 2 cycles of
+ * the timer source clock. We will use for that the clocksource timer
+ * that is already setup and runs at the same frequency than the other
+ * timers, and we never will be disabled.
+ */
+static void sun5i_clkevt_sync(void)
+{
+	u32 old = readl(timer_base + TIMER_CNTVAL_LO_REG(1));
+
+	while ((old - readl(timer_base + TIMER_CNTVAL_LO_REG(1))) < TIMER_SYNC_TICKS)
+		cpu_relax();
+}
+
+static void sun5i_clkevt_time_stop(u8 timer)
+{
+	u32 val = readl(timer_base + TIMER_CTL_REG(timer));
+	writel(val & ~TIMER_CTL_ENABLE, timer_base + TIMER_CTL_REG(timer));
+
+	sun5i_clkevt_sync();
+}
+
+static void sun5i_clkevt_time_setup(u8 timer, u32 delay)
+{
+	writel(delay, timer_base + TIMER_INTVAL_LO_REG(timer));
+}
+
+static void sun5i_clkevt_time_start(u8 timer, bool periodic)
+{
+	u32 val = readl(timer_base + TIMER_CTL_REG(timer));
+
+	if (periodic)
+		val &= ~TIMER_CTL_ONESHOT;
+	else
+		val |= TIMER_CTL_ONESHOT;
+
+	writel(val | TIMER_CTL_ENABLE | TIMER_CTL_RELOAD,
+	       timer_base + TIMER_CTL_REG(timer));
+}
+
+static void sun5i_clkevt_mode(enum clock_event_mode mode,
+			      struct clock_event_device *clk)
+{
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		sun5i_clkevt_time_stop(0);
+		sun5i_clkevt_time_setup(0, ticks_per_jiffy);
+		sun5i_clkevt_time_start(0, true);
+		break;
+	case CLOCK_EVT_MODE_ONESHOT:
+		sun5i_clkevt_time_stop(0);
+		sun5i_clkevt_time_start(0, false);
+		break;
+	case CLOCK_EVT_MODE_UNUSED:
+	case CLOCK_EVT_MODE_SHUTDOWN:
+	default:
+		sun5i_clkevt_time_stop(0);
+		break;
+	}
+}
+
+static int sun5i_clkevt_next_event(unsigned long evt,
+				   struct clock_event_device *unused)
+{
+	sun5i_clkevt_time_stop(0);
+	sun5i_clkevt_time_setup(0, evt - TIMER_SYNC_TICKS);
+	sun5i_clkevt_time_start(0, false);
+
+	return 0;
+}
+
+static struct clock_event_device sun5i_clockevent = {
+	.name = "sun5i_tick",
+	.rating = 340,
+	.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
+	.set_mode = sun5i_clkevt_mode,
+	.set_next_event = sun5i_clkevt_next_event,
+};
+
+
+static irqreturn_t sun5i_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = (struct clock_event_device *)dev_id;
+
+	writel(0x1, timer_base + TIMER_IRQ_ST_REG);
+	evt->event_handler(evt);
+
+	return IRQ_HANDLED;
+}
+
+static struct irqaction sun5i_timer_irq = {
+	.name = "sun5i_timer0",
+	.flags = IRQF_TIMER | IRQF_IRQPOLL,
+	.handler = sun5i_timer_interrupt,
+	.dev_id = &sun5i_clockevent,
+};
+
+static u32 sun5i_timer_sched_read(void)
+{
+	return ~readl(timer_base + TIMER_CNTVAL_LO_REG(1));
+}
+
+static void __init sun5i_timer_init(struct device_node *node)
+{
+	unsigned long rate;
+	struct clk *clk;
+	int ret, irq;
+	u32 val;
+
+	timer_base = of_iomap(node, 0);
+	if (!timer_base)
+		panic("Can't map registers");
+
+	irq = irq_of_parse_and_map(node, 0);
+	if (irq <= 0)
+		panic("Can't parse IRQ");
+
+	clk = of_clk_get(node, 0);
+	if (IS_ERR(clk))
+		panic("Can't get timer clock");
+	clk_prepare_enable(clk);
+	rate = clk_get_rate(clk);
+
+	writel(~0, timer_base + TIMER_INTVAL_LO_REG(1));
+	writel(TIMER_CTL_ENABLE | TIMER_CTL_RELOAD,
+	       timer_base + TIMER_CTL_REG(1));
+
+	setup_sched_clock(sun5i_timer_sched_read, 32, rate);
+	clocksource_mmio_init(timer_base + TIMER_CNTVAL_LO_REG(1), node->name,
+			      rate, 340, 32, clocksource_mmio_readl_down);
+
+	ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
+
+	ret = setup_irq(irq, &sun5i_timer_irq);
+	if (ret)
+		pr_warn("failed to setup irq %d\n", irq);
+
+	/* Enable timer0 interrupt */
+	val = readl(timer_base + TIMER_IRQ_EN_REG);
+	writel(val | TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_EN_REG);
+
+	sun5i_clockevent.cpumask = cpu_possible_mask;
+	sun5i_clockevent.irq = irq;
+
+	clockevents_config_and_register(&sun5i_clockevent, rate,
+					TIMER_SYNC_TICKS, 0xffffffff);
+}
+CLOCKSOURCE_OF_DECLARE(sun5i_a13, "allwinner,sun5i-a13-hstimer",
+		       sun5i_timer_init);
+CLOCKSOURCE_OF_DECLARE(sun7i_a20, "allwinner,sun7i-a20-hstimer",
+		       sun5i_timer_init);
-- 
cgit v0.10.2


From f2b5002889cd2ca25d1dfe522755ade701f49044 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime.ripard@free-electrons.com>
Date: Thu, 7 Nov 2013 12:01:48 +0100
Subject: ARM: sun5i: a10s: Add support for the High Speed Timers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Allwinner A10s has support for two high speed timers. Now that we
have a driver to support it, we can enable them in the device tree.

Signed-off-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Tested-by: Emilio López <emilio@elopez.com.ar>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi
index 5247674..e674c94 100644
--- a/arch/arm/boot/dts/sun5i-a10s.dtsi
+++ b/arch/arm/boot/dts/sun5i-a10s.dtsi
@@ -332,5 +332,12 @@
 			clock-frequency = <100000>;
 			status = "disabled";
 		};
+
+		timer@01c60000 {
+			compatible = "allwinner,sun5i-a13-hstimer";
+			reg = <0x01c60000 0x1000>;
+			interrupts = <82>, <83>;
+			clocks = <&ahb_gates 28>;
+		};
 	};
 };
-- 
cgit v0.10.2


From 4411902a13e6b64873dc21abafeb57db335efcf1 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime.ripard@free-electrons.com>
Date: Thu, 7 Nov 2013 12:01:48 +0100
Subject: ARM: sun5i: a13: Add support for the High Speed Timers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Allwinner A13 has support for two high speed timers. Now that we
have a driver to support it, we can enable them in the device tree.

Signed-off-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Tested-by: Emilio López <emilio@elopez.com.ar>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi
index ce8ef2a..1ccd75d 100644
--- a/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/arch/arm/boot/dts/sun5i-a13.dtsi
@@ -273,5 +273,12 @@
 			clock-frequency = <100000>;
 			status = "disabled";
 		};
+
+		timer@01c60000 {
+			compatible = "allwinner,sun5i-a13-hstimer";
+			reg = <0x01c60000 0x1000>;
+			interrupts = <82>, <83>;
+			clocks = <&ahb_gates 28>;
+		};
 	};
 };
-- 
cgit v0.10.2


From 31f8ad387e4306ec1fb2a01c5cd0d648b5e9bff5 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime.ripard@free-electrons.com>
Date: Thu, 7 Nov 2013 12:01:48 +0100
Subject: ARM: sun7i: a20: Add support for the High Speed Timers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Allwinner A20 has support for four high speed timers. Apart for the
number of timers (4 vs 2), it's basically the same logic than the high
speed timers found in the sun5i chips.

Now that we have a driver to support it, we can enable them in the
device tree.

[dlezcano] : Fixed conflict with 428abbb8 "Enable the I2C controllers"

Signed-off-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Tested-by: Emilio López <emilio@elopez.com.ar>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index e46cfed..ee6cec7 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -395,6 +395,16 @@
 			status = "disabled";
 		};
 
+		hstimer@01c60000 {
+			compatible = "allwinner,sun7i-a20-hstimer";
+			reg = <0x01c60000 0x1000>;
+			interrupts = <0 81 1>,
+				     <0 82 1>,
+				     <0 83 1>,
+				     <0 84 1>;
+			clocks = <&ahb_gates 28>;
+		};
+
 		gic: interrupt-controller@01c81000 {
 			compatible = "arm,cortex-a7-gic", "arm,cortex-a15-gic";
 			reg = <0x01c81000 0x1000>,
-- 
cgit v0.10.2


From af066fce5fa6b615588732cad6909c450a9eb616 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@codeaurora.org>
Date: Wed, 20 Nov 2013 00:47:32 +0100
Subject: clocksource: arm_global_timer: Switch to sched_clock_register()

The 32 bit sched_clock interface now supports 64 bits. Upgrade to
the 64 bit function to allow us to remove the 32 bit registration
interface. While we're here increase the number of bits that
sched_clock can handle to 64 to make full use of the counter.

Cc: Stuart Menefy <stuart.menefy@st.com>
Cc: Srinivas Kandagatla <srinivas.kandagatla@st.com>
Acked-by: Srinivas Kandagatla <srinivas.kandagatla@st.com>
Acked-by: Stuart Menefy <stuart.menefy@st.com>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c
index c639b1a..0fc31d0 100644
--- a/drivers/clocksource/arm_global_timer.c
+++ b/drivers/clocksource/arm_global_timer.c
@@ -202,7 +202,7 @@ static struct clocksource gt_clocksource = {
 };
 
 #ifdef CONFIG_CLKSRC_ARM_GLOBAL_TIMER_SCHED_CLOCK
-static u32 notrace gt_sched_clock_read(void)
+static u64 notrace gt_sched_clock_read(void)
 {
 	return gt_counter_read();
 }
@@ -217,7 +217,7 @@ static void __init gt_clocksource_init(void)
 	writel(GT_CONTROL_TIMER_ENABLE, gt_base + GT_CONTROL);
 
 #ifdef CONFIG_CLKSRC_ARM_GLOBAL_TIMER_SCHED_CLOCK
-	setup_sched_clock(gt_sched_clock_read, 32, gt_clk_rate);
+	sched_clock_register(gt_sched_clock_read, 64, gt_clk_rate);
 #endif
 	clocksource_register_hz(&gt_clocksource, gt_clk_rate);
 }
-- 
cgit v0.10.2


From dfded00902d7437963870accbcf4b39114e85f59 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@codeaurora.org>
Date: Wed, 20 Nov 2013 00:47:32 +0100
Subject: clocksource: cadence_ttc_timer: Switch to sched_clock_register()

The 32 bit sched_clock interface now supports 64 bits. Upgrade to
the 64 bit function to allow us to remove the 32 bit registration
interface.

Cc: Soren Brinkmann <soren.brinkmann@xilinx.com>
Cc: Michal Simek <monstr@monstr.eu>
Tested-by: Soren Brinkmann <soren.brinkmann@xilinx.com>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/drivers/clocksource/cadence_ttc_timer.c b/drivers/clocksource/cadence_ttc_timer.c
index b2bb3a4b..b865b4e 100644
--- a/drivers/clocksource/cadence_ttc_timer.c
+++ b/drivers/clocksource/cadence_ttc_timer.c
@@ -158,7 +158,7 @@ static cycle_t __ttc_clocksource_read(struct clocksource *cs)
 				TTC_COUNT_VAL_OFFSET);
 }
 
-static u32 notrace ttc_sched_clock_read(void)
+static u64 notrace ttc_sched_clock_read(void)
 {
 	return __raw_readl(ttc_sched_clock_val_reg);
 }
@@ -306,7 +306,7 @@ static void __init ttc_setup_clocksource(struct clk *clk, void __iomem *base)
 	}
 
 	ttc_sched_clock_val_reg = base + TTC_COUNT_VAL_OFFSET;
-	setup_sched_clock(ttc_sched_clock_read, 16,
+	sched_clock_register(ttc_sched_clock_read, 16,
 			clk_get_rate(ttccs->ttc.clk) / PRESCALE);
 }
 
-- 
cgit v0.10.2


From 662e7230ee16951e6858c01e72db87c5dc46150e Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@codeaurora.org>
Date: Wed, 20 Nov 2013 00:47:32 +0100
Subject: clocksource: sun4i: Switch to sched_clock_register()

The 32 bit sched_clock interface now supports 64 bits. Upgrade to
the 64 bit function to allow us to remove the 32 bit registration
interface. While we're here, mark the sched_clock function as
notrace to prevent ftrace recursion crashes.

Cc: Maxime Ripard <maxime.ripard@free-electrons.com>
Acked-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c
index d7a1a1a..1911874 100644
--- a/drivers/clocksource/sun4i_timer.c
+++ b/drivers/clocksource/sun4i_timer.c
@@ -138,7 +138,7 @@ static struct irqaction sun4i_timer_irq = {
 	.dev_id = &sun4i_clockevent,
 };
 
-static u32 sun4i_timer_sched_read(void)
+static u64 notrace sun4i_timer_sched_read(void)
 {
 	return ~readl(timer_base + TIMER_CNTVAL_REG(1));
 }
@@ -170,7 +170,7 @@ static void __init sun4i_timer_init(struct device_node *node)
 	       TIMER_CTL_CLK_SRC(TIMER_CTL_CLK_SRC_OSC24M),
 	       timer_base + TIMER_CTL_REG(1));
 
-	setup_sched_clock(sun4i_timer_sched_read, 32, rate);
+	sched_clock_register(sun4i_timer_sched_read, 32, rate);
 	clocksource_mmio_init(timer_base + TIMER_CNTVAL_REG(1), node->name,
 			      rate, 350, 32, clocksource_mmio_readl_down);
 
-- 
cgit v0.10.2


From 2e8bac532f8bcd3834853e0a22b130b9fd59270d Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@codeaurora.org>
Date: Wed, 20 Nov 2013 00:47:32 +0100
Subject: clocksource: orion: Switch to sched_clock_register()

The 32 bit sched_clock interface now supports 64 bits. Upgrade to
the 64 bit function to allow us to remove the 32 bit registration
interface.

Cc: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Tested-by: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/drivers/clocksource/time-orion.c b/drivers/clocksource/time-orion.c
index 9c7f018..2006622 100644
--- a/drivers/clocksource/time-orion.c
+++ b/drivers/clocksource/time-orion.c
@@ -53,7 +53,7 @@ EXPORT_SYMBOL(orion_timer_ctrl_clrset);
 /*
  * Free-running clocksource handling.
  */
-static u32 notrace orion_read_sched_clock(void)
+static u64 notrace orion_read_sched_clock(void)
 {
 	return ~readl(timer_base + TIMER0_VAL);
 }
@@ -135,7 +135,7 @@ static void __init orion_timer_init(struct device_node *np)
 	clocksource_mmio_init(timer_base + TIMER0_VAL, "orion_clocksource",
 			      clk_get_rate(clk), 300, 32,
 			      clocksource_mmio_readl_down);
-	setup_sched_clock(orion_read_sched_clock, 32, clk_get_rate(clk));
+	sched_clock_register(orion_read_sched_clock, 32, clk_get_rate(clk));
 
 	/* setup timer1 as clockevent timer */
 	if (setup_irq(irq, &orion_clkevt_irq))
-- 
cgit v0.10.2


From fdca679d87bb4ac0fdc882dbf3deb47a1f58b813 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 20 Nov 2013 09:58:56 +0100
Subject: clocksource: clksrc-of: Warn if no clock sources are found

Many platforms rely on clocksource_of_init() being implicitly
called for registering clock sources and will get zero warnings
if no working clock source is available. Let's print a critical
error message if no clock source is found.

Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/drivers/clocksource/clksrc-of.c b/drivers/clocksource/clksrc-of.c
index 35639cf4..a30b42c 100644
--- a/drivers/clocksource/clksrc-of.c
+++ b/drivers/clocksource/clksrc-of.c
@@ -28,6 +28,7 @@ void __init clocksource_of_init(void)
 	struct device_node *np;
 	const struct of_device_id *match;
 	clocksource_of_init_fn init_func;
+	unsigned clocksources = 0;
 
 	for_each_matching_node_and_match(np, __clksrc_of_table, &match) {
 		if (!of_device_is_available(np))
@@ -36,5 +37,8 @@ void __init clocksource_of_init(void)
 		init_func = match->data;
 		init_func(np);
 		of_node_put(np);
+		clocksources++;
 	}
+	if (!clocksources)
+		pr_crit("%s: no matching clocksources found\n", __func__);
 }
-- 
cgit v0.10.2


From 08cb8e460956489fcfbfab5a7d33e62acd190b9a Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel.garcia@free-electrons.com>
Date: Mon, 2 Dec 2013 11:39:56 +0100
Subject: clocksource: armada-370-xp: Enable timer divider only when needed

The current code sets the timer divider bits always. However, when
the 25 MHz timer is enabled, this is not needed and has no effect.
As this causes some confusion, rework the code so the divider is
set only when needed, i.e. when the 25 MHz timer is not in use.

Acked-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
Signed-off-by: Ezequiel Garcia <ezequiel.garcia@free-electrons.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/drivers/clocksource/time-armada-370-xp.c b/drivers/clocksource/time-armada-370-xp.c
index d8e47e5..0450f6b 100644
--- a/drivers/clocksource/time-armada-370-xp.c
+++ b/drivers/clocksource/time-armada-370-xp.c
@@ -76,6 +76,7 @@
 static void __iomem *timer_base, *local_base;
 static unsigned int timer_clk;
 static bool timer25Mhz = true;
+static u32 enable_mask;
 
 /*
  * Number of timer ticks per jiffy.
@@ -121,8 +122,7 @@ armada_370_xp_clkevt_next_event(unsigned long delta,
 	/*
 	 * Enable the timer.
 	 */
-	local_timer_ctrl_clrset(TIMER0_RELOAD_EN,
-				TIMER0_EN | TIMER0_DIV(TIMER_DIVIDER_SHIFT));
+	local_timer_ctrl_clrset(TIMER0_RELOAD_EN, enable_mask);
 	return 0;
 }
 
@@ -141,9 +141,7 @@ armada_370_xp_clkevt_mode(enum clock_event_mode mode,
 		/*
 		 * Enable timer.
 		 */
-		local_timer_ctrl_clrset(0, TIMER0_RELOAD_EN |
-					   TIMER0_EN |
-					   TIMER0_DIV(TIMER_DIVIDER_SHIFT));
+		local_timer_ctrl_clrset(0, TIMER0_RELOAD_EN | enable_mask);
 	} else {
 		/*
 		 * Disable timer.
@@ -240,10 +238,13 @@ static void __init armada_370_xp_timer_common_init(struct device_node *np)
 	WARN_ON(!timer_base);
 	local_base = of_iomap(np, 1);
 
-	if (timer25Mhz)
+	if (timer25Mhz) {
 		set = TIMER0_25MHZ;		
-	else
+		enable_mask = TIMER0_EN;
+	} else {
 		clr = TIMER0_25MHZ;
+		enable_mask = TIMER0_EN | TIMER0_DIV(TIMER_DIVIDER_SHIFT);
+	}
 	timer_ctrl_clrset(clr, set);
 	local_timer_ctrl_clrset(clr, set);
 
@@ -267,8 +268,7 @@ static void __init armada_370_xp_timer_common_init(struct device_node *np)
 	writel(0xffffffff, timer_base + TIMER0_VAL_OFF);
 	writel(0xffffffff, timer_base + TIMER0_RELOAD_OFF);
 
-	timer_ctrl_clrset(0, TIMER0_EN | TIMER0_RELOAD_EN |
-			     TIMER0_DIV(TIMER_DIVIDER_SHIFT));
+	timer_ctrl_clrset(0, TIMER0_RELOAD_EN | enable_mask);
 
 	clocksource_mmio_init(timer_base + TIMER0_VAL_OFF,
 			      "armada_370_xp_clocksource",
-- 
cgit v0.10.2


From 5707f18c28f4df0f993d965aff1c168b69637d63 Mon Sep 17 00:00:00 2001
From: Jingoo Han <jg1.han@samsung.com>
Date: Tue, 3 Dec 2013 15:50:09 +0900
Subject: clocksource: sh_tmu: Remove unnecessary platform_set_drvdata()

The driver core clears the driver data to NULL after device_release
or on probe failure. Thus, it is not needed to manually clear the
device driver data to NULL.

Signed-off-by: Jingoo Han <jg1.han@samsung.com>
Acked-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/drivers/clocksource/sh_tmu.c b/drivers/clocksource/sh_tmu.c
index 78b8dae..54ab475 100644
--- a/drivers/clocksource/sh_tmu.c
+++ b/drivers/clocksource/sh_tmu.c
@@ -509,7 +509,6 @@ static int sh_tmu_probe(struct platform_device *pdev)
 	ret = sh_tmu_setup(p, pdev);
 	if (ret) {
 		kfree(p);
-		platform_set_drvdata(pdev, NULL);
 		pm_runtime_idle(&pdev->dev);
 		return ret;
 	}
-- 
cgit v0.10.2


From 87d4bb9fced08054afb83af2d85f5cf0ba0e21e4 Mon Sep 17 00:00:00 2001
From: Jingoo Han <jg1.han@samsung.com>
Date: Tue, 3 Dec 2013 15:51:06 +0900
Subject: clocksource: sh_mtu2: Remove unnecessary platform_set_drvdata()

The driver core clears the driver data to NULL after device_release
or on probe failure. Thus, it is not needed to manually clear the
device driver data to NULL.

Signed-off-by: Jingoo Han <jg1.han@samsung.com>
Acked-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/drivers/clocksource/sh_mtu2.c b/drivers/clocksource/sh_mtu2.c
index 4aac9ee..f02648e 100644
--- a/drivers/clocksource/sh_mtu2.c
+++ b/drivers/clocksource/sh_mtu2.c
@@ -346,7 +346,6 @@ static int sh_mtu2_probe(struct platform_device *pdev)
 	ret = sh_mtu2_setup(p, pdev);
 	if (ret) {
 		kfree(p);
-		platform_set_drvdata(pdev, NULL);
 		pm_runtime_idle(&pdev->dev);
 		return ret;
 	}
-- 
cgit v0.10.2


From 38c30a8421ce8b06492121deee422ba7ecfaeef2 Mon Sep 17 00:00:00 2001
From: Michael Opdenacker <michael.opdenacker@free-electrons.com>
Date: Mon, 9 Dec 2013 10:12:10 +0100
Subject: clocksource: misc drivers: Remove deprecated IRQF_DISABLED

This patch removes the use of the IRQF_DISABLED flag

It's a NOOP since 2.6.35 and it will be removed one day.

[dlezcano] : slightly changed the changelog

Signed-off-by: Michael Opdenacker <michael.opdenacker@free-electrons.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/drivers/clocksource/cadence_ttc_timer.c b/drivers/clocksource/cadence_ttc_timer.c
index b865b4e..8c7382b 100644
--- a/drivers/clocksource/cadence_ttc_timer.c
+++ b/drivers/clocksource/cadence_ttc_timer.c
@@ -388,8 +388,7 @@ static void __init ttc_setup_clockevent(struct clk *clk,
 	__raw_writel(0x1,  ttcce->ttc.base_addr + TTC_IER_OFFSET);
 
 	err = request_irq(irq, ttc_clock_event_interrupt,
-			  IRQF_DISABLED | IRQF_TIMER,
-			  ttcce->ce.name, ttcce);
+			  IRQF_TIMER, ttcce->ce.name, ttcce);
 	if (WARN_ON(err)) {
 		kfree(ttcce);
 		return;
diff --git a/drivers/clocksource/cs5535-clockevt.c b/drivers/clocksource/cs5535-clockevt.c
index ea21048..db21052 100644
--- a/drivers/clocksource/cs5535-clockevt.c
+++ b/drivers/clocksource/cs5535-clockevt.c
@@ -131,7 +131,7 @@ static irqreturn_t mfgpt_tick(int irq, void *dev_id)
 
 static struct irqaction mfgptirq  = {
 	.handler = mfgpt_tick,
-	.flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TIMER | IRQF_SHARED,
+	.flags = IRQF_NOBALANCING | IRQF_TIMER | IRQF_SHARED,
 	.name = DRV_NAME,
 };
 
diff --git a/drivers/clocksource/dw_apb_timer.c b/drivers/clocksource/dw_apb_timer.c
index e54ca10..f3656a6 100644
--- a/drivers/clocksource/dw_apb_timer.c
+++ b/drivers/clocksource/dw_apb_timer.c
@@ -243,8 +243,7 @@ dw_apb_clockevent_init(int cpu, const char *name, unsigned rating,
 	dw_ced->irqaction.dev_id	= &dw_ced->ced;
 	dw_ced->irqaction.irq		= irq;
 	dw_ced->irqaction.flags		= IRQF_TIMER | IRQF_IRQPOLL |
-					  IRQF_NOBALANCING |
-					  IRQF_DISABLED;
+					  IRQF_NOBALANCING;
 
 	dw_ced->eoi = apbt_eoi;
 	err = setup_irq(irq, &dw_ced->irqaction);
diff --git a/drivers/clocksource/nomadik-mtu.c b/drivers/clocksource/nomadik-mtu.c
index ed7b73b..152a3f3 100644
--- a/drivers/clocksource/nomadik-mtu.c
+++ b/drivers/clocksource/nomadik-mtu.c
@@ -187,7 +187,7 @@ static irqreturn_t nmdk_timer_interrupt(int irq, void *dev_id)
 
 static struct irqaction nmdk_timer_irq = {
 	.name		= "Nomadik Timer Tick",
-	.flags		= IRQF_DISABLED | IRQF_TIMER,
+	.flags		= IRQF_TIMER,
 	.handler	= nmdk_timer_interrupt,
 	.dev_id		= &nmdk_clkevt,
 };
diff --git a/drivers/clocksource/samsung_pwm_timer.c b/drivers/clocksource/samsung_pwm_timer.c
index 85082e8..5645cfc 100644
--- a/drivers/clocksource/samsung_pwm_timer.c
+++ b/drivers/clocksource/samsung_pwm_timer.c
@@ -264,7 +264,7 @@ static irqreturn_t samsung_clock_event_isr(int irq, void *dev_id)
 
 static struct irqaction samsung_clock_event_irq = {
 	.name		= "samsung_time_irq",
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
 	.handler	= samsung_clock_event_isr,
 	.dev_id		= &time_event_device,
 };
diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c
index 0965e98..c618633 100644
--- a/drivers/clocksource/sh_cmt.c
+++ b/drivers/clocksource/sh_cmt.c
@@ -726,8 +726,7 @@ static int sh_cmt_setup(struct sh_cmt_priv *p, struct platform_device *pdev)
 	p->irqaction.name = dev_name(&p->pdev->dev);
 	p->irqaction.handler = sh_cmt_interrupt;
 	p->irqaction.dev_id = p;
-	p->irqaction.flags = IRQF_DISABLED | IRQF_TIMER | \
-			     IRQF_IRQPOLL  | IRQF_NOBALANCING;
+	p->irqaction.flags = IRQF_TIMER | IRQF_IRQPOLL | IRQF_NOBALANCING;
 
 	/* get hold of clock */
 	p->clk = clk_get(&p->pdev->dev, "cmt_fck");
diff --git a/drivers/clocksource/sh_mtu2.c b/drivers/clocksource/sh_mtu2.c
index f02648e..b6a56b1 100644
--- a/drivers/clocksource/sh_mtu2.c
+++ b/drivers/clocksource/sh_mtu2.c
@@ -302,8 +302,7 @@ static int sh_mtu2_setup(struct sh_mtu2_priv *p, struct platform_device *pdev)
 	p->irqaction.handler = sh_mtu2_interrupt;
 	p->irqaction.dev_id = p;
 	p->irqaction.irq = irq;
-	p->irqaction.flags = IRQF_DISABLED | IRQF_TIMER | \
-			     IRQF_IRQPOLL  | IRQF_NOBALANCING;
+	p->irqaction.flags = IRQF_TIMER | IRQF_IRQPOLL | IRQF_NOBALANCING;
 
 	/* get hold of clock */
 	p->clk = clk_get(&p->pdev->dev, "mtu2_fck");
diff --git a/drivers/clocksource/sh_tmu.c b/drivers/clocksource/sh_tmu.c
index 54ab475..fc752f7 100644
--- a/drivers/clocksource/sh_tmu.c
+++ b/drivers/clocksource/sh_tmu.c
@@ -462,8 +462,7 @@ static int sh_tmu_setup(struct sh_tmu_priv *p, struct platform_device *pdev)
 	p->irqaction.handler = sh_tmu_interrupt;
 	p->irqaction.dev_id = p;
 	p->irqaction.irq = irq;
-	p->irqaction.flags = IRQF_DISABLED | IRQF_TIMER | \
-			     IRQF_IRQPOLL  | IRQF_NOBALANCING;
+	p->irqaction.flags = IRQF_TIMER | IRQF_IRQPOLL | IRQF_NOBALANCING;
 
 	/* get hold of clock */
 	p->clk = clk_get(&p->pdev->dev, "tmu_fck");
-- 
cgit v0.10.2


From 39304fad8f31b2114492e9a09fe0bd1ac7eb1834 Mon Sep 17 00:00:00 2001
From: Michael Opdenacker <michael.opdenacker@free-electrons.com>
Date: Mon, 9 Dec 2013 10:35:45 +0100
Subject: clocksource: tegra: Remove deprecated IRQF_DISABLED

This patch removes the use of the IRQF_DISABLED flag.

It's a NOOP since 2.6.35 and it will be removed one day.

[dlezcano] : slightly changed the changelog

Signed-off-by: Michael Opdenacker <michael.opdenacker@free-electrons.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/drivers/clocksource/tegra20_timer.c b/drivers/clocksource/tegra20_timer.c
index 6428492..d1869f0 100644
--- a/drivers/clocksource/tegra20_timer.c
+++ b/drivers/clocksource/tegra20_timer.c
@@ -149,7 +149,7 @@ static irqreturn_t tegra_timer_interrupt(int irq, void *dev_id)
 
 static struct irqaction tegra_timer_irq = {
 	.name		= "timer0",
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_TRIGGER_HIGH,
+	.flags		= IRQF_TIMER | IRQF_TRIGGER_HIGH,
 	.handler	= tegra_timer_interrupt,
 	.dev_id		= &tegra_clockevent,
 };
-- 
cgit v0.10.2


From 39039eb31c6e5252e25ec6336d92ddef938ccafa Mon Sep 17 00:00:00 2001
From: Michael Opdenacker <michael.opdenacker@free-electrons.com>
Date: Mon, 9 Dec 2013 10:38:50 +0100
Subject: clocksource: vt8500: Remove deprecated IRQF_DISABLED

This patch removes the use of the IRQF_DISABLED flag.

It's a NOOP since 2.6.35 and it will be removed one day.

[dlezcano] : slightly changed the changelog

Signed-off-by: Michael Opdenacker <michael.opdenacker@free-electrons.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/drivers/clocksource/vt8500_timer.c b/drivers/clocksource/vt8500_timer.c
index ad3c0e8..1098ed3 100644
--- a/drivers/clocksource/vt8500_timer.c
+++ b/drivers/clocksource/vt8500_timer.c
@@ -124,7 +124,7 @@ static irqreturn_t vt8500_timer_interrupt(int irq, void *dev_id)
 
 static struct irqaction irq = {
 	.name    = "vt8500_timer",
-	.flags   = IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.flags   = IRQF_TIMER | IRQF_IRQPOLL,
 	.handler = vt8500_timer_interrupt,
 	.dev_id  = &clockevent,
 };
-- 
cgit v0.10.2


From 6d19944bd2609a1d7d48149605aa9f62ca8bf640 Mon Sep 17 00:00:00 2001
From: Axel Lin <axel.lin@ingics.com>
Date: Mon, 25 Nov 2013 09:54:45 +0800
Subject: clocksource: bcm_kona_timer: Remove unused bcm_timer_ids

bcm_timer_ids is no longer used after converting to CLOCKSOURCE_OF_DECLARE.

Signed-off-by: Axel Lin <axel.lin@ingics.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/drivers/clocksource/bcm_kona_timer.c b/drivers/clocksource/bcm_kona_timer.c
index 0d7d8c3..5176e76 100644
--- a/drivers/clocksource/bcm_kona_timer.c
+++ b/drivers/clocksource/bcm_kona_timer.c
@@ -98,12 +98,6 @@ kona_timer_get_counter(void *timer_base, uint32_t *msw, uint32_t *lsw)
 	return;
 }
 
-static const struct of_device_id bcm_timer_ids[] __initconst = {
-	{.compatible = "brcm,kona-timer"},
-	{.compatible = "bcm,kona-timer"}, /* deprecated name */
-	{},
-};
-
 static void __init kona_timers_init(struct device_node *node)
 {
 	u32 freq;
-- 
cgit v0.10.2


From 6f041e99fc7ba00e7e65a431527f9235d6b16463 Mon Sep 17 00:00:00 2001
From: James Hogan <james.hogan@imgtec.com>
Date: Thu, 21 Nov 2013 13:44:14 +0000
Subject: of: Fix NULL dereference in unflatten_and_copy()

Check whether initial_boot_params is NULL before dereferencing it in
unflatten_and_copy_device_tree() for the case where no device tree is
available but the arch can still boot to a minimal usable system without
it. In this case also log a warning for when the kernel log buffer is
obtainable.

Signed-off-by: James Hogan <james.hogan@imgtec.com>
Cc: Rob Herring <rob.herring@calxeda.com>
Signed-off-by: Grant Likely <grant.likely@linaro.org>

diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 2fa024b..758b4f8 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -922,8 +922,16 @@ void __init unflatten_device_tree(void)
  */
 void __init unflatten_and_copy_device_tree(void)
 {
-	int size = __be32_to_cpu(initial_boot_params->totalsize);
-	void *dt = early_init_dt_alloc_memory_arch(size,
+	int size;
+	void *dt;
+
+	if (!initial_boot_params) {
+		pr_warn("No valid device tree found, continuing without\n");
+		return;
+	}
+
+	size = __be32_to_cpu(initial_boot_params->totalsize);
+	dt = early_init_dt_alloc_memory_arch(size,
 		__alignof__(struct boot_param_header));
 
 	if (dt) {
-- 
cgit v0.10.2


From c7f2e3cd6c1f4932ccc4135d050eae3f7c7aef63 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 25 Nov 2013 11:49:10 +0100
Subject: perf: Optimize ring-buffer write by depending on control dependencies

Remove a full barrier from the ring-buffer write path by relying on
a control dependency to order a LOAD -> STORE scenario.

Cc: "Paul E. McKenney" <paulmck@us.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-8alv40z6ikk57jzbaobnxrjl@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index e8b168a..146a579 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -61,19 +61,20 @@ again:
 	 *
 	 *   kernel				user
 	 *
-	 *   READ ->data_tail			READ ->data_head
-	 *   smp_mb()	(A)			smp_rmb()	(C)
-	 *   WRITE $data			READ $data
-	 *   smp_wmb()	(B)			smp_mb()	(D)
-	 *   STORE ->data_head			WRITE ->data_tail
+	 *   if (LOAD ->data_tail) {		LOAD ->data_head
+	 *			(A)		smp_rmb()	(C)
+	 *	STORE $data			LOAD $data
+	 *	smp_wmb()	(B)		smp_mb()	(D)
+	 *	STORE ->data_head		STORE ->data_tail
+	 *   }
 	 *
 	 * Where A pairs with D, and B pairs with C.
 	 *
-	 * I don't think A needs to be a full barrier because we won't in fact
-	 * write data until we see the store from userspace. So we simply don't
-	 * issue the data WRITE until we observe it. Be conservative for now.
+	 * In our case (A) is a control dependency that separates the load of
+	 * the ->data_tail and the stores of $data. In case ->data_tail
+	 * indicates there is no room in the buffer to store $data we do not.
 	 *
-	 * OTOH, D needs to be a full barrier since it separates the data READ
+	 * D needs to be a full barrier since it separates the data READ
 	 * from the tail WRITE.
 	 *
 	 * For B a WMB is sufficient since it separates two WRITEs, and for C
@@ -81,7 +82,7 @@ again:
 	 *
 	 * See perf_output_begin().
 	 */
-	smp_wmb();
+	smp_wmb(); /* B, matches C */
 	rb->user_page->data_head = head;
 
 	/*
@@ -144,17 +145,26 @@ int perf_output_begin(struct perf_output_handle *handle,
 		if (!rb->overwrite &&
 		    unlikely(CIRC_SPACE(head, tail, perf_data_size(rb)) < size))
 			goto fail;
+
+		/*
+		 * The above forms a control dependency barrier separating the
+		 * @tail load above from the data stores below. Since the @tail
+		 * load is required to compute the branch to fail below.
+		 *
+		 * A, matches D; the full memory barrier userspace SHOULD issue
+		 * after reading the data and before storing the new tail
+		 * position.
+		 *
+		 * See perf_output_put_handle().
+		 */
+
 		head += size;
 	} while (local_cmpxchg(&rb->head, offset, head) != offset);
 
 	/*
-	 * Separate the userpage->tail read from the data stores below.
-	 * Matches the MB userspace SHOULD issue after reading the data
-	 * and before storing the new tail position.
-	 *
-	 * See perf_output_put_handle().
+	 * We rely on the implied barrier() by local_cmpxchg() to ensure
+	 * none of the data stores below can be lifted up by the compiler.
 	 */
-	smp_mb();
 
 	if (unlikely(head - local_read(&rb->wakeup) > rb->watermark))
 		local_add(rb->watermark, &rb->wakeup);
-- 
cgit v0.10.2


From c700f013adb0ec57518a7fe0163e3117659ce249 Mon Sep 17 00:00:00 2001
From: "Chen, Gong" <gong.chen@linux.intel.com>
Date: Fri, 6 Dec 2013 01:17:08 -0500
Subject: EDAC: Add an edac_report parameter to EDAC

This new parameter is used to control how to report HW error reporting,
especially for newer Intel platform, like Ivybridge-EX, which contains
an enhanced error decoding functionality in the firmware, i.e. eMCA.

Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
Acked-by: Tony Luck <tony.luck@intel.com>
Link: http://lkml.kernel.org/r/1386310630-12529-2-git-send-email-gong.chen@linux.intel.com
[ Boris: massage commit message. ]
Signed-off-by: Borislav Petkov <bp@suse.de>

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 50680a5..453092c 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -881,6 +881,14 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 			The xen output can only be used by Xen PV guests.
 
+	edac_report=	[HW,EDAC] Control how to report EDAC event
+			Format: {"on" | "off" | "force"}
+			on: enable EDAC to report H/W event. May be overridden
+			by other higher priority error reporting module.
+			off: disable H/W event reporting through EDAC.
+			force: enforce the use of EDAC to report H/W event.
+			default: on.
+
 	ekgdboc=	[X86,KGDB] Allow early kernel console debugging
 			ekgdboc=kbd
 
diff --git a/drivers/edac/edac_stub.c b/drivers/edac/edac_stub.c
index 351945f..9d9e18a 100644
--- a/drivers/edac/edac_stub.c
+++ b/drivers/edac/edac_stub.c
@@ -29,6 +29,25 @@ EXPORT_SYMBOL_GPL(edac_err_assert);
 
 static atomic_t edac_subsys_valid = ATOMIC_INIT(0);
 
+int edac_report_status = EDAC_REPORTING_ENABLED;
+EXPORT_SYMBOL_GPL(edac_report_status);
+
+static int __init edac_report_setup(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!strncmp(str, "on", 2))
+		set_edac_report_status(EDAC_REPORTING_ENABLED);
+	else if (!strncmp(str, "off", 3))
+		set_edac_report_status(EDAC_REPORTING_DISABLED);
+	else if (!strncmp(str, "force", 5))
+		set_edac_report_status(EDAC_REPORTING_FORCE);
+
+	return 0;
+}
+__setup("edac_report=", edac_report_setup);
+
 /*
  * called to determine if there is an EDAC driver interested in
  * knowing an event (such as NMI) occurred
diff --git a/include/linux/edac.h b/include/linux/edac.h
index dbdffe8..8e6c20a 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -35,6 +35,34 @@ extern void edac_atomic_assert_error(void);
 extern struct bus_type *edac_get_sysfs_subsys(void);
 extern void edac_put_sysfs_subsys(void);
 
+enum {
+	EDAC_REPORTING_ENABLED,
+	EDAC_REPORTING_DISABLED,
+	EDAC_REPORTING_FORCE
+};
+
+extern int edac_report_status;
+#ifdef CONFIG_EDAC
+static inline int get_edac_report_status(void)
+{
+	return edac_report_status;
+}
+
+static inline void set_edac_report_status(int new)
+{
+	edac_report_status = new;
+}
+#else
+static inline int get_edac_report_status(void)
+{
+	return EDAC_REPORTING_DISABLED;
+}
+
+static inline void set_edac_report_status(int new)
+{
+}
+#endif
+
 static inline void opstate_init(void)
 {
 	switch (edac_op_state) {
-- 
cgit v0.10.2


From fd521039666529a4674b9822f1cc873672f57ee6 Mon Sep 17 00:00:00 2001
From: "Chen, Gong" <gong.chen@linux.intel.com>
Date: Fri, 6 Dec 2013 01:17:09 -0500
Subject: EDAC, sb_edac: Modify H/W event reporting policy

Newer Intel platforms support more than one method to report H/W event.
On this kind of platform, H/W event report can adopt new method and
traditional EDAC method should be disabled. Moreover, if EDAC event
report method is set to *force*, it means event must be reported via
EDAC interface. IOW, it overrides the default event report policy.

Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
Acked-by: Tony Luck <tony.luck@intel.com>
Link: http://lkml.kernel.org/r/1386310630-12529-3-git-send-email-gong.chen@linux.intel.com
[ Boris: massage commit and error messages ]
Signed-off-by: Borislav Petkov <bp@suse.de>

diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 8472405..e2e2cb3 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -1829,6 +1829,9 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val,
 	struct mem_ctl_info *mci;
 	struct sbridge_pvt *pvt;
 
+	if (get_edac_report_status() == EDAC_REPORTING_DISABLED)
+		return NOTIFY_DONE;
+
 	mci = get_mci_for_node_id(mce->socketid);
 	if (!mci)
 		return NOTIFY_BAD;
@@ -2142,9 +2145,10 @@ static int __init sbridge_init(void)
 	opstate_init();
 
 	pci_rc = pci_register_driver(&sbridge_driver);
-
 	if (pci_rc >= 0) {
 		mce_register_decode_chain(&sbridge_mce_dec);
+		if (get_edac_report_status() == EDAC_REPORTING_DISABLED)
+			sbridge_printk(KERN_WARNING, "Loading driver, error reporting disabled.\n");
 		return 0;
 	}
 
-- 
cgit v0.10.2


From 42139eb356e3384759ca143ae04d82376346eb4c Mon Sep 17 00:00:00 2001
From: "Chen, Gong" <gong.chen@linux.intel.com>
Date: Fri, 6 Dec 2013 01:17:10 -0500
Subject: ACPI, eMCA: Combine eMCA/EDAC event reporting priority

eMCA has higher H/W event reporting priority. Once it is
loaded, EDAC event reporting should be disabled, unless EDAC
overrides eMCA priority via command line parameter "edac_report=force".

Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
Acked-by: Tony Luck <tony.luck@intel.com>
Link: http://lkml.kernel.org/r/1386310630-12529-4-git-send-email-gong.chen@linux.intel.com
[ Boris: massage printk message. ]
Signed-off-by: Borislav Petkov <bp@suse.de>

diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
index a6869e1..5d33c54 100644
--- a/drivers/acpi/acpi_extlog.c
+++ b/drivers/acpi/acpi_extlog.c
@@ -12,6 +12,7 @@
 #include <acpi/acpi_bus.h>
 #include <linux/cper.h>
 #include <linux/ratelimit.h>
+#include <linux/edac.h>
 #include <asm/cpu.h>
 #include <asm/mce.h>
 
@@ -43,6 +44,8 @@ struct extlog_l1_head {
 	u8  rev1[12];
 };
 
+static int old_edac_report_status;
+
 static u8 extlog_dsm_uuid[] = "663E35AF-CC10-41A4-88EA-5470AF055295";
 
 /* L1 table related physical address */
@@ -150,7 +153,7 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
 
 	rc = print_extlog_rcd(NULL, (struct acpi_generic_status *)elog_buf, cpu);
 
-	return NOTIFY_DONE;
+	return NOTIFY_STOP;
 }
 
 static int extlog_get_dsm(acpi_handle handle, int rev, int func, u64 *ret)
@@ -231,8 +234,12 @@ static int __init extlog_init(void)
 	u64 cap;
 	int rc;
 
-	rc = -ENODEV;
+	if (get_edac_report_status() == EDAC_REPORTING_FORCE) {
+		pr_warn("Not loading eMCA, error reporting force-enabled through EDAC.\n");
+		return -EPERM;
+	}
 
+	rc = -ENODEV;
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
 	if (!(cap & MCG_ELOG_P))
 		return rc;
@@ -287,6 +294,12 @@ static int __init extlog_init(void)
 	if (elog_buf == NULL)
 		goto err_release_elog;
 
+	/*
+	 * eMCA event report method has higher priority than EDAC method,
+	 * unless EDAC event report method is mandatory.
+	 */
+	old_edac_report_status = get_edac_report_status();
+	set_edac_report_status(EDAC_REPORTING_DISABLED);
 	mce_register_decode_chain(&extlog_mce_dec);
 	/* enable OS to be involved to take over management from BIOS */
 	((struct extlog_l1_head *)extlog_l1_addr)->flags |= FLAG_OS_OPTIN;
@@ -308,6 +321,7 @@ err:
 
 static void __exit extlog_exit(void)
 {
+	set_edac_report_status(old_edac_report_status);
 	mce_unregister_decode_chain(&extlog_mce_dec);
 	((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN;
 	if (extlog_l1_addr)
-- 
cgit v0.10.2


From 8e80bf05ff7e7bda6f1683b1201ada56c4efa4c1 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Wed, 11 Dec 2013 15:40:46 -0500
Subject: ktest: Add special variable ${KERNEL_VERSION}

Add a special variable that can be used in other variables called
${KERNEL_VERSION}. This will embed the current kernel version into
the variable. For example:

WARNINGS_FILE = ${OUTPUT_DIR}/warnings-${KERNEL_VERSION}

If the current version is v3.8 then the WARNINGS_FILE will become

  ${OUTPUT_DIR}/warnings-v3.8

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 5dc5704..b285933 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -1129,6 +1129,10 @@ sub __eval_option {
 	} elsif (defined($opt{$var})) {
 	    $o = $opt{$var};
 	    $retval = "$retval$o";
+	} elsif ($var eq "KERNEL_VERSION" && defined($make)) {
+	    # special option KERNEL_VERSION uses kernel version
+	    get_version();
+	    $retval = "$retval$version";
 	} else {
 	    $retval = "$retval\$\{$var\}";
 	}
@@ -3919,6 +3923,18 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
 
     my $makecmd = set_test_option("MAKE_CMD", $i);
 
+    $outputdir = set_test_option("OUTPUT_DIR", $i);
+    $builddir = set_test_option("BUILD_DIR", $i);
+
+    chdir $builddir || die "can't change directory to $builddir";
+
+    if (!-d $outputdir) {
+	mkpath($outputdir) or
+	    die "can't create $outputdir";
+    }
+
+    $make = "$makecmd O=$outputdir";
+
     # Load all the options into their mapped variable names
     foreach my $opt (keys %option_map) {
 	${$option_map{$opt}} = set_test_option($opt, $i);
@@ -3943,13 +3959,9 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
 	$start_minconfig = $minconfig;
     }
 
-    chdir $builddir || die "can't change directory to $builddir";
-
-    foreach my $dir ($tmpdir, $outputdir) {
-	if (!-d $dir) {
-	    mkpath($dir) or
-		die "can't create $dir";
-	}
+    if (!-d $tmpdir) {
+	mkpath($tmpdir) or
+	    die "can't create $tmpdir";
     }
 
     $ENV{"SSH_USER"} = $ssh_user;
@@ -3958,7 +3970,6 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
     $buildlog = "$tmpdir/buildlog-$machine";
     $testlog = "$tmpdir/testlog-$machine";
     $dmesg = "$tmpdir/dmesg-$machine";
-    $make = "$makecmd O=$outputdir";
     $output_config = "$outputdir/.config";
 
     if (!$buildonly) {
-- 
cgit v0.10.2


From c75d22d9c675c4c77d87ff36de6e5023f14724ef Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Wed, 11 Dec 2013 21:16:59 -0500
Subject: ktest: Add eval '=~' command to modify variables in config file

With the added variable ${KERNEL_VERSION}, it is useful to be
able to use parts of it for other variables.

For example, if you want to create a warnings file for each major
kernel version to test sub versions against you can create
your warnings file with like this:

  WARNINGS_FILE = warnings-file-${KERNEL_VERSION}

But this may add 3.8.12 or something, and we want all 3.8.* to
use the same file, and 3.10.* to use another file, and so on.
With the eval command we can, by adding:

  WARNINGS_FILE =~ s/(-file-\d+\.\d+).*/$1/

Which will chop off the extra characters after the 3.8.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index b285933..82006c2 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -18,6 +18,7 @@ $| = 1;
 my %opt;
 my %repeat_tests;
 my %repeats;
+my %evals;
 
 #default opts
 my %default = (
@@ -448,6 +449,27 @@ $config_help{"REBOOT_SCRIPT"} = << "EOF"
 EOF
     ;
 
+sub _logit {
+    if (defined($opt{"LOG_FILE"})) {
+	open(OUT, ">> $opt{LOG_FILE}") or die "Can't write to $opt{LOG_FILE}";
+	print OUT @_;
+	close(OUT);
+    }
+}
+
+sub logit {
+    if (defined($opt{"LOG_FILE"})) {
+	_logit @_;
+    } else {
+	print @_;
+    }
+}
+
+sub doprint {
+    print @_;
+    _logit @_;
+}
+
 sub read_prompt {
     my ($cancel, $prompt) = @_;
 
@@ -665,6 +687,22 @@ sub set_value {
     }
 }
 
+sub set_eval {
+    my ($lvalue, $rvalue, $name) = @_;
+
+    my $prvalue = process_variables($rvalue);
+    my $arr;
+
+    if (defined($evals{$lvalue})) {
+	$arr = $evals{$lvalue};
+    } else {
+	$arr = [];
+	$evals{$lvalue} = $arr;
+    }
+
+    push @{$arr}, $rvalue;
+}
+
 sub set_variable {
     my ($lvalue, $rvalue) = @_;
 
@@ -950,6 +988,20 @@ sub __read_config {
 		$test_case = 1;
 	    }
 
+	} elsif (/^\s*([A-Z_\[\]\d]+)\s*=~\s*(.*?)\s*$/) {
+
+	    next if ($skip);
+
+	    my $lvalue = $1;
+	    my $rvalue = $2;
+
+	    if ($default || $lvalue =~ /\[\d+\]$/) {
+		set_eval($lvalue, $rvalue, $name);
+	    } else {
+		my $val = "$lvalue\[$test_num\]";
+		set_eval($val, $rvalue, $name);
+	    }
+
 	} elsif (/^\s*([A-Z_\[\]\d]+)\s*=\s*(.*?)\s*$/) {
 
 	    next if ($skip);
@@ -1147,6 +1199,33 @@ sub __eval_option {
     return $retval;
 }
 
+sub process_evals {
+    my ($name, $option, $i) = @_;
+
+    my $option_name = "$name\[$i\]";
+    my $ev;
+
+    my $old_option = $option;
+
+    if (defined($evals{$option_name})) {
+	$ev = $evals{$option_name};
+    } elsif (defined($evals{$name})) {
+	$ev = $evals{$name};
+    } else {
+	return $option;
+    }
+
+    for my $e (@{$ev}) {
+	eval "\$option =~ $e";
+    }
+
+    if ($option ne $old_option) {
+	doprint("$name changed from '$old_option' to '$option'\n");
+    }
+
+    return $option;
+}
+
 sub eval_option {
     my ($name, $option, $i) = @_;
 
@@ -1167,28 +1246,9 @@ sub eval_option {
 	$option = __eval_option($name, $option, $i);
     }
 
-    return $option;
-}
-
-sub _logit {
-    if (defined($opt{"LOG_FILE"})) {
-	open(OUT, ">> $opt{LOG_FILE}") or die "Can't write to $opt{LOG_FILE}";
-	print OUT @_;
-	close(OUT);
-    }
-}
-
-sub logit {
-    if (defined($opt{"LOG_FILE"})) {
-	_logit @_;
-    } else {
-	print @_;
-    }
-}
+    $option = process_evals($name, $option, $i);
 
-sub doprint {
-    print @_;
-    _logit @_;
+    return $option;
 }
 
 sub run_command;
-- 
cgit v0.10.2


From d8af4ce490e92adfa123ae79899332bd829903e7 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 12 Dec 2013 14:46:42 +0100
Subject: x86/traps: Clean up error exception handler definitions

So I was reading the exception handler generation code and got a real
headache looking at the unstructured mess that our DO_ERROR*()
generation code is today.

Make it more readable.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: http://lkml.kernel.org/n/tip-kuabysiykvUJpgus35lhnhvs@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index b857ed8..57409f6 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -211,21 +211,17 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code)	\
 	exception_exit(prev_state);					\
 }
 
-DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV,
-		regs->ip)
-DO_ERROR(X86_TRAP_OF, SIGSEGV, "overflow", overflow)
-DO_ERROR(X86_TRAP_BR, SIGSEGV, "bounds", bounds)
-DO_ERROR_INFO(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN,
-		regs->ip)
-DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun",
-		coprocessor_segment_overrun)
-DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS)
-DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present)
+DO_ERROR_INFO(X86_TRAP_DE,     SIGFPE,  "divide error",			divide_error,		     FPE_INTDIV, regs->ip )
+DO_ERROR     (X86_TRAP_OF,     SIGSEGV, "overflow",			overflow					  )
+DO_ERROR     (X86_TRAP_BR,     SIGSEGV, "bounds",			bounds						  )
+DO_ERROR_INFO(X86_TRAP_UD,     SIGILL,  "invalid opcode",		invalid_op,		     ILL_ILLOPN, regs->ip )
+DO_ERROR     (X86_TRAP_OLD_MF, SIGFPE,  "coprocessor segment overrun",	coprocessor_segment_overrun			  )
+DO_ERROR     (X86_TRAP_TS,     SIGSEGV, "invalid TSS",			invalid_TSS					  )
+DO_ERROR     (X86_TRAP_NP,     SIGBUS,  "segment not present",		segment_not_present				  )
 #ifdef CONFIG_X86_32
-DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment)
+DO_ERROR     (X86_TRAP_SS,     SIGBUS,  "stack segment",		stack_segment					  )
 #endif
-DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check,
-		BUS_ADRALN, 0)
+DO_ERROR_INFO(X86_TRAP_AC,     SIGBUS,  "alignment check",		alignment_check,	     BUS_ADRALN, 0	  )
 
 #ifdef CONFIG_X86_64
 /* Runs on IST stack */
-- 
cgit v0.10.2


From ac7c8e3dd2ed6489be1f6bc722029fb4855c3a34 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 11 Oct 2013 10:17:39 -0700
Subject: rcu: Add comment on evaluate-once properties of rcu_assign_pointer().

The rcu_assign_pointer() macro, as with most cpp macros, must not evaluate
its argument more than once.  And it in fact does not.  But this might
not be obvious to the casual observer, because one of the arguments
appears no less than three times.  However, but one expansion is only
visible to sparse (__CHECKER__), and one lives inside a typeof (where
it will never be evaluated), so this is in fact safe.

This commit therefore adds a comment making this explicit.

Reported-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 39cbb88..00ad281 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -911,6 +911,14 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  * rcu_assign_pointer() is a very bad thing that results in
  * impossible-to-diagnose memory corruption.  So please be careful.
  * See the RCU_INIT_POINTER() comment header for details.
+ *
+ * Note that rcu_assign_pointer() evaluates each of its arguments only
+ * once, appearances notwithstanding.  One of the "extra" evaluations
+ * is in typeof() and the other visible only to sparse (__CHECKER__),
+ * neither of which actually execute the argument.  As with most cpp
+ * macros, this execute-arguments-only-once property is important, so
+ * please be careful when making changes to rcu_assign_pointer() and the
+ * other macros that it invokes.
  */
 #define rcu_assign_pointer(p, v) \
 	__rcu_assign_pointer((p), (v), __rcu)
-- 
cgit v0.10.2


From 36708b89e00951b004b4dd6c14181301e2e98354 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 9 Dec 2013 15:19:53 -0800
Subject: bonding: Use RCU_INIT_POINTER() for better overhead and for sparse

Although rcu_assign_pointer() can be used to assign a constant
NULL pointer, doing so gets you an unnecessary memory barrier and
in some circumstances, sparse warnings.  This commit therefore
changes the rcu_assign_pointer() of NULL in __bond_release_one() to
RCU_INIT_POINTER().

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 4dd5ee2..a0b97c4 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1763,7 +1763,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 	}
 
 	if (all) {
-		rcu_assign_pointer(bond->curr_active_slave, NULL);
+		RCU_INIT_POINTER(bond->curr_active_slave, NULL);
 	} else if (oldcurrent == slave) {
 		/*
 		 * Note that we hold RTNL over this sequence, so there
-- 
cgit v0.10.2


From 9d162cd06349dfee6b4f254b3abf1355cf0aee43 Mon Sep 17 00:00:00 2001
From: Josh Triplett <josh@joshtriplett.org>
Date: Sun, 1 Sep 2013 16:42:52 -0700
Subject: rcu: Make rcu_assign_pointer's assignment volatile and type-safe

The rcu_assign_pointer() primitive needs to use ACCESS_ONCE to make
the assignment to the destination pointer volatile, to protect against
compilers too clever for their own good.

Signed-off-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 00ad281..97853cd 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -551,7 +551,7 @@ static inline void rcu_preempt_sleep_check(void)
 #define __rcu_assign_pointer(p, v, space) \
 	do { \
 		smp_wmb(); \
-		(p) = (typeof(*v) __force space *)(v); \
+		ACCESS_ONCE(p) = (typeof(*(v)) __force space *)(v); \
 	} while (0)
 
 
-- 
cgit v0.10.2


From 462225ae47d7175f886281d8a91708550cd5178c Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 11 Nov 2013 09:59:34 -0800
Subject: rcu: Add an RCU_INITIALIZER for global RCU-protected pointers

There is currently no way to initialize a global RCU-protected pointer
without either putting up with sparse complaints or open-coding an
obscure cast.  This commit therefore creates RCU_INITIALIZER(), which
is intended to be used as follows:

	struct foo __rcu *p = RCU_INITIALIZER(&my_rcu_structure);

This commit also applies RCU_INITIALIZER() to eliminate repeated
open-coded obscure casts in __rcu_assign_pointer(), RCU_INIT_POINTER(),
and RCU_POINTER_INITIALIZER().  This commit also inlines
__rcu_assign_pointer() into its only caller, rcu_assign_pointer().

Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 97853cd..ea3816c 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -548,10 +548,48 @@ static inline void rcu_preempt_sleep_check(void)
 		smp_read_barrier_depends(); \
 		(_________p1); \
 	})
-#define __rcu_assign_pointer(p, v, space) \
+
+/**
+ * RCU_INITIALIZER() - statically initialize an RCU-protected global variable
+ * @v: The value to statically initialize with.
+ */
+#define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v)
+
+/**
+ * rcu_assign_pointer() - assign to RCU-protected pointer
+ * @p: pointer to assign to
+ * @v: value to assign (publish)
+ *
+ * Assigns the specified value to the specified RCU-protected
+ * pointer, ensuring that any concurrent RCU readers will see
+ * any prior initialization.
+ *
+ * Inserts memory barriers on architectures that require them
+ * (which is most of them), and also prevents the compiler from
+ * reordering the code that initializes the structure after the pointer
+ * assignment.  More importantly, this call documents which pointers
+ * will be dereferenced by RCU read-side code.
+ *
+ * In some special cases, you may use RCU_INIT_POINTER() instead
+ * of rcu_assign_pointer().  RCU_INIT_POINTER() is a bit faster due
+ * to the fact that it does not constrain either the CPU or the compiler.
+ * That said, using RCU_INIT_POINTER() when you should have used
+ * rcu_assign_pointer() is a very bad thing that results in
+ * impossible-to-diagnose memory corruption.  So please be careful.
+ * See the RCU_INIT_POINTER() comment header for details.
+ *
+ * Note that rcu_assign_pointer() evaluates each of its arguments only
+ * once, appearances notwithstanding.  One of the "extra" evaluations
+ * is in typeof() and the other visible only to sparse (__CHECKER__),
+ * neither of which actually execute the argument.  As with most cpp
+ * macros, this execute-arguments-only-once property is important, so
+ * please be careful when making changes to rcu_assign_pointer() and the
+ * other macros that it invokes.
+ */
+#define rcu_assign_pointer(p, v) \
 	do { \
 		smp_wmb(); \
-		ACCESS_ONCE(p) = (typeof(*(v)) __force space *)(v); \
+		ACCESS_ONCE(p) = RCU_INITIALIZER(v); \
 	} while (0)
 
 
@@ -890,40 +928,6 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 }
 
 /**
- * rcu_assign_pointer() - assign to RCU-protected pointer
- * @p: pointer to assign to
- * @v: value to assign (publish)
- *
- * Assigns the specified value to the specified RCU-protected
- * pointer, ensuring that any concurrent RCU readers will see
- * any prior initialization.
- *
- * Inserts memory barriers on architectures that require them
- * (which is most of them), and also prevents the compiler from
- * reordering the code that initializes the structure after the pointer
- * assignment.  More importantly, this call documents which pointers
- * will be dereferenced by RCU read-side code.
- *
- * In some special cases, you may use RCU_INIT_POINTER() instead
- * of rcu_assign_pointer().  RCU_INIT_POINTER() is a bit faster due
- * to the fact that it does not constrain either the CPU or the compiler.
- * That said, using RCU_INIT_POINTER() when you should have used
- * rcu_assign_pointer() is a very bad thing that results in
- * impossible-to-diagnose memory corruption.  So please be careful.
- * See the RCU_INIT_POINTER() comment header for details.
- *
- * Note that rcu_assign_pointer() evaluates each of its arguments only
- * once, appearances notwithstanding.  One of the "extra" evaluations
- * is in typeof() and the other visible only to sparse (__CHECKER__),
- * neither of which actually execute the argument.  As with most cpp
- * macros, this execute-arguments-only-once property is important, so
- * please be careful when making changes to rcu_assign_pointer() and the
- * other macros that it invokes.
- */
-#define rcu_assign_pointer(p, v) \
-	__rcu_assign_pointer((p), (v), __rcu)
-
-/**
  * RCU_INIT_POINTER() - initialize an RCU protected pointer
  *
  * Initialize an RCU-protected pointer in special cases where readers
@@ -957,7 +961,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  */
 #define RCU_INIT_POINTER(p, v) \
 	do { \
-		p = (typeof(*v) __force __rcu *)(v); \
+		p = RCU_INITIALIZER(v); \
 	} while (0)
 
 /**
@@ -966,7 +970,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  * GCC-style initialization for an RCU-protected pointer in a structure field.
  */
 #define RCU_POINTER_INITIALIZER(p, v) \
-		.p = (typeof(*v) __force __rcu *)(v)
+		.p = RCU_INITIALIZER(v)
 
 /*
  * Does the specified offset indicate that the corresponding rcu_head
-- 
cgit v0.10.2


From 79a62f957e0b37c59610a96d018cc341aebb48f4 Mon Sep 17 00:00:00 2001
From: Lai Jiangshan <laijs@cn.fujitsu.com>
Date: Wed, 30 Oct 2013 04:13:22 -0700
Subject: rcu: Warn on allegedly impossible rcu_read_unlock_special() from irq

After commit #10f39bb1b2c1 (rcu: protect __rcu_read_unlock() against
scheduler-using irq handlers), it is no longer possible to enter
the main body of rcu_read_lock_special() from an NMI, interrupt, or
softirq handler.  In theory, this implies that the check for "in_irq()
|| in_serving_softirq()" must always fail, so that in theory this check
could be removed entirely.

In practice, this commit wraps this condition with a WARN_ON_ONCE().
If this warning never triggers, then the condition will be removed
entirely.

[ paulmck: And one way of triggering the WARN_ON() is if a scheduling
  clock interrupt occurs in an RCU read-side critical section, setting
  RCU_READ_UNLOCK_NEED_QS, which is handled by rcu_read_unlock_special().
  Updated this commit to return if only that bit was set. ]

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 752ffaa..fa7a18b 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -361,10 +361,14 @@ void rcu_read_unlock_special(struct task_struct *t)
 	special = t->rcu_read_unlock_special;
 	if (special & RCU_READ_UNLOCK_NEED_QS) {
 		rcu_preempt_qs(smp_processor_id());
+		if (!t->rcu_read_unlock_special) {
+			local_irq_restore(flags);
+			return;
+		}
 	}
 
-	/* Hardware IRQ handlers cannot block. */
-	if (in_irq() || in_serving_softirq()) {
+	/* Hardware IRQ handlers cannot block, complain if they get here. */
+	if (WARN_ON_ONCE(in_irq() || in_serving_softirq())) {
 		local_irq_restore(flags);
 		return;
 	}
-- 
cgit v0.10.2


From a096932f0c9c9dca9cce72f1c0fb2395df8f2dff Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 8 Nov 2013 09:03:10 -0800
Subject: rcu: Don't activate RCU core on NO_HZ_FULL CPUs

Whenever a CPU receives a scheduling-clock interrupt, RCU checks to see
if the RCU core needs anything from this CPU.  If so, RCU raises
RCU_SOFTIRQ to carry out any needed processing.

This approach has worked well historically, but it is undesirable on
NO_HZ_FULL CPUs.  Such CPUs are expected to spend almost all of their time
in userspace, so that scheduling-clock interrupts can be disabled while
there is only one runnable task on the CPU in question.  Unfortunately,
raising any softirq has the potential to wake up ksoftirqd, which would
provide the second runnable task on that CPU, preventing disabling of
scheduling-clock interrupts.

What is needed instead is for RCU to leave NO_HZ_FULL CPUs alone,
relying on the grace-period kthreads' quiescent-state forcing to
do any needed RCU work on behalf of those CPUs.

This commit therefore refrains from raising RCU_SOFTIRQ on any
NO_HZ_FULL CPUs during any grace periods that have been in effect
for less than one second.  The one-second limit handles the case
where an inappropriate workload is running on a NO_HZ_FULL CPU
that features lots of scheduling-clock interrupts, but no idle
or userspace time.

Reported-by: Mike Galbraith <bitbucket@online.de>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Mike Galbraith <bitbucket@online.de>
Toasted-by: Frederic Weisbecker <fweisbec@gmail.com>

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index db1a9fd..e37bd56 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2796,6 +2796,10 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 	/* Check for CPU stalls, if enabled. */
 	check_cpu_stall(rsp, rdp);
 
+	/* Is this CPU a NO_HZ_FULL CPU that should ignore RCU? */
+	if (rcu_nohz_full_cpu(rsp))
+		return 0;
+
 	/* Is the RCU core waiting for a quiescent state from this CPU? */
 	if (rcu_scheduler_fully_active &&
 	    rdp->qs_pending && !rdp->passed_quiesce) {
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index a87adfc..8c19873 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -571,6 +571,7 @@ static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle,
 				  unsigned long maxj);
 static void rcu_bind_gp_kthread(void);
 static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp);
+static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
 
 #endif /* #ifndef RCU_TREE_NONCORE */
 
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index fa7a18b..e0885cb 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2872,3 +2872,23 @@ static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp)
 }
 
 #endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
+
+/*
+ * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the
+ * grace-period kthread will do force_quiescent_state() processing?
+ * The idea is to avoid waking up RCU core processing on such a
+ * CPU unless the grace period has extended for too long.
+ *
+ * This code relies on the fact that all NO_HZ_FULL CPUs are also
+ * CONFIG_RCU_NOCB_CPUs.
+ */
+static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
+{
+#ifdef CONFIG_NO_HZ_FULL
+	if (tick_nohz_full_cpu(smp_processor_id()) &&
+	    (!rcu_gp_in_progress(rsp) ||
+	     ULONG_CMP_LT(jiffies, ACCESS_ONCE(rsp->gp_start) + HZ)))
+		return 1;
+#endif /* #ifdef CONFIG_NO_HZ_FULL */
+	return 0;
+}
-- 
cgit v0.10.2


From d10089508613f42b8b54cf33456a821c7cf3d442 Mon Sep 17 00:00:00 2001
From: Chen Gang <gang.chen@asianux.com>
Date: Thu, 7 Nov 2013 10:30:25 +0800
Subject: rcu/torture: Dynamically allocate SRCU output buffer to avoid
 overflow

If the rcutorture SRCU output exceeds 4096 bytes, for example, if you
have more than about 75 CPUs, it will overflow the current statically
allocated buffer.  This commit therefore replaces this static buffer
with a dynamically buffer whose size is based on the number of CPUs.

Benefits:

 - Avoids both buffer overflow and output truncation.
 - Handles an arbitrarily large number of CPUs.
 - Straightforward implementation.

Shortcomings:

 - Some memory is wasted:

   1 cpu now comsumes 50 - 60 bytes, and this patch provides 200 bytes.
   Therefore, for 1K CPUs, roughly 100KB of memory will be wasted.
   However, the memory is freed immediately after printing, so this
   wastage should not be a problem in practice.

Testing (Fedora16 2 CPUs, 2GB RAM x86_64):

 - as module, with/without "torture_type=srcu".
 - build-in not boot runnable, with/without "torture_type=srcu".
 - build-in let boot runnable, with/without "torture_type=srcu".

Signed-off-by: Chen Gang <gang.chen@asianux.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/kernel/rcu/torture.c b/kernel/rcu/torture.c
index 69a4ec8..732f8ae 100644
--- a/kernel/rcu/torture.c
+++ b/kernel/rcu/torture.c
@@ -139,8 +139,6 @@ MODULE_PARM_DESC(verbose, "Enable verbose debugging printk()s");
 #define VERBOSE_PRINTK_ERRSTRING(s) \
 	do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! " s "\n", torture_type); } while (0)
 
-static char printk_buf[4096];
-
 static int nrealreaders;
 static struct task_struct *writer_task;
 static struct task_struct **fakewriter_tasks;
@@ -376,7 +374,7 @@ struct rcu_torture_ops {
 	void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
 	void (*cb_barrier)(void);
 	void (*fqs)(void);
-	int (*stats)(char *page);
+	void (*stats)(char *page);
 	int irq_capable;
 	int can_boost;
 	const char *name;
@@ -578,21 +576,19 @@ static void srcu_torture_barrier(void)
 	srcu_barrier(&srcu_ctl);
 }
 
-static int srcu_torture_stats(char *page)
+static void srcu_torture_stats(char *page)
 {
-	int cnt = 0;
 	int cpu;
 	int idx = srcu_ctl.completed & 0x1;
 
-	cnt += sprintf(&page[cnt], "%s%s per-CPU(idx=%d):",
+	page += sprintf(page, "%s%s per-CPU(idx=%d):",
 		       torture_type, TORTURE_FLAG, idx);
 	for_each_possible_cpu(cpu) {
-		cnt += sprintf(&page[cnt], " %d(%lu,%lu)", cpu,
+		page += sprintf(page, " %d(%lu,%lu)", cpu,
 			       per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx],
 			       per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]);
 	}
-	cnt += sprintf(&page[cnt], "\n");
-	return cnt;
+	sprintf(page, "\n");
 }
 
 static void srcu_torture_synchronize_expedited(void)
@@ -1052,10 +1048,9 @@ rcu_torture_reader(void *arg)
 /*
  * Create an RCU-torture statistics message in the specified buffer.
  */
-static int
+static void
 rcu_torture_printk(char *page)
 {
-	int cnt = 0;
 	int cpu;
 	int i;
 	long pipesummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
@@ -1071,8 +1066,8 @@ rcu_torture_printk(char *page)
 		if (pipesummary[i] != 0)
 			break;
 	}
-	cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG);
-	cnt += sprintf(&page[cnt],
+	page += sprintf(page, "%s%s ", torture_type, TORTURE_FLAG);
+	page += sprintf(page,
 		       "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d ",
 		       rcu_torture_current,
 		       rcu_torture_current_version,
@@ -1080,53 +1075,52 @@ rcu_torture_printk(char *page)
 		       atomic_read(&n_rcu_torture_alloc),
 		       atomic_read(&n_rcu_torture_alloc_fail),
 		       atomic_read(&n_rcu_torture_free));
-	cnt += sprintf(&page[cnt], "rtmbe: %d rtbke: %ld rtbre: %ld ",
+	page += sprintf(page, "rtmbe: %d rtbke: %ld rtbre: %ld ",
 		       atomic_read(&n_rcu_torture_mberror),
 		       n_rcu_torture_boost_ktrerror,
 		       n_rcu_torture_boost_rterror);
-	cnt += sprintf(&page[cnt], "rtbf: %ld rtb: %ld nt: %ld ",
+	page += sprintf(page, "rtbf: %ld rtb: %ld nt: %ld ",
 		       n_rcu_torture_boost_failure,
 		       n_rcu_torture_boosts,
 		       n_rcu_torture_timers);
-	cnt += sprintf(&page[cnt],
+	page += sprintf(page,
 		       "onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ",
 		       n_online_successes, n_online_attempts,
 		       n_offline_successes, n_offline_attempts,
 		       min_online, max_online,
 		       min_offline, max_offline,
 		       sum_online, sum_offline, HZ);
-	cnt += sprintf(&page[cnt], "barrier: %ld/%ld:%ld",
+	page += sprintf(page, "barrier: %ld/%ld:%ld",
 		       n_barrier_successes,
 		       n_barrier_attempts,
 		       n_rcu_torture_barrier_error);
-	cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
+	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
 	if (atomic_read(&n_rcu_torture_mberror) != 0 ||
 	    n_rcu_torture_barrier_error != 0 ||
 	    n_rcu_torture_boost_ktrerror != 0 ||
 	    n_rcu_torture_boost_rterror != 0 ||
 	    n_rcu_torture_boost_failure != 0 ||
 	    i > 1) {
-		cnt += sprintf(&page[cnt], "!!! ");
+		page += sprintf(page, "!!! ");
 		atomic_inc(&n_rcu_torture_error);
 		WARN_ON_ONCE(1);
 	}
-	cnt += sprintf(&page[cnt], "Reader Pipe: ");
+	page += sprintf(page, "Reader Pipe: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
-		cnt += sprintf(&page[cnt], " %ld", pipesummary[i]);
-	cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
-	cnt += sprintf(&page[cnt], "Reader Batch: ");
+		page += sprintf(page, " %ld", pipesummary[i]);
+	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
+	page += sprintf(page, "Reader Batch: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++)
-		cnt += sprintf(&page[cnt], " %ld", batchsummary[i]);
-	cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG);
-	cnt += sprintf(&page[cnt], "Free-Block Circulation: ");
+		page += sprintf(page, " %ld", batchsummary[i]);
+	page += sprintf(page, "\n%s%s ", torture_type, TORTURE_FLAG);
+	page += sprintf(page, "Free-Block Circulation: ");
 	for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) {
-		cnt += sprintf(&page[cnt], " %d",
+		page += sprintf(page, " %d",
 			       atomic_read(&rcu_torture_wcount[i]));
 	}
-	cnt += sprintf(&page[cnt], "\n");
+	page += sprintf(page, "\n");
 	if (cur_ops->stats)
-		cnt += cur_ops->stats(&page[cnt]);
-	return cnt;
+		cur_ops->stats(page);
 }
 
 /*
@@ -1140,10 +1134,17 @@ rcu_torture_printk(char *page)
 static void
 rcu_torture_stats_print(void)
 {
-	int cnt;
+	int size = nr_cpu_ids * 200 + 8192;
+	char *buf;
 
-	cnt = rcu_torture_printk(printk_buf);
-	pr_alert("%s", printk_buf);
+	buf = kmalloc(size, GFP_KERNEL);
+	if (!buf) {
+		pr_err("rcu-torture: Out of memory, need: %d", size);
+		return;
+	}
+	rcu_torture_printk(buf);
+	pr_alert("%s", buf);
+	kfree(buf);
 }
 
 /*
-- 
cgit v0.10.2


From 584dc4ce55267765b415a8517613d1207f1741e5 Mon Sep 17 00:00:00 2001
From: Teodora Baluta <teobaluta@gmail.com>
Date: Mon, 11 Nov 2013 17:11:23 +0200
Subject: rcu: Remove "extern" from function declarations in
 include/linux/*rcu*.h

Function prototypes don't need to have the "extern" keyword since this
is the default behavior. Its explicit use is redundant.  This commit
therefore removes them.

Signed-off-by: Teodora Baluta <teobaluta@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 45a0a9e..dbaf990 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -55,8 +55,8 @@ static inline void __list_add_rcu(struct list_head *new,
 	next->prev = new;
 }
 #else
-extern void __list_add_rcu(struct list_head *new,
-		struct list_head *prev, struct list_head *next);
+void __list_add_rcu(struct list_head *new,
+		    struct list_head *prev, struct list_head *next);
 #endif
 
 /**
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index a94a580..52c1b13 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -50,13 +50,13 @@ extern int rcutorture_runnable; /* for sysctl */
 #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
-extern void rcutorture_record_test_transition(void);
-extern void rcutorture_record_progress(unsigned long vernum);
-extern void do_trace_rcu_torture_read(const char *rcutorturename,
-				      struct rcu_head *rhp,
-				      unsigned long secs,
-				      unsigned long c_old,
-				      unsigned long c);
+void rcutorture_record_test_transition(void);
+void rcutorture_record_progress(unsigned long vernum);
+void do_trace_rcu_torture_read(const char *rcutorturename,
+			       struct rcu_head *rhp,
+			       unsigned long secs,
+			       unsigned long c_old,
+			       unsigned long c);
 #else
 static inline void rcutorture_record_test_transition(void)
 {
@@ -65,11 +65,11 @@ static inline void rcutorture_record_progress(unsigned long vernum)
 {
 }
 #ifdef CONFIG_RCU_TRACE
-extern void do_trace_rcu_torture_read(const char *rcutorturename,
-				      struct rcu_head *rhp,
-				      unsigned long secs,
-				      unsigned long c_old,
-				      unsigned long c);
+void do_trace_rcu_torture_read(const char *rcutorturename,
+			       struct rcu_head *rhp,
+			       unsigned long secs,
+			       unsigned long c_old,
+			       unsigned long c);
 #else
 #define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
 	do { } while (0)
@@ -118,8 +118,8 @@ extern void do_trace_rcu_torture_read(const char *rcutorturename,
  * if CPU A and CPU B are the same CPU (but again only if the system has
  * more than one CPU).
  */
-extern void call_rcu(struct rcu_head *head,
-			      void (*func)(struct rcu_head *head));
+void call_rcu(struct rcu_head *head,
+	      void (*func)(struct rcu_head *head));
 
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
@@ -149,8 +149,8 @@ extern void call_rcu(struct rcu_head *head,
  * See the description of call_rcu() for more detailed information on
  * memory ordering guarantees.
  */
-extern void call_rcu_bh(struct rcu_head *head,
-			void (*func)(struct rcu_head *head));
+void call_rcu_bh(struct rcu_head *head,
+		 void (*func)(struct rcu_head *head));
 
 /**
  * call_rcu_sched() - Queue an RCU for invocation after sched grace period.
@@ -171,16 +171,16 @@ extern void call_rcu_bh(struct rcu_head *head,
  * See the description of call_rcu() for more detailed information on
  * memory ordering guarantees.
  */
-extern void call_rcu_sched(struct rcu_head *head,
-			   void (*func)(struct rcu_head *rcu));
+void call_rcu_sched(struct rcu_head *head,
+		    void (*func)(struct rcu_head *rcu));
 
-extern void synchronize_sched(void);
+void synchronize_sched(void);
 
 #ifdef CONFIG_PREEMPT_RCU
 
-extern void __rcu_read_lock(void);
-extern void __rcu_read_unlock(void);
-extern void rcu_read_unlock_special(struct task_struct *t);
+void __rcu_read_lock(void);
+void __rcu_read_unlock(void);
+void rcu_read_unlock_special(struct task_struct *t);
 void synchronize_rcu(void);
 
 /*
@@ -216,19 +216,19 @@ static inline int rcu_preempt_depth(void)
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
 /* Internal to kernel */
-extern void rcu_init(void);
-extern void rcu_sched_qs(int cpu);
-extern void rcu_bh_qs(int cpu);
-extern void rcu_check_callbacks(int cpu, int user);
+void rcu_init(void);
+void rcu_sched_qs(int cpu);
+void rcu_bh_qs(int cpu);
+void rcu_check_callbacks(int cpu, int user);
 struct notifier_block;
-extern void rcu_idle_enter(void);
-extern void rcu_idle_exit(void);
-extern void rcu_irq_enter(void);
-extern void rcu_irq_exit(void);
+void rcu_idle_enter(void);
+void rcu_idle_exit(void);
+void rcu_irq_enter(void);
+void rcu_irq_exit(void);
 
 #ifdef CONFIG_RCU_USER_QS
-extern void rcu_user_enter(void);
-extern void rcu_user_exit(void);
+void rcu_user_enter(void);
+void rcu_user_exit(void);
 #else
 static inline void rcu_user_enter(void) { }
 static inline void rcu_user_exit(void) { }
@@ -262,7 +262,7 @@ static inline void rcu_user_hooks_switch(struct task_struct *prev,
 	} while (0)
 
 #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP)
-extern bool __rcu_is_watching(void);
+bool __rcu_is_watching(void);
 #endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */
 
 /*
@@ -289,8 +289,8 @@ void wait_rcu_gp(call_rcu_func_t crf);
  * initialization.
  */
 #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
-extern void init_rcu_head_on_stack(struct rcu_head *head);
-extern void destroy_rcu_head_on_stack(struct rcu_head *head);
+void init_rcu_head_on_stack(struct rcu_head *head);
+void destroy_rcu_head_on_stack(struct rcu_head *head);
 #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 static inline void init_rcu_head_on_stack(struct rcu_head *head)
 {
@@ -363,7 +363,7 @@ static inline int rcu_read_lock_held(void)
  * rcu_read_lock_bh_held() is defined out of line to avoid #include-file
  * hell.
  */
-extern int rcu_read_lock_bh_held(void);
+int rcu_read_lock_bh_held(void);
 
 /**
  * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
@@ -449,7 +449,7 @@ static inline int rcu_read_lock_sched_held(void)
 
 #ifdef CONFIG_PROVE_RCU
 
-extern int rcu_my_thread_group_empty(void);
+int rcu_my_thread_group_empty(void);
 
 /**
  * rcu_lockdep_assert - emit lockdep splat if specified condition not met
@@ -1006,7 +1006,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
 	__kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head))
 
 #ifdef CONFIG_RCU_NOCB_CPU
-extern bool rcu_is_nocb_cpu(int cpu);
+bool rcu_is_nocb_cpu(int cpu);
 #else
 static inline bool rcu_is_nocb_cpu(int cpu) { return false; }
 #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
@@ -1014,8 +1014,8 @@ static inline bool rcu_is_nocb_cpu(int cpu) { return false; }
 
 /* Only for use by adaptive-ticks code. */
 #ifdef CONFIG_NO_HZ_FULL_SYSIDLE
-extern bool rcu_sys_is_idle(void);
-extern void rcu_sysidle_force_exit(void);
+bool rcu_sys_is_idle(void);
+void rcu_sysidle_force_exit(void);
 #else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
 
 static inline bool rcu_sys_is_idle(void)
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 09ebcbe..6f01771 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -125,7 +125,7 @@ static inline void exit_rcu(void)
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 extern int rcu_scheduler_active __read_mostly;
-extern void rcu_scheduler_starting(void);
+void rcu_scheduler_starting(void);
 #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 static inline void rcu_scheduler_starting(void)
 {
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 4b9c815..72137ee 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -30,9 +30,9 @@
 #ifndef __LINUX_RCUTREE_H
 #define __LINUX_RCUTREE_H
 
-extern void rcu_note_context_switch(int cpu);
-extern int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies);
-extern void rcu_cpu_stall_reset(void);
+void rcu_note_context_switch(int cpu);
+int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies);
+void rcu_cpu_stall_reset(void);
 
 /*
  * Note a virtualization-based context switch.  This is simply a
@@ -44,9 +44,9 @@ static inline void rcu_virt_note_context_switch(int cpu)
 	rcu_note_context_switch(cpu);
 }
 
-extern void synchronize_rcu_bh(void);
-extern void synchronize_sched_expedited(void);
-extern void synchronize_rcu_expedited(void);
+void synchronize_rcu_bh(void);
+void synchronize_sched_expedited(void);
+void synchronize_rcu_expedited(void);
 
 void kfree_call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
 
@@ -71,25 +71,25 @@ static inline void synchronize_rcu_bh_expedited(void)
 	synchronize_sched_expedited();
 }
 
-extern void rcu_barrier(void);
-extern void rcu_barrier_bh(void);
-extern void rcu_barrier_sched(void);
+void rcu_barrier(void);
+void rcu_barrier_bh(void);
+void rcu_barrier_sched(void);
 
 extern unsigned long rcutorture_testseq;
 extern unsigned long rcutorture_vernum;
-extern long rcu_batches_completed(void);
-extern long rcu_batches_completed_bh(void);
-extern long rcu_batches_completed_sched(void);
+long rcu_batches_completed(void);
+long rcu_batches_completed_bh(void);
+long rcu_batches_completed_sched(void);
 
-extern void rcu_force_quiescent_state(void);
-extern void rcu_bh_force_quiescent_state(void);
-extern void rcu_sched_force_quiescent_state(void);
+void rcu_force_quiescent_state(void);
+void rcu_bh_force_quiescent_state(void);
+void rcu_sched_force_quiescent_state(void);
 
-extern void exit_rcu(void);
+void exit_rcu(void);
 
-extern void rcu_scheduler_starting(void);
+void rcu_scheduler_starting(void);
 extern int rcu_scheduler_active __read_mostly;
 
-extern bool rcu_is_watching(void);
+bool rcu_is_watching(void);
 
 #endif /* __LINUX_RCUTREE_H */
-- 
cgit v0.10.2


From bd73a7f5cd434f5aa611c9043490911c32084270 Mon Sep 17 00:00:00 2001
From: Teodora Baluta <teobaluta@gmail.com>
Date: Mon, 11 Nov 2013 17:11:24 +0200
Subject: rcu: Remove "extern" from function declarations in kernel/rcu/rcu.h

Function prototypes don't need to have the "extern" keyword since this
is the default behavior. Its explicit use is redundant.  This commit
therefore removes them.

Signed-off-by: Teodora Baluta <teobaluta@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index a8f981a..79c3877 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -96,7 +96,7 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 }
 #endif	/* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
-extern void kfree(const void *);
+void kfree(const void *);
 
 static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
 {
-- 
cgit v0.10.2


From c506c96b61fa96c9a52ad4d25e895e45c1692650 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 11 Dec 2013 09:15:00 -0300
Subject: tools lib symbol: Start carving out symbol parsing routines from perf

Eventually this should be useful to other tools/ living utilities.

For now don't try to build any .a, just trying the minimal approach of
separating existing code into multiple .c files that can then be
included wherever they are needed, using whatever build machinery
already in place.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-pfa8i5zpf4bf9rcccryi0lt3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/symbol/kallsyms.c b/tools/lib/symbol/kallsyms.c
new file mode 100644
index 0000000..18bc271
--- /dev/null
+++ b/tools/lib/symbol/kallsyms.c
@@ -0,0 +1,58 @@
+#include "symbol/kallsyms.h"
+#include <stdio.h>
+#include <stdlib.h>
+
+int kallsyms__parse(const char *filename, void *arg,
+		    int (*process_symbol)(void *arg, const char *name,
+					  char type, u64 start))
+{
+	char *line = NULL;
+	size_t n;
+	int err = -1;
+	FILE *file = fopen(filename, "r");
+
+	if (file == NULL)
+		goto out_failure;
+
+	err = 0;
+
+	while (!feof(file)) {
+		u64 start;
+		int line_len, len;
+		char symbol_type;
+		char *symbol_name;
+
+		line_len = getline(&line, &n, file);
+		if (line_len < 0 || !line)
+			break;
+
+		line[--line_len] = '\0'; /* \n */
+
+		len = hex2u64(line, &start);
+
+		len++;
+		if (len + 2 >= line_len)
+			continue;
+
+		symbol_type = line[len];
+		len += 2;
+		symbol_name = line + len;
+		len = line_len - len;
+
+		if (len >= KSYM_NAME_LEN) {
+			err = -1;
+			break;
+		}
+
+		err = process_symbol(arg, symbol_name, symbol_type, start);
+		if (err)
+			break;
+	}
+
+	free(line);
+	fclose(file);
+	return err;
+
+out_failure:
+	return -1;
+}
diff --git a/tools/lib/symbol/kallsyms.h b/tools/lib/symbol/kallsyms.h
new file mode 100644
index 0000000..6084f5e
--- /dev/null
+++ b/tools/lib/symbol/kallsyms.h
@@ -0,0 +1,24 @@
+#ifndef __TOOLS_KALLSYMS_H_
+#define __TOOLS_KALLSYMS_H_ 1
+
+#include <elf.h>
+#include <linux/ctype.h>
+#include <linux/types.h>
+
+#ifndef KSYM_NAME_LEN
+#define KSYM_NAME_LEN 256
+#endif
+
+static inline u8 kallsyms2elf_type(char type)
+{
+	if (type == 'W')
+		return STB_WEAK;
+
+	return isupper(type) ? STB_GLOBAL : STB_LOCAL;
+}
+
+int kallsyms__parse(const char *filename, void *arg,
+		    int (*process_symbol)(void *arg, const char *name,
+					  char type, u64 start));
+
+#endif /* __TOOLS_KALLSYMS_H_ */
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 025de79..3170a7f 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -2,6 +2,8 @@ tools/perf
 tools/scripts
 tools/lib/traceevent
 tools/lib/lk
+tools/lib/symbol/kallsyms.c
+tools/lib/symbol/kallsyms.h
 include/linux/const.h
 include/linux/perf_event.h
 include/linux/rbtree.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 9a8cf37..fad6107 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -202,6 +202,7 @@ $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c
 
 LIB_FILE=$(OUTPUT)libperf.a
 
+LIB_H += ../lib/symbol/kallsyms.h
 LIB_H += ../../include/uapi/linux/perf_event.h
 LIB_H += ../../include/linux/rbtree.h
 LIB_H += ../../include/linux/list.h
@@ -312,6 +313,7 @@ LIB_OBJS += $(OUTPUT)util/evlist.o
 LIB_OBJS += $(OUTPUT)util/evsel.o
 LIB_OBJS += $(OUTPUT)util/exec_cmd.o
 LIB_OBJS += $(OUTPUT)util/help.o
+LIB_OBJS += $(OUTPUT)util/kallsyms.o
 LIB_OBJS += $(OUTPUT)util/levenshtein.o
 LIB_OBJS += $(OUTPUT)util/parse-options.o
 LIB_OBJS += $(OUTPUT)util/parse-events.o
@@ -672,6 +674,9 @@ $(OUTPUT)ui/browsers/map.o: ui/browsers/map.c $(OUTPUT)PERF-CFLAGS
 $(OUTPUT)ui/browsers/scripts.o: ui/browsers/scripts.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -DENABLE_SLFUTURE_CONST $<
 
+$(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c $(OUTPUT)PERF-CFLAGS
+	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) $<
+
 $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index c77814b..6948768 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -7,6 +7,7 @@
 #include "strlist.h"
 #include "thread.h"
 #include "thread_map.h"
+#include "symbol/kallsyms.h"
 
 static const char *perf_event__names[] = {
 	[0]					= "TOTAL",
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 751454b..c78cc84 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -9,6 +9,7 @@
 #include "strlist.h"
 #include "thread.h"
 #include <stdbool.h>
+#include <symbol/kallsyms.h>
 #include "unwind.h"
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index eed0b96..bf0ce29 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -6,6 +6,7 @@
 #include <inttypes.h>
 
 #include "symbol.h"
+#include <symbol/kallsyms.h>
 #include "debug.h"
 
 #ifndef HAVE_ELF_GETPHDRNUM_SUPPORT
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index e377c2e..61eb1cd 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -18,12 +18,9 @@
 
 #include <elf.h>
 #include <limits.h>
+#include <symbol/kallsyms.h>
 #include <sys/utsname.h>
 
-#ifndef KSYM_NAME_LEN
-#define KSYM_NAME_LEN 256
-#endif
-
 static int dso__load_kernel_sym(struct dso *dso, struct map *map,
 				symbol_filter_t filter);
 static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
@@ -446,62 +443,6 @@ size_t dso__fprintf_symbols_by_name(struct dso *dso,
 	return ret;
 }
 
-int kallsyms__parse(const char *filename, void *arg,
-		    int (*process_symbol)(void *arg, const char *name,
-					  char type, u64 start))
-{
-	char *line = NULL;
-	size_t n;
-	int err = -1;
-	FILE *file = fopen(filename, "r");
-
-	if (file == NULL)
-		goto out_failure;
-
-	err = 0;
-
-	while (!feof(file)) {
-		u64 start;
-		int line_len, len;
-		char symbol_type;
-		char *symbol_name;
-
-		line_len = getline(&line, &n, file);
-		if (line_len < 0 || !line)
-			break;
-
-		line[--line_len] = '\0'; /* \n */
-
-		len = hex2u64(line, &start);
-
-		len++;
-		if (len + 2 >= line_len)
-			continue;
-
-		symbol_type = line[len];
-		len += 2;
-		symbol_name = line + len;
-		len = line_len - len;
-
-		if (len >= KSYM_NAME_LEN) {
-			err = -1;
-			break;
-		}
-
-		err = process_symbol(arg, symbol_name,
-				     symbol_type, start);
-		if (err)
-			break;
-	}
-
-	free(line);
-	fclose(file);
-	return err;
-
-out_failure:
-	return -1;
-}
-
 int modules__parse(const char *filename, void *arg,
 		   int (*process_module)(void *arg, const char *name,
 					 u64 start))
@@ -565,14 +506,6 @@ struct process_kallsyms_args {
 	struct dso *dso;
 };
 
-static u8 kallsyms2elf_type(char type)
-{
-	if (type == 'W')
-		return STB_WEAK;
-
-	return isupper(type) ? STB_GLOBAL : STB_LOCAL;
-}
-
 bool symbol__is_idle(struct symbol *sym)
 {
 	const char * const idle_symbols[] = {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 6de9c2b..8a9d910 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -221,9 +221,6 @@ struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
 
 int filename__read_build_id(const char *filename, void *bf, size_t size);
 int sysfs__read_build_id(const char *filename, void *bf, size_t size);
-int kallsyms__parse(const char *filename, void *arg,
-		    int (*process_symbol)(void *arg, const char *name,
-					  char type, u64 start));
 int modules__parse(const char *filename, void *arg,
 		   int (*process_module)(void *arg, const char *name,
 					 u64 start));
-- 
cgit v0.10.2


From 1a47245d2f3bf6276c95cd37901b562962d6ae47 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Wed, 11 Dec 2013 14:36:23 +0200
Subject: perf tools: Add perf_event_paranoid()

Add a function to return the value of
/proc/sys/kernel/perf_event_paranoid.

This will be used to determine default values for mmap size because perf
is not subject to mmap limits when perf_event_paranoid is less than
zero.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1386765443-26966-12-git-send-email-alexander.shishkin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index af25055..2eb7378 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1191,8 +1191,7 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
 				    "Error:\t%s.\n"
 				    "Hint:\tCheck /proc/sys/kernel/perf_event_paranoid setting.", emsg);
 
-		if (filename__read_int("/proc/sys/kernel/perf_event_paranoid", &value))
-			break;
+		value = perf_event_paranoid();
 
 		printed += scnprintf(buf + printed, size - printed, "\nHint:\t");
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 4a57609..8f63dba 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -1,5 +1,6 @@
 #include "../perf.h"
 #include "util.h"
+#include "fs.h"
 #include <sys/mman.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
 #include <execinfo.h>
@@ -8,6 +9,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <errno.h>
+#include <limits.h>
 #include <linux/kernel.h>
 
 /*
@@ -496,3 +498,20 @@ const char *get_filename_for_perf_kvm(void)
 
 	return filename;
 }
+
+int perf_event_paranoid(void)
+{
+	char path[PATH_MAX];
+	const char *procfs = procfs__mountpoint();
+	int value;
+
+	if (!procfs)
+		return INT_MAX;
+
+	scnprintf(path, PATH_MAX, "%s/sys/kernel/perf_event_paranoid", procfs);
+
+	if (filename__read_int(path, &value))
+		return INT_MAX;
+
+	return value;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 0171213..1e7d413 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -321,6 +321,7 @@ void free_srcline(char *srcline);
 
 int filename__read_int(const char *filename, int *value);
 int filename__read_str(const char *filename, char **buf, size_t *sizep);
+int perf_event_paranoid(void);
 
 const char *get_filename_for_perf_kvm(void);
 #endif /* GIT_COMPAT_UTIL_H */
-- 
cgit v0.10.2


From d645c442e68d24e64c46845bc8bb5d5a0a70b249 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Wed, 11 Dec 2013 14:36:28 +0200
Subject: perf header: Allow header->data_offset to be predetermined

It will be necessary to predetermine header->data_offset to allow space
for attributes that are added later.  Consequently, do not change
header->data_offset if it is non-zero.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1386765443-26966-17-git-send-email-alexander.shishkin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 0bb830f..61c5421 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2327,7 +2327,8 @@ int perf_session__write_header(struct perf_session *session,
 		}
 	}
 
-	header->data_offset = lseek(fd, 0, SEEK_CUR);
+	if (!header->data_offset)
+		header->data_offset = lseek(fd, 0, SEEK_CUR);
 	header->feat_offset = header->data_offset + header->data_size;
 
 	if (at_exit) {
-- 
cgit v0.10.2


From c09ec622629eeb4b7877646a42852e7156363425 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Wed, 11 Dec 2013 14:36:29 +0200
Subject: perf evlist: Add can_select_event() method

Add a function to determine whether an event can be selected.

This function is needed to allow a tool to automatically select
additional events, but only if they are available.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1386765443-26966-18-git-send-email-alexander.shishkin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 649d6ea..8a04aae 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -193,4 +193,6 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md,
 	pc->data_tail = tail;
 }
 
+bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str);
+
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index c8845b1..e510453 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -177,3 +177,40 @@ int perf_record_opts__config(struct perf_record_opts *opts)
 {
 	return perf_record_opts__config_freq(opts);
 }
+
+bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
+{
+	struct perf_evlist *temp_evlist;
+	struct perf_evsel *evsel;
+	int err, fd, cpu;
+	bool ret = false;
+
+	temp_evlist = perf_evlist__new();
+	if (!temp_evlist)
+		return false;
+
+	err = parse_events(temp_evlist, str);
+	if (err)
+		goto out_delete;
+
+	evsel = perf_evlist__last(temp_evlist);
+
+	if (!evlist || cpu_map__empty(evlist->cpus)) {
+		struct cpu_map *cpus = cpu_map__new(NULL);
+
+		cpu =  cpus ? cpus->map[0] : 0;
+		cpu_map__delete(cpus);
+	} else {
+		cpu = evlist->cpus->map[0];
+	}
+
+	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, 0);
+	if (fd >= 0) {
+		close(fd);
+		ret = true;
+	}
+
+out_delete:
+	perf_evlist__delete(temp_evlist);
+	return ret;
+}
-- 
cgit v0.10.2


From 71db07b12eace6a3619335d03eaf3cbe2de131ed Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Wed, 11 Dec 2013 14:36:32 +0200
Subject: perf tools: Move mem_bswap32/64 to util.c

Move functions mem_bswap_32() and mem_bswap_64() so they can be reused.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1386765443-26966-21-git-send-email-alexander.shishkin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index e748f29..989b2e3 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -247,27 +247,6 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 	}
 }
  
-void mem_bswap_32(void *src, int byte_size)
-{
-	u32 *m = src;
-	while (byte_size > 0) {
-		*m = bswap_32(*m);
-		byte_size -= sizeof(u32);
-		++m;
-	}
-}
-
-void mem_bswap_64(void *src, int byte_size)
-{
-	u64 *m = src;
-
-	while (byte_size > 0) {
-		*m = bswap_64(*m);
-		byte_size -= sizeof(u64);
-		++m;
-	}
-}
-
 static void swap_sample_id_all(union perf_event *event, void *data)
 {
 	void *end = (void *) event + event->header.size;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 2a3955e..9c25d49 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -74,8 +74,6 @@ int perf_session__resolve_callchain(struct perf_session *session,
 
 bool perf_session__has_traces(struct perf_session *session, const char *msg);
 
-void mem_bswap_64(void *src, int byte_size);
-void mem_bswap_32(void *src, int byte_size);
 void perf_event__attr_swap(struct perf_event_attr *attr);
 
 int perf_session__create_kernel_maps(struct perf_session *session);
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 8f63dba..42ad667 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -10,6 +10,7 @@
 #include <string.h>
 #include <errno.h>
 #include <limits.h>
+#include <byteswap.h>
 #include <linux/kernel.h>
 
 /*
@@ -515,3 +516,24 @@ int perf_event_paranoid(void)
 
 	return value;
 }
+
+void mem_bswap_32(void *src, int byte_size)
+{
+	u32 *m = src;
+	while (byte_size > 0) {
+		*m = bswap_32(*m);
+		byte_size -= sizeof(u32);
+		++m;
+	}
+}
+
+void mem_bswap_64(void *src, int byte_size)
+{
+	u64 *m = src;
+
+	while (byte_size > 0) {
+		*m = bswap_64(*m);
+		byte_size -= sizeof(u64);
+		++m;
+	}
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 1e7d413..a1eea3e 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -323,5 +323,8 @@ int filename__read_int(const char *filename, int *value);
 int filename__read_str(const char *filename, char **buf, size_t *sizep);
 int perf_event_paranoid(void);
 
+void mem_bswap_64(void *src, int byte_size);
+void mem_bswap_32(void *src, int byte_size);
+
 const char *get_filename_for_perf_kvm(void);
 #endif /* GIT_COMPAT_UTIL_H */
-- 
cgit v0.10.2


From 8d00be815c05ed0f0202f606bab4e54f98fd3b30 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 10 Dec 2013 21:35:38 -0700
Subject: perf tools: Fix inverted error verification bug in thread__fork

Commit 1902efe7f for the new comm infra added the wrong check for return
code on thread__set_comm. err == 0 is normal, so don't return at that
point unless err != 0.

Signed-off-by: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/1386736538-23525-1-git-send-email-dsahern@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 49eaf1d..e394861 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -126,7 +126,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
 		if (!comm)
 			return -ENOMEM;
 		err = thread__set_comm(thread, comm, timestamp);
-		if (!err)
+		if (err)
 			return err;
 		thread->comm_set = true;
 	}
-- 
cgit v0.10.2


From a025e4f0d8a92b38539d39b495b530015296b4d9 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Wed, 11 Dec 2013 14:36:35 +0200
Subject: perf evlist: Add perf_evlist__to_front()

Add a function to move a selected event to the
front of the list.

This is needed because it is not possible
to use the PERF_EVENT_IOC_SET_OUTPUT IOCTL
from an Instruction Tracing event to a
non-Instruction Tracing event.  Thus the
Instruction Tracing event must come first.

Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1386765443-26966-24-git-send-email-alexander.shishkin@linux.intel.com
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 2eb7378..0b31cee 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1212,3 +1212,20 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
 
 	return 0;
 }
+
+void perf_evlist__to_front(struct perf_evlist *evlist,
+			   struct perf_evsel *move_evsel)
+{
+	struct perf_evsel *evsel, *n;
+	LIST_HEAD(move);
+
+	if (move_evsel == perf_evlist__first(evlist))
+		return;
+
+	list_for_each_entry_safe(evsel, n, &evlist->entries, node) {
+		if (evsel->leader == move_evsel->leader)
+			list_move_tail(&evsel->node, &move);
+	}
+
+	list_splice(&move, &evlist->entries);
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 8a04aae..9f64ede 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -194,5 +194,8 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md,
 }
 
 bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str);
+void perf_evlist__to_front(struct perf_evlist *evlist,
+			   struct perf_evsel *move_evsel);
+
 
 #endif /* __PERF_EVLIST_H */
-- 
cgit v0.10.2


From 8f2f5ada719560954174da30ce0a67261c616e39 Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <artagnon@gmail.com>
Date: Wed, 11 Dec 2013 16:04:15 +0530
Subject: perf completion: Complete 'perf kvm'

Currently, there is no way to enumerate the subcommands under 'perf
kvm', so hardcode them.

Signed-off-by: Ramkumar Ramachandra <artagnon@gmail.com>
Link: http://lkml.kernel.org/r/1386758056-24618-2-git-send-email-artagnon@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/perf-completion.sh b/tools/perf/perf-completion.sh
index 4949488..496e2ab 100644
--- a/tools/perf/perf-completion.sh
+++ b/tools/perf/perf-completion.sh
@@ -121,6 +121,10 @@ __perf_main ()
 	elif [[ $prev == "-e" && "${words[1]}" == @(record|stat|top) ]]; then
 		evts=$($cmd list --raw-dump)
 		__perfcomp_colon "$evts" "$cur"
+	# List subcommands for 'perf kvm'
+	elif [[ $prev == "kvm" ]]; then
+		subcmds="top record report diff buildid-list stat"
+		__perfcomp_colon "$subcmds" "$cur"
 	# List long option names
 	elif [[ $cur == --* ]];  then
 		subcmd=${words[1]}
-- 
cgit v0.10.2


From 9451a2fd78c785445afe0f6966b2043c3ee187ca Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 12 Dec 2013 16:36:04 +0900
Subject: tools lib traceevent: Get rid of malloc_or_die() in show_error()

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386833777-3790-2-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index ab402fb..d4b0bac 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -56,7 +56,21 @@ static void show_error(char **error_str, const char *fmt, ...)
 	index = pevent_get_input_buf_ptr();
 	len = input ? strlen(input) : 0;
 
-	error = malloc_or_die(MAX_ERR_STR_SIZE + (len*2) + 3);
+	error = malloc(MAX_ERR_STR_SIZE + (len*2) + 3);
+	if (error == NULL) {
+		/*
+		 * Maybe it's due to len is too long.
+		 * Retry without the input buffer part.
+		 */
+		len = 0;
+
+		error = malloc(MAX_ERR_STR_SIZE);
+		if (error == NULL) {
+			/* no memory */
+			*error_str = NULL;
+			return;
+		}
+	}
 
 	if (len) {
 		strcpy(error, input);
-- 
cgit v0.10.2


From ef3072cd1d5c2ea229f7abf8d6475e0c200eeb71 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 12 Dec 2013 16:36:05 +0900
Subject: tools lib traceevent: Get rid of die in add_filter_type()

The realloc() should check return value and not to overwrite previous
pointer in case of error.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386833777-3790-3-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index d4b0bac..767de4f 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -161,11 +161,13 @@ add_filter_type(struct event_filter *filter, int id)
 	if (filter_type)
 		return filter_type;
 
-	filter->event_filters =	realloc(filter->event_filters,
-					sizeof(*filter->event_filters) *
-					(filter->filters + 1));
-	if (!filter->event_filters)
-		die("Could not allocate filter");
+	filter_type = realloc(filter->event_filters,
+			      sizeof(*filter->event_filters) *
+			      (filter->filters + 1));
+	if (!filter_type)
+		return NULL;
+
+	filter->event_filters = filter_type;
 
 	for (i = 0; i < filter->filters; i++) {
 		if (filter->event_filters[i].event_id > id)
@@ -1180,6 +1182,12 @@ static int filter_event(struct event_filter *filter,
 	}
 
 	filter_type = add_filter_type(filter, event->id);
+	if (filter_type == NULL) {
+		show_error(error_str, "failed to add a new filter: %s",
+			   filter_str ? filter_str : "true");
+		return -1;
+	}
+
 	if (filter_type->filter)
 		free_arg(filter_type->filter);
 	filter_type->filter = arg;
@@ -1417,6 +1425,9 @@ static int copy_filter_type(struct event_filter *filter,
 			arg->boolean.value = 0;
 
 		filter_type = add_filter_type(filter, event->id);
+		if (filter_type == NULL)
+			return -1;
+
 		filter_type->filter = arg;
 
 		free(str);
-- 
cgit v0.10.2


From 2e4eb10d7e59df71ab649343b3f1bff9259da15d Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 12 Dec 2013 16:36:06 +0900
Subject: tools lib traceevent: Get rid of malloc_or_die() allocate_arg()

Also check return value and handle it.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386833777-3790-4-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 767de4f..ab9cefe 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -211,12 +211,7 @@ struct event_filter *pevent_filter_alloc(struct pevent *pevent)
 
 static struct filter_arg *allocate_arg(void)
 {
-	struct filter_arg *arg;
-
-	arg = malloc_or_die(sizeof(*arg));
-	memset(arg, 0, sizeof(*arg));
-
-	return arg;
+	return calloc(1, sizeof(struct filter_arg));
 }
 
 static void free_arg(struct filter_arg *arg)
@@ -369,6 +364,10 @@ create_arg_item(struct event_format *event, const char *token,
 	struct filter_arg *arg;
 
 	arg = allocate_arg();
+	if (arg == NULL) {
+		show_error(error_str, "failed to allocate filter arg");
+		return NULL;
+	}
 
 	switch (type) {
 
@@ -422,6 +421,9 @@ create_arg_op(enum filter_op_type btype)
 	struct filter_arg *arg;
 
 	arg = allocate_arg();
+	if (!arg)
+		return NULL;
+
 	arg->type = FILTER_ARG_OP;
 	arg->op.type = btype;
 
@@ -434,6 +436,9 @@ create_arg_exp(enum filter_exp_type etype)
 	struct filter_arg *arg;
 
 	arg = allocate_arg();
+	if (!arg)
+		return NULL;
+
 	arg->type = FILTER_ARG_EXP;
 	arg->op.type = etype;
 
@@ -446,6 +451,9 @@ create_arg_cmp(enum filter_exp_type etype)
 	struct filter_arg *arg;
 
 	arg = allocate_arg();
+	if (!arg)
+		return NULL;
+
 	/* Use NUM and change if necessary */
 	arg->type = FILTER_ARG_NUM;
 	arg->op.type = etype;
@@ -909,8 +917,10 @@ static struct filter_arg *collapse_tree(struct filter_arg *arg)
 	case FILTER_VAL_FALSE:
 		free_arg(arg);
 		arg = allocate_arg();
-		arg->type = FILTER_ARG_BOOLEAN;
-		arg->boolean.value = ret == FILTER_VAL_TRUE;
+		if (arg) {
+			arg->type = FILTER_ARG_BOOLEAN;
+			arg->boolean.value = ret == FILTER_VAL_TRUE;
+		}
 	}
 
 	return arg;
@@ -1057,6 +1067,8 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 			switch (op_type) {
 			case OP_BOOL:
 				arg = create_arg_op(btype);
+				if (arg == NULL)
+					goto fail_alloc;
 				if (current_op)
 					ret = add_left(arg, current_op);
 				else
@@ -1067,6 +1079,8 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 
 			case OP_NOT:
 				arg = create_arg_op(btype);
+				if (arg == NULL)
+					goto fail_alloc;
 				if (current_op)
 					ret = add_right(current_op, arg, error_str);
 				if (ret < 0)
@@ -1086,6 +1100,8 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 					arg = create_arg_exp(etype);
 				else
 					arg = create_arg_cmp(ctype);
+				if (arg == NULL)
+					goto fail_alloc;
 
 				if (current_op)
 					ret = add_right(current_op, arg, error_str);
@@ -1119,11 +1135,16 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 		current_op = current_exp;
 
 	current_op = collapse_tree(current_op);
+	if (current_op == NULL)
+		goto fail_alloc;
 
 	*parg = current_op;
 
 	return 0;
 
+ fail_alloc:
+	show_error(error_str, "failed to allocate filter arg");
+	goto fail;
  fail_print:
 	show_error(error_str, "Syntax error");
  fail:
@@ -1154,6 +1175,10 @@ process_event(struct event_format *event, const char *filter_str,
 	/* If parg is NULL, then make it into FALSE */
 	if (!*parg) {
 		*parg = allocate_arg();
+		if (*parg == NULL) {
+			show_error(error_str, "failed to allocate filter arg");
+			return -1;
+		}
 		(*parg)->type = FILTER_ARG_BOOLEAN;
 		(*parg)->boolean.value = FILTER_FALSE;
 	}
@@ -1177,6 +1202,10 @@ static int filter_event(struct event_filter *filter,
 	} else {
 		/* just add a TRUE arg */
 		arg = allocate_arg();
+		if (arg == NULL) {
+			show_error(error_str, "failed to allocate filter arg");
+			return -1;
+		}
 		arg->type = FILTER_ARG_BOOLEAN;
 		arg->boolean.value = FILTER_TRUE;
 	}
@@ -1418,6 +1447,9 @@ static int copy_filter_type(struct event_filter *filter,
 	if (strcmp(str, "TRUE") == 0 || strcmp(str, "FALSE") == 0) {
 		/* Add trivial event */
 		arg = allocate_arg();
+		if (arg == NULL)
+			return -1;
+
 		arg->type = FILTER_ARG_BOOLEAN;
 		if (strcmp(str, "TRUE") == 0)
 			arg->boolean.value = 1;
-- 
cgit v0.10.2


From 91dfa49bdd8ef9600d850ef68ec892eb70824e3d Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 12 Dec 2013 16:36:07 +0900
Subject: tools lib traceevent: Get rid of malloc_or_die() in read_token()

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386833777-3790-5-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index ab9cefe..246ee81 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -109,7 +109,11 @@ static enum event_type read_token(char **tok)
 	    (strcmp(token, "=") == 0 || strcmp(token, "!") == 0) &&
 	    pevent_peek_char() == '~') {
 		/* append it */
-		*tok = malloc_or_die(3);
+		*tok = malloc(3);
+		if (*tok == NULL) {
+			free_token(token);
+			return EVENT_ERROR;
+		}
 		sprintf(*tok, "%c%c", *token, '~');
 		free_token(token);
 		/* Now remove the '~' from the buffer */
@@ -1123,6 +1127,8 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 			break;
 		case EVENT_NONE:
 			break;
+		case EVENT_ERROR:
+			goto fail_alloc;
 		default:
 			goto fail_print;
 		}
-- 
cgit v0.10.2


From 605b8fda958a578e0a50ed1df3cac5a12f1fe8dc Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 12 Dec 2013 16:36:08 +0900
Subject: tools lib traceevent: Get rid of malloc_or_die() in find_event()

Make it return pevent_errno to distinguish malloc allocation failure.
Since it'll be returned to user later, add more error code.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386833777-3790-6-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 6e23f19..abdfd3c 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -356,7 +356,9 @@ enum pevent_flag {
 	_PE(READ_FORMAT_FAILED,	"failed to read event format"),		      \
 	_PE(READ_PRINT_FAILED,	"failed to read event print fmt"), 	      \
 	_PE(OLD_FTRACE_ARG_FAILED,"failed to allocate field name for ftrace"),\
-	_PE(INVALID_ARG_TYPE,	"invalid argument type")
+	_PE(INVALID_ARG_TYPE,	"invalid argument type"),		      \
+	_PE(INVALID_EVENT_NAME,	"invalid event name"),			      \
+	_PE(EVENT_NOT_FOUND,	"No event found")
 
 #undef _PE
 #define _PE(__code, __str) PEVENT_ERRNO__ ## __code
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 246ee81..a0ab040 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -287,7 +287,7 @@ static int event_match(struct event_format *event,
 		!regexec(ereg, event->name, 0, NULL, 0);
 }
 
-static int
+static enum pevent_errno
 find_event(struct pevent *pevent, struct event_list **events,
 	   char *sys_name, char *event_name)
 {
@@ -306,23 +306,31 @@ find_event(struct pevent *pevent, struct event_list **events,
 		sys_name = NULL;
 	}
 
-	reg = malloc_or_die(strlen(event_name) + 3);
+	reg = malloc(strlen(event_name) + 3);
+	if (reg == NULL)
+		return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+
 	sprintf(reg, "^%s$", event_name);
 
 	ret = regcomp(&ereg, reg, REG_ICASE|REG_NOSUB);
 	free(reg);
 
 	if (ret)
-		return -1;
+		return PEVENT_ERRNO__INVALID_EVENT_NAME;
 
 	if (sys_name) {
-		reg = malloc_or_die(strlen(sys_name) + 3);
+		reg = malloc(strlen(sys_name) + 3);
+		if (reg == NULL) {
+			regfree(&ereg);
+			return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+		}
+
 		sprintf(reg, "^%s$", sys_name);
 		ret = regcomp(&sreg, reg, REG_ICASE|REG_NOSUB);
 		free(reg);
 		if (ret) {
 			regfree(&ereg);
-			return -1;
+			return PEVENT_ERRNO__INVALID_EVENT_NAME;
 		}
 	}
 
@@ -342,9 +350,9 @@ find_event(struct pevent *pevent, struct event_list **events,
 		regfree(&sreg);
 
 	if (!match)
-		return -1;
+		return PEVENT_ERRNO__EVENT_NOT_FOUND;
 	if (fail)
-		return -2;
+		return PEVENT_ERRNO__MEM_ALLOC_FAILED;
 
 	return 0;
 }
@@ -1312,7 +1320,10 @@ int pevent_filter_add_filter_str(struct event_filter *filter,
 		/* Find this event */
 		ret = find_event(pevent, &events, strim(sys_name), strim(event_name));
 		if (ret < 0) {
-			if (event_name)
+			if (ret == PEVENT_ERRNO__MEM_ALLOC_FAILED)
+				show_error(error_str,
+					   "Memory allocation failure");
+			else if (event_name)
 				show_error(error_str,
 					   "No event found under '%s.%s'",
 					   sys_name, event_name);
-- 
cgit v0.10.2


From 02d62d6d17b9b718be2878477cdcae95df0d5b4e Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 12 Dec 2013 16:36:09 +0900
Subject: tools lib traceevent: Get rid of die() in add_right()

Refactor it to return appropriate pevent_errno value.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386833777-3790-7-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index abdfd3c..89e4dfd4 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -358,7 +358,13 @@ enum pevent_flag {
 	_PE(OLD_FTRACE_ARG_FAILED,"failed to allocate field name for ftrace"),\
 	_PE(INVALID_ARG_TYPE,	"invalid argument type"),		      \
 	_PE(INVALID_EVENT_NAME,	"invalid event name"),			      \
-	_PE(EVENT_NOT_FOUND,	"No event found")
+	_PE(EVENT_NOT_FOUND,	"no event found"),			      \
+	_PE(SYNTAX_ERROR,	"syntax error"),			      \
+	_PE(ILLEGAL_RVALUE,	"illegal rvalue"),			      \
+	_PE(ILLEGAL_LVALUE,	"illegal lvalue for string comparison"),      \
+	_PE(INVALID_REGEX,	"regex did not compute"),		      \
+	_PE(ILLEGAL_STRING_CMP,	"illegal comparison for string"), 	      \
+	_PE(ILLEGAL_INTEGER_CMP,"illegal comparison for integer")
 
 #undef _PE
 #define _PE(__code, __str) PEVENT_ERRNO__ ## __code
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index a0ab040..c08ce59 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -473,8 +473,8 @@ create_arg_cmp(enum filter_exp_type etype)
 	return arg;
 }
 
-static int add_right(struct filter_arg *op, struct filter_arg *arg,
-		     char **error_str)
+static enum pevent_errno
+add_right(struct filter_arg *op, struct filter_arg *arg, char **error_str)
 {
 	struct filter_arg *left;
 	char *str;
@@ -505,9 +505,8 @@ static int add_right(struct filter_arg *op, struct filter_arg *arg,
 		case FILTER_ARG_FIELD:
 			break;
 		default:
-			show_error(error_str,
-				   "Illegal rvalue");
-			return -1;
+			show_error(error_str, "Illegal rvalue");
+			return PEVENT_ERRNO__ILLEGAL_RVALUE;
 		}
 
 		/*
@@ -554,7 +553,7 @@ static int add_right(struct filter_arg *op, struct filter_arg *arg,
 			if (left->type != FILTER_ARG_FIELD) {
 				show_error(error_str,
 					   "Illegal lvalue for string comparison");
-				return -1;
+				return PEVENT_ERRNO__ILLEGAL_LVALUE;
 			}
 
 			/* Make sure this is a valid string compare */
@@ -573,25 +572,31 @@ static int add_right(struct filter_arg *op, struct filter_arg *arg,
 					show_error(error_str,
 						   "RegEx '%s' did not compute",
 						   str);
-					return -1;
+					return PEVENT_ERRNO__INVALID_REGEX;
 				}
 				break;
 			default:
 				show_error(error_str,
 					   "Illegal comparison for string");
-				return -1;
+				return PEVENT_ERRNO__ILLEGAL_STRING_CMP;
 			}
 
 			op->type = FILTER_ARG_STR;
 			op->str.type = op_type;
 			op->str.field = left->field.field;
 			op->str.val = strdup(str);
-			if (!op->str.val)
-				die("malloc string");
+			if (!op->str.val) {
+				show_error(error_str, "Failed to allocate string filter");
+				return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+			}
 			/*
 			 * Need a buffer to copy data for tests
 			 */
-			op->str.buffer = malloc_or_die(op->str.field->size + 1);
+			op->str.buffer = malloc(op->str.field->size + 1);
+			if (!op->str.buffer) {
+				show_error(error_str, "Failed to allocate string filter");
+				return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+			}
 			/* Null terminate this buffer */
 			op->str.buffer[op->str.field->size] = 0;
 
@@ -609,7 +614,7 @@ static int add_right(struct filter_arg *op, struct filter_arg *arg,
 			case FILTER_CMP_NOT_REGEX:
 				show_error(error_str,
 					   "Op not allowed with integers");
-				return -1;
+				return PEVENT_ERRNO__ILLEGAL_INTEGER_CMP;
 
 			default:
 				break;
@@ -629,9 +634,8 @@ static int add_right(struct filter_arg *op, struct filter_arg *arg,
 	return 0;
 
  out_fail:
-	show_error(error_str,
-		   "Syntax error");
-	return -1;
+	show_error(error_str, "Syntax error");
+	return PEVENT_ERRNO__SYNTAX_ERROR;
 }
 
 static struct filter_arg *
-- 
cgit v0.10.2


From ff533fc058975579dffbb62a731f63911ae714be Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung.kim@lge.com>
Date: Thu, 12 Dec 2013 16:36:10 +0900
Subject: tools lib traceevent: Make add_left() return pevent_errno

So that it can propagate error properly.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386833777-3790-8-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index c08ce59..774c3e4 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -648,7 +648,7 @@ rotate_op_right(struct filter_arg *a, struct filter_arg *b)
 	return arg;
 }
 
-static int add_left(struct filter_arg *op, struct filter_arg *arg)
+static enum pevent_errno add_left(struct filter_arg *op, struct filter_arg *arg)
 {
 	switch (op->type) {
 	case FILTER_ARG_EXP:
@@ -667,11 +667,11 @@ static int add_left(struct filter_arg *op, struct filter_arg *arg)
 		/* left arg of compares must be a field */
 		if (arg->type != FILTER_ARG_FIELD &&
 		    arg->type != FILTER_ARG_BOOLEAN)
-			return -1;
+			return PEVENT_ERRNO__INVALID_ARG_TYPE;
 		op->num.left = arg;
 		break;
 	default:
-		return -1;
+		return PEVENT_ERRNO__INVALID_ARG_TYPE;
 	}
 	return 0;
 }
-- 
cgit v0.10.2


From 7bb73553e2490ac6667387ee723e0faa61e9d999 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 12 Dec 2013 16:36:11 +0900
Subject: tools lib traceevent: Get rid of die() in reparent_op_arg()

To do that, make the function returns the error code.  Also pass
error_str so that it can set proper error message when error occurred.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386833777-3790-9-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 89e4dfd4..5e4392d 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -364,7 +364,10 @@ enum pevent_flag {
 	_PE(ILLEGAL_LVALUE,	"illegal lvalue for string comparison"),      \
 	_PE(INVALID_REGEX,	"regex did not compute"),		      \
 	_PE(ILLEGAL_STRING_CMP,	"illegal comparison for string"), 	      \
-	_PE(ILLEGAL_INTEGER_CMP,"illegal comparison for integer")
+	_PE(ILLEGAL_INTEGER_CMP,"illegal comparison for integer"), 	      \
+	_PE(REPARENT_NOT_OP,	"cannot reparent other than OP"),	      \
+	_PE(REPARENT_FAILED,	"failed to reparent filter OP"),	      \
+	_PE(BAD_FILTER_ARG,	"bad arg in filter tree")
 
 #undef _PE
 #define _PE(__code, __str) PEVENT_ERRNO__ ## __code
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 774c3e4..9b05892 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -784,15 +784,18 @@ enum filter_vals {
 	FILTER_VAL_TRUE,
 };
 
-void reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
-		  struct filter_arg *arg)
+static enum pevent_errno
+reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
+		struct filter_arg *arg, char **error_str)
 {
 	struct filter_arg *other_child;
 	struct filter_arg **ptr;
 
 	if (parent->type != FILTER_ARG_OP &&
-	    arg->type != FILTER_ARG_OP)
-		die("can not reparent other than OP");
+	    arg->type != FILTER_ARG_OP) {
+		show_error(error_str, "can not reparent other than OP");
+		return PEVENT_ERRNO__REPARENT_NOT_OP;
+	}
 
 	/* Get the sibling */
 	if (old_child->op.right == arg) {
@@ -801,8 +804,10 @@ void reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
 	} else if (old_child->op.left == arg) {
 		ptr = &old_child->op.left;
 		other_child = old_child->op.right;
-	} else
-		die("Error in reparent op, find other child");
+	} else {
+		show_error(error_str, "Error in reparent op, find other child");
+		return PEVENT_ERRNO__REPARENT_FAILED;
+	}
 
 	/* Detach arg from old_child */
 	*ptr = NULL;
@@ -813,23 +818,29 @@ void reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
 		*parent = *arg;
 		/* Free arg without recussion */
 		free(arg);
-		return;
+		return 0;
 	}
 
 	if (parent->op.right == old_child)
 		ptr = &parent->op.right;
 	else if (parent->op.left == old_child)
 		ptr = &parent->op.left;
-	else
-		die("Error in reparent op");
+	else {
+		show_error(error_str, "Error in reparent op");
+		return PEVENT_ERRNO__REPARENT_FAILED;
+	}
+
 	*ptr = arg;
 
 	free_arg(old_child);
+	return 0;
 }
 
-enum filter_vals test_arg(struct filter_arg *parent, struct filter_arg *arg)
+/* Returns either filter_vals (success) or pevent_errno (failfure) */
+static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
+		    char **error_str)
 {
-	enum filter_vals lval, rval;
+	int lval, rval;
 
 	switch (arg->type) {
 
@@ -844,63 +855,68 @@ enum filter_vals test_arg(struct filter_arg *parent, struct filter_arg *arg)
 		return FILTER_VAL_NORM;
 
 	case FILTER_ARG_EXP:
-		lval = test_arg(arg, arg->exp.left);
+		lval = test_arg(arg, arg->exp.left, error_str);
 		if (lval != FILTER_VAL_NORM)
 			return lval;
-		rval = test_arg(arg, arg->exp.right);
+		rval = test_arg(arg, arg->exp.right, error_str);
 		if (rval != FILTER_VAL_NORM)
 			return rval;
 		return FILTER_VAL_NORM;
 
 	case FILTER_ARG_NUM:
-		lval = test_arg(arg, arg->num.left);
+		lval = test_arg(arg, arg->num.left, error_str);
 		if (lval != FILTER_VAL_NORM)
 			return lval;
-		rval = test_arg(arg, arg->num.right);
+		rval = test_arg(arg, arg->num.right, error_str);
 		if (rval != FILTER_VAL_NORM)
 			return rval;
 		return FILTER_VAL_NORM;
 
 	case FILTER_ARG_OP:
 		if (arg->op.type != FILTER_OP_NOT) {
-			lval = test_arg(arg, arg->op.left);
+			lval = test_arg(arg, arg->op.left, error_str);
 			switch (lval) {
 			case FILTER_VAL_NORM:
 				break;
 			case FILTER_VAL_TRUE:
 				if (arg->op.type == FILTER_OP_OR)
 					return FILTER_VAL_TRUE;
-				rval = test_arg(arg, arg->op.right);
+				rval = test_arg(arg, arg->op.right, error_str);
 				if (rval != FILTER_VAL_NORM)
 					return rval;
 
-				reparent_op_arg(parent, arg, arg->op.right);
-				return FILTER_VAL_NORM;
+				return reparent_op_arg(parent, arg, arg->op.right,
+						       error_str);
 
 			case FILTER_VAL_FALSE:
 				if (arg->op.type == FILTER_OP_AND)
 					return FILTER_VAL_FALSE;
-				rval = test_arg(arg, arg->op.right);
+				rval = test_arg(arg, arg->op.right, error_str);
 				if (rval != FILTER_VAL_NORM)
 					return rval;
 
-				reparent_op_arg(parent, arg, arg->op.right);
-				return FILTER_VAL_NORM;
+				return reparent_op_arg(parent, arg, arg->op.right,
+						       error_str);
+
+			default:
+				return lval;
 			}
 		}
 
-		rval = test_arg(arg, arg->op.right);
+		rval = test_arg(arg, arg->op.right, error_str);
 		switch (rval) {
 		case FILTER_VAL_NORM:
+		default:
 			break;
+
 		case FILTER_VAL_TRUE:
 			if (arg->op.type == FILTER_OP_OR)
 				return FILTER_VAL_TRUE;
 			if (arg->op.type == FILTER_OP_NOT)
 				return FILTER_VAL_FALSE;
 
-			reparent_op_arg(parent, arg, arg->op.left);
-			return FILTER_VAL_NORM;
+			return reparent_op_arg(parent, arg, arg->op.left,
+					       error_str);
 
 		case FILTER_VAL_FALSE:
 			if (arg->op.type == FILTER_OP_AND)
@@ -908,26 +924,27 @@ enum filter_vals test_arg(struct filter_arg *parent, struct filter_arg *arg)
 			if (arg->op.type == FILTER_OP_NOT)
 				return FILTER_VAL_TRUE;
 
-			reparent_op_arg(parent, arg, arg->op.left);
-			return FILTER_VAL_NORM;
+			return reparent_op_arg(parent, arg, arg->op.left,
+					       error_str);
 		}
 
-		return FILTER_VAL_NORM;
+		return rval;
 	default:
-		die("bad arg in filter tree");
+		show_error(error_str, "bad arg in filter tree");
+		return PEVENT_ERRNO__BAD_FILTER_ARG;
 	}
 	return FILTER_VAL_NORM;
 }
 
 /* Remove any unknown event fields */
-static struct filter_arg *collapse_tree(struct filter_arg *arg)
+static struct filter_arg *collapse_tree(struct filter_arg *arg, char **error_str)
 {
 	enum filter_vals ret;
 
-	ret = test_arg(arg, arg);
+	ret = test_arg(arg, arg, error_str);
 	switch (ret) {
 	case FILTER_VAL_NORM:
-		return arg;
+		break;
 
 	case FILTER_VAL_TRUE:
 	case FILTER_VAL_FALSE:
@@ -936,7 +953,16 @@ static struct filter_arg *collapse_tree(struct filter_arg *arg)
 		if (arg) {
 			arg->type = FILTER_ARG_BOOLEAN;
 			arg->boolean.value = ret == FILTER_VAL_TRUE;
+		} else {
+			show_error(error_str, "Failed to allocate filter arg");
 		}
+		break;
+
+	default:
+		/* test_arg() already set the error_str */
+		free_arg(arg);
+		arg = NULL;
+		break;
 	}
 
 	return arg;
@@ -1152,9 +1178,9 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 	if (!current_op)
 		current_op = current_exp;
 
-	current_op = collapse_tree(current_op);
+	current_op = collapse_tree(current_op, error_str);
 	if (current_op == NULL)
-		goto fail_alloc;
+		goto fail;
 
 	*parg = current_op;
 
-- 
cgit v0.10.2


From c8ea690dd0d1385a766d68c51832497181e013b8 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung.kim@lge.com>
Date: Thu, 12 Dec 2013 16:36:12 +0900
Subject: tools lib traceevent: Refactor create_arg_item()

So that it can return a proper pevent_errno value.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386833777-3790-10-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 5e4392d..57b66ae 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -367,7 +367,8 @@ enum pevent_flag {
 	_PE(ILLEGAL_INTEGER_CMP,"illegal comparison for integer"), 	      \
 	_PE(REPARENT_NOT_OP,	"cannot reparent other than OP"),	      \
 	_PE(REPARENT_FAILED,	"failed to reparent filter OP"),	      \
-	_PE(BAD_FILTER_ARG,	"bad arg in filter tree")
+	_PE(BAD_FILTER_ARG,	"bad arg in filter tree"),		      \
+	_PE(UNEXPECTED_TYPE,	"unexpected type (not a value)")
 
 #undef _PE
 #define _PE(__code, __str) PEVENT_ERRNO__ ## __code
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 9b05892..8d71208 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -368,9 +368,9 @@ static void free_events(struct event_list *events)
 	}
 }
 
-static struct filter_arg *
+static enum pevent_errno
 create_arg_item(struct event_format *event, const char *token,
-		enum event_type type, char **error_str)
+		enum event_type type, struct filter_arg **parg, char **error_str)
 {
 	struct format_field *field;
 	struct filter_arg *arg;
@@ -378,7 +378,7 @@ create_arg_item(struct event_format *event, const char *token,
 	arg = allocate_arg();
 	if (arg == NULL) {
 		show_error(error_str, "failed to allocate filter arg");
-		return NULL;
+		return PEVENT_ERRNO__MEM_ALLOC_FAILED;
 	}
 
 	switch (type) {
@@ -392,7 +392,7 @@ create_arg_item(struct event_format *event, const char *token,
 		if (!arg->value.str) {
 			free_arg(arg);
 			show_error(error_str, "failed to allocate string filter arg");
-			return NULL;
+			return PEVENT_ERRNO__MEM_ALLOC_FAILED;
 		}
 		break;
 	case EVENT_ITEM:
@@ -420,11 +420,11 @@ create_arg_item(struct event_format *event, const char *token,
 		break;
 	default:
 		free_arg(arg);
-		show_error(error_str, "expected a value but found %s",
-			   token);
-		return NULL;
+		show_error(error_str, "expected a value but found %s", token);
+		return PEVENT_ERRNO__UNEXPECTED_TYPE;
 	}
-	return arg;
+	*parg = arg;
+	return 0;
 }
 
 static struct filter_arg *
@@ -993,8 +993,8 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 		case EVENT_SQUOTE:
 		case EVENT_DQUOTE:
 		case EVENT_ITEM:
-			arg = create_arg_item(event, token, type, error_str);
-			if (!arg)
+			ret = create_arg_item(event, token, type, &arg, error_str);
+			if (ret < 0)
 				goto fail;
 			if (!left_item)
 				left_item = arg;
-- 
cgit v0.10.2


From 42d6194d133cbaf12f34cbdc4111bd8f7dc0ed2a Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung.kim@lge.com>
Date: Thu, 12 Dec 2013 16:36:13 +0900
Subject: tools lib traceevent: Refactor process_filter()

So that it can return a proper pevent_errno value.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386833777-3790-11-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 57b66ae..da942d5 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -368,7 +368,11 @@ enum pevent_flag {
 	_PE(REPARENT_NOT_OP,	"cannot reparent other than OP"),	      \
 	_PE(REPARENT_FAILED,	"failed to reparent filter OP"),	      \
 	_PE(BAD_FILTER_ARG,	"bad arg in filter tree"),		      \
-	_PE(UNEXPECTED_TYPE,	"unexpected type (not a value)")
+	_PE(UNEXPECTED_TYPE,	"unexpected type (not a value)"),	      \
+	_PE(ILLEGAL_TOKEN,	"illegal token"),			      \
+	_PE(INVALID_PAREN,	"open parenthesis cannot come here"), 	      \
+	_PE(UNBALANCED_PAREN,	"unbalanced number of parenthesis"),	      \
+	_PE(UNKNOWN_TOKEN,	"unknown token")
 
 #undef _PE
 #define _PE(__code, __str) PEVENT_ERRNO__ ## __code
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 8d71208..5aa5012 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -937,9 +937,10 @@ static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
 }
 
 /* Remove any unknown event fields */
-static struct filter_arg *collapse_tree(struct filter_arg *arg, char **error_str)
+static int collapse_tree(struct filter_arg *arg,
+			 struct filter_arg **arg_collapsed, char **error_str)
 {
-	enum filter_vals ret;
+	int ret;
 
 	ret = test_arg(arg, arg, error_str);
 	switch (ret) {
@@ -955,6 +956,7 @@ static struct filter_arg *collapse_tree(struct filter_arg *arg, char **error_str
 			arg->boolean.value = ret == FILTER_VAL_TRUE;
 		} else {
 			show_error(error_str, "Failed to allocate filter arg");
+			ret = PEVENT_ERRNO__MEM_ALLOC_FAILED;
 		}
 		break;
 
@@ -965,10 +967,11 @@ static struct filter_arg *collapse_tree(struct filter_arg *arg, char **error_str
 		break;
 	}
 
-	return arg;
+	*arg_collapsed = arg;
+	return ret;
 }
 
-static int
+static enum pevent_errno
 process_filter(struct event_format *event, struct filter_arg **parg,
 	       char **error_str, int not)
 {
@@ -982,7 +985,7 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 	enum filter_op_type btype;
 	enum filter_exp_type etype;
 	enum filter_cmp_type ctype;
-	int ret;
+	enum pevent_errno ret;
 
 	*parg = NULL;
 
@@ -1007,20 +1010,20 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 				if (not) {
 					arg = NULL;
 					if (current_op)
-						goto fail_print;
+						goto fail_syntax;
 					free(token);
 					*parg = current_exp;
 					return 0;
 				}
 			} else
-				goto fail_print;
+				goto fail_syntax;
 			arg = NULL;
 			break;
 
 		case EVENT_DELIM:
 			if (*token == ',') {
-				show_error(error_str,
-					   "Illegal token ','");
+				show_error(error_str, "Illegal token ','");
+				ret = PEVENT_ERRNO__ILLEGAL_TOKEN;
 				goto fail;
 			}
 
@@ -1028,19 +1031,23 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 				if (left_item) {
 					show_error(error_str,
 						   "Open paren can not come after item");
+					ret = PEVENT_ERRNO__INVALID_PAREN;
 					goto fail;
 				}
 				if (current_exp) {
 					show_error(error_str,
 						   "Open paren can not come after expression");
+					ret = PEVENT_ERRNO__INVALID_PAREN;
 					goto fail;
 				}
 
 				ret = process_filter(event, &arg, error_str, 0);
-				if (ret != 1) {
-					if (ret == 0)
+				if (ret != PEVENT_ERRNO__UNBALANCED_PAREN) {
+					if (ret == 0) {
 						show_error(error_str,
 							   "Unbalanced number of '('");
+						ret = PEVENT_ERRNO__UNBALANCED_PAREN;
+					}
 					goto fail;
 				}
 				ret = 0;
@@ -1048,7 +1055,7 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 				/* A not wants just one expression */
 				if (not) {
 					if (current_op)
-						goto fail_print;
+						goto fail_syntax;
 					*parg = arg;
 					return 0;
 				}
@@ -1063,19 +1070,19 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 
 			} else { /* ')' */
 				if (!current_op && !current_exp)
-					goto fail_print;
+					goto fail_syntax;
 
 				/* Make sure everything is finished at this level */
 				if (current_exp && !check_op_done(current_exp))
-					goto fail_print;
+					goto fail_syntax;
 				if (current_op && !check_op_done(current_op))
-					goto fail_print;
+					goto fail_syntax;
 
 				if (current_op)
 					*parg = current_op;
 				else
 					*parg = current_exp;
-				return 1;
+				return PEVENT_ERRNO__UNBALANCED_PAREN;
 			}
 			break;
 
@@ -1087,21 +1094,22 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 			case OP_BOOL:
 				/* Logic ops need a left expression */
 				if (!current_exp && !current_op)
-					goto fail_print;
+					goto fail_syntax;
 				/* fall through */
 			case OP_NOT:
 				/* logic only processes ops and exp */
 				if (left_item)
-					goto fail_print;
+					goto fail_syntax;
 				break;
 			case OP_EXP:
 			case OP_CMP:
 				if (!left_item)
-					goto fail_print;
+					goto fail_syntax;
 				break;
 			case OP_NONE:
 				show_error(error_str,
 					   "Unknown op token %s", token);
+				ret = PEVENT_ERRNO__UNKNOWN_TOKEN;
 				goto fail;
 			}
 
@@ -1152,7 +1160,7 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 				ret = add_left(arg, left_item);
 				if (ret < 0) {
 					arg = NULL;
-					goto fail_print;
+					goto fail_syntax;
 				}
 				current_exp = arg;
 				break;
@@ -1161,25 +1169,25 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 			}
 			arg = NULL;
 			if (ret < 0)
-				goto fail_print;
+				goto fail_syntax;
 			break;
 		case EVENT_NONE:
 			break;
 		case EVENT_ERROR:
 			goto fail_alloc;
 		default:
-			goto fail_print;
+			goto fail_syntax;
 		}
 	} while (type != EVENT_NONE);
 
 	if (!current_op && !current_exp)
-		goto fail_print;
+		goto fail_syntax;
 
 	if (!current_op)
 		current_op = current_exp;
 
-	current_op = collapse_tree(current_op, error_str);
-	if (current_op == NULL)
+	ret = collapse_tree(current_op, parg, error_str);
+	if (ret < 0)
 		goto fail;
 
 	*parg = current_op;
@@ -1188,15 +1196,17 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 
  fail_alloc:
 	show_error(error_str, "failed to allocate filter arg");
+	ret = PEVENT_ERRNO__MEM_ALLOC_FAILED;
 	goto fail;
- fail_print:
+ fail_syntax:
 	show_error(error_str, "Syntax error");
+	ret = PEVENT_ERRNO__SYNTAX_ERROR;
  fail:
 	free_arg(current_op);
 	free_arg(current_exp);
 	free_arg(arg);
 	free(token);
-	return -1;
+	return ret;
 }
 
 static int
-- 
cgit v0.10.2


From 69c770a690422c6cdc4ea52d9edbba7c20cd1aff Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung.kim@lge.com>
Date: Thu, 12 Dec 2013 16:36:14 +0900
Subject: tools lib traceevent: Make pevent_filter_add_filter_str() return
 pevent_errno

Refactor the pevent_filter_add_filter_str() to return a proper error
code and get rid of the third error_str argument.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386833777-3790-12-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index da942d5..089964e 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -372,7 +372,8 @@ enum pevent_flag {
 	_PE(ILLEGAL_TOKEN,	"illegal token"),			      \
 	_PE(INVALID_PAREN,	"open parenthesis cannot come here"), 	      \
 	_PE(UNBALANCED_PAREN,	"unbalanced number of parenthesis"),	      \
-	_PE(UNKNOWN_TOKEN,	"unknown token")
+	_PE(UNKNOWN_TOKEN,	"unknown token"),			      \
+	_PE(FILTER_NOT_FOUND,	"no filter found")
 
 #undef _PE
 #define _PE(__code, __str) PEVENT_ERRNO__ ## __code
@@ -863,9 +864,8 @@ enum filter_trivial_type {
 	FILTER_TRIVIAL_BOTH,
 };
 
-int pevent_filter_add_filter_str(struct event_filter *filter,
-				 const char *filter_str,
-				 char **error_str);
+enum pevent_errno pevent_filter_add_filter_str(struct event_filter *filter,
+					       const char *filter_str);
 
 
 int pevent_filter_match(struct event_filter *filter,
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 5aa5012..78440d7 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -1209,7 +1209,7 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 	return ret;
 }
 
-static int
+static enum pevent_errno
 process_event(struct event_format *event, const char *filter_str,
 	      struct filter_arg **parg, char **error_str)
 {
@@ -1218,21 +1218,15 @@ process_event(struct event_format *event, const char *filter_str,
 	pevent_buffer_init(filter_str, strlen(filter_str));
 
 	ret = process_filter(event, parg, error_str, 0);
-	if (ret == 1) {
-		show_error(error_str,
-			   "Unbalanced number of ')'");
-		return -1;
-	}
 	if (ret < 0)
 		return ret;
 
 	/* If parg is NULL, then make it into FALSE */
 	if (!*parg) {
 		*parg = allocate_arg();
-		if (*parg == NULL) {
-			show_error(error_str, "failed to allocate filter arg");
-			return -1;
-		}
+		if (*parg == NULL)
+			return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+
 		(*parg)->type = FILTER_ARG_BOOLEAN;
 		(*parg)->boolean.value = FILTER_FALSE;
 	}
@@ -1240,13 +1234,13 @@ process_event(struct event_format *event, const char *filter_str,
 	return 0;
 }
 
-static int filter_event(struct event_filter *filter,
-			struct event_format *event,
-			const char *filter_str, char **error_str)
+static enum pevent_errno
+filter_event(struct event_filter *filter, struct event_format *event,
+	     const char *filter_str, char **error_str)
 {
 	struct filter_type *filter_type;
 	struct filter_arg *arg;
-	int ret;
+	enum pevent_errno ret;
 
 	if (filter_str) {
 		ret = process_event(event, filter_str, &arg, error_str);
@@ -1256,20 +1250,16 @@ static int filter_event(struct event_filter *filter,
 	} else {
 		/* just add a TRUE arg */
 		arg = allocate_arg();
-		if (arg == NULL) {
-			show_error(error_str, "failed to allocate filter arg");
-			return -1;
-		}
+		if (arg == NULL)
+			return PEVENT_ERRNO__MEM_ALLOC_FAILED;
+
 		arg->type = FILTER_ARG_BOOLEAN;
 		arg->boolean.value = FILTER_TRUE;
 	}
 
 	filter_type = add_filter_type(filter, event->id);
-	if (filter_type == NULL) {
-		show_error(error_str, "failed to add a new filter: %s",
-			   filter_str ? filter_str : "true");
-		return -1;
-	}
+	if (filter_type == NULL)
+		return PEVENT_ERRNO__MEM_ALLOC_FAILED;
 
 	if (filter_type->filter)
 		free_arg(filter_type->filter);
@@ -1282,18 +1272,12 @@ static int filter_event(struct event_filter *filter,
  * pevent_filter_add_filter_str - add a new filter
  * @filter: the event filter to add to
  * @filter_str: the filter string that contains the filter
- * @error_str: string containing reason for failed filter
- *
- * Returns 0 if the filter was successfully added
- *   -1 if there was an error.
  *
- * On error, if @error_str points to a string pointer,
- * it is set to the reason that the filter failed.
- * This string must be freed with "free".
+ * Returns 0 if the filter was successfully added or a
+ * negative error code.
  */
-int pevent_filter_add_filter_str(struct event_filter *filter,
-				 const char *filter_str,
-				 char **error_str)
+enum pevent_errno pevent_filter_add_filter_str(struct event_filter *filter,
+					       const char *filter_str)
 {
 	struct pevent *pevent = filter->pevent;
 	struct event_list *event;
@@ -1304,23 +1288,20 @@ int pevent_filter_add_filter_str(struct event_filter *filter,
 	char *event_name = NULL;
 	char *sys_name = NULL;
 	char *sp;
-	int rtn = 0;
+	enum pevent_errno rtn = 0; /* PEVENT_ERRNO__SUCCESS */
 	int len;
 	int ret;
+	char *error_str = NULL;
 
 	/* clear buffer to reset show error */
 	pevent_buffer_init("", 0);
 
-	if (error_str)
-		*error_str = NULL;
-
 	filter_start = strchr(filter_str, ':');
 	if (filter_start)
 		len = filter_start - filter_str;
 	else
 		len = strlen(filter_str);
 
-
 	do {
 		next_event = strchr(filter_str, ',');
 		if (next_event &&
@@ -1333,10 +1314,9 @@ int pevent_filter_add_filter_str(struct event_filter *filter,
 
 		this_event = malloc(len + 1);
 		if (this_event == NULL) {
-			show_error(error_str, "Memory allocation failure");
 			/* This can only happen when events is NULL, but still */
 			free_events(events);
-			return -1;
+			return PEVENT_ERRNO__MEM_ALLOC_FAILED;
 		}
 		memcpy(this_event, filter_str, len);
 		this_event[len] = 0;
@@ -1350,30 +1330,18 @@ int pevent_filter_add_filter_str(struct event_filter *filter,
 		event_name = strtok_r(NULL, "/", &sp);
 
 		if (!sys_name) {
-			show_error(error_str, "No filter found");
 			/* This can only happen when events is NULL, but still */
 			free_events(events);
 			free(this_event);
-			return -1;
+			return PEVENT_ERRNO__FILTER_NOT_FOUND;
 		}
 
 		/* Find this event */
 		ret = find_event(pevent, &events, strim(sys_name), strim(event_name));
 		if (ret < 0) {
-			if (ret == PEVENT_ERRNO__MEM_ALLOC_FAILED)
-				show_error(error_str,
-					   "Memory allocation failure");
-			else if (event_name)
-				show_error(error_str,
-					   "No event found under '%s.%s'",
-					   sys_name, event_name);
-			else
-				show_error(error_str,
-					   "No event found under '%s'",
-					   sys_name);
 			free_events(events);
 			free(this_event);
-			return -1;
+			return ret;
 		}
 		free(this_event);
 	} while (filter_str);
@@ -1385,7 +1353,7 @@ int pevent_filter_add_filter_str(struct event_filter *filter,
 	/* filter starts here */
 	for (event = events; event; event = event->next) {
 		ret = filter_event(filter, event->event, filter_start,
-				   error_str);
+				   &error_str);
 		/* Failures are returned if a parse error happened */
 		if (ret < 0)
 			rtn = ret;
-- 
cgit v0.10.2


From 41e12e580a7b0c151199f927193548b84d3e874c Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 12 Dec 2013 16:36:15 +0900
Subject: tools lib traceevent: Refactor pevent_filter_match() to get rid of
 die()

The test_filter() function is for testing given filter is matched to a
given record.  However it doesn't handle error cases properly so add a
new argument err to save error info during the test and also pass it to
internal test functions.

The return value of pevent_filter_match() also converted to pevent_errno
to indicate an exact error case.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386833777-3790-13-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 089964e..3ad784f 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -357,6 +357,8 @@ enum pevent_flag {
 	_PE(READ_PRINT_FAILED,	"failed to read event print fmt"), 	      \
 	_PE(OLD_FTRACE_ARG_FAILED,"failed to allocate field name for ftrace"),\
 	_PE(INVALID_ARG_TYPE,	"invalid argument type"),		      \
+	_PE(INVALID_EXP_TYPE,	"invalid expression type"),		      \
+	_PE(INVALID_OP_TYPE,	"invalid operator type"),		      \
 	_PE(INVALID_EVENT_NAME,	"invalid event name"),			      \
 	_PE(EVENT_NOT_FOUND,	"no event found"),			      \
 	_PE(SYNTAX_ERROR,	"syntax error"),			      \
@@ -373,12 +375,16 @@ enum pevent_flag {
 	_PE(INVALID_PAREN,	"open parenthesis cannot come here"), 	      \
 	_PE(UNBALANCED_PAREN,	"unbalanced number of parenthesis"),	      \
 	_PE(UNKNOWN_TOKEN,	"unknown token"),			      \
-	_PE(FILTER_NOT_FOUND,	"no filter found")
+	_PE(FILTER_NOT_FOUND,	"no filter found"),			      \
+	_PE(NOT_A_NUMBER,	"must have number field"),		      \
+	_PE(NO_FILTER,		"no filters exists"),			      \
+	_PE(FILTER_MISS,	"record does not match to filter")
 
 #undef _PE
 #define _PE(__code, __str) PEVENT_ERRNO__ ## __code
 enum pevent_errno {
 	PEVENT_ERRNO__SUCCESS			= 0,
+	PEVENT_ERRNO__FILTER_MATCH		= PEVENT_ERRNO__SUCCESS,
 
 	/*
 	 * Choose an arbitrary negative big number not to clash with standard
@@ -853,10 +859,11 @@ struct event_filter {
 
 struct event_filter *pevent_filter_alloc(struct pevent *pevent);
 
-#define FILTER_NONE		-2
-#define FILTER_NOEXIST		-1
-#define FILTER_MISS		0
-#define FILTER_MATCH		1
+/* for backward compatibility */
+#define FILTER_NONE		PEVENT_ERRNO__FILTER_NOT_FOUND
+#define FILTER_NOEXIST		PEVENT_ERRNO__NO_FILTER
+#define FILTER_MISS		PEVENT_ERRNO__FILTER_MISS
+#define FILTER_MATCH		PEVENT_ERRNO__FILTER_MATCH
 
 enum filter_trivial_type {
 	FILTER_TRIVIAL_FALSE,
@@ -868,8 +875,8 @@ enum pevent_errno pevent_filter_add_filter_str(struct event_filter *filter,
 					       const char *filter_str);
 
 
-int pevent_filter_match(struct event_filter *filter,
-			struct pevent_record *record);
+enum pevent_errno pevent_filter_match(struct event_filter *filter,
+				      struct pevent_record *record);
 
 int pevent_event_filtered(struct event_filter *filter,
 			  int event_id);
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 78440d7..9303c55 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -1678,8 +1678,8 @@ int pevent_filter_event_has_trivial(struct event_filter *filter,
 	}
 }
 
-static int test_filter(struct event_format *event,
-		       struct filter_arg *arg, struct pevent_record *record);
+static int test_filter(struct event_format *event, struct filter_arg *arg,
+		       struct pevent_record *record, enum pevent_errno *err);
 
 static const char *
 get_comm(struct event_format *event, struct pevent_record *record)
@@ -1725,15 +1725,24 @@ get_value(struct event_format *event,
 }
 
 static unsigned long long
-get_arg_value(struct event_format *event, struct filter_arg *arg, struct pevent_record *record);
+get_arg_value(struct event_format *event, struct filter_arg *arg,
+	      struct pevent_record *record, enum pevent_errno *err);
 
 static unsigned long long
-get_exp_value(struct event_format *event, struct filter_arg *arg, struct pevent_record *record)
+get_exp_value(struct event_format *event, struct filter_arg *arg,
+	      struct pevent_record *record, enum pevent_errno *err)
 {
 	unsigned long long lval, rval;
 
-	lval = get_arg_value(event, arg->exp.left, record);
-	rval = get_arg_value(event, arg->exp.right, record);
+	lval = get_arg_value(event, arg->exp.left, record, err);
+	rval = get_arg_value(event, arg->exp.right, record, err);
+
+	if (*err) {
+		/*
+		 * There was an error, no need to process anymore.
+		 */
+		return 0;
+	}
 
 	switch (arg->exp.type) {
 	case FILTER_EXP_ADD:
@@ -1768,39 +1777,51 @@ get_exp_value(struct event_format *event, struct filter_arg *arg, struct pevent_
 
 	case FILTER_EXP_NOT:
 	default:
-		die("error in exp");
+		if (!*err)
+			*err = PEVENT_ERRNO__INVALID_EXP_TYPE;
 	}
 	return 0;
 }
 
 static unsigned long long
-get_arg_value(struct event_format *event, struct filter_arg *arg, struct pevent_record *record)
+get_arg_value(struct event_format *event, struct filter_arg *arg,
+	      struct pevent_record *record, enum pevent_errno *err)
 {
 	switch (arg->type) {
 	case FILTER_ARG_FIELD:
 		return get_value(event, arg->field.field, record);
 
 	case FILTER_ARG_VALUE:
-		if (arg->value.type != FILTER_NUMBER)
-			die("must have number field!");
+		if (arg->value.type != FILTER_NUMBER) {
+			if (!*err)
+				*err = PEVENT_ERRNO__NOT_A_NUMBER;
+		}
 		return arg->value.val;
 
 	case FILTER_ARG_EXP:
-		return get_exp_value(event, arg, record);
+		return get_exp_value(event, arg, record, err);
 
 	default:
-		die("oops in filter");
+		if (!*err)
+			*err = PEVENT_ERRNO__INVALID_ARG_TYPE;
 	}
 	return 0;
 }
 
-static int test_num(struct event_format *event,
-		    struct filter_arg *arg, struct pevent_record *record)
+static int test_num(struct event_format *event, struct filter_arg *arg,
+		    struct pevent_record *record, enum pevent_errno *err)
 {
 	unsigned long long lval, rval;
 
-	lval = get_arg_value(event, arg->num.left, record);
-	rval = get_arg_value(event, arg->num.right, record);
+	lval = get_arg_value(event, arg->num.left, record, err);
+	rval = get_arg_value(event, arg->num.right, record, err);
+
+	if (*err) {
+		/*
+		 * There was an error, no need to process anymore.
+		 */
+		return 0;
+	}
 
 	switch (arg->num.type) {
 	case FILTER_CMP_EQ:
@@ -1822,7 +1843,8 @@ static int test_num(struct event_format *event,
 		return lval <= rval;
 
 	default:
-		/* ?? */
+		if (!*err)
+			*err = PEVENT_ERRNO__ILLEGAL_INTEGER_CMP;
 		return 0;
 	}
 }
@@ -1869,8 +1891,8 @@ static const char *get_field_str(struct filter_arg *arg, struct pevent_record *r
 	return val;
 }
 
-static int test_str(struct event_format *event,
-		    struct filter_arg *arg, struct pevent_record *record)
+static int test_str(struct event_format *event, struct filter_arg *arg,
+		    struct pevent_record *record, enum pevent_errno *err)
 {
 	const char *val;
 
@@ -1894,48 +1916,57 @@ static int test_str(struct event_format *event,
 		return regexec(&arg->str.reg, val, 0, NULL, 0);
 
 	default:
-		/* ?? */
+		if (!*err)
+			*err = PEVENT_ERRNO__ILLEGAL_STRING_CMP;
 		return 0;
 	}
 }
 
-static int test_op(struct event_format *event,
-		   struct filter_arg *arg, struct pevent_record *record)
+static int test_op(struct event_format *event, struct filter_arg *arg,
+		   struct pevent_record *record, enum pevent_errno *err)
 {
 	switch (arg->op.type) {
 	case FILTER_OP_AND:
-		return test_filter(event, arg->op.left, record) &&
-			test_filter(event, arg->op.right, record);
+		return test_filter(event, arg->op.left, record, err) &&
+			test_filter(event, arg->op.right, record, err);
 
 	case FILTER_OP_OR:
-		return test_filter(event, arg->op.left, record) ||
-			test_filter(event, arg->op.right, record);
+		return test_filter(event, arg->op.left, record, err) ||
+			test_filter(event, arg->op.right, record, err);
 
 	case FILTER_OP_NOT:
-		return !test_filter(event, arg->op.right, record);
+		return !test_filter(event, arg->op.right, record, err);
 
 	default:
-		/* ?? */
+		if (!*err)
+			*err = PEVENT_ERRNO__INVALID_OP_TYPE;
 		return 0;
 	}
 }
 
-static int test_filter(struct event_format *event,
-		       struct filter_arg *arg, struct pevent_record *record)
+static int test_filter(struct event_format *event, struct filter_arg *arg,
+		       struct pevent_record *record, enum pevent_errno *err)
 {
+	if (*err) {
+		/*
+		 * There was an error, no need to process anymore.
+		 */
+		return 0;
+	}
+
 	switch (arg->type) {
 	case FILTER_ARG_BOOLEAN:
 		/* easy case */
 		return arg->boolean.value;
 
 	case FILTER_ARG_OP:
-		return test_op(event, arg, record);
+		return test_op(event, arg, record, err);
 
 	case FILTER_ARG_NUM:
-		return test_num(event, arg, record);
+		return test_num(event, arg, record, err);
 
 	case FILTER_ARG_STR:
-		return test_str(event, arg, record);
+		return test_str(event, arg, record, err);
 
 	case FILTER_ARG_EXP:
 	case FILTER_ARG_VALUE:
@@ -1944,11 +1975,11 @@ static int test_filter(struct event_format *event,
 		 * Expressions, fields and values evaluate
 		 * to true if they return non zero
 		 */
-		return !!get_arg_value(event, arg, record);
+		return !!get_arg_value(event, arg, record, err);
 
 	default:
-		die("oops!");
-		/* ?? */
+		if (!*err)
+			*err = PEVENT_ERRNO__INVALID_ARG_TYPE;
 		return 0;
 	}
 }
@@ -1961,8 +1992,7 @@ static int test_filter(struct event_format *event,
  * Returns 1 if filter found for @event_id
  *   otherwise 0;
  */
-int pevent_event_filtered(struct event_filter *filter,
-			  int event_id)
+int pevent_event_filtered(struct event_filter *filter, int event_id)
 {
 	struct filter_type *filter_type;
 
@@ -1979,31 +2009,36 @@ int pevent_event_filtered(struct event_filter *filter,
  * @filter: filter struct with filter information
  * @record: the record to test against the filter
  *
- * Returns:
- *  1 - filter found for event and @record matches
- *  0 - filter found for event and @record does not match
- * -1 - no filter found for @record's event
- * -2 - if no filters exist
+ * Returns: match result or error code (prefixed with PEVENT_ERRNO__)
+ * FILTER_MATCH - filter found for event and @record matches
+ * FILTER_MISS  - filter found for event and @record does not match
+ * FILTER_NOT_FOUND - no filter found for @record's event
+ * NO_FILTER - if no filters exist
+ * otherwise - error occurred during test
  */
-int pevent_filter_match(struct event_filter *filter,
-			struct pevent_record *record)
+enum pevent_errno pevent_filter_match(struct event_filter *filter,
+				      struct pevent_record *record)
 {
 	struct pevent *pevent = filter->pevent;
 	struct filter_type *filter_type;
 	int event_id;
+	int ret;
+	enum pevent_errno err = 0;
 
 	if (!filter->filters)
-		return FILTER_NONE;
+		return PEVENT_ERRNO__NO_FILTER;
 
 	event_id = pevent_data_type(pevent, record);
 
 	filter_type = find_filter_type(filter, event_id);
-
 	if (!filter_type)
-		return FILTER_NOEXIST;
+		return PEVENT_ERRNO__FILTER_NOT_FOUND;
+
+	ret = test_filter(filter_type->event, filter_type->filter, record, &err);
+	if (err)
+		return err;
 
-	return test_filter(filter_type->event, filter_type->filter, record) ?
-		FILTER_MATCH : FILTER_MISS;
+	return ret ? PEVENT_ERRNO__FILTER_MATCH : PEVENT_ERRNO__FILTER_MISS;
 }
 
 static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
-- 
cgit v0.10.2


From f9b0e058cbd04ada76b13afffa7e1df830543c24 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Sat, 14 Dec 2013 04:21:26 +0800
Subject: writeback: Fix data corruption on NFS

Commit 4f8ad655dbc8 "writeback: Refactor writeback_single_inode()" added
a condition to skip clean inode. However this is wrong in WB_SYNC_ALL
mode because there we also want to wait for outstanding writeback on
possibly clean inode. This was causing occasional data corruption issues
on NFS because it uses sync_inode() to make sure all outstanding writes
are flushed to the server before truncating the inode and with
sync_inode() returning prematurely file was sometimes extended back
by an outstanding write after it was truncated.

So modify the test to also check for pages under writeback in
WB_SYNC_ALL mode.

CC: stable@vger.kernel.org # >= 3.5
Fixes: 4f8ad655dbc82cf05d2edc11e66b78a42d38bf93
Reported-and-tested-by: Dan Duval <dan.duval@oracle.com>
Signed-off-by: Jan Kara <jack@suse.cz>

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 1f4a10e..e0259a1 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -516,13 +516,16 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	}
 	WARN_ON(inode->i_state & I_SYNC);
 	/*
-	 * Skip inode if it is clean. We don't want to mess with writeback
-	 * lists in this function since flusher thread may be doing for example
-	 * sync in parallel and if we move the inode, it could get skipped. So
-	 * here we make sure inode is on some writeback list and leave it there
-	 * unless we have completely cleaned the inode.
+	 * Skip inode if it is clean and we have no outstanding writeback in
+	 * WB_SYNC_ALL mode. We don't want to mess with writeback lists in this
+	 * function since flusher thread may be doing for example sync in
+	 * parallel and if we move the inode, it could get skipped. So here we
+	 * make sure inode is on some writeback list and leave it there unless
+	 * we have completely cleaned the inode.
 	 */
-	if (!(inode->i_state & I_DIRTY))
+	if (!(inode->i_state & I_DIRTY) &&
+	    (wbc->sync_mode != WB_SYNC_ALL ||
+	     !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK)))
 		goto out;
 	inode->i_state |= I_SYNC;
 	spin_unlock(&inode->i_lock);
-- 
cgit v0.10.2


From dfe5b9ad83a63180f358b27d1018649a27b394a9 Mon Sep 17 00:00:00 2001
From: Steven Whitehouse <swhiteho@redhat.com>
Date: Fri, 6 Dec 2013 11:52:34 +0000
Subject: GFS2: don't hold s_umount over blkdev_put

This is a GFS2 version of Tejun's patch:
4f331f01b9c43bf001d3ffee578a97a1e0633eac
vfs: don't hold s_umount over close_bdev_exclusive() call

In this case its blkdev_put itself that is the issue and this
patch uses the same solution of dropping and retaking s_umount.

Reported-by: Tejun Heo <tj@kernel.org>
Reported-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 82303b4..52fa883 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1366,8 +1366,18 @@ static struct dentry *gfs2_mount(struct file_system_type *fs_type, int flags,
 	if (IS_ERR(s))
 		goto error_bdev;
 
-	if (s->s_root)
+	if (s->s_root) {
+		/*
+		 * s_umount nests inside bd_mutex during
+		 * __invalidate_device().  blkdev_put() acquires
+		 * bd_mutex and can't be called under s_umount.  Drop
+		 * s_umount temporarily.  This is safe as we're
+		 * holding an active reference.
+		 */
+		up_write(&s->s_umount);
 		blkdev_put(bdev, mode);
+		down_write(&s->s_umount);
+	}
 
 	memset(&args, 0, sizeof(args));
 	args.ar_quota = GFS2_QUOTA_DEFAULT;
-- 
cgit v0.10.2


From 9290a9a7c0bcf5400e8dbfbf9707fa68ea3fb338 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Tue, 10 Dec 2013 12:06:35 -0500
Subject: GFS2: Fix use-after-free race when calling gfs2_remove_from_ail

Function gfs2_remove_from_ail drops the reference on the bh via
brelse. This patch fixes a race condition whereby bh is deferenced
after the brelse when setting bd->bd_blkno = bh->b_blocknr;
Under certain rare circumstances, bh might be gone or reused,
and bd->bd_blkno is set to whatever that memory happens to be,
which is often 0. Later, in gfs2_trans_add_unrevoke, that bd fails
the test "bd->bd_blkno >= blkno" which causes it to never be freed.
The end result is that the bd is never freed from the bufdata cache,
which results in this error:
slab error in kmem_cache_destroy(): cache `gfs2_bufdata': Can't free all objects

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 610613f..9dcb977 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -551,10 +551,10 @@ void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
 	struct buffer_head *bh = bd->bd_bh;
 	struct gfs2_glock *gl = bd->bd_gl;
 
-	gfs2_remove_from_ail(bd);
-	bd->bd_bh = NULL;
 	bh->b_private = NULL;
 	bd->bd_blkno = bh->b_blocknr;
+	gfs2_remove_from_ail(bd); /* drops ref on bh */
+	bd->bd_bh = NULL;
 	bd->bd_ops = &gfs2_revoke_lops;
 	sdp->sd_log_num_revoke++;
 	atomic_inc(&gl->gl_revokes);
-- 
cgit v0.10.2


From 502be2a32f09f388e4ff34ef2e3ebcabbbb261da Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Fri, 13 Dec 2013 08:31:06 -0500
Subject: GFS2: Fix slab memory leak in gfs2_bufdata

This patch fixes a slab memory leak that sometimes can occur
for files with a very short lifespan. The problem occurs when
a dinode is deleted before it has gotten to the journal properly.
In the leak scenario, the bd object is pinned for journal
committment (queued to the metadata buffers queue: sd_log_le_buf)
but is subsequently unpinned and dequeued before it finds its way
to the ail or the revoke queue. In this rare circumstance, the bd
object needs to be freed from slab memory, or it is forgotten.
We have to be very careful how we do it, though, because
multiple processes can call gfs2_remove_from_journal. In order to
avoid double-frees, only the process that does the unpinning is
allowed to free the bd.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 9324150..52f177b 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -258,6 +258,7 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int
 	struct address_space *mapping = bh->b_page->mapping;
 	struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping);
 	struct gfs2_bufdata *bd = bh->b_private;
+	int was_pinned = 0;
 
 	if (test_clear_buffer_pinned(bh)) {
 		trace_gfs2_pin(bd, 0);
@@ -273,12 +274,16 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int
 			tr->tr_num_databuf_rm++;
 		}
 		tr->tr_touched = 1;
+		was_pinned = 1;
 		brelse(bh);
 	}
 	if (bd) {
 		spin_lock(&sdp->sd_ail_lock);
 		if (bd->bd_tr) {
 			gfs2_trans_add_revoke(sdp, bd);
+		} else if (was_pinned) {
+			bh->b_private = NULL;
+			kmem_cache_free(gfs2_bufdata_cachep, bd);
 		}
 		spin_unlock(&sdp->sd_ail_lock);
 	}
-- 
cgit v0.10.2


From 499e61279d0f8dc6ecf46b75479118589df58b56 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Heiko=20St=C3=BCbner?= <heiko@sntech.de>
Date: Sat, 14 Dec 2013 01:41:55 -0800
Subject: Input: zforce - fix possible driver hang during suspend

handle_level_irq masks the interrupt before handling it, and only
unmasks it after the handler is finished. So when a touch event
happens after threads are suspended, but before the system is fully asleep
the irq handler tries to wakeup the thread which will only happen on the
next resume, resulting in the wakeup event never being sent and the driver
not being able to wake the system from sleep due to the masked irq.

Therefore move the wakeup_event to a small non-threaded handler.

Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>

diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c
index 75762d6..aa127ba 100644
--- a/drivers/input/touchscreen/zforce_ts.c
+++ b/drivers/input/touchscreen/zforce_ts.c
@@ -455,7 +455,18 @@ static void zforce_complete(struct zforce_ts *ts, int cmd, int result)
 	}
 }
 
-static irqreturn_t zforce_interrupt(int irq, void *dev_id)
+static irqreturn_t zforce_irq(int irq, void *dev_id)
+{
+	struct zforce_ts *ts = dev_id;
+	struct i2c_client *client = ts->client;
+
+	if (ts->suspended && device_may_wakeup(&client->dev))
+		pm_wakeup_event(&client->dev, 500);
+
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t zforce_irq_thread(int irq, void *dev_id)
 {
 	struct zforce_ts *ts = dev_id;
 	struct i2c_client *client = ts->client;
@@ -465,12 +476,10 @@ static irqreturn_t zforce_interrupt(int irq, void *dev_id)
 	u8 *payload;
 
 	/*
-	 * When suspended, emit a wakeup signal if necessary and return.
+	 * When still suspended, return.
 	 * Due to the level-interrupt we will get re-triggered later.
 	 */
 	if (ts->suspended) {
-		if (device_may_wakeup(&client->dev))
-			pm_wakeup_event(&client->dev, 500);
 		msleep(20);
 		return IRQ_HANDLED;
 	}
@@ -763,8 +772,8 @@ static int zforce_probe(struct i2c_client *client,
 	 * Therefore we can trigger the interrupt anytime it is low and do
 	 * not need to limit it to the interrupt edge.
 	 */
-	ret = devm_request_threaded_irq(&client->dev, client->irq, NULL,
-					zforce_interrupt,
+	ret = devm_request_threaded_irq(&client->dev, client->irq,
+					zforce_irq, zforce_irq_thread,
 					IRQF_TRIGGER_LOW | IRQF_ONESHOT,
 					input_dev->name, ts);
 	if (ret) {
-- 
cgit v0.10.2


From 79db57cef949cfd0fe7f53e30666bd6945ec400a Mon Sep 17 00:00:00 2001
From: Rashika Kheria <rashika.kheria@gmail.com>
Date: Sat, 14 Dec 2013 19:28:24 +0530
Subject: amd64_edac: Mark amd64_decode_bus_error as static
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch marks the function amd64_decode_bus_error() as static because
it is not used outside of amd64_edac.c.

It also eliminates the following warning:
drivers/edac/amd64_edac.c:2038:6: warning: no previous prototype for ‘amd64_decode_bus_error’ [-Wmissing-prototypes]

Signed-off-by: Rashika Kheria <rashika.kheria@gmail.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Link: http://lkml.kernel.org/r/7cddbd4c69ed493f183383e98853181aaf75b26b.1387029387.git.rashika.kheria@gmail.com
Signed-off-by: Borislav Petkov <bp@suse.de>

diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index a2f1854..6b2542e 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -2035,7 +2035,7 @@ static inline void __amd64_decode_bus_error(struct mem_ctl_info *mci,
 	__log_bus_error(mci, &err, ecc_type);
 }
 
-void amd64_decode_bus_error(int node_id, struct mce *m)
+static void amd64_decode_bus_error(int node_id, struct mce *m)
 {
 	__amd64_decode_bus_error(mcis[node_id], m);
 }
-- 
cgit v0.10.2


From df781d0386a3e29c31f1d8eaf845b3224e65dd7f Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Sun, 15 Dec 2013 17:29:44 +0100
Subject: amd64_edac: Simplify code around decode_bus_error

Drop wrapper function and prefixes.

Signed-off-by: Borislav Petkov <bp@suse.de>

diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 6b2542e..568e97f 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -2005,9 +2005,9 @@ static void __log_bus_error(struct mem_ctl_info *mci, struct err_info *err,
 			     string, "");
 }
 
-static inline void __amd64_decode_bus_error(struct mem_ctl_info *mci,
-					    struct mce *m)
+static inline void decode_bus_error(int node_id, struct mce *m)
 {
+	struct mem_ctl_info *mci = mcis[node_id];
 	struct amd64_pvt *pvt = mci->pvt_info;
 	u8 ecc_type = (m->status >> 45) & 0x3;
 	u8 xec = XEC(m->status, 0x1f);
@@ -2035,11 +2035,6 @@ static inline void __amd64_decode_bus_error(struct mem_ctl_info *mci,
 	__log_bus_error(mci, &err, ecc_type);
 }
 
-static void amd64_decode_bus_error(int node_id, struct mce *m)
-{
-	__amd64_decode_bus_error(mcis[node_id], m);
-}
-
 /*
  * Use pvt->F2 which contains the F2 CPU PCI device to get the related
  * F1 (AddrMap) and F3 (Misc) devices. Return negative value on error.
@@ -2680,7 +2675,7 @@ static int amd64_init_one_instance(struct pci_dev *F2)
 	if (report_gart_errors)
 		amd_report_gart_errors(true);
 
-	amd_register_ecc_decoder(amd64_decode_bus_error);
+	amd_register_ecc_decoder(decode_bus_error);
 
 	mcis[nid] = mci;
 
@@ -2777,7 +2772,7 @@ static void amd64_remove_one_instance(struct pci_dev *pdev)
 
 	/* unregister from EDAC MCE */
 	amd_report_gart_errors(false);
-	amd_unregister_ecc_decoder(amd64_decode_bus_error);
+	amd_unregister_ecc_decoder(decode_bus_error);
 
 	kfree(ecc_stngs[nid]);
 	ecc_stngs[nid] = NULL;
-- 
cgit v0.10.2


From d1ea71cdc9801c829d97eb42204329c28a4b2f52 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Sun, 15 Dec 2013 17:54:27 +0100
Subject: amd64_edac: Remove "amd64" prefix from static functions

No need for the namespace tagging there. Cleanup setup_pci_device while
at it.

Signed-off-by: Borislav Petkov <bp@suse.de>

diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 568e97f..98e14ee 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -1,7 +1,7 @@
 #include "amd64_edac.h"
 #include <asm/amd_nb.h>
 
-static struct edac_pci_ctl_info *amd64_ctl_pci;
+static struct edac_pci_ctl_info *pci_ctl;
 
 static int report_gart_errors;
 module_param(report_gart_errors, int, 0644);
@@ -162,7 +162,7 @@ static int f15_read_dct_pci_cfg(struct amd64_pvt *pvt, int addr, u32 *val,
  * scan the scrub rate mapping table for a close or matching bandwidth value to
  * issue. If requested is too big, then use last maximum value found.
  */
-static int __amd64_set_scrub_rate(struct pci_dev *ctl, u32 new_bw, u32 min_rate)
+static int __set_scrub_rate(struct pci_dev *ctl, u32 new_bw, u32 min_rate)
 {
 	u32 scrubval;
 	int i;
@@ -198,7 +198,7 @@ static int __amd64_set_scrub_rate(struct pci_dev *ctl, u32 new_bw, u32 min_rate)
 	return 0;
 }
 
-static int amd64_set_scrub_rate(struct mem_ctl_info *mci, u32 bw)
+static int set_scrub_rate(struct mem_ctl_info *mci, u32 bw)
 {
 	struct amd64_pvt *pvt = mci->pvt_info;
 	u32 min_scrubrate = 0x5;
@@ -210,10 +210,10 @@ static int amd64_set_scrub_rate(struct mem_ctl_info *mci, u32 bw)
 	if (pvt->fam == 0x15 && pvt->model < 0x10)
 		f15h_select_dct(pvt, 0);
 
-	return __amd64_set_scrub_rate(pvt->F3, bw, min_scrubrate);
+	return __set_scrub_rate(pvt->F3, bw, min_scrubrate);
 }
 
-static int amd64_get_scrub_rate(struct mem_ctl_info *mci)
+static int get_scrub_rate(struct mem_ctl_info *mci)
 {
 	struct amd64_pvt *pvt = mci->pvt_info;
 	u32 scrubval = 0;
@@ -240,8 +240,7 @@ static int amd64_get_scrub_rate(struct mem_ctl_info *mci)
  * returns true if the SysAddr given by sys_addr matches the
  * DRAM base/limit associated with node_id
  */
-static bool amd64_base_limit_match(struct amd64_pvt *pvt, u64 sys_addr,
-				   u8 nid)
+static bool base_limit_match(struct amd64_pvt *pvt, u64 sys_addr, u8 nid)
 {
 	u64 addr;
 
@@ -285,7 +284,7 @@ static struct mem_ctl_info *find_mc_by_sys_addr(struct mem_ctl_info *mci,
 
 	if (intlv_en == 0) {
 		for (node_id = 0; node_id < DRAM_RANGES; node_id++) {
-			if (amd64_base_limit_match(pvt, sys_addr, node_id))
+			if (base_limit_match(pvt, sys_addr, node_id))
 				goto found;
 		}
 		goto err_no_match;
@@ -309,7 +308,7 @@ static struct mem_ctl_info *find_mc_by_sys_addr(struct mem_ctl_info *mci,
 	}
 
 	/* sanity test for sys_addr */
-	if (unlikely(!amd64_base_limit_match(pvt, sys_addr, node_id))) {
+	if (unlikely(!base_limit_match(pvt, sys_addr, node_id))) {
 		amd64_warn("%s: sys_addr 0x%llx falls outside base/limit address"
 			   "range for node %d with node interleaving enabled.\n",
 			   __func__, sys_addr, node_id);
@@ -660,7 +659,7 @@ static int get_channel_from_ecc_syndrome(struct mem_ctl_info *, u16);
  * Determine if the DIMMs have ECC enabled. ECC is enabled ONLY if all the DIMMs
  * are ECC capable.
  */
-static unsigned long amd64_determine_edac_cap(struct amd64_pvt *pvt)
+static unsigned long determine_edac_cap(struct amd64_pvt *pvt)
 {
 	u8 bit;
 	unsigned long edac_cap = EDAC_FLAG_NONE;
@@ -675,9 +674,9 @@ static unsigned long amd64_determine_edac_cap(struct amd64_pvt *pvt)
 	return edac_cap;
 }
 
-static void amd64_debug_display_dimm_sizes(struct amd64_pvt *, u8);
+static void debug_display_dimm_sizes(struct amd64_pvt *, u8);
 
-static void amd64_dump_dramcfg_low(struct amd64_pvt *pvt, u32 dclr, int chan)
+static void debug_dump_dramcfg_low(struct amd64_pvt *pvt, u32 dclr, int chan)
 {
 	edac_dbg(1, "F2x%d90 (DRAM Cfg Low): 0x%08x\n", chan, dclr);
 
@@ -711,7 +710,7 @@ static void dump_misc_regs(struct amd64_pvt *pvt)
 		 (pvt->nbcap & NBCAP_SECDED) ? "yes" : "no",
 		 (pvt->nbcap & NBCAP_CHIPKILL) ? "yes" : "no");
 
-	amd64_dump_dramcfg_low(pvt, pvt->dclr0, 0);
+	debug_dump_dramcfg_low(pvt, pvt->dclr0, 0);
 
 	edac_dbg(1, "F3xB0 (Online Spare): 0x%08x\n", pvt->online_spare);
 
@@ -722,19 +721,19 @@ static void dump_misc_regs(struct amd64_pvt *pvt)
 
 	edac_dbg(1, "  DramHoleValid: %s\n", dhar_valid(pvt) ? "yes" : "no");
 
-	amd64_debug_display_dimm_sizes(pvt, 0);
+	debug_display_dimm_sizes(pvt, 0);
 
 	/* everything below this point is Fam10h and above */
 	if (pvt->fam == 0xf)
 		return;
 
-	amd64_debug_display_dimm_sizes(pvt, 1);
+	debug_display_dimm_sizes(pvt, 1);
 
 	amd64_info("using %s syndromes.\n", ((pvt->ecc_sym_sz == 8) ? "x8" : "x4"));
 
 	/* Only if NOT ganged does dclr1 have valid info */
 	if (!dct_ganging_enabled(pvt))
-		amd64_dump_dramcfg_low(pvt, pvt->dclr1, 1);
+		debug_dump_dramcfg_low(pvt, pvt->dclr1, 1);
 }
 
 /*
@@ -800,7 +799,7 @@ static void read_dct_base_mask(struct amd64_pvt *pvt)
 	}
 }
 
-static enum mem_type amd64_determine_memory_type(struct amd64_pvt *pvt, int cs)
+static enum mem_type determine_memory_type(struct amd64_pvt *pvt, int cs)
 {
 	enum mem_type type;
 
@@ -1702,7 +1701,7 @@ static void f1x_map_sysaddr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr,
  * debug routine to display the memory sizes of all logical DIMMs and its
  * CSROWs
  */
-static void amd64_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl)
+static void debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl)
 {
 	int dimm, size0, size1;
 	u32 *dcsb = ctrl ? pvt->csels[1].csbases : pvt->csels[0].csbases;
@@ -1744,7 +1743,7 @@ static void amd64_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl)
 	}
 }
 
-static struct amd64_family_type amd64_family_types[] = {
+static struct amd64_family_type family_types[] = {
 	[K8_CPUS] = {
 		.ctl_name = "K8",
 		.f1_id = PCI_DEVICE_ID_AMD_K8_NB_ADDRMAP,
@@ -2191,7 +2190,7 @@ static void read_mc_regs(struct amd64_pvt *pvt)
  *	encompasses
  *
  */
-static u32 amd64_csrow_nr_pages(struct amd64_pvt *pvt, u8 dct, int csrow_nr)
+static u32 get_csrow_nr_pages(struct amd64_pvt *pvt, u8 dct, int csrow_nr)
 {
 	u32 cs_mode, nr_pages;
 	u32 dbam = dct ? pvt->dbam1 : pvt->dbam0;
@@ -2258,19 +2257,19 @@ static int init_csrows(struct mem_ctl_info *mci)
 			    pvt->mc_node_id, i);
 
 		if (row_dct0) {
-			nr_pages = amd64_csrow_nr_pages(pvt, 0, i);
+			nr_pages = get_csrow_nr_pages(pvt, 0, i);
 			csrow->channels[0]->dimm->nr_pages = nr_pages;
 		}
 
 		/* K8 has only one DCT */
 		if (pvt->fam != 0xf && row_dct1) {
-			int row_dct1_pages = amd64_csrow_nr_pages(pvt, 1, i);
+			int row_dct1_pages = get_csrow_nr_pages(pvt, 1, i);
 
 			csrow->channels[1]->dimm->nr_pages = row_dct1_pages;
 			nr_pages += row_dct1_pages;
 		}
 
-		mtype = amd64_determine_memory_type(pvt, i);
+		mtype = determine_memory_type(pvt, i);
 
 		edac_dbg(1, "Total csrow%d pages: %u\n", i, nr_pages);
 
@@ -2304,7 +2303,7 @@ static void get_cpus_on_this_dct_cpumask(struct cpumask *mask, u16 nid)
 }
 
 /* check MCG_CTL on all the cpus on this node */
-static bool amd64_nb_mce_bank_enabled_on_node(u16 nid)
+static bool nb_mce_bank_enabled_on_node(u16 nid)
 {
 	cpumask_var_t mask;
 	int cpu, nbe;
@@ -2477,7 +2476,7 @@ static bool ecc_enabled(struct pci_dev *F3, u16 nid)
 	ecc_en = !!(value & NBCFG_ECC_ENABLE);
 	amd64_info("DRAM ECC %s.\n", (ecc_en ? "enabled" : "disabled"));
 
-	nb_mce_en = amd64_nb_mce_bank_enabled_on_node(nid);
+	nb_mce_en = nb_mce_bank_enabled_on_node(nid);
 	if (!nb_mce_en)
 		amd64_notice("NB MCE bank disabled, set MSR "
 			     "0x%08x[4] on node %d to enable.\n",
@@ -2532,7 +2531,7 @@ static void setup_mci_misc_attrs(struct mem_ctl_info *mci,
 	if (pvt->nbcap & NBCAP_CHIPKILL)
 		mci->edac_ctl_cap |= EDAC_FLAG_S4ECD4ED;
 
-	mci->edac_cap		= amd64_determine_edac_cap(pvt);
+	mci->edac_cap		= determine_edac_cap(pvt);
 	mci->mod_name		= EDAC_MOD_STR;
 	mci->mod_ver		= EDAC_AMD64_VERSION;
 	mci->ctl_name		= fam->ctl_name;
@@ -2540,14 +2539,14 @@ static void setup_mci_misc_attrs(struct mem_ctl_info *mci,
 	mci->ctl_page_to_phys	= NULL;
 
 	/* memory scrubber interface */
-	mci->set_sdram_scrub_rate = amd64_set_scrub_rate;
-	mci->get_sdram_scrub_rate = amd64_get_scrub_rate;
+	mci->set_sdram_scrub_rate = set_scrub_rate;
+	mci->get_sdram_scrub_rate = get_scrub_rate;
 }
 
 /*
  * returns a pointer to the family descriptor on success, NULL otherwise.
  */
-static struct amd64_family_type *amd64_per_family_init(struct amd64_pvt *pvt)
+static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt)
 {
 	struct amd64_family_type *fam_type = NULL;
 
@@ -2558,29 +2557,29 @@ static struct amd64_family_type *amd64_per_family_init(struct amd64_pvt *pvt)
 
 	switch (pvt->fam) {
 	case 0xf:
-		fam_type		= &amd64_family_types[K8_CPUS];
-		pvt->ops		= &amd64_family_types[K8_CPUS].ops;
+		fam_type	= &family_types[K8_CPUS];
+		pvt->ops	= &family_types[K8_CPUS].ops;
 		break;
 
 	case 0x10:
-		fam_type		= &amd64_family_types[F10_CPUS];
-		pvt->ops		= &amd64_family_types[F10_CPUS].ops;
+		fam_type	= &family_types[F10_CPUS];
+		pvt->ops	= &family_types[F10_CPUS].ops;
 		break;
 
 	case 0x15:
 		if (pvt->model == 0x30) {
-			fam_type	= &amd64_family_types[F15_M30H_CPUS];
-			pvt->ops	= &amd64_family_types[F15_M30H_CPUS].ops;
+			fam_type = &family_types[F15_M30H_CPUS];
+			pvt->ops = &family_types[F15_M30H_CPUS].ops;
 			break;
 		}
 
-		fam_type		= &amd64_family_types[F15_CPUS];
-		pvt->ops		= &amd64_family_types[F15_CPUS].ops;
+		fam_type	= &family_types[F15_CPUS];
+		pvt->ops	= &family_types[F15_CPUS].ops;
 		break;
 
 	case 0x16:
-		fam_type		= &amd64_family_types[F16_CPUS];
-		pvt->ops		= &amd64_family_types[F16_CPUS].ops;
+		fam_type	= &family_types[F16_CPUS];
+		pvt->ops	= &family_types[F16_CPUS].ops;
 		break;
 
 	default:
@@ -2596,7 +2595,7 @@ static struct amd64_family_type *amd64_per_family_init(struct amd64_pvt *pvt)
 	return fam_type;
 }
 
-static int amd64_init_one_instance(struct pci_dev *F2)
+static int init_one_instance(struct pci_dev *F2)
 {
 	struct amd64_pvt *pvt = NULL;
 	struct amd64_family_type *fam_type = NULL;
@@ -2614,7 +2613,7 @@ static int amd64_init_one_instance(struct pci_dev *F2)
 	pvt->F2 = F2;
 
 	ret = -EINVAL;
-	fam_type = amd64_per_family_init(pvt);
+	fam_type = per_family_init(pvt);
 	if (!fam_type)
 		goto err_free;
 
@@ -2698,8 +2697,8 @@ err_ret:
 	return ret;
 }
 
-static int amd64_probe_one_instance(struct pci_dev *pdev,
-				    const struct pci_device_id *mc_type)
+static int probe_one_instance(struct pci_dev *pdev,
+			      const struct pci_device_id *mc_type)
 {
 	u16 nid = amd_get_node_id(pdev);
 	struct pci_dev *F3 = node_to_amd_nb(nid)->misc;
@@ -2731,7 +2730,7 @@ static int amd64_probe_one_instance(struct pci_dev *pdev,
 			goto err_enable;
 	}
 
-	ret = amd64_init_one_instance(pdev);
+	ret = init_one_instance(pdev);
 	if (ret < 0) {
 		amd64_err("Error probing instance: %d\n", nid);
 		restore_ecc_error_reporting(s, nid, F3);
@@ -2747,7 +2746,7 @@ err_out:
 	return ret;
 }
 
-static void amd64_remove_one_instance(struct pci_dev *pdev)
+static void remove_one_instance(struct pci_dev *pdev)
 {
 	struct mem_ctl_info *mci;
 	struct amd64_pvt *pvt;
@@ -2838,8 +2837,8 @@ MODULE_DEVICE_TABLE(pci, amd64_pci_table);
 
 static struct pci_driver amd64_pci_driver = {
 	.name		= EDAC_MOD_STR,
-	.probe		= amd64_probe_one_instance,
-	.remove		= amd64_remove_one_instance,
+	.probe		= probe_one_instance,
+	.remove		= remove_one_instance,
 	.id_table	= amd64_pci_table,
 };
 
@@ -2848,23 +2847,18 @@ static void setup_pci_device(void)
 	struct mem_ctl_info *mci;
 	struct amd64_pvt *pvt;
 
-	if (amd64_ctl_pci)
+	if (pci_ctl)
 		return;
 
 	mci = mcis[0];
-	if (mci) {
-
-		pvt = mci->pvt_info;
-		amd64_ctl_pci =
-			edac_pci_create_generic_ctl(&pvt->F2->dev, EDAC_MOD_STR);
-
-		if (!amd64_ctl_pci) {
-			pr_warning("%s(): Unable to create PCI control\n",
-				   __func__);
+	if (!mci)
+		return;
 
-			pr_warning("%s(): PCI error report via EDAC not set\n",
-				   __func__);
-			}
+	pvt = mci->pvt_info;
+	pci_ctl = edac_pci_create_generic_ctl(&pvt->F2->dev, EDAC_MOD_STR);
+	if (!pci_ctl) {
+		pr_warn("%s(): Unable to create PCI control\n", __func__);
+		pr_warn("%s(): PCI error report via EDAC not set\n", __func__);
 	}
 }
 
@@ -2920,8 +2914,8 @@ err_ret:
 
 static void __exit amd64_edac_exit(void)
 {
-	if (amd64_ctl_pci)
-		edac_pci_release_generic_ctl(amd64_ctl_pci);
+	if (pci_ctl)
+		edac_pci_release_generic_ctl(pci_ctl);
 
 	pci_unregister_driver(&amd64_pci_driver);
 
-- 
cgit v0.10.2


From 95285933d086271c2e05edd3949a190551625928 Mon Sep 17 00:00:00 2001
From: Rashika Kheria <rashika.kheria@gmail.com>
Date: Sat, 14 Dec 2013 19:30:11 +0530
Subject: EDAC: Mark edac_create_debug_nodes as static
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch marks the function edac_create_debug_nodes() as static
because it is not used outside of edac_mc_sysfs.c.

Thus, it also eliminates the following warning:
drivers/edac/edac_mc_sysfs.c:917:5: warning: no previous prototype for ‘edac_create_debug_nodes’ [-Wmissing-prototypes]

Signed-off-by: Rashika Kheria <rashika.kheria@gmail.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Link: http://lkml.kernel.org/r/a1c863b08c0d6f67d03280cf908c771bf26a3239.1387029387.git.rashika.kheria@gmail.com
Signed-off-by: Borislav Petkov <bp@suse.de>

diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index 9f7e0e60..51c0362 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -914,7 +914,7 @@ void __exit edac_debugfs_exit(void)
 	debugfs_remove(edac_debugfs);
 }
 
-int edac_create_debug_nodes(struct mem_ctl_info *mci)
+static int edac_create_debug_nodes(struct mem_ctl_info *mci)
 {
 	struct dentry *d, *parent;
 	char name[80];
-- 
cgit v0.10.2


From 8112c0cdf7b86f5917cdffcff4ffc477eaa62ed4 Mon Sep 17 00:00:00 2001
From: Rashika Kheria <rashika.kheria@gmail.com>
Date: Sat, 14 Dec 2013 19:32:09 +0530
Subject: sb_edac: Mark get_mci_for_node_id as static
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch marks the function get_mci_for_node_id() as static because it
is not used outside of sb_edac.c.

Thus, it also eliminates the following warning:
drivers/edac/sb_edac.c:918:22: warning: no previous prototype for ‘get_mci_for_node_id’ [-Wmissing-prototypes]

Signed-off-by: Rashika Kheria <rashika.kheria@gmail.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Link: http://lkml.kernel.org/r/0441f508186fc4eeabc8e9c3e4dde013d99405d4.1387029387.git.rashika.kheria@gmail.com
Signed-off-by: Borislav Petkov <bp@suse.de>

diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index b5d254b..747421e 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -915,7 +915,7 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 	}
 }
 
-struct mem_ctl_info *get_mci_for_node_id(u8 node_id)
+static struct mem_ctl_info *get_mci_for_node_id(u8 node_id)
 {
 	struct sbridge_dev *sbridge_dev;
 
-- 
cgit v0.10.2


From 2a4d81547b88b4ff566d4b4f9c0e36285ed07634 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= <zajec5@gmail.com>
Date: Sun, 15 Dec 2013 21:00:48 -0800
Subject: Input: define KEY_WWAN for Wireless WAN
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some devices with support for mobile networks may have buttons for
enabling/disabling such connection. An example can be Linksys router 54G3G.
We already have KEY_BLUETOOTH, KEY_WLAN and KEY_UWB so it makes sense to
add KEY_WWAN as well.  As we already have KEY_WIMAX, use it's value for
KEY_WWAN and make it an alias.

Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>

diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h
index ecc8859..bd24470 100644
--- a/include/uapi/linux/input.h
+++ b/include/uapi/linux/input.h
@@ -464,7 +464,8 @@ struct input_keymap_entry {
 #define KEY_BRIGHTNESS_ZERO	244	/* brightness off, use ambient */
 #define KEY_DISPLAY_OFF		245	/* display device to off state */
 
-#define KEY_WIMAX		246
+#define KEY_WWAN		246	/* Wireless WAN (LTE, UMTS, GSM, etc.) */
+#define KEY_WIMAX		KEY_WWAN
 #define KEY_RFKILL		247	/* Key that controls all radios */
 
 #define KEY_MICMUTE		248	/* Mute / unmute the microphone */
-- 
cgit v0.10.2


From 2ecf810121c7eae34473b8fa108112036bc61127 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 11 Dec 2013 13:59:04 -0800
Subject: Documentation/memory-barriers.txt: Add needed ACCESS_ONCE() calls to
 memory-barriers.txt

The Documentation/memory-barriers.txt file was written before
the need for ACCESS_ONCE() was fully appreciated.  It therefore
contains no ACCESS_ONCE() calls, which can be a problem when
people lift examples from it.  This commit therefore adds
ACCESS_ONCE() calls.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: <linux-arch@vger.kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1386799151-2219-1-git-send-email-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 020cccd..1d06723 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -194,18 +194,22 @@ There are some minimal guarantees that may be expected of a CPU:
  (*) On any given CPU, dependent memory accesses will be issued in order, with
      respect to itself.  This means that for:
 
-	Q = P; D = *Q;
+	ACCESS_ONCE(Q) = P; smp_read_barrier_depends(); D = ACCESS_ONCE(*Q);
 
      the CPU will issue the following memory operations:
 
 	Q = LOAD P, D = LOAD *Q
 
-     and always in that order.
+     and always in that order.  On most systems, smp_read_barrier_depends()
+     does nothing, but it is required for DEC Alpha.  The ACCESS_ONCE()
+     is required to prevent compiler mischief.  Please note that you
+     should normally use something like rcu_dereference() instead of
+     open-coding smp_read_barrier_depends().
 
  (*) Overlapping loads and stores within a particular CPU will appear to be
      ordered within that CPU.  This means that for:
 
-	a = *X; *X = b;
+	a = ACCESS_ONCE(*X); ACCESS_ONCE(*X) = b;
 
      the CPU will only issue the following sequence of memory operations:
 
@@ -213,7 +217,7 @@ There are some minimal guarantees that may be expected of a CPU:
 
      And for:
 
-	*X = c; d = *X;
+	ACCESS_ONCE(*X) = c; d = ACCESS_ONCE(*X);
 
      the CPU will only issue:
 
@@ -224,6 +228,41 @@ There are some minimal guarantees that may be expected of a CPU:
 
 And there are a number of things that _must_ or _must_not_ be assumed:
 
+ (*) It _must_not_ be assumed that the compiler will do what you want with
+     memory references that are not protected by ACCESS_ONCE().  Without
+     ACCESS_ONCE(), the compiler is within its rights to do all sorts
+     of "creative" transformations:
+
+     (-) Repeat the load, possibly getting a different value on the second
+         and subsequent loads.  This is especially prone to happen when
+	 register pressure is high.
+
+     (-) Merge adjacent loads and stores to the same location.  The most
+         familiar example is the transformation from:
+
+		while (a)
+			do_something();
+
+         to something like:
+
+		if (a)
+			for (;;)
+				do_something();
+
+         Using ACCESS_ONCE() as follows prevents this sort of optimization:
+
+		while (ACCESS_ONCE(a))
+			do_something();
+
+     (-) "Store tearing", where a single store in the source code is split
+         into smaller stores in the object code.  Note that gcc really
+	 will do this on some architectures when storing certain constants.
+	 It can be cheaper to do a series of immediate stores than to
+	 form the constant in a register and then to store that register.
+
+     (-) "Load tearing", which splits loads in a manner analogous to
+     	 store tearing.
+
  (*) It _must_not_ be assumed that independent loads and stores will be issued
      in the order given.  This means that for:
 
@@ -450,14 +489,14 @@ The usage requirements of data dependency barriers are a little subtle, and
 it's not always obvious that they're needed.  To illustrate, consider the
 following sequence of events:
 
-	CPU 1		CPU 2
-	===============	===============
+	CPU 1		      CPU 2
+	===============	      ===============
 	{ A == 1, B == 2, C = 3, P == &A, Q == &C }
 	B = 4;
 	<write barrier>
-	P = &B
-			Q = P;
-			D = *Q;
+	ACCESS_ONCE(P) = &B
+			      Q = ACCESS_ONCE(P);
+			      D = *Q;
 
 There's a clear data dependency here, and it would seem that by the end of the
 sequence, Q must be either &A or &B, and that:
@@ -477,15 +516,15 @@ Alpha).
 To deal with this, a data dependency barrier or better must be inserted
 between the address load and the data load:
 
-	CPU 1		CPU 2
-	===============	===============
+	CPU 1		      CPU 2
+	===============	      ===============
 	{ A == 1, B == 2, C = 3, P == &A, Q == &C }
 	B = 4;
 	<write barrier>
-	P = &B
-			Q = P;
-			<data dependency barrier>
-			D = *Q;
+	ACCESS_ONCE(P) = &B
+			      Q = ACCESS_ONCE(P);
+			      <data dependency barrier>
+			      D = *Q;
 
 This enforces the occurrence of one of the two implications, and prevents the
 third possibility from arising.
@@ -504,21 +543,22 @@ Another example of where data dependency barriers might be required is where a
 number is read from memory and then used to calculate the index for an array
 access:
 
-	CPU 1		CPU 2
-	===============	===============
+	CPU 1		      CPU 2
+	===============	      ===============
 	{ M[0] == 1, M[1] == 2, M[3] = 3, P == 0, Q == 3 }
 	M[1] = 4;
 	<write barrier>
-	P = 1
-			Q = P;
-			<data dependency barrier>
-			D = M[Q];
+	ACCESS_ONCE(P) = 1
+			      Q = ACCESS_ONCE(P);
+			      <data dependency barrier>
+			      D = M[Q];
 
 
-The data dependency barrier is very important to the RCU system, for example.
-See rcu_dereference() in include/linux/rcupdate.h.  This permits the current
-target of an RCU'd pointer to be replaced with a new modified target, without
-the replacement target appearing to be incompletely initialised.
+The data dependency barrier is very important to the RCU system,
+for example.  See rcu_assign_pointer() and rcu_dereference() in
+include/linux/rcupdate.h.  This permits the current target of an RCU'd
+pointer to be replaced with a new modified target, without the replacement
+target appearing to be incompletely initialised.
 
 See also the subsection on "Cache Coherency" for a more thorough example.
 
@@ -530,22 +570,23 @@ A control dependency requires a full read memory barrier, not simply a data
 dependency barrier to make it work correctly.  Consider the following bit of
 code:
 
-	q = &a;
+	q = ACCESS_ONCE(a);
 	if (p) {
 		<data dependency barrier>
-		q = &b;
+		q = ACCESS_ONCE(b);
 	}
 	x = *q;
 
 This will not have the desired effect because there is no actual data
-dependency, but rather a control dependency that the CPU may short-circuit by
-attempting to predict the outcome in advance.  In such a case what's actually
-required is:
+dependency, but rather a control dependency that the CPU may short-circuit
+by attempting to predict the outcome in advance, so that other CPUs see
+the load from b as having happened before the load from a.  In such a
+case what's actually required is:
 
-	q = &a;
+	q = ACCESS_ONCE(a);
 	if (p) {
 		<read barrier>
-		q = &b;
+		q = ACCESS_ONCE(b);
 	}
 	x = *q;
 
@@ -561,23 +602,23 @@ barrier, though a general barrier would also be viable.  Similarly a read
 barrier or a data dependency barrier should always be paired with at least an
 write barrier, though, again, a general barrier is viable:
 
-	CPU 1		CPU 2
-	===============	===============
-	a = 1;
+	CPU 1		      CPU 2
+	===============	      ===============
+	ACCESS_ONCE(a) = 1;
 	<write barrier>
-	b = 2;		x = b;
-			<read barrier>
-			y = a;
+	ACCESS_ONCE(b) = 2;   x = ACCESS_ONCE(b);
+			      <read barrier>
+			      y = ACCESS_ONCE(a);
 
 Or:
 
-	CPU 1		CPU 2
-	===============	===============================
+	CPU 1		      CPU 2
+	===============	      ===============================
 	a = 1;
 	<write barrier>
-	b = &a;		x = b;
-			<data dependency barrier>
-			y = *x;
+	ACCESS_ONCE(b) = &a;  x = ACCESS_ONCE(b);
+			      <data dependency barrier>
+			      y = *x;
 
 Basically, the read barrier always has to be there, even though it can be of
 the "weaker" type.
@@ -586,13 +627,13 @@ the "weaker" type.
 match the loads after the read barrier or the data dependency barrier, and vice
 versa:
 
-	CPU 1                           CPU 2
-	===============                 ===============
-	a = 1;           }----   --->{  v = c
-	b = 2;           }    \ /    {  w = d
-	<write barrier>        \        <read barrier>
-	c = 3;           }    / \    {  x = a;
-	d = 4;           }----   --->{  y = b;
+	CPU 1                               CPU 2
+	===================                 ===================
+	ACCESS_ONCE(a) = 1;  }----   --->{  v = ACCESS_ONCE(c);
+	ACCESS_ONCE(b) = 2;  }    \ /    {  w = ACCESS_ONCE(d);
+	<write barrier>            \        <read barrier>
+	ACCESS_ONCE(c) = 3;  }    / \    {  x = ACCESS_ONCE(a);
+	ACCESS_ONCE(d) = 4;  }----   --->{  y = ACCESS_ONCE(b);
 
 
 EXAMPLES OF MEMORY BARRIER SEQUENCES
@@ -1435,12 +1476,12 @@ three CPUs; then should the following sequence of events occur:
 
 	CPU 1				CPU 2
 	===============================	===============================
-	*A = a;				*E = e;
+	ACCESS_ONCE(*A) = a;		ACCESS_ONCE(*E) = e;
 	LOCK M				LOCK Q
-	*B = b;				*F = f;
-	*C = c;				*G = g;
+	ACCESS_ONCE(*B) = b;		ACCESS_ONCE(*F) = f;
+	ACCESS_ONCE(*C) = c;		ACCESS_ONCE(*G) = g;
 	UNLOCK M			UNLOCK Q
-	*D = d;				*H = h;
+	ACCESS_ONCE(*D) = d;		ACCESS_ONCE(*H) = h;
 
 Then there is no guarantee as to what order CPU 3 will see the accesses to *A
 through *H occur in, other than the constraints imposed by the separate locks
@@ -1460,17 +1501,17 @@ However, if the following occurs:
 
 	CPU 1				CPU 2
 	===============================	===============================
-	*A = a;
-	LOCK M		[1]
-	*B = b;
-	*C = c;
-	UNLOCK M	[1]
-	*D = d;				*E = e;
-					LOCK M		[2]
-					*F = f;
-					*G = g;
-					UNLOCK M	[2]
-					*H = h;
+	ACCESS_ONCE(*A) = a;
+	LOCK M		     [1]
+	ACCESS_ONCE(*B) = b;
+	ACCESS_ONCE(*C) = c;
+	UNLOCK M	     [1]
+	ACCESS_ONCE(*D) = d;		ACCESS_ONCE(*E) = e;
+					LOCK M		     [2]
+					ACCESS_ONCE(*F) = f;
+					ACCESS_ONCE(*G) = g;
+					UNLOCK M	     [2]
+					ACCESS_ONCE(*H) = h;
 
 CPU 3 might see:
 
@@ -2177,11 +2218,11 @@ A programmer might take it for granted that the CPU will perform memory
 operations in exactly the order specified, so that if the CPU is, for example,
 given the following piece of code to execute:
 
-	a = *A;
-	*B = b;
-	c = *C;
-	d = *D;
-	*E = e;
+	a = ACCESS_ONCE(*A);
+	ACCESS_ONCE(*B) = b;
+	c = ACCESS_ONCE(*C);
+	d = ACCESS_ONCE(*D);
+	ACCESS_ONCE(*E) = e;
 
 they would then expect that the CPU will complete the memory operation for each
 instruction before moving on to the next one, leading to a definite sequence of
@@ -2228,12 +2269,12 @@ However, it is guaranteed that a CPU will be self-consistent: it will see its
 _own_ accesses appear to be correctly ordered, without the need for a memory
 barrier.  For instance with the following code:
 
-	U = *A;
-	*A = V;
-	*A = W;
-	X = *A;
-	*A = Y;
-	Z = *A;
+	U = ACCESS_ONCE(*A);
+	ACCESS_ONCE(*A) = V;
+	ACCESS_ONCE(*A) = W;
+	X = ACCESS_ONCE(*A);
+	ACCESS_ONCE(*A) = Y;
+	Z = ACCESS_ONCE(*A);
 
 and assuming no intervention by an external influence, it can be assumed that
 the final result will appear to be:
@@ -2250,7 +2291,12 @@ accesses:
 
 in that order, but, without intervention, the sequence may have almost any
 combination of elements combined or discarded, provided the program's view of
-the world remains consistent.
+the world remains consistent.  Note that ACCESS_ONCE() is -not- optional
+in the above example, as there are architectures where a given CPU might
+interchange successive loads to the same location.  On such architectures,
+ACCESS_ONCE() does whatever is necessary to prevent this, for example, on
+Itanium the volatile casts used by ACCESS_ONCE() cause GCC to emit the
+special ld.acq and st.rel instructions that prevent such reordering.
 
 The compiler may also combine, discard or defer elements of the sequence before
 the CPU even sees them.
@@ -2264,13 +2310,13 @@ may be reduced to:
 
 	*A = W;
 
-since, without a write barrier, it can be assumed that the effect of the
-storage of V to *A is lost.  Similarly:
+since, without either a write barrier or an ACCESS_ONCE(), it can be
+assumed that the effect of the storage of V to *A is lost.  Similarly:
 
 	*A = Y;
 	Z = *A;
 
-may, without a memory barrier, be reduced to:
+may, without a memory barrier or an ACCESS_ONCE(), be reduced to:
 
 	*A = Y;
 	Z = Y;
-- 
cgit v0.10.2


From fb2b581968db140586e8d7db38ff278f60872313 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 11 Dec 2013 13:59:05 -0800
Subject: Documentation/memory-barriers.txt: Add long atomic examples to
 memory-barriers.txt

Although the atomic_long_t functions are quite useful, they are
a bit obscure.  This commit therefore adds the common ones
alongside their atomic_t counterparts in
Documentation/memory-barriers.txt.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: <linux-arch@vger.kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1386799151-2219-2-git-send-email-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 1d06723..2d22da0 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -1728,21 +1728,23 @@ explicit lock operations, described later).  These include:
 
 	xchg();
 	cmpxchg();
-	atomic_xchg();
-	atomic_cmpxchg();
-	atomic_inc_return();
-	atomic_dec_return();
-	atomic_add_return();
-	atomic_sub_return();
-	atomic_inc_and_test();
-	atomic_dec_and_test();
-	atomic_sub_and_test();
-	atomic_add_negative();
-	atomic_add_unless();	/* when succeeds (returns 1) */
+	atomic_xchg();			atomic_long_xchg();
+	atomic_cmpxchg();		atomic_long_cmpxchg();
+	atomic_inc_return();		atomic_long_inc_return();
+	atomic_dec_return();		atomic_long_dec_return();
+	atomic_add_return();		atomic_long_add_return();
+	atomic_sub_return();		atomic_long_sub_return();
+	atomic_inc_and_test();		atomic_long_inc_and_test();
+	atomic_dec_and_test();		atomic_long_dec_and_test();
+	atomic_sub_and_test();		atomic_long_sub_and_test();
+	atomic_add_negative();		atomic_long_add_negative();
 	test_and_set_bit();
 	test_and_clear_bit();
 	test_and_change_bit();
 
+	/* when succeeds (returns 1) */
+	atomic_add_unless();		atomic_long_add_unless();
+
 These are used for such things as implementing LOCK-class and UNLOCK-class
 operations and adjusting reference counters towards object destruction, and as
 such the implicit memory barrier effects are necessary.
-- 
cgit v0.10.2


From 18c03c61444a211237f3d4782353cb38dba795df Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 11 Dec 2013 13:59:06 -0800
Subject: Documentation/memory-barriers.txt: Prohibit speculative writes

No SMP architecture currently supporting Linux allows
speculative writes, so this commit updates
Documentation/memory-barriers.txt to prohibit them in Linux core
code.  It also records restrictions on their use.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: <linux-arch@vger.kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1386799151-2219-3-git-send-email-paulmck@linux.vnet.ibm.com
[ Paul modified the original patch from Peter. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 2d22da0..deafa36 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -571,11 +571,10 @@ dependency barrier to make it work correctly.  Consider the following bit of
 code:
 
 	q = ACCESS_ONCE(a);
-	if (p) {
-		<data dependency barrier>
-		q = ACCESS_ONCE(b);
+	if (q) {
+		<data dependency barrier>  /* BUG: No data dependency!!! */
+		p = ACCESS_ONCE(b);
 	}
-	x = *q;
 
 This will not have the desired effect because there is no actual data
 dependency, but rather a control dependency that the CPU may short-circuit
@@ -584,11 +583,176 @@ the load from b as having happened before the load from a.  In such a
 case what's actually required is:
 
 	q = ACCESS_ONCE(a);
-	if (p) {
+	if (q) {
 		<read barrier>
-		q = ACCESS_ONCE(b);
+		p = ACCESS_ONCE(b);
 	}
-	x = *q;
+
+However, stores are not speculated.  This means that ordering -is- provided
+in the following example:
+
+	q = ACCESS_ONCE(a);
+	if (ACCESS_ONCE(q)) {
+		ACCESS_ONCE(b) = p;
+	}
+
+Please note that ACCESS_ONCE() is not optional!  Without the ACCESS_ONCE(),
+the compiler is within its rights to transform this example:
+
+	q = a;
+	if (q) {
+		b = p;  /* BUG: Compiler can reorder!!! */
+		do_something();
+	} else {
+		b = p;  /* BUG: Compiler can reorder!!! */
+		do_something_else();
+	}
+
+into this, which of course defeats the ordering:
+
+	b = p;
+	q = a;
+	if (q)
+		do_something();
+	else
+		do_something_else();
+
+Worse yet, if the compiler is able to prove (say) that the value of
+variable 'a' is always non-zero, it would be well within its rights
+to optimize the original example by eliminating the "if" statement
+as follows:
+
+	q = a;
+	b = p;  /* BUG: Compiler can reorder!!! */
+	do_something();
+
+The solution is again ACCESS_ONCE(), which preserves the ordering between
+the load from variable 'a' and the store to variable 'b':
+
+	q = ACCESS_ONCE(a);
+	if (q) {
+		ACCESS_ONCE(b) = p;
+		do_something();
+	} else {
+		ACCESS_ONCE(b) = p;
+		do_something_else();
+	}
+
+You could also use barrier() to prevent the compiler from moving
+the stores to variable 'b', but barrier() would not prevent the
+compiler from proving to itself that a==1 always, so ACCESS_ONCE()
+is also needed.
+
+It is important to note that control dependencies absolutely require a
+a conditional.  For example, the following "optimized" version of
+the above example breaks ordering:
+
+	q = ACCESS_ONCE(a);
+	ACCESS_ONCE(b) = p;  /* BUG: No ordering vs. load from a!!! */
+	if (q) {
+		/* ACCESS_ONCE(b) = p; -- moved up, BUG!!! */
+		do_something();
+	} else {
+		/* ACCESS_ONCE(b) = p; -- moved up, BUG!!! */
+		do_something_else();
+	}
+
+It is of course legal for the prior load to be part of the conditional,
+for example, as follows:
+
+	if (ACCESS_ONCE(a) > 0) {
+		ACCESS_ONCE(b) = q / 2;
+		do_something();
+	} else {
+		ACCESS_ONCE(b) = q / 3;
+		do_something_else();
+	}
+
+This will again ensure that the load from variable 'a' is ordered before the
+stores to variable 'b'.
+
+In addition, you need to be careful what you do with the local variable 'q',
+otherwise the compiler might be able to guess the value and again remove
+the needed conditional.  For example:
+
+	q = ACCESS_ONCE(a);
+	if (q % MAX) {
+		ACCESS_ONCE(b) = p;
+		do_something();
+	} else {
+		ACCESS_ONCE(b) = p;
+		do_something_else();
+	}
+
+If MAX is defined to be 1, then the compiler knows that (q % MAX) is
+equal to zero, in which case the compiler is within its rights to
+transform the above code into the following:
+
+	q = ACCESS_ONCE(a);
+	ACCESS_ONCE(b) = p;
+	do_something_else();
+
+This transformation loses the ordering between the load from variable 'a'
+and the store to variable 'b'.  If you are relying on this ordering, you
+should do something like the following:
+
+	q = ACCESS_ONCE(a);
+	BUILD_BUG_ON(MAX <= 1); /* Order load from a with store to b. */
+	if (q % MAX) {
+		ACCESS_ONCE(b) = p;
+		do_something();
+	} else {
+		ACCESS_ONCE(b) = p;
+		do_something_else();
+	}
+
+Finally, control dependencies do -not- provide transitivity.  This is
+demonstrated by two related examples:
+
+	CPU 0                     CPU 1
+	=====================     =====================
+	r1 = ACCESS_ONCE(x);      r2 = ACCESS_ONCE(y);
+	if (r1 >= 0)              if (r2 >= 0)
+	  ACCESS_ONCE(y) = 1;       ACCESS_ONCE(x) = 1;
+
+	assert(!(r1 == 1 && r2 == 1));
+
+The above two-CPU example will never trigger the assert().  However,
+if control dependencies guaranteed transitivity (which they do not),
+then adding the following two CPUs would guarantee a related assertion:
+
+	CPU 2                     CPU 3
+	=====================     =====================
+	ACCESS_ONCE(x) = 2;       ACCESS_ONCE(y) = 2;
+
+	assert(!(r1 == 2 && r2 == 2 && x == 1 && y == 1)); /* FAILS!!! */
+
+But because control dependencies do -not- provide transitivity, the
+above assertion can fail after the combined four-CPU example completes.
+If you need the four-CPU example to provide ordering, you will need
+smp_mb() between the loads and stores in the CPU 0 and CPU 1 code fragments.
+
+In summary:
+
+  (*) Control dependencies can order prior loads against later stores.
+      However, they do -not- guarantee any other sort of ordering:
+      Not prior loads against later loads, nor prior stores against
+      later anything.  If you need these other forms of ordering,
+      use smb_rmb(), smp_wmb(), or, in the case of prior stores and
+      later loads, smp_mb().
+
+  (*) Control dependencies require at least one run-time conditional
+      between the prior load and the subsequent store.  If the compiler
+      is able to optimize the conditional away, it will have also
+      optimized away the ordering.  Careful use of ACCESS_ONCE() can
+      help to preserve the needed conditional.
+
+  (*) Control dependencies require that the compiler avoid reordering the
+      dependency into nonexistence.  Careful use of ACCESS_ONCE() or
+      barrier() can help to preserve your control dependency.
+
+  (*) Control dependencies do -not- provide transitivity.  If you
+      need transitivity, use smp_mb().
 
 
 SMP BARRIER PAIRING
@@ -1083,7 +1247,10 @@ compiler from moving the memory accesses either side of it to the other side:
 
 	barrier();
 
-This is a general barrier - lesser varieties of compiler barrier do not exist.
+This is a general barrier -- there are no read-read or write-write variants
+of barrier().  Howevever, ACCESS_ONCE() can be thought of as a weak form
+for barrier() that affects only the specific accesses flagged by the
+ACCESS_ONCE().
 
 The compiler barrier has no direct effect on the CPU, which may then reorder
 things however it wishes.
-- 
cgit v0.10.2


From 692118dac47e65f5131686b1103ebfebf0cbfa8e Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 11 Dec 2013 13:59:07 -0800
Subject: Documentation/memory-barriers.txt: Document ACCESS_ONCE()

The situations in which ACCESS_ONCE() is required are not well
documented, so this commit adds some verbiage to
memory-barriers.txt.

Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: <linux-arch@vger.kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1386799151-2219-4-git-send-email-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index deafa36..919fd60 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -231,37 +231,8 @@ And there are a number of things that _must_ or _must_not_ be assumed:
  (*) It _must_not_ be assumed that the compiler will do what you want with
      memory references that are not protected by ACCESS_ONCE().  Without
      ACCESS_ONCE(), the compiler is within its rights to do all sorts
-     of "creative" transformations:
-
-     (-) Repeat the load, possibly getting a different value on the second
-         and subsequent loads.  This is especially prone to happen when
-	 register pressure is high.
-
-     (-) Merge adjacent loads and stores to the same location.  The most
-         familiar example is the transformation from:
-
-		while (a)
-			do_something();
-
-         to something like:
-
-		if (a)
-			for (;;)
-				do_something();
-
-         Using ACCESS_ONCE() as follows prevents this sort of optimization:
-
-		while (ACCESS_ONCE(a))
-			do_something();
-
-     (-) "Store tearing", where a single store in the source code is split
-         into smaller stores in the object code.  Note that gcc really
-	 will do this on some architectures when storing certain constants.
-	 It can be cheaper to do a series of immediate stores than to
-	 form the constant in a register and then to store that register.
-
-     (-) "Load tearing", which splits loads in a manner analogous to
-     	 store tearing.
+     of "creative" transformations, which are covered in the Compiler
+     Barrier section.
 
  (*) It _must_not_ be assumed that independent loads and stores will be issued
      in the order given.  This means that for:
@@ -749,7 +720,8 @@ In summary:
 
   (*) Control dependencies require that the compiler avoid reordering the
       dependency into nonexistence.  Careful use of ACCESS_ONCE() or
-      barrier() can help to preserve your control dependency.
+      barrier() can help to preserve your control dependency.  Please
+      see the Compiler Barrier section for more information.
 
   (*) Control dependencies do -not- provide transitivity.  If you
       need transitivity, use smp_mb().
@@ -1248,12 +1220,276 @@ compiler from moving the memory accesses either side of it to the other side:
 	barrier();
 
 This is a general barrier -- there are no read-read or write-write variants
-of barrier().  Howevever, ACCESS_ONCE() can be thought of as a weak form
+of barrier().  However, ACCESS_ONCE() can be thought of as a weak form
 for barrier() that affects only the specific accesses flagged by the
 ACCESS_ONCE().
 
-The compiler barrier has no direct effect on the CPU, which may then reorder
-things however it wishes.
+The barrier() function has the following effects:
+
+ (*) Prevents the compiler from reordering accesses following the
+     barrier() to precede any accesses preceding the barrier().
+     One example use for this property is to ease communication between
+     interrupt-handler code and the code that was interrupted.
+
+ (*) Within a loop, forces the compiler to load the variables used
+     in that loop's conditional on each pass through that loop.
+
+The ACCESS_ONCE() function can prevent any number of optimizations that,
+while perfectly safe in single-threaded code, can be fatal in concurrent
+code.  Here are some examples of these sorts of optimizations:
+
+ (*) The compiler is within its rights to merge successive loads from
+     the same variable.  Such merging can cause the compiler to "optimize"
+     the following code:
+
+	while (tmp = a)
+		do_something_with(tmp);
+
+     into the following code, which, although in some sense legitimate
+     for single-threaded code, is almost certainly not what the developer
+     intended:
+
+	if (tmp = a)
+		for (;;)
+			do_something_with(tmp);
+
+     Use ACCESS_ONCE() to prevent the compiler from doing this to you:
+
+	while (tmp = ACCESS_ONCE(a))
+		do_something_with(tmp);
+
+ (*) The compiler is within its rights to reload a variable, for example,
+     in cases where high register pressure prevents the compiler from
+     keeping all data of interest in registers.  The compiler might
+     therefore optimize the variable 'tmp' out of our previous example:
+
+	while (tmp = a)
+		do_something_with(tmp);
+
+     This could result in the following code, which is perfectly safe in
+     single-threaded code, but can be fatal in concurrent code:
+
+	while (a)
+		do_something_with(a);
+
+     For example, the optimized version of this code could result in
+     passing a zero to do_something_with() in the case where the variable
+     a was modified by some other CPU between the "while" statement and
+     the call to do_something_with().
+
+     Again, use ACCESS_ONCE() to prevent the compiler from doing this:
+
+	while (tmp = ACCESS_ONCE(a))
+		do_something_with(tmp);
+
+     Note that if the compiler runs short of registers, it might save
+     tmp onto the stack.  The overhead of this saving and later restoring
+     is why compilers reload variables.  Doing so is perfectly safe for
+     single-threaded code, so you need to tell the compiler about cases
+     where it is not safe.
+
+ (*) The compiler is within its rights to omit a load entirely if it knows
+     what the value will be.  For example, if the compiler can prove that
+     the value of variable 'a' is always zero, it can optimize this code:
+
+	while (tmp = a)
+		do_something_with(tmp);
+
+     Into this:
+
+	do { } while (0);
+
+     This transformation is a win for single-threaded code because it gets
+     rid of a load and a branch.  The problem is that the compiler will
+     carry out its proof assuming that the current CPU is the only one
+     updating variable 'a'.  If variable 'a' is shared, then the compiler's
+     proof will be erroneous.  Use ACCESS_ONCE() to tell the compiler
+     that it doesn't know as much as it thinks it does:
+
+	while (tmp = ACCESS_ONCE(a))
+		do_something_with(tmp);
+
+     But please note that the compiler is also closely watching what you
+     do with the value after the ACCESS_ONCE().  For example, suppose you
+     do the following and MAX is a preprocessor macro with the value 1:
+
+	while ((tmp = ACCESS_ONCE(a)) % MAX)
+		do_something_with(tmp);
+
+     Then the compiler knows that the result of the "%" operator applied
+     to MAX will always be zero, again allowing the compiler to optimize
+     the code into near-nonexistence.  (It will still load from the
+     variable 'a'.)
+
+ (*) Similarly, the compiler is within its rights to omit a store entirely
+     if it knows that the variable already has the value being stored.
+     Again, the compiler assumes that the current CPU is the only one
+     storing into the variable, which can cause the compiler to do the
+     wrong thing for shared variables.  For example, suppose you have
+     the following:
+
+	a = 0;
+	/* Code that does not store to variable a. */
+	a = 0;
+
+     The compiler sees that the value of variable 'a' is already zero, so
+     it might well omit the second store.  This would come as a fatal
+     surprise if some other CPU might have stored to variable 'a' in the
+     meantime.
+
+     Use ACCESS_ONCE() to prevent the compiler from making this sort of
+     wrong guess:
+
+	ACCESS_ONCE(a) = 0;
+	/* Code that does not store to variable a. */
+	ACCESS_ONCE(a) = 0;
+
+ (*) The compiler is within its rights to reorder memory accesses unless
+     you tell it not to.  For example, consider the following interaction
+     between process-level code and an interrupt handler:
+
+	void process_level(void)
+	{
+		msg = get_message();
+		flag = true;
+	}
+
+	void interrupt_handler(void)
+	{
+		if (flag)
+			process_message(msg);
+	}
+
+     There is nothing to prevent the the compiler from transforming
+     process_level() to the following, in fact, this might well be a
+     win for single-threaded code:
+
+	void process_level(void)
+	{
+		flag = true;
+		msg = get_message();
+	}
+
+     If the interrupt occurs between these two statement, then
+     interrupt_handler() might be passed a garbled msg.  Use ACCESS_ONCE()
+     to prevent this as follows:
+
+	void process_level(void)
+	{
+		ACCESS_ONCE(msg) = get_message();
+		ACCESS_ONCE(flag) = true;
+	}
+
+	void interrupt_handler(void)
+	{
+		if (ACCESS_ONCE(flag))
+			process_message(ACCESS_ONCE(msg));
+	}
+
+     Note that the ACCESS_ONCE() wrappers in interrupt_handler()
+     are needed if this interrupt handler can itself be interrupted
+     by something that also accesses 'flag' and 'msg', for example,
+     a nested interrupt or an NMI.  Otherwise, ACCESS_ONCE() is not
+     needed in interrupt_handler() other than for documentation purposes.
+     (Note also that nested interrupts do not typically occur in modern
+     Linux kernels, in fact, if an interrupt handler returns with
+     interrupts enabled, you will get a WARN_ONCE() splat.)
+
+     You should assume that the compiler can move ACCESS_ONCE() past
+     code not containing ACCESS_ONCE(), barrier(), or similar primitives.
+
+     This effect could also be achieved using barrier(), but ACCESS_ONCE()
+     is more selective:  With ACCESS_ONCE(), the compiler need only forget
+     the contents of the indicated memory locations, while with barrier()
+     the compiler must discard the value of all memory locations that
+     it has currented cached in any machine registers.  Of course,
+     the compiler must also respect the order in which the ACCESS_ONCE()s
+     occur, though the CPU of course need not do so.
+
+ (*) The compiler is within its rights to invent stores to a variable,
+     as in the following example:
+
+	if (a)
+		b = a;
+	else
+		b = 42;
+
+     The compiler might save a branch by optimizing this as follows:
+
+	b = 42;
+	if (a)
+		b = a;
+
+     In single-threaded code, this is not only safe, but also saves
+     a branch.  Unfortunately, in concurrent code, this optimization
+     could cause some other CPU to see a spurious value of 42 -- even
+     if variable 'a' was never zero -- when loading variable 'b'.
+     Use ACCESS_ONCE() to prevent this as follows:
+
+	if (a)
+		ACCESS_ONCE(b) = a;
+	else
+		ACCESS_ONCE(b) = 42;
+
+     The compiler can also invent loads.  These are usually less
+     damaging, but they can result in cache-line bouncing and thus in
+     poor performance and scalability.  Use ACCESS_ONCE() to prevent
+     invented loads.
+
+ (*) For aligned memory locations whose size allows them to be accessed
+     with a single memory-reference instruction, prevents "load tearing"
+     and "store tearing," in which a single large access is replaced by
+     multiple smaller accesses.  For example, given an architecture having
+     16-bit store instructions with 7-bit immediate fields, the compiler
+     might be tempted to use two 16-bit store-immediate instructions to
+     implement the following 32-bit store:
+
+	p = 0x00010002;
+
+     Please note that GCC really does use this sort of optimization,
+     which is not surprising given that it would likely take more
+     than two instructions to build the constant and then store it.
+     This optimization can therefore be a win in single-threaded code.
+     In fact, a recent bug (since fixed) caused GCC to incorrectly use
+     this optimization in a volatile store.  In the absence of such bugs,
+     use of ACCESS_ONCE() prevents store tearing in the following example:
+
+	ACCESS_ONCE(p) = 0x00010002;
+
+     Use of packed structures can also result in load and store tearing,
+     as in this example:
+
+	struct __attribute__((__packed__)) foo {
+		short a;
+		int b;
+		short c;
+	};
+	struct foo foo1, foo2;
+	...
+
+	foo2.a = foo1.a;
+	foo2.b = foo1.b;
+	foo2.c = foo1.c;
+
+     Because there are no ACCESS_ONCE() wrappers and no volatile markings,
+     the compiler would be well within its rights to implement these three
+     assignment statements as a pair of 32-bit loads followed by a pair
+     of 32-bit stores.  This would result in load tearing on 'foo1.b'
+     and store tearing on 'foo2.b'.  ACCESS_ONCE() again prevents tearing
+     in this example:
+
+	foo2.a = foo1.a;
+	ACCESS_ONCE(foo2.b) = ACCESS_ONCE(foo1.b);
+	foo2.c = foo1.c;
+
+All that aside, it is never necessary to use ACCESS_ONCE() on a variable
+that has been marked volatile.  For example, because 'jiffies' is marked
+volatile, it is never necessary to say ACCESS_ONCE(jiffies).  The reason
+for this is that ACCESS_ONCE() is implemented as a volatile cast, which
+has no effect when its argument is already marked volatile.
+
+Please note that these compiler barriers have no direct effect on the CPU,
+which may then reorder things however it wishes.
 
 
 CPU MEMORY BARRIERS
-- 
cgit v0.10.2


From 01352fb81658cbf78c55844de8e3d1d606bbf3f8 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 11 Dec 2013 13:59:08 -0800
Subject: locking: Add an smp_mb__after_unlock_lock() for UNLOCK+BLOCK barrier

The Linux kernel has traditionally required that an UNLOCK+LOCK
pair act as a full memory barrier when either (1) that
UNLOCK+LOCK pair was executed by the same CPU or task, or (2)
the same lock variable was used for the UNLOCK and LOCK.  It now
seems likely that very few places in the kernel rely on this
full-memory-barrier semantic, and with the advent of queued
locks, providing this semantic either requires complex
reasoning, or for some architectures, added overhead.

This commit therefore adds a smp_mb__after_unlock_lock(), which
may be placed after a LOCK primitive to restore the
full-memory-barrier semantic. All definitions are currently
no-ops, but will be upgraded for some architectures when queued
locks arrive.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: <linux-arch@vger.kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1386799151-2219-5-git-send-email-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 75f3494..3f2867f 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -130,6 +130,16 @@ do {								\
 #define smp_mb__before_spinlock()	smp_wmb()
 #endif
 
+/*
+ * Place this after a lock-acquisition primitive to guarantee that
+ * an UNLOCK+LOCK pair act as a full barrier.  This guarantee applies
+ * if the UNLOCK and LOCK are executed by the same CPU or if the
+ * UNLOCK and LOCK operate on the same lock variable.
+ */
+#ifndef smp_mb__after_unlock_lock
+#define smp_mb__after_unlock_lock()	do { } while (0)
+#endif
+
 /**
  * raw_spin_unlock_wait - wait until the spinlock gets unlocked
  * @lock: the spinlock in question.
-- 
cgit v0.10.2


From 17eb88e068430014deb709e5af34197cdf2390c9 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 11 Dec 2013 13:59:09 -0800
Subject: Documentation/memory-barriers.txt: Downgrade UNLOCK+BLOCK

Historically, an UNLOCK+LOCK pair executed by one CPU, by one
task, or on a given lock variable has implied a full memory
barrier.  In a recent LKML thread, the wisdom of this historical
approach was called into question:
http://www.spinics.net/lists/linux-mm/msg65653.html, in part due
to the memory-order complexities of low-handoff-overhead queued
locks on x86 systems.

This patch therefore removes this guarantee from the
documentation, and further documents how to restore it via a new
smp_mb__after_unlock_lock() primitive.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: <linux-arch@vger.kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1386799151-2219-6-git-send-email-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 919fd60..cb753c8 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -402,12 +402,18 @@ And a couple of implicit varieties:
      Memory operations that occur after an UNLOCK operation may appear to
      happen before it completes.
 
-     LOCK and UNLOCK operations are guaranteed to appear with respect to each
-     other strictly in the order specified.
-
      The use of LOCK and UNLOCK operations generally precludes the need for
      other sorts of memory barrier (but note the exceptions mentioned in the
-     subsection "MMIO write barrier").
+     subsection "MMIO write barrier").  In addition, an UNLOCK+LOCK pair
+     is -not- guaranteed to act as a full memory barrier.  However,
+     after a LOCK on a given lock variable, all memory accesses preceding any
+     prior UNLOCK on that same variable are guaranteed to be visible.
+     In other words, within a given lock variable's critical section,
+     all accesses of all previous critical sections for that lock variable
+     are guaranteed to have completed.
+
+     This means that LOCK acts as a minimal "acquire" operation and
+     UNLOCK acts as a minimal "release" operation.
 
 
 Memory barriers are only required where there's a possibility of interaction
@@ -1633,8 +1639,12 @@ for each construct.  These operations all imply certain barriers:
      Memory operations issued after the LOCK will be completed after the LOCK
      operation has completed.
 
-     Memory operations issued before the LOCK may be completed after the LOCK
-     operation has completed.
+     Memory operations issued before the LOCK may be completed after the
+     LOCK operation has completed.  An smp_mb__before_spinlock(), combined
+     with a following LOCK, orders prior loads against subsequent stores
+     and stores and prior stores against subsequent stores.  Note that
+     this is weaker than smp_mb()!  The smp_mb__before_spinlock()
+     primitive is free on many architectures.
 
  (2) UNLOCK operation implication:
 
@@ -1654,9 +1664,6 @@ for each construct.  These operations all imply certain barriers:
      All LOCK operations issued before an UNLOCK operation will be completed
      before the UNLOCK operation.
 
-     All UNLOCK operations issued before a LOCK operation will be completed
-     before the LOCK operation.
-
  (5) Failed conditional LOCK implication:
 
      Certain variants of the LOCK operation may fail, either due to being
@@ -1664,9 +1671,6 @@ for each construct.  These operations all imply certain barriers:
      signal whilst asleep waiting for the lock to become available.  Failed
      locks do not imply any sort of barrier.
 
-Therefore, from (1), (2) and (4) an UNLOCK followed by an unconditional LOCK is
-equivalent to a full barrier, but a LOCK followed by an UNLOCK is not.
-
 [!] Note: one of the consequences of LOCKs and UNLOCKs being only one-way
     barriers is that the effects of instructions outside of a critical section
     may seep into the inside of the critical section.
@@ -1677,13 +1681,57 @@ LOCK, and an access following the UNLOCK to happen before the UNLOCK, and the
 two accesses can themselves then cross:
 
 	*A = a;
-	LOCK
-	UNLOCK
+	LOCK M
+	UNLOCK M
 	*B = b;
 
 may occur as:
 
-	LOCK, STORE *B, STORE *A, UNLOCK
+	LOCK M, STORE *B, STORE *A, UNLOCK M
+
+This same reordering can of course occur if the LOCK and UNLOCK are
+to the same lock variable, but only from the perspective of another
+CPU not holding that lock.
+
+In short, an UNLOCK followed by a LOCK may -not- be assumed to be a full
+memory barrier because it is possible for a preceding UNLOCK to pass a
+later LOCK from the viewpoint of the CPU, but not from the viewpoint
+of the compiler.  Note that deadlocks cannot be introduced by this
+interchange because if such a deadlock threatened, the UNLOCK would
+simply complete.
+
+If it is necessary for an UNLOCK-LOCK pair to produce a full barrier,
+the LOCK can be followed by an smp_mb__after_unlock_lock() invocation.
+This will produce a full barrier if either (a) the UNLOCK and the LOCK
+are executed by the same CPU or task, or (b) the UNLOCK and LOCK act
+on the same lock variable.  The smp_mb__after_unlock_lock() primitive
+is free on many architectures.  Without smp_mb__after_unlock_lock(),
+the critical sections corresponding to the UNLOCK and the LOCK can cross:
+
+	*A = a;
+	UNLOCK M
+	LOCK N
+	*B = b;
+
+could occur as:
+
+	LOCK N, STORE *B, STORE *A, UNLOCK M
+
+With smp_mb__after_unlock_lock(), they cannot, so that:
+
+	*A = a;
+	UNLOCK M
+	LOCK N
+	smp_mb__after_unlock_lock();
+	*B = b;
+
+will always occur as either of the following:
+
+	STORE *A, UNLOCK, LOCK, STORE *B
+	STORE *A, LOCK, UNLOCK, STORE *B
+
+If the UNLOCK and LOCK were instead both operating on the same lock
+variable, only the first of these two alternatives can occur.
 
 Locks and semaphores may not provide any guarantee of ordering on UP compiled
 systems, and so cannot be counted on in such a situation to actually achieve
@@ -1911,6 +1959,7 @@ However, if the following occurs:
 	UNLOCK M	     [1]
 	ACCESS_ONCE(*D) = d;		ACCESS_ONCE(*E) = e;
 					LOCK M		     [2]
+					smp_mb__after_unlock_lock();
 					ACCESS_ONCE(*F) = f;
 					ACCESS_ONCE(*G) = g;
 					UNLOCK M	     [2]
@@ -1928,6 +1977,11 @@ But assuming CPU 1 gets the lock first, CPU 3 won't see any of:
 	*F, *G or *H preceding LOCK M [2]
 	*A, *B, *C, *E, *F or *G following UNLOCK M [2]
 
+Note that the smp_mb__after_unlock_lock() is critically important
+here: Without it CPU 3 might see some of the above orderings.
+Without smp_mb__after_unlock_lock(), the accesses are not guaranteed
+to be seen in order unless CPU 3 holds lock M.
+
 
 LOCKS VS I/O ACCESSES
 ---------------------
-- 
cgit v0.10.2


From 6303b9c87d52eaedc82968d3ff59c471e7682afc Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 11 Dec 2013 13:59:10 -0800
Subject: rcu: Apply smp_mb__after_unlock_lock() to preserve grace periods

RCU must ensure that there is the equivalent of a full memory
barrier between any memory access preceding grace period and any
memory access following that same grace period, regardless of
which CPU(s) happen to execute the two memory accesses.
Therefore, downgrading UNLOCK+LOCK to no longer imply a full
memory barrier requires some adjustments to RCU.

This commit therefore adds smp_mb__after_unlock_lock()
invocations as needed after the RCU lock acquisitions that need
to be part of a full-memory-barrier UNLOCK+LOCK.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: <linux-arch@vger.kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1386799151-2219-7-git-send-email-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index dd08198..a6205a0 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1133,8 +1133,10 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp)
 	 * hold it, acquire the root rcu_node structure's lock in order to
 	 * start one (if needed).
 	 */
-	if (rnp != rnp_root)
+	if (rnp != rnp_root) {
 		raw_spin_lock(&rnp_root->lock);
+		smp_mb__after_unlock_lock();
+	}
 
 	/*
 	 * Get a new grace-period number.  If there really is no grace
@@ -1354,6 +1356,7 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 		local_irq_restore(flags);
 		return;
 	}
+	smp_mb__after_unlock_lock();
 	__note_gp_changes(rsp, rnp, rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
@@ -1368,6 +1371,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 
 	rcu_bind_gp_kthread();
 	raw_spin_lock_irq(&rnp->lock);
+	smp_mb__after_unlock_lock();
 	if (rsp->gp_flags == 0) {
 		/* Spurious wakeup, tell caller to go back to sleep.  */
 		raw_spin_unlock_irq(&rnp->lock);
@@ -1409,6 +1413,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq(&rnp->lock);
+		smp_mb__after_unlock_lock();
 		rdp = this_cpu_ptr(rsp->rda);
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
@@ -1463,6 +1468,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 	/* Clear flag to prevent immediate re-entry. */
 	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		raw_spin_lock_irq(&rnp->lock);
+		smp_mb__after_unlock_lock();
 		rsp->gp_flags &= ~RCU_GP_FLAG_FQS;
 		raw_spin_unlock_irq(&rnp->lock);
 	}
@@ -1480,6 +1486,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	raw_spin_lock_irq(&rnp->lock);
+	smp_mb__after_unlock_lock();
 	gp_duration = jiffies - rsp->gp_start;
 	if (gp_duration > rsp->gp_max)
 		rsp->gp_max = gp_duration;
@@ -1505,6 +1512,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq(&rnp->lock);
+		smp_mb__after_unlock_lock();
 		ACCESS_ONCE(rnp->completed) = rsp->gpnum;
 		rdp = this_cpu_ptr(rsp->rda);
 		if (rnp == rdp->mynode)
@@ -1515,6 +1523,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	}
 	rnp = rcu_get_root(rsp);
 	raw_spin_lock_irq(&rnp->lock);
+	smp_mb__after_unlock_lock();
 	rcu_nocb_gp_set(rnp, nocb);
 
 	rsp->completed = rsp->gpnum; /* Declare grace period done. */
@@ -1749,6 +1758,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 		rnp_c = rnp;
 		rnp = rnp->parent;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		WARN_ON_ONCE(rnp_c->qsmask);
 	}
 
@@ -1778,6 +1788,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 
 	rnp = rdp->mynode;
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	if (rdp->passed_quiesce == 0 || rdp->gpnum != rnp->gpnum ||
 	    rnp->completed == rnp->gpnum) {
 
@@ -1992,6 +2003,7 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 	mask = rdp->grpmask;	/* rnp->grplo is constant. */
 	do {
 		raw_spin_lock(&rnp->lock);	/* irqs already disabled. */
+		smp_mb__after_unlock_lock();
 		rnp->qsmaskinit &= ~mask;
 		if (rnp->qsmaskinit != 0) {
 			if (rnp != rdp->mynode)
@@ -2202,6 +2214,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
 		cond_resched();
 		mask = 0;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		if (!rcu_gp_in_progress(rsp)) {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 			return;
@@ -2231,6 +2244,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
 	rnp = rcu_get_root(rsp);
 	if (rnp->qsmask == 0) {
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
 	}
 }
@@ -2263,6 +2277,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
 
 	/* Reached the root of the rcu_node tree, acquire lock. */
 	raw_spin_lock_irqsave(&rnp_old->lock, flags);
+	smp_mb__after_unlock_lock();
 	raw_spin_unlock(&rnp_old->fqslock);
 	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		rsp->n_force_qs_lh++;
@@ -2378,6 +2393,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 			struct rcu_node *rnp_root = rcu_get_root(rsp);
 
 			raw_spin_lock(&rnp_root->lock);
+			smp_mb__after_unlock_lock();
 			rcu_start_gp(rsp);
 			raw_spin_unlock(&rnp_root->lock);
 		} else {
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 6abb03d..eb161d8 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -204,6 +204,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 		rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
 		rnp = rdp->mynode;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
 		t->rcu_blocked_node = rnp;
 
@@ -312,6 +313,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
 	mask = rnp->grpmask;
 	raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
 	raw_spin_lock(&rnp_p->lock);	/* irqs already disabled. */
+	smp_mb__after_unlock_lock();
 	rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags);
 }
 
@@ -381,6 +383,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 		for (;;) {
 			rnp = t->rcu_blocked_node;
 			raw_spin_lock(&rnp->lock);  /* irqs already disabled. */
+			smp_mb__after_unlock_lock();
 			if (rnp == t->rcu_blocked_node)
 				break;
 			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
@@ -605,6 +608,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
 	while (!list_empty(lp)) {
 		t = list_entry(lp->next, typeof(*t), rcu_node_entry);
 		raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+		smp_mb__after_unlock_lock();
 		list_del(&t->rcu_node_entry);
 		t->rcu_blocked_node = rnp_root;
 		list_add(&t->rcu_node_entry, lp_root);
@@ -629,6 +633,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
 	 * in this case.
 	 */
 	raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+	smp_mb__after_unlock_lock();
 	if (rnp_root->boost_tasks != NULL &&
 	    rnp_root->boost_tasks != rnp_root->gp_tasks &&
 	    rnp_root->boost_tasks != rnp_root->exp_tasks)
@@ -772,6 +777,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 	unsigned long mask;
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	for (;;) {
 		if (!sync_rcu_preempt_exp_done(rnp)) {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -787,6 +793,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 		raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
 		rnp = rnp->parent;
 		raw_spin_lock(&rnp->lock); /* irqs already disabled */
+		smp_mb__after_unlock_lock();
 		rnp->expmask &= ~mask;
 	}
 }
@@ -806,6 +813,7 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
 	int must_wait = 0;
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	if (list_empty(&rnp->blkd_tasks)) {
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	} else {
@@ -886,6 +894,7 @@ void synchronize_rcu_expedited(void)
 	/* Initialize ->expmask for all non-leaf rcu_node structures. */
 	rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		rnp->expmask = rnp->qsmaskinit;
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
@@ -1191,6 +1200,7 @@ static int rcu_boost(struct rcu_node *rnp)
 		return 0;  /* Nothing left to boost. */
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 
 	/*
 	 * Recheck under the lock: all tasks in need of boosting
@@ -1377,6 +1387,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	if (IS_ERR(t))
 		return PTR_ERR(t);
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	rnp->boost_kthread_task = t;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	sp.sched_priority = RCU_BOOST_PRIO;
@@ -1769,6 +1780,7 @@ static void rcu_prepare_for_idle(int cpu)
 			continue;
 		rnp = rdp->mynode;
 		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+		smp_mb__after_unlock_lock();
 		rcu_accelerate_cbs(rsp, rnp, rdp);
 		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 	}
@@ -2209,6 +2221,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	struct rcu_node *rnp = rdp->mynode;
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	c = rcu_start_future_gp(rnp, rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
-- 
cgit v0.10.2


From 919fc6e34831d1c2b58bfb5ae261dc3facc9b269 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 11 Dec 2013 13:59:11 -0800
Subject: powerpc: Full barrier for smp_mb__after_unlock_lock()

The powerpc lock acquisition sequence is as follows:

	lwarx; cmpwi; bne; stwcx.; lwsync;

Lock release is as follows:

	lwsync; stw;

If CPU 0 does a store (say, x=1) then a lock release, and CPU 1
does a lock acquisition then a load (say, r1=y), then there is
no guarantee of a full memory barrier between the store to 'x'
and the load from 'y'. To see this, suppose that CPUs 0 and 1
are hardware threads in the same core that share a store buffer,
and that CPU 2 is in some other core, and that CPU 2 does the
following:

	y = 1; sync; r2 = x;

If 'x' and 'y' are both initially zero, then the lock
acquisition and release sequences above can result in r1 and r2
both being equal to zero, which could not happen if unlock+lock
was a full barrier.

This commit therefore makes powerpc's
smp_mb__after_unlock_lock() be a full barrier.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: <linux-arch@vger.kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1386799151-2219-8-git-send-email-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index 5f54a74..f6e78d6 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -28,6 +28,8 @@
 #include <asm/synch.h>
 #include <asm/ppc-opcode.h>
 
+#define smp_mb__after_unlock_lock()	smp_mb()  /* Full ordering for lock. */
+
 #define arch_spin_is_locked(x)		((x)->slock != 0)
 
 #ifdef CONFIG_PPC64
-- 
cgit v0.10.2


From bd02cd2549cfcdfc57cb5ce57ffc3feb94f70575 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 16 Dec 2013 12:04:36 +0100
Subject: radiotap: fix bitmap-end-finding buffer overrun

Evan Huus found (by fuzzing in wireshark) that the radiotap
iterator code can access beyond the length of the buffer if
the first bitmap claims an extension but then there's no
data at all. Fix this.

Cc: stable@vger.kernel.org
Reported-by: Evan Huus <eapache@gmail.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c
index a271c27..722da61 100644
--- a/net/wireless/radiotap.c
+++ b/net/wireless/radiotap.c
@@ -124,6 +124,10 @@ int ieee80211_radiotap_iterator_init(
 	/* find payload start allowing for extended bitmap(s) */
 
 	if (iterator->_bitmap_shifter & (1<<IEEE80211_RADIOTAP_EXT)) {
+		if ((unsigned long)iterator->_arg -
+		    (unsigned long)iterator->_rtheader + sizeof(uint32_t) >
+		    (unsigned long)iterator->_max_length)
+			return -EINVAL;
 		while (get_unaligned_le32(iterator->_arg) &
 					(1 << IEEE80211_RADIOTAP_EXT)) {
 			iterator->_arg += sizeof(uint32_t);
-- 
cgit v0.10.2


From 449666dd1efacaf3f0eb020cc617dd702356575c Mon Sep 17 00:00:00 2001
From: Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
Date: Tue, 26 Nov 2013 14:55:56 +0100
Subject: s390/cio: More efficient handling of CHPID availability events

The CIO layer processes hardware events that indicate that a channel
path has become available by performing a scan of available subchannels
using the Store Subchannel (STSCH) instruction. Performing too many
STSCH instructions in a tight loop can cause high Hypervisor overhead
which can negatively impact the performance of the virtual machine as
a whole.

This patch reduces the number of STSCH instructions performed while
processing a resource accessibility event and while varying a CHPID
online.

In both cases, Linux first performs a STSCH instruction on each unused
subchannel to see if the subchannel has become available. If the STSCH
instruction indicates that the subchannel is available, a full
evaluation of this subchannel is scheduled. Since the full evaluation
includes performing a STSCH instruction, the initial STSCH is
unnecessary and can be removed.

Signed-off-by: Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
Reviewed-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index 13299f9..eee70cb 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -237,26 +237,6 @@ void chsc_chp_offline(struct chp_id chpid)
 	for_each_subchannel_staged(s390_subchannel_remove_chpid, NULL, &link);
 }
 
-static int s390_process_res_acc_new_sch(struct subchannel_id schid, void *data)
-{
-	struct schib schib;
-	/*
-	 * We don't know the device yet, but since a path
-	 * may be available now to the device we'll have
-	 * to do recognition again.
-	 * Since we don't have any idea about which chpid
-	 * that beast may be on we'll have to do a stsch
-	 * on all devices, grr...
-	 */
-	if (stsch_err(schid, &schib))
-		/* We're through */
-		return -ENXIO;
-
-	/* Put it on the slow path. */
-	css_schedule_eval(schid);
-	return 0;
-}
-
 static int __s390_process_res_acc(struct subchannel *sch, void *data)
 {
 	spin_lock_irq(sch->lock);
@@ -287,8 +267,8 @@ static void s390_process_res_acc(struct chp_link *link)
 	 * The more information we have (info), the less scanning
 	 * will we have to do.
 	 */
-	for_each_subchannel_staged(__s390_process_res_acc,
-				   s390_process_res_acc_new_sch, link);
+	for_each_subchannel_staged(__s390_process_res_acc, NULL, link);
+	css_schedule_reprobe();
 }
 
 static int
@@ -663,19 +643,6 @@ static int s390_subchannel_vary_chpid_on(struct subchannel *sch, void *data)
 	return 0;
 }
 
-static int
-__s390_vary_chpid_on(struct subchannel_id schid, void *data)
-{
-	struct schib schib;
-
-	if (stsch_err(schid, &schib))
-		/* We're through */
-		return -ENXIO;
-	/* Put it on the slow path. */
-	css_schedule_eval(schid);
-	return 0;
-}
-
 /**
  * chsc_chp_vary - propagate channel-path vary operation to subchannels
  * @chpid: channl-path ID
@@ -694,7 +661,8 @@ int chsc_chp_vary(struct chp_id chpid, int on)
 		/* Try to update the channel path description. */
 		chp_update_desc(chp);
 		for_each_subchannel_staged(s390_subchannel_vary_chpid_on,
-					   __s390_vary_chpid_on, &chpid);
+					   NULL, &chpid);
+		css_schedule_reprobe();
 	} else
 		for_each_subchannel_staged(s390_subchannel_vary_chpid_off,
 					   NULL, &chpid);
-- 
cgit v0.10.2


From b207f5a8f9a60fda4e995151af7d8670015e261d Mon Sep 17 00:00:00 2001
From: Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
Date: Tue, 26 Nov 2013 14:57:13 +0100
Subject: s390/cio: Relax subchannel scan loop

The CIO layer scans for newly available I/O devices by performing a scan
of available subchannels using the Store Subchannel (STSCH) instruction.
This processing can take a significant amount of time during which no
other task can run on the same CPU (unless CONFIG_PREEMPT has been
enabled). As a result, scheduling latencies for other tasks are
increased noticeably, especially on a single-CPU system.

Fix this problem by explicitly allowing other tasks to be scheduled
each time a subchannel has been processed.

Signed-off-by: Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
Reviewed-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index 8c2cb87..c1f9cc7 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -553,6 +553,9 @@ static int slow_eval_unknown_fn(struct subchannel_id schid, void *data)
 		default:
 			rc = 0;
 		}
+		/* Allow scheduling here since the containing loop might
+		 * take a while.  */
+		cond_resched();
 	}
 	return rc;
 }
-- 
cgit v0.10.2


From 175746eb06a8925274558793814d8c802dc48276 Mon Sep 17 00:00:00 2001
From: Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
Date: Tue, 26 Nov 2013 14:58:08 +0100
Subject: s390/cio: Delay scan for newly available I/O devices

The CIO layer scans for newly available I/O devices by performing a scan
of available subchannels using the Store Subchannel (STSCH) instruction.
Performing too many STSCH instructions in a tight loop can cause high
Hypervisor overhead which can negatively impact the performance of the
virtual machine as a whole.

A subchannel scan is triggered for example during a hardware event that
indicates that a channel path has become available. It is also triggered
by the DASD device driver for each device that is set online.

This patch reduces the number of STSCH instructions being performed by
delaying the start of the actual subchannel scan by 1 second. Multiple
scan requests that are scheduled during this time will be merged into a
single scan loop.

The trade-off consists of a short delay that is introduced between
the time that the event is processed and a newly available device
becoming usable. This delay should be acceptable since it only
affects devices that have not been in use before.

Signed-off-by: Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
Reviewed-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/drivers/s390/cio/blacklist.c b/drivers/s390/cio/blacklist.c
index a9fe3de..77ee4da 100644
--- a/drivers/s390/cio/blacklist.c
+++ b/drivers/s390/cio/blacklist.c
@@ -269,7 +269,7 @@ static int blacklist_parse_proc_parameters(char *buf)
 	else
 		return -EINVAL;
 
-	css_schedule_reprobe();
+	css_schedule_eval_all_unreg(0);
 
 	return rc;
 }
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index c1f9cc7..604333e 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -575,7 +575,7 @@ static void css_slow_path_func(struct work_struct *unused)
 	spin_unlock_irqrestore(&slow_subchannel_lock, flags);
 }
 
-static DECLARE_WORK(slow_path_work, css_slow_path_func);
+static DECLARE_DELAYED_WORK(slow_path_work, css_slow_path_func);
 struct workqueue_struct *cio_work_q;
 
 void css_schedule_eval(struct subchannel_id schid)
@@ -585,7 +585,7 @@ void css_schedule_eval(struct subchannel_id schid)
 	spin_lock_irqsave(&slow_subchannel_lock, flags);
 	idset_sch_add(slow_subchannel_set, schid);
 	atomic_set(&css_eval_scheduled, 1);
-	queue_work(cio_work_q, &slow_path_work);
+	queue_delayed_work(cio_work_q, &slow_path_work, 0);
 	spin_unlock_irqrestore(&slow_subchannel_lock, flags);
 }
 
@@ -596,7 +596,7 @@ void css_schedule_eval_all(void)
 	spin_lock_irqsave(&slow_subchannel_lock, flags);
 	idset_fill(slow_subchannel_set);
 	atomic_set(&css_eval_scheduled, 1);
-	queue_work(cio_work_q, &slow_path_work);
+	queue_delayed_work(cio_work_q, &slow_path_work, 0);
 	spin_unlock_irqrestore(&slow_subchannel_lock, flags);
 }
 
@@ -609,7 +609,7 @@ static int __unset_registered(struct device *dev, void *data)
 	return 0;
 }
 
-static void css_schedule_eval_all_unreg(void)
+void css_schedule_eval_all_unreg(unsigned long delay)
 {
 	unsigned long flags;
 	struct idset *unreg_set;
@@ -627,7 +627,7 @@ static void css_schedule_eval_all_unreg(void)
 	spin_lock_irqsave(&slow_subchannel_lock, flags);
 	idset_add_set(slow_subchannel_set, unreg_set);
 	atomic_set(&css_eval_scheduled, 1);
-	queue_work(cio_work_q, &slow_path_work);
+	queue_delayed_work(cio_work_q, &slow_path_work, delay);
 	spin_unlock_irqrestore(&slow_subchannel_lock, flags);
 	idset_free(unreg_set);
 }
@@ -640,7 +640,8 @@ void css_wait_for_slow_path(void)
 /* Schedule reprobing of all unregistered subchannels. */
 void css_schedule_reprobe(void)
 {
-	css_schedule_eval_all_unreg();
+	/* Schedule with a delay to allow merging of subsequent calls. */
+	css_schedule_eval_all_unreg(1 * HZ);
 }
 EXPORT_SYMBOL_GPL(css_schedule_reprobe);
 
diff --git a/drivers/s390/cio/css.h b/drivers/s390/cio/css.h
index 2935132..2c9107e 100644
--- a/drivers/s390/cio/css.h
+++ b/drivers/s390/cio/css.h
@@ -133,6 +133,7 @@ extern struct channel_subsystem *channel_subsystems[];
 /* Helper functions to build lists for the slow path. */
 void css_schedule_eval(struct subchannel_id schid);
 void css_schedule_eval_all(void);
+void css_schedule_eval_all_unreg(unsigned long delay);
 int css_complete_work(void);
 
 int sch_is_pseudo_sch(struct subchannel *);
-- 
cgit v0.10.2


From 47d30674d6c79197fa7bfb0d09d5857f61e0277b Mon Sep 17 00:00:00 2001
From: Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
Date: Tue, 26 Nov 2013 14:59:21 +0100
Subject: s390/css: Prevent unnecessary allocation in subchannel loop

Subchannel looping function for_each_subchannel_staged() allocates a
subchannel-ID-bitmap to efficiently iterate over the list of known
and unknown subchannels. Since this function is also used to iterate
over known-subchannels only, optimize that case by not requiring the
ID-bitmap allocation and falling back to simple bus_for_each_dev()
looping.

Signed-off-by: Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
Reviewed-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index 604333e..0268e5f 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -69,7 +69,8 @@ static int call_fn_known_sch(struct device *dev, void *data)
 	struct cb_data *cb = data;
 	int rc = 0;
 
-	idset_sch_del(cb->set, sch->schid);
+	if (cb->set)
+		idset_sch_del(cb->set, sch->schid);
 	if (cb->fn_known_sch)
 		rc = cb->fn_known_sch(sch, cb->data);
 	return rc;
@@ -115,6 +116,13 @@ int for_each_subchannel_staged(int (*fn_known)(struct subchannel *, void *),
 	cb.fn_known_sch = fn_known;
 	cb.fn_unknown_sch = fn_unknown;
 
+	if (fn_known && !fn_unknown) {
+		/* Skip idset allocation in case of known-only loop. */
+		cb.set = NULL;
+		return bus_for_each_dev(&css_bus_type, NULL, &cb,
+					call_fn_known_sch);
+	}
+
 	cb.set = idset_sch_new();
 	if (!cb.set)
 		/* fall back to brute force scanning in case of oom */
-- 
cgit v0.10.2


From e6b2551425d961e68e70e806e22ec40787f7ed67 Mon Sep 17 00:00:00 2001
From: Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
Date: Tue, 26 Nov 2013 15:00:37 +0100
Subject: s390/blacklist: Perform subchannel scan only when needed

Move scheduling of a subchannel scan to those instances where new
devices may actually have become available. This reduces unnecessary
scan work in case devices were added to the blacklist.

Signed-off-by: Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
Reviewed-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/drivers/s390/cio/blacklist.c b/drivers/s390/cio/blacklist.c
index 77ee4da..b3f791b 100644
--- a/drivers/s390/cio/blacklist.c
+++ b/drivers/s390/cio/blacklist.c
@@ -260,16 +260,16 @@ static int blacklist_parse_proc_parameters(char *buf)
 
 	parm = strsep(&buf, " ");
 
-	if (strcmp("free", parm) == 0)
+	if (strcmp("free", parm) == 0) {
 		rc = blacklist_parse_parameters(buf, free, 0);
-	else if (strcmp("add", parm) == 0)
+		css_schedule_eval_all_unreg(0);
+	} else if (strcmp("add", parm) == 0)
 		rc = blacklist_parse_parameters(buf, add, 0);
 	else if (strcmp("purge", parm) == 0)
 		return ccw_purge_blacklisted();
 	else
 		return -EINVAL;
 
-	css_schedule_eval_all_unreg(0);
 
 	return rc;
 }
-- 
cgit v0.10.2


From dea24190fbfb340dea5224e32161955514bef31b Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Tue, 3 Dec 2013 10:06:29 +0100
Subject: s390/smp: only send external call ipi if needed

If the per cpu ec_mask bit of the receiving cpu is already set there is
no need to send an ipi, since a different cpu has already sent an ipi
and the receiving cpu has not yet executed the external call ipi handler.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index dc4a534..86b2913 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -159,9 +159,9 @@ static void pcpu_ec_call(struct pcpu *pcpu, int ec_bit)
 {
 	int order;
 
-	set_bit(ec_bit, &pcpu->ec_mask);
-	order = pcpu_running(pcpu) ?
-		SIGP_EXTERNAL_CALL : SIGP_EMERGENCY_SIGNAL;
+	if (test_and_set_bit(ec_bit, &pcpu->ec_mask))
+		return;
+	order = pcpu_running(pcpu) ? SIGP_EXTERNAL_CALL : SIGP_EMERGENCY_SIGNAL;
 	pcpu_sigp_retry(pcpu, order, 0);
 }
 
-- 
cgit v0.10.2


From 1c182a628075af7431edb8155601740867b5ae51 Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Tue, 3 Dec 2013 11:09:10 +0100
Subject: s390/ptrace: simplify enable/disable single step

The user_enable_single_step() and user_disable_sindle_step() functions
are always called on the inferior, never for the currently active
process. Remove the unnecessary check for the current process and
the update_cr_regs() call from the enable/disable functions.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index e65c91c..c369a26 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -107,15 +107,11 @@ void update_cr_regs(struct task_struct *task)
 void user_enable_single_step(struct task_struct *task)
 {
 	set_tsk_thread_flag(task, TIF_SINGLE_STEP);
-	if (task == current)
-		update_cr_regs(task);
 }
 
 void user_disable_single_step(struct task_struct *task)
 {
 	clear_tsk_thread_flag(task, TIF_SINGLE_STEP);
-	if (task == current)
-		update_cr_regs(task);
 }
 
 /*
-- 
cgit v0.10.2


From c63badebfebacdba827ab1cc1d420fc81bd8d818 Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Tue, 3 Dec 2013 14:57:18 +0100
Subject: s390: optimize control register update

It is less expensive to update control registers 0 and 2 with two
individual stctg/lctlg instructions as with a single one that spans
control register 0, 1 and 2.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index c369a26..f6be608 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -56,25 +56,26 @@ void update_cr_regs(struct task_struct *task)
 #ifdef CONFIG_64BIT
 	/* Take care of the enable/disable of transactional execution. */
 	if (MACHINE_HAS_TE) {
-		unsigned long cr[3], cr_new[3];
+		unsigned long cr, cr_new;
 
-		__ctl_store(cr, 0, 2);
-		cr_new[1] = cr[1];
+		__ctl_store(cr, 0, 0);
 		/* Set or clear transaction execution TXC bit 8. */
+		cr_new = cr | (1UL << 55);
 		if (task->thread.per_flags & PER_FLAG_NO_TE)
-			cr_new[0] = cr[0] & ~(1UL << 55);
-		else
-			cr_new[0] = cr[0] | (1UL << 55);
+			cr_new &= ~(1UL << 55);
+		if (cr_new != cr)
+			__ctl_load(cr, 0, 0);
 		/* Set or clear transaction execution TDC bits 62 and 63. */
-		cr_new[2] = cr[2] & ~3UL;
+		__ctl_store(cr, 2, 2);
+		cr_new = cr & ~3UL;
 		if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND) {
 			if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND_TEND)
-				cr_new[2] |= 1UL;
+				cr_new |= 1UL;
 			else
-				cr_new[2] |= 2UL;
+				cr_new |= 2UL;
 		}
-		if (memcmp(&cr_new, &cr, sizeof(cr)))
-			__ctl_load(cr_new, 0, 2);
+		if (cr_new != cr)
+			__ctl_load(cr_new, 2, 2);
 	}
 #endif
 	/* Copy user specified PER registers */
-- 
cgit v0.10.2


From 03439e7d0a7ab3d77a74523b9ba64736c0fc28de Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Wed, 4 Dec 2013 14:29:11 +0100
Subject: s390/3270: fix use after free of tty3270_screen structure

The deactivation and freeing of the tty view of the 3270 device
can race with a tty3270_update invocation via the update timer.
To fix this move the del_timer_sync call for the update timer from
tty3270_free_view to tty3270_free prior to the tty3270_free_screen
call.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/drivers/s390/char/tty3270.c b/drivers/s390/char/tty3270.c
index 3f4ca4e..07cf182 100644
--- a/drivers/s390/char/tty3270.c
+++ b/drivers/s390/char/tty3270.c
@@ -125,10 +125,7 @@ static void tty3270_resize_work(struct work_struct *work);
  */
 static void tty3270_set_timer(struct tty3270 *tp, int expires)
 {
-	if (expires == 0)
-		del_timer(&tp->timer);
-	else
-		mod_timer(&tp->timer, jiffies + expires);
+	mod_timer(&tp->timer, jiffies + expires);
 }
 
 /*
@@ -744,7 +741,6 @@ tty3270_free_view(struct tty3270 *tp)
 {
 	int pages;
 
-	del_timer_sync(&tp->timer);
 	kbd_free(tp->kbd);
 	raw3270_request_free(tp->kreset);
 	raw3270_request_free(tp->read);
@@ -877,6 +873,7 @@ tty3270_free(struct raw3270_view *view)
 {
 	struct tty3270 *tp = container_of(view, struct tty3270, view);
 
+	del_timer_sync(&tp->timer);
 	tty3270_free_screen(tp->screen, tp->view.rows);
 	tty3270_free_view(tp);
 }
-- 
cgit v0.10.2


From 96619fc1b3d06703113ab4c5cd8c15f35a42dc99 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Thu, 5 Dec 2013 12:42:09 +0100
Subject: s390/smp: reduce memory consumption of pcpu_devices array

Remove the embedded struct cpu from struct pcpu and replace it with a
pointer instead. The struct cpu now gets allocated when a new cpu gets
detected.

The size of the pcpu_devices array (NR_CPUS * sizeof(struct pcpu)) gets
reduced by nearly 120KB.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 86b2913..8ceefc9 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -59,7 +59,7 @@ enum {
 };
 
 struct pcpu {
-	struct cpu cpu;
+	struct cpu *cpu;
 	struct _lowcore *lowcore;	/* lowcore page(s) for the cpu */
 	unsigned long async_stack;	/* async stack for the cpu */
 	unsigned long panic_stack;	/* panic stack for the cpu */
@@ -958,7 +958,7 @@ static int smp_cpu_notify(struct notifier_block *self, unsigned long action,
 			  void *hcpu)
 {
 	unsigned int cpu = (unsigned int)(long)hcpu;
-	struct cpu *c = &pcpu_devices[cpu].cpu;
+	struct cpu *c = pcpu_devices[cpu].cpu;
 	struct device *s = &c->dev;
 	int err = 0;
 
@@ -975,10 +975,15 @@ static int smp_cpu_notify(struct notifier_block *self, unsigned long action,
 
 static int smp_add_present_cpu(int cpu)
 {
-	struct cpu *c = &pcpu_devices[cpu].cpu;
-	struct device *s = &c->dev;
+	struct device *s;
+	struct cpu *c;
 	int rc;
 
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return -ENOMEM;
+	pcpu_devices[cpu].cpu = c;
+	s = &c->dev;
 	c->hotpluggable = 1;
 	rc = register_cpu(c, cpu);
 	if (rc)
-- 
cgit v0.10.2


From 41932bc1c86e527f866acfcd26506da3bd20509b Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Tue, 10 Dec 2013 16:18:07 +0100
Subject: s390/compat: correct check for EFAULT in rt-signal frame creation

The return code of the __put_user call to store the rt_sigreturn
system call to the user stack if not properly checked, the err
variable is only checked before to the __put_user. Use an if
statement instead.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 95e7ba0..8b84bc3 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -412,8 +412,9 @@ static int setup_rt_frame32(int sig, struct k_sigaction *ka, siginfo_t *info,
 		regs->gprs[14] = (__u64 __force) ka->sa.sa_restorer | PSW32_ADDR_AMODE;
 	} else {
 		regs->gprs[14] = (__u64 __force) frame->retcode | PSW32_ADDR_AMODE;
-		err |= __put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn,
-				  (u16 __force __user *)(frame->retcode));
+		if (__put_user(S390_SYSCALL_OPCODE | __NR_rt_sigreturn,
+			       (u16 __force __user *)(frame->retcode)))
+			goto give_sigsegv;
 	}
 
 	/* Set up backchain. */
-- 
cgit v0.10.2


From 333cce91f384409fb6a3e656dc11e21e872c5ea2 Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Thu, 5 Dec 2013 18:46:51 +0100
Subject: s390/sclp_early: Get rid of sclp_early_read_info_sccb_valid

The early sclp detect functions gather the available SCLP facility
information. The sclp_early_read_info_sccb_valid indicates whether the
early sclp request was valid.  However, one external reference to it
checks for particular sclp facility bits and this should be sufficient.
Another occurance is in the sclp_get_ipl_info() function that is called
later.  Because all information are available at the early stage, save
the ipl information when detecting the sclp facilities.  Hence, no more
checks for sclp_early_read_info_sccb_valid are required.

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Reviewed-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/drivers/s390/char/sclp.h b/drivers/s390/char/sclp.h
index 6fbe096..fea76ae 100644
--- a/drivers/s390/char/sclp.h
+++ b/drivers/s390/char/sclp.h
@@ -183,7 +183,6 @@ extern unsigned long sclp_console_full;
 extern u8 sclp_fac84;
 extern unsigned long long sclp_rzm;
 extern unsigned long long sclp_rnmax;
-extern __initdata int sclp_early_read_info_sccb_valid;
 
 /* useful inlines */
 
diff --git a/drivers/s390/char/sclp_cmd.c b/drivers/s390/char/sclp_cmd.c
index eaa21d5..cb3c4e0 100644
--- a/drivers/s390/char/sclp_cmd.c
+++ b/drivers/s390/char/sclp_cmd.c
@@ -455,8 +455,6 @@ static int __init sclp_detect_standby_memory(void)
 
 	if (OLDMEM_BASE) /* No standby memory in kdump mode */
 		return 0;
-	if (!sclp_early_read_info_sccb_valid)
-		return 0;
 	if ((sclp_facilities & 0xe00000000000ULL) != 0xe00000000000ULL)
 		return 0;
 	rc = -ENOMEM;
diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c
index 1465e95..e4e5b32 100644
--- a/drivers/s390/char/sclp_early.c
+++ b/drivers/s390/char/sclp_early.c
@@ -38,8 +38,8 @@ struct read_info_sccb {
 static __initdata struct read_info_sccb early_read_info_sccb;
 static __initdata char sccb_early[PAGE_SIZE] __aligned(PAGE_SIZE);
 static unsigned long sclp_hsa_size;
+static struct sclp_ipl_info sclp_ipl_info;
 
-__initdata int sclp_early_read_info_sccb_valid;
 u64 sclp_facilities;
 u8 sclp_fac84;
 unsigned long long sclp_rzm;
@@ -63,10 +63,9 @@ out:
 	return rc;
 }
 
-static void __init sclp_read_info_early(void)
+static int __init sclp_read_info_early(void)
 {
-	int rc;
-	int i;
+	int rc, i;
 	struct read_info_sccb *sccb;
 	sclp_cmdw_t commands[] = {SCLP_CMDW_READ_SCP_INFO_FORCED,
 				  SCLP_CMDW_READ_SCP_INFO};
@@ -83,21 +82,19 @@ static void __init sclp_read_info_early(void)
 
 		if (rc)
 			break;
-		if (sccb->header.response_code == 0x10) {
-			sclp_early_read_info_sccb_valid = 1;
-			break;
-		}
+		if (sccb->header.response_code == 0x10)
+			return 0;
 		if (sccb->header.response_code != 0x1f0)
 			break;
 	}
+	return -EIO;
 }
 
 static void __init sclp_facilities_detect(void)
 {
 	struct read_info_sccb *sccb;
 
-	sclp_read_info_early();
-	if (!sclp_early_read_info_sccb_valid)
+	if (sclp_read_info_early())
 		return;
 
 	sccb = &early_read_info_sccb;
@@ -108,6 +105,12 @@ static void __init sclp_facilities_detect(void)
 	sclp_rnmax = sccb->rnmax ? sccb->rnmax : sccb->rnmax2;
 	sclp_rzm = sccb->rnsize ? sccb->rnsize : sccb->rnsize2;
 	sclp_rzm <<= 20;
+
+	/* Save IPL information */
+	sclp_ipl_info.is_valid = 1;
+	if (sccb->flags & 0x2)
+		sclp_ipl_info.has_dump = 1;
+	memcpy(&sclp_ipl_info.loadparm, &sccb->loadparm, LOADPARM_LEN);
 }
 
 bool __init sclp_has_linemode(void)
@@ -146,19 +149,12 @@ unsigned long long sclp_get_rzm(void)
 
 /*
  * This function will be called after sclp_facilities_detect(), which gets
- * called from early.c code. Therefore the sccb should have valid contents.
+ * called from early.c code. The sclp_facilities_detect() function retrieves
+ * and saves the IPL information.
  */
 void __init sclp_get_ipl_info(struct sclp_ipl_info *info)
 {
-	struct read_info_sccb *sccb;
-
-	if (!sclp_early_read_info_sccb_valid)
-		return;
-	sccb = &early_read_info_sccb;
-	info->is_valid = 1;
-	if (sccb->flags & 0x2)
-		info->has_dump = 1;
-	memcpy(&info->loadparm, &sccb->loadparm, LOADPARM_LEN);
+	*info = sclp_ipl_info;
 }
 
 static int __init sclp_cmd_early(sclp_cmdw_t cmd, void *sccb)
-- 
cgit v0.10.2


From 56e57a84a7856130f45009ce1713dc8ec8e59887 Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Thu, 5 Dec 2013 19:03:50 +0100
Subject: s390/sclp_early: Replace early_read_info_sccb with sccb_early

Replace early_read_info_sccb and use sccb_early instead.
Also saves some memory.

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Reviewed-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c
index e4e5b32..dc4ed04 100644
--- a/drivers/s390/char/sclp_early.c
+++ b/drivers/s390/char/sclp_early.c
@@ -35,8 +35,7 @@ struct read_info_sccb {
 	u8	_reserved5[4096 - 112];	/* 112-4095 */
 } __packed __aligned(PAGE_SIZE);
 
-static __initdata struct read_info_sccb early_read_info_sccb;
-static __initdata char sccb_early[PAGE_SIZE] __aligned(PAGE_SIZE);
+static char sccb_early[PAGE_SIZE] __aligned(PAGE_SIZE) __initdata;
 static unsigned long sclp_hsa_size;
 static struct sclp_ipl_info sclp_ipl_info;
 
@@ -63,14 +62,12 @@ out:
 	return rc;
 }
 
-static int __init sclp_read_info_early(void)
+static int __init sclp_read_info_early(struct read_info_sccb *sccb)
 {
 	int rc, i;
-	struct read_info_sccb *sccb;
 	sclp_cmdw_t commands[] = {SCLP_CMDW_READ_SCP_INFO_FORCED,
 				  SCLP_CMDW_READ_SCP_INFO};
 
-	sccb = &early_read_info_sccb;
 	for (i = 0; i < ARRAY_SIZE(commands); i++) {
 		do {
 			memset(sccb, 0, sizeof(*sccb));
@@ -92,12 +89,11 @@ static int __init sclp_read_info_early(void)
 
 static void __init sclp_facilities_detect(void)
 {
-	struct read_info_sccb *sccb;
+	struct read_info_sccb *sccb = (void *) &sccb_early;
 
-	if (sclp_read_info_early())
+	if (sclp_read_info_early(sccb))
 		return;
 
-	sccb = &early_read_info_sccb;
 	sclp_facilities = sccb->facilities;
 	sclp_fac84 = sccb->fac84;
 	if (sccb->fac85 & 0x02)
-- 
cgit v0.10.2


From 5d5de1a068efffb0dcc03235e6fa258201096f02 Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Thu, 5 Dec 2013 19:13:36 +0100
Subject: s390/sclp_early: Pass sccb pointer to every *_detect() function

Add a sccb pointer parameter to *_detect() functions instead of accessing
the global sccb_early variable directly.

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Reviewed-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c
index dc4ed04..1af3555 100644
--- a/drivers/s390/char/sclp_early.c
+++ b/drivers/s390/char/sclp_early.c
@@ -87,10 +87,8 @@ static int __init sclp_read_info_early(struct read_info_sccb *sccb)
 	return -EIO;
 }
 
-static void __init sclp_facilities_detect(void)
+static void __init sclp_facilities_detect(struct read_info_sccb *sccb)
 {
-	struct read_info_sccb *sccb = (void *) &sccb_early;
-
 	if (sclp_read_info_early(sccb))
 		return;
 
@@ -181,11 +179,10 @@ static void __init sccb_init_eq_size(struct sdias_sccb *sccb)
 	sccb->evbuf.dbs = 1;
 }
 
-static int __init sclp_set_event_mask(unsigned long receive_mask,
+static int __init sclp_set_event_mask(struct init_sccb *sccb,
+				      unsigned long receive_mask,
 				      unsigned long send_mask)
 {
-	struct init_sccb *sccb = (void *) &sccb_early;
-
 	memset(sccb, 0, sizeof(*sccb));
 	sccb->header.length = sizeof(*sccb);
 	sccb->mask_length = sizeof(sccb_mask_t);
@@ -194,10 +191,8 @@ static int __init sclp_set_event_mask(unsigned long receive_mask,
 	return sclp_cmd_early(SCLP_CMDW_WRITE_EVENT_MASK, sccb);
 }
 
-static long __init sclp_hsa_size_init(void)
+static long __init sclp_hsa_size_init(struct sdias_sccb *sccb)
 {
-	struct sdias_sccb *sccb = (void *) &sccb_early;
-
 	sccb_init_eq_size(sccb);
 	if (sclp_cmd_early(SCLP_CMDW_WRITE_EVENT_DATA, sccb))
 		return -EIO;
@@ -206,10 +201,8 @@ static long __init sclp_hsa_size_init(void)
 	return 0;
 }
 
-static long __init sclp_hsa_copy_wait(void)
+static long __init sclp_hsa_copy_wait(struct sccb_header *sccb)
 {
-	struct sccb_header *sccb = (void *) &sccb_early;
-
 	memset(sccb, 0, PAGE_SIZE);
 	sccb->length = PAGE_SIZE;
 	if (sclp_cmd_early(SCLP_CMDW_READ_EVENT_DATA, sccb))
@@ -222,25 +215,25 @@ unsigned long sclp_get_hsa_size(void)
 	return sclp_hsa_size;
 }
 
-static void __init sclp_hsa_size_detect(void)
+static void __init sclp_hsa_size_detect(void *sccb)
 {
 	long size;
 
 	/* First try synchronous interface (LPAR) */
-	if (sclp_set_event_mask(0, 0x40000010))
+	if (sclp_set_event_mask(sccb, 0, 0x40000010))
 		return;
-	size = sclp_hsa_size_init();
+	size = sclp_hsa_size_init(sccb);
 	if (size < 0)
 		return;
 	if (size != 0)
 		goto out;
 	/* Then try asynchronous interface (z/VM) */
-	if (sclp_set_event_mask(0x00000010, 0x40000010))
+	if (sclp_set_event_mask(sccb, 0x00000010, 0x40000010))
 		return;
-	size = sclp_hsa_size_init();
+	size = sclp_hsa_size_init(sccb);
 	if (size < 0)
 		return;
-	size = sclp_hsa_copy_wait();
+	size = sclp_hsa_copy_wait(sccb);
 	if (size < 0)
 		return;
 out:
@@ -249,7 +242,9 @@ out:
 
 void __init sclp_early_detect(void)
 {
-	sclp_facilities_detect();
-	sclp_hsa_size_detect();
-	sclp_set_event_mask(0, 0);
+	void *sccb = &sccb_early;
+
+	sclp_facilities_detect(sccb);
+	sclp_hsa_size_detect(sccb);
+	sclp_set_event_mask(sccb, 0, 0);
 }
-- 
cgit v0.10.2


From 52733e0152dad719ed6374b56fd1c33e784e44b3 Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Thu, 5 Dec 2013 19:28:39 +0100
Subject: s390/sclp_early: Add function to detect sclp console capabilities

Add SCLP console detect functions to encapsulate detection of SCLP console
capabilities, for example, VT220 support.  Reuse the sclp_send/receive masks
that were stored by the most recent sclp_set_event_mask() call to prevent
unnecessary SCLP calls.

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Reviewed-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 2f39095..220e171 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -52,8 +52,8 @@ int sclp_chp_configure(struct chp_id chpid);
 int sclp_chp_deconfigure(struct chp_id chpid);
 int sclp_chp_read_info(struct sclp_chp_info *info);
 void sclp_get_ipl_info(struct sclp_ipl_info *info);
-bool sclp_has_linemode(void);
-bool sclp_has_vt220(void);
+bool __init sclp_has_linemode(void);
+bool __init sclp_has_vt220(void);
 int sclp_pci_configure(u32 fid);
 int sclp_pci_deconfigure(u32 fid);
 int memcpy_hsa(void *dest, unsigned long src, size_t count, int mode);
diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c
index 1af3555..82f2c38 100644
--- a/drivers/s390/char/sclp_early.c
+++ b/drivers/s390/char/sclp_early.c
@@ -36,6 +36,8 @@ struct read_info_sccb {
 } __packed __aligned(PAGE_SIZE);
 
 static char sccb_early[PAGE_SIZE] __aligned(PAGE_SIZE) __initdata;
+static unsigned int sclp_con_has_vt220 __initdata;
+static unsigned int sclp_con_has_linemode __initdata;
 static unsigned long sclp_hsa_size;
 static struct sclp_ipl_info sclp_ipl_info;
 
@@ -109,26 +111,12 @@ static void __init sclp_facilities_detect(struct read_info_sccb *sccb)
 
 bool __init sclp_has_linemode(void)
 {
-	struct init_sccb *sccb = (void *) &sccb_early;
-
-	if (sccb->header.response_code != 0x20)
-		return 0;
-	if (!(sccb->sclp_send_mask & (EVTYP_OPCMD_MASK | EVTYP_PMSGCMD_MASK)))
-		return 0;
-	if (!(sccb->sclp_receive_mask & (EVTYP_MSG_MASK | EVTYP_PMSGCMD_MASK)))
-		return 0;
-	return 1;
+	return !!sclp_con_has_linemode;
 }
 
 bool __init sclp_has_vt220(void)
 {
-	struct init_sccb *sccb = (void *) &sccb_early;
-
-	if (sccb->header.response_code != 0x20)
-		return 0;
-	if (sccb->sclp_send_mask & EVTYP_VT220MSG_MASK)
-		return 1;
-	return 0;
+	return !!sclp_con_has_vt220;
 }
 
 unsigned long long sclp_get_rnmax(void)
@@ -240,11 +228,37 @@ out:
 	sclp_hsa_size = size;
 }
 
+static unsigned int __init sclp_con_check_linemode(struct init_sccb *sccb)
+{
+	if (!(sccb->sclp_send_mask & (EVTYP_OPCMD_MASK | EVTYP_PMSGCMD_MASK)))
+		return 0;
+	if (!(sccb->sclp_receive_mask & (EVTYP_MSG_MASK | EVTYP_PMSGCMD_MASK)))
+		return 0;
+	return 1;
+}
+
+static void __init sclp_console_detect(struct init_sccb *sccb)
+{
+	if (sccb->header.response_code != 0x20)
+		return;
+
+	if (sccb->sclp_send_mask & EVTYP_VT220MSG_MASK)
+		sclp_con_has_vt220 = 1;
+
+	if (sclp_con_check_linemode(sccb))
+		sclp_con_has_linemode = 1;
+}
+
 void __init sclp_early_detect(void)
 {
 	void *sccb = &sccb_early;
 
 	sclp_facilities_detect(sccb);
 	sclp_hsa_size_detect(sccb);
+
+	/* Turn off SCLP event notifications.  Also save remote masks in the
+	 * sccb.  These are sufficient to detect sclp console capabilities.
+	 */
 	sclp_set_event_mask(sccb, 0, 0);
+	sclp_console_detect(sccb);
 }
-- 
cgit v0.10.2


From cf48ad83278aad39d4a0158cd085b6038b2941e6 Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Wed, 11 Dec 2013 12:15:52 +0100
Subject: s390/oprofile: move hwsampler interfaces to cpu_mf.h

Extract and move the oprofile hwsampler data structures and interfaces to
the cpu_mf.h header file which contains common interface definitions
for the various CPU-measurement facilities.   This change is necessary for
a new perf PMU.

Few interface names have been revised to fit to the latest CPU-measurement
facilities documentation.  Also declare the data structures as __packed and
correct checkpatch findings.

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index c879fad..f6dddea 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -56,6 +56,78 @@ struct cpumf_ctr_info {
 	u32   reserved2[12];
 } __packed;
 
+/* QUERY SAMPLING INFORMATION block */
+struct hws_qsi_info_block {	    /* Bit(s) */
+	unsigned int b0_13:14;	    /* 0-13: zeros			 */
+	unsigned int as:1;	    /* 14: sampling authorisation control*/
+	unsigned int b15_21:7;	    /* 15-21: zeros			 */
+	unsigned int es:1;	    /* 22: sampling enable control	 */
+	unsigned int b23_29:7;	    /* 23-29: zeros			 */
+	unsigned int cs:1;	    /* 30: sampling activation control	 */
+	unsigned int:1; 	    /* 31: reserved			 */
+	unsigned int bsdes:16;	    /* 4-5: size of basic sampling entry      */
+	unsigned int dsdes:16;	    /* 6-7: size of diagnostic sampling entry */
+	unsigned long min_sampl_rate; /* 8-15: minimum sampling interval */
+	unsigned long max_sampl_rate; /* 16-23: maximum sampling interval*/
+	unsigned long tear;	    /* 24-31: TEAR contents		 */
+	unsigned long dear;	    /* 32-39: DEAR contents		 */
+	unsigned int rsvrd0;	    /* 40-43: reserved			 */
+	unsigned int cpu_speed;     /* 44-47: CPU speed 		 */
+	unsigned long long rsvrd1;  /* 48-55: reserved			 */
+	unsigned long long rsvrd2;  /* 56-63: reserved			 */
+} __packed;
+
+/* SET SAMPLING CONTROLS request block */
+struct hws_lsctl_request_block {
+	unsigned int s:1;	    /* 0: maximum buffer indicator	 */
+	unsigned int h:1;	    /* 1: part. level reserved for VM use*/
+	unsigned long long b2_53:52;/* 2-53: zeros			 */
+	unsigned int es:1;	    /* 54: sampling enable control	 */
+	unsigned int b55_61:7;	    /* 55-61: - zeros			 */
+	unsigned int cs:1;	    /* 62: sampling activation control	 */
+	unsigned int b63:1;	    /* 63: zero 			 */
+	unsigned long interval;     /* 8-15: sampling interval		 */
+	unsigned long tear;	    /* 16-23: TEAR contents		 */
+	unsigned long dear;	    /* 24-31: DEAR contents		 */
+	/* 32-63:							 */
+	unsigned long rsvrd1;	    /* reserved 			 */
+	unsigned long rsvrd2;	    /* reserved 			 */
+	unsigned long rsvrd3;	    /* reserved 			 */
+	unsigned long rsvrd4;	    /* reserved 			 */
+} __packed;
+
+
+struct hws_data_entry {
+	unsigned int def:16;	    /* 0-15  Data Entry Format		 */
+	unsigned int R:4;	    /* 16-19 reserved			 */
+	unsigned int U:4;	    /* 20-23 Number of unique instruct.  */
+	unsigned int z:2;	    /* zeros				 */
+	unsigned int T:1;	    /* 26 PSW DAT mode			 */
+	unsigned int W:1;	    /* 27 PSW wait state		 */
+	unsigned int P:1;	    /* 28 PSW Problem state		 */
+	unsigned int AS:2;	    /* 29-30 PSW address-space control	 */
+	unsigned int I:1;	    /* 31 entry valid or invalid	 */
+	unsigned int:16;
+	unsigned int prim_asn:16;   /* primary ASN			 */
+	unsigned long long ia;	    /* Instruction Address		 */
+	unsigned long long gpp;     /* Guest Program Parameter		 */
+	unsigned long long hpp;     /* Host Program Parameter		 */
+} __packed;
+
+struct hws_trailer_entry {
+	unsigned int f:1;	    /* 0 - Block Full Indicator 	 */
+	unsigned int a:1;	    /* 1 - Alert request control	 */
+	unsigned int t:1;	    /* 2 - Timestamp format		 */
+	unsigned long long:61;	    /* 3 - 63: Reserved 		 */
+	unsigned long long overflow;	 /* 64 - sample Overflow count	      */
+	unsigned long long timestamp;	 /* 16 - time-stamp		      */
+	unsigned long long timestamp1;	 /*				      */
+	unsigned long long reserved1;	 /* 32 -Reserved		      */
+	unsigned long long reserved2;	 /*				      */
+	unsigned long long progusage1;	 /* 48 - reserved for programming use */
+	unsigned long long progusage2;	 /*				      */
+} __packed;
+
 /* Query counter information */
 static inline int qctri(struct cpumf_ctr_info *info)
 {
@@ -99,4 +171,70 @@ static inline int ecctr(u64 ctr, u64 *val)
 	return cc;
 }
 
+/* Query sampling information */
+static inline int qsi(struct hws_qsi_info_block *info)
+{
+	int cc;
+	cc = 1;
+
+	asm volatile(
+		"0:	.insn	s,0xb2860000,0(%1)\n"
+		"1:	lhi	%0,0\n"
+		"2:\n"
+		EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
+		: "=d" (cc), "+a" (info)
+		: "m" (*info)
+		: "cc", "memory");
+
+	return cc ? -EINVAL : 0;
+}
+
+/* Load sampling controls */
+static inline int lsctl(struct hws_lsctl_request_block *req)
+{
+	int cc;
+
+	cc = 1;
+	asm volatile(
+		"0:	.insn	s,0xb2870000,0(%1)\n"
+		"1:	ipm	%0\n"
+		"	srl	%0,28\n"
+		"2:\n"
+		EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
+		: "+d" (cc), "+a" (req)
+		: "m" (*req)
+		: "cc", "memory");
+
+	return cc ? -EINVAL : 0;
+}
+
+/* Sampling control helper functions */
+
+#define SDB_TE_ALERT_REQ_MASK	0x4000000000000000UL
+#define SDB_TE_BUFFER_FULL_MASK 0x8000000000000000UL
+
+/* Return pointer to trailer entry of an sample data block */
+static inline unsigned long *trailer_entry_ptr(unsigned long v)
+{
+	void *ret;
+
+	ret = (void *) v;
+	ret += PAGE_SIZE;
+	ret -= sizeof(struct hws_trailer_entry);
+
+	return (unsigned long *) ret;
+}
+
+/* Return if the entry in the sample data block table (sdbt)
+ * is a link to the next sdbt */
+static inline int is_link_entry(unsigned long *s)
+{
+	return *s & 0x1ul ? 1 : 0;
+}
+
+/* Return pointer to the linked sdbt */
+static inline unsigned long *get_next_sdbt(unsigned long *s)
+{
+	return (unsigned long *) (*s & ~0x1ul);
+}
 #endif /* _ASM_S390_CPU_MF_H */
diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c
index 231ceca..bbca76a 100644
--- a/arch/s390/oprofile/hwsampler.c
+++ b/arch/s390/oprofile/hwsampler.c
@@ -26,9 +26,6 @@
 #define MAX_NUM_SDB 511
 #define MIN_NUM_SDB 1
 
-#define ALERT_REQ_MASK   0x4000000000000000ul
-#define BUFFER_FULL_MASK 0x8000000000000000ul
-
 DECLARE_PER_CPU(struct hws_cpu_buffer, sampler_cpu_buffer);
 
 struct hws_execute_parms {
@@ -65,43 +62,6 @@ static unsigned long interval;
 static unsigned long min_sampler_rate;
 static unsigned long max_sampler_rate;
 
-static int ssctl(void *buffer)
-{
-	int cc;
-
-	/* set in order to detect a program check */
-	cc = 1;
-
-	asm volatile(
-		"0: .insn s,0xB2870000,0(%1)\n"
-		"1: ipm %0\n"
-		"   srl %0,28\n"
-		"2:\n"
-		EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
-		: "+d" (cc), "+a" (buffer)
-		: "m" (*((struct hws_ssctl_request_block *)buffer))
-		: "cc", "memory");
-
-	return cc ? -EINVAL : 0 ;
-}
-
-static int qsi(void *buffer)
-{
-	int cc;
-	cc = 1;
-
-	asm volatile(
-		"0: .insn s,0xB2860000,0(%1)\n"
-		"1: lhi %0,0\n"
-		"2:\n"
-		EX_TABLE(0b, 2b) EX_TABLE(1b, 2b)
-		: "=d" (cc), "+a" (buffer)
-		: "m" (*((struct hws_qsi_info_block *)buffer))
-		: "cc", "memory");
-
-	return cc ? -EINVAL : 0;
-}
-
 static void execute_qsi(void *parms)
 {
 	struct hws_execute_parms *ep = parms;
@@ -113,7 +73,7 @@ static void execute_ssctl(void *parms)
 {
 	struct hws_execute_parms *ep = parms;
 
-	ep->rc = ssctl(ep->buffer);
+	ep->rc = lsctl(ep->buffer);
 }
 
 static int smp_ctl_ssctl_stop(int cpu)
@@ -214,17 +174,6 @@ static int smp_ctl_qsi(int cpu)
 	return ep.rc;
 }
 
-static inline unsigned long *trailer_entry_ptr(unsigned long v)
-{
-	void *ret;
-
-	ret = (void *)v;
-	ret += PAGE_SIZE;
-	ret -= sizeof(struct hws_trailer_entry);
-
-	return (unsigned long *) ret;
-}
-
 static void hws_ext_handler(struct ext_code ext_code,
 			    unsigned int param32, unsigned long param64)
 {
@@ -256,16 +205,6 @@ static void init_all_cpu_buffers(void)
 	}
 }
 
-static int is_link_entry(unsigned long *s)
-{
-	return *s & 0x1ul ? 1 : 0;
-}
-
-static unsigned long *get_next_sdbt(unsigned long *s)
-{
-	return (unsigned long *) (*s & ~0x1ul);
-}
-
 static int prepare_cpu_buffers(void)
 {
 	int cpu;
@@ -353,7 +292,7 @@ static int allocate_sdbt(int cpu)
 			}
 			*sdbt = sdb;
 			trailer = trailer_entry_ptr(*sdbt);
-			*trailer = ALERT_REQ_MASK;
+			*trailer = SDB_TE_ALERT_REQ_MASK;
 			sdbt++;
 			mutex_unlock(&hws_sem_oom);
 		}
@@ -829,7 +768,7 @@ static void worker_on_interrupt(unsigned int cpu)
 
 		trailer = trailer_entry_ptr(*sdbt);
 		/* leave loop if no more work to do */
-		if (!(*trailer & BUFFER_FULL_MASK)) {
+		if (!(*trailer & SDB_TE_BUFFER_FULL_MASK)) {
 			done = 1;
 			if (!hws_flush_all)
 				continue;
diff --git a/arch/s390/oprofile/hwsampler.h b/arch/s390/oprofile/hwsampler.h
index 0022e1e..a483d06 100644
--- a/arch/s390/oprofile/hwsampler.h
+++ b/arch/s390/oprofile/hwsampler.h
@@ -9,27 +9,7 @@
 #define HWSAMPLER_H_
 
 #include <linux/workqueue.h>
-
-struct hws_qsi_info_block          /* QUERY SAMPLING information block  */
-{ /* Bit(s) */
-	unsigned int b0_13:14;      /* 0-13: zeros                       */
-	unsigned int as:1;          /* 14: sampling authorisation control*/
-	unsigned int b15_21:7;      /* 15-21: zeros                      */
-	unsigned int es:1;          /* 22: sampling enable control       */
-	unsigned int b23_29:7;      /* 23-29: zeros                      */
-	unsigned int cs:1;          /* 30: sampling activation control   */
-	unsigned int:1;             /* 31: reserved                      */
-	unsigned int bsdes:16;      /* 4-5: size of sampling entry       */
-	unsigned int:16;            /* 6-7: reserved                     */
-	unsigned long min_sampl_rate; /* 8-15: minimum sampling interval */
-	unsigned long max_sampl_rate; /* 16-23: maximum sampling interval*/
-	unsigned long tear;         /* 24-31: TEAR contents              */
-	unsigned long dear;         /* 32-39: DEAR contents              */
-	unsigned int rsvrd0;        /* 40-43: reserved                   */
-	unsigned int cpu_speed;     /* 44-47: CPU speed                  */
-	unsigned long long rsvrd1;  /* 48-55: reserved                   */
-	unsigned long long rsvrd2;  /* 56-63: reserved                   */
-};
+#include <asm/cpu_mf.h>
 
 struct hws_ssctl_request_block     /* SET SAMPLING CONTROLS req block   */
 { /* bytes 0 - 7  Bit(s) */
@@ -68,36 +48,6 @@ struct hws_cpu_buffer {
 	unsigned int stop_mode:1;
 };
 
-struct hws_data_entry {
-	unsigned int def:16;        /* 0-15  Data Entry Format           */
-	unsigned int R:4;           /* 16-19 reserved                    */
-	unsigned int U:4;           /* 20-23 Number of unique instruct.  */
-	unsigned int z:2;           /* zeros                             */
-	unsigned int T:1;           /* 26 PSW DAT mode                   */
-	unsigned int W:1;           /* 27 PSW wait state                 */
-	unsigned int P:1;           /* 28 PSW Problem state              */
-	unsigned int AS:2;          /* 29-30 PSW address-space control   */
-	unsigned int I:1;           /* 31 entry valid or invalid         */
-	unsigned int:16;
-	unsigned int prim_asn:16;   /* primary ASN                       */
-	unsigned long long ia;      /* Instruction Address               */
-	unsigned long long gpp;     /* Guest Program Parameter		 */
-	unsigned long long hpp;     /* Host Program Parameter		 */
-};
-
-struct hws_trailer_entry {
-	unsigned int f:1;           /* 0 - Block Full Indicator          */
-	unsigned int a:1;           /* 1 - Alert request control         */
-	unsigned long:62;           /* 2 - 63: Reserved                  */
-	unsigned long overflow;     /* 64 - sample Overflow count        */
-	unsigned long timestamp;    /* 16 - time-stamp                   */
-	unsigned long timestamp1;   /*                                   */
-	unsigned long reserved1;    /* 32 -Reserved                      */
-	unsigned long reserved2;    /*                                   */
-	unsigned long progusage1;   /* 48 - reserved for programming use */
-	unsigned long progusage2;   /*                                   */
-};
-
 int hwsampler_setup(void);
 int hwsampler_shutdown(void);
 int hwsampler_allocate(unsigned long sdbt, unsigned long sdb);
-- 
cgit v0.10.2


From c716832513f30430179b60ac5ffd203c53f7eb40 Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Wed, 11 Dec 2013 12:44:40 +0100
Subject: s390/cpum_cf: Export event names in sysfs

Provide PMU event attributes for supported counters and export their symbolic
names to the sysfs "events" directory.

See the /sys/devices/cpum_cf/events/ directory for a list of available counters.
Note that you might require counter set authorizations for the LPAR to use them.

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index 1141fb3..3418502 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -1,11 +1,18 @@
 /*
  * Performance event support - s390 specific definitions.
  *
- * Copyright IBM Corp. 2009, 2012
+ * Copyright IBM Corp. 2009, 2013
  * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
  *	      Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  */
 
+#ifndef _ASM_S390_PERF_EVENT_H
+#define _ASM_S390_PERF_EVENT_H
+
+#ifdef CONFIG_64BIT
+
+#include <linux/perf_event.h>
+#include <linux/device.h>
 #include <asm/cpu_mf.h>
 
 /* CPU-measurement counter facility */
@@ -15,7 +22,18 @@
 #define PMU_F_RESERVED			0x1000
 #define PMU_F_ENABLED			0x2000
 
-#ifdef CONFIG_64BIT
+/* Perf defintions for PMU event attributes in sysfs */
+extern __init const struct attribute_group **cpumf_cf_event_group(void);
+extern ssize_t cpumf_events_sysfs_show(struct device *dev,
+				       struct device_attribute *attr,
+				       char *page);
+#define EVENT_VAR(_cat, _name)		event_attr_##_cat##_##_name
+#define EVENT_PTR(_cat, _name)		(&EVENT_VAR(_cat, _name).attr.attr)
+
+#define CPUMF_EVENT_ATTR(cat, name, id)			\
+	PMU_EVENT_ATTR(name, EVENT_VAR(cat, name), id, cpumf_events_sysfs_show)
+#define CPUMF_EVENT_PTR(cat, name)	EVENT_PTR(cat, name)
+
 
 /* Perf callbacks */
 struct pt_regs;
@@ -24,3 +42,4 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define perf_misc_flags(regs) perf_misc_flags(regs)
 
 #endif /* CONFIG_64BIT */
+#endif /* _ASM_S390_PERF_EVENT_H */
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 2403303..9f1e2ad 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -60,7 +60,8 @@ obj-$(CONFIG_FTRACE_SYSCALLS)  += ftrace.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 
 ifdef CONFIG_64BIT
-obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_cpum_cf.o
+obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_cpum_cf.o \
+						perf_cpum_cf_events.o
 obj-y				+= runtime_instr.o cache.o
 endif
 
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 1105502..f51214c 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -680,6 +680,7 @@ static int __init cpumf_pmu_init(void)
 		goto out;
 	}
 
+	cpumf_pmu.attr_groups = cpumf_cf_event_group();
 	rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW);
 	if (rc) {
 		pr_err("Registering the cpum_cf PMU failed with rc=%i\n", rc);
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
new file mode 100644
index 0000000..4554a4b
--- /dev/null
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -0,0 +1,322 @@
+/*
+ * Perf PMU sysfs events attributes for available CPU-measurement counters
+ *
+ */
+
+#include <linux/slab.h>
+#include <linux/perf_event.h>
+
+
+/* BEGIN: CPUM_CF COUNTER DEFINITIONS =================================== */
+
+CPUMF_EVENT_ATTR(cf, CPU_CYCLES, 0x0000);
+CPUMF_EVENT_ATTR(cf, INSTRUCTIONS, 0x0001);
+CPUMF_EVENT_ATTR(cf, L1I_DIR_WRITES, 0x0002);
+CPUMF_EVENT_ATTR(cf, L1I_PENALTY_CYCLES, 0x0003);
+CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_CPU_CYCLES, 0x0020);
+CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_INSTRUCTIONS, 0x0021);
+CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_L1I_DIR_WRITES, 0x0022);
+CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_L1I_PENALTY_CYCLES, 0x0023);
+CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_L1D_DIR_WRITES, 0x0024);
+CPUMF_EVENT_ATTR(cf, PROBLEM_STATE_L1D_PENALTY_CYCLES, 0x0025);
+CPUMF_EVENT_ATTR(cf, L1D_DIR_WRITES, 0x0004);
+CPUMF_EVENT_ATTR(cf, L1D_PENALTY_CYCLES, 0x0005);
+CPUMF_EVENT_ATTR(cf, PRNG_FUNCTIONS, 0x0040);
+CPUMF_EVENT_ATTR(cf, PRNG_CYCLES, 0x0041);
+CPUMF_EVENT_ATTR(cf, PRNG_BLOCKED_FUNCTIONS, 0x0042);
+CPUMF_EVENT_ATTR(cf, PRNG_BLOCKED_CYCLES, 0x0043);
+CPUMF_EVENT_ATTR(cf, SHA_FUNCTIONS, 0x0044);
+CPUMF_EVENT_ATTR(cf, SHA_CYCLES, 0x0045);
+CPUMF_EVENT_ATTR(cf, SHA_BLOCKED_FUNCTIONS, 0x0046);
+CPUMF_EVENT_ATTR(cf, SHA_BLOCKED_CYCLES, 0x0047);
+CPUMF_EVENT_ATTR(cf, DEA_FUNCTIONS, 0x0048);
+CPUMF_EVENT_ATTR(cf, DEA_CYCLES, 0x0049);
+CPUMF_EVENT_ATTR(cf, DEA_BLOCKED_FUNCTIONS, 0x004a);
+CPUMF_EVENT_ATTR(cf, DEA_BLOCKED_CYCLES, 0x004b);
+CPUMF_EVENT_ATTR(cf, AES_FUNCTIONS, 0x004c);
+CPUMF_EVENT_ATTR(cf, AES_CYCLES, 0x004d);
+CPUMF_EVENT_ATTR(cf, AES_BLOCKED_FUNCTIONS, 0x004e);
+CPUMF_EVENT_ATTR(cf, AES_BLOCKED_CYCLES, 0x004f);
+CPUMF_EVENT_ATTR(cf_z10, L1I_L2_SOURCED_WRITES, 0x0080);
+CPUMF_EVENT_ATTR(cf_z10, L1D_L2_SOURCED_WRITES, 0x0081);
+CPUMF_EVENT_ATTR(cf_z10, L1I_L3_LOCAL_WRITES, 0x0082);
+CPUMF_EVENT_ATTR(cf_z10, L1D_L3_LOCAL_WRITES, 0x0083);
+CPUMF_EVENT_ATTR(cf_z10, L1I_L3_REMOTE_WRITES, 0x0084);
+CPUMF_EVENT_ATTR(cf_z10, L1D_L3_REMOTE_WRITES, 0x0085);
+CPUMF_EVENT_ATTR(cf_z10, L1D_LMEM_SOURCED_WRITES, 0x0086);
+CPUMF_EVENT_ATTR(cf_z10, L1I_LMEM_SOURCED_WRITES, 0x0087);
+CPUMF_EVENT_ATTR(cf_z10, L1D_RO_EXCL_WRITES, 0x0088);
+CPUMF_EVENT_ATTR(cf_z10, L1I_CACHELINE_INVALIDATES, 0x0089);
+CPUMF_EVENT_ATTR(cf_z10, ITLB1_WRITES, 0x008a);
+CPUMF_EVENT_ATTR(cf_z10, DTLB1_WRITES, 0x008b);
+CPUMF_EVENT_ATTR(cf_z10, TLB2_PTE_WRITES, 0x008c);
+CPUMF_EVENT_ATTR(cf_z10, TLB2_CRSTE_WRITES, 0x008d);
+CPUMF_EVENT_ATTR(cf_z10, TLB2_CRSTE_HPAGE_WRITES, 0x008e);
+CPUMF_EVENT_ATTR(cf_z10, ITLB1_MISSES, 0x0091);
+CPUMF_EVENT_ATTR(cf_z10, DTLB1_MISSES, 0x0092);
+CPUMF_EVENT_ATTR(cf_z10, L2C_STORES_SENT, 0x0093);
+CPUMF_EVENT_ATTR(cf_z196, L1D_L2_SOURCED_WRITES, 0x0080);
+CPUMF_EVENT_ATTR(cf_z196, L1I_L2_SOURCED_WRITES, 0x0081);
+CPUMF_EVENT_ATTR(cf_z196, DTLB1_MISSES, 0x0082);
+CPUMF_EVENT_ATTR(cf_z196, ITLB1_MISSES, 0x0083);
+CPUMF_EVENT_ATTR(cf_z196, L2C_STORES_SENT, 0x0085);
+CPUMF_EVENT_ATTR(cf_z196, L1D_OFFBOOK_L3_SOURCED_WRITES, 0x0086);
+CPUMF_EVENT_ATTR(cf_z196, L1D_ONBOOK_L4_SOURCED_WRITES, 0x0087);
+CPUMF_EVENT_ATTR(cf_z196, L1I_ONBOOK_L4_SOURCED_WRITES, 0x0088);
+CPUMF_EVENT_ATTR(cf_z196, L1D_RO_EXCL_WRITES, 0x0089);
+CPUMF_EVENT_ATTR(cf_z196, L1D_OFFBOOK_L4_SOURCED_WRITES, 0x008a);
+CPUMF_EVENT_ATTR(cf_z196, L1I_OFFBOOK_L4_SOURCED_WRITES, 0x008b);
+CPUMF_EVENT_ATTR(cf_z196, DTLB1_HPAGE_WRITES, 0x008c);
+CPUMF_EVENT_ATTR(cf_z196, L1D_LMEM_SOURCED_WRITES, 0x008d);
+CPUMF_EVENT_ATTR(cf_z196, L1I_LMEM_SOURCED_WRITES, 0x008e);
+CPUMF_EVENT_ATTR(cf_z196, L1I_OFFBOOK_L3_SOURCED_WRITES, 0x008f);
+CPUMF_EVENT_ATTR(cf_z196, DTLB1_WRITES, 0x0090);
+CPUMF_EVENT_ATTR(cf_z196, ITLB1_WRITES, 0x0091);
+CPUMF_EVENT_ATTR(cf_z196, TLB2_PTE_WRITES, 0x0092);
+CPUMF_EVENT_ATTR(cf_z196, TLB2_CRSTE_HPAGE_WRITES, 0x0093);
+CPUMF_EVENT_ATTR(cf_z196, TLB2_CRSTE_WRITES, 0x0094);
+CPUMF_EVENT_ATTR(cf_z196, L1D_ONCHIP_L3_SOURCED_WRITES, 0x0096);
+CPUMF_EVENT_ATTR(cf_z196, L1D_OFFCHIP_L3_SOURCED_WRITES, 0x0098);
+CPUMF_EVENT_ATTR(cf_z196, L1I_ONCHIP_L3_SOURCED_WRITES, 0x0099);
+CPUMF_EVENT_ATTR(cf_z196, L1I_OFFCHIP_L3_SOURCED_WRITES, 0x009b);
+CPUMF_EVENT_ATTR(cf_zec12, DTLB1_MISSES, 0x0080);
+CPUMF_EVENT_ATTR(cf_zec12, ITLB1_MISSES, 0x0081);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_L2I_SOURCED_WRITES, 0x0082);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_L2I_SOURCED_WRITES, 0x0083);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_L2D_SOURCED_WRITES, 0x0084);
+CPUMF_EVENT_ATTR(cf_zec12, DTLB1_WRITES, 0x0085);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_LMEM_SOURCED_WRITES, 0x0087);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_LMEM_SOURCED_WRITES, 0x0089);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_RO_EXCL_WRITES, 0x008a);
+CPUMF_EVENT_ATTR(cf_zec12, DTLB1_HPAGE_WRITES, 0x008b);
+CPUMF_EVENT_ATTR(cf_zec12, ITLB1_WRITES, 0x008c);
+CPUMF_EVENT_ATTR(cf_zec12, TLB2_PTE_WRITES, 0x008d);
+CPUMF_EVENT_ATTR(cf_zec12, TLB2_CRSTE_HPAGE_WRITES, 0x008e);
+CPUMF_EVENT_ATTR(cf_zec12, TLB2_CRSTE_WRITES, 0x008f);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_ONCHIP_L3_SOURCED_WRITES, 0x0090);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFCHIP_L3_SOURCED_WRITES, 0x0091);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFBOOK_L3_SOURCED_WRITES, 0x0092);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_ONBOOK_L4_SOURCED_WRITES, 0x0093);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFBOOK_L4_SOURCED_WRITES, 0x0094);
+CPUMF_EVENT_ATTR(cf_zec12, TX_NC_TEND, 0x0095);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_ONCHIP_L3_SOURCED_WRITES_IV, 0x0096);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFCHIP_L3_SOURCED_WRITES_IV, 0x0097);
+CPUMF_EVENT_ATTR(cf_zec12, L1D_OFFBOOK_L3_SOURCED_WRITES_IV, 0x0098);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_ONCHIP_L3_SOURCED_WRITES, 0x0099);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFCHIP_L3_SOURCED_WRITES, 0x009a);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFBOOK_L3_SOURCED_WRITES, 0x009b);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_ONBOOK_L4_SOURCED_WRITES, 0x009c);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFBOOK_L4_SOURCED_WRITES, 0x009d);
+CPUMF_EVENT_ATTR(cf_zec12, TX_C_TEND, 0x009e);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_ONCHIP_L3_SOURCED_WRITES_IV, 0x009f);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFCHIP_L3_SOURCED_WRITES_IV, 0x00a0);
+CPUMF_EVENT_ATTR(cf_zec12, L1I_OFFBOOK_L3_SOURCED_WRITES_IV, 0x00a1);
+CPUMF_EVENT_ATTR(cf_zec12, TX_NC_TABORT, 0x00b1);
+CPUMF_EVENT_ATTR(cf_zec12, TX_C_TABORT_NO_SPECIAL, 0x00b2);
+CPUMF_EVENT_ATTR(cf_zec12, TX_C_TABORT_SPECIAL, 0x00b3);
+
+static struct attribute *cpumcf_pmu_event_attr[] = {
+	CPUMF_EVENT_PTR(cf, CPU_CYCLES),
+	CPUMF_EVENT_PTR(cf, INSTRUCTIONS),
+	CPUMF_EVENT_PTR(cf, L1I_DIR_WRITES),
+	CPUMF_EVENT_PTR(cf, L1I_PENALTY_CYCLES),
+	CPUMF_EVENT_PTR(cf, PROBLEM_STATE_CPU_CYCLES),
+	CPUMF_EVENT_PTR(cf, PROBLEM_STATE_INSTRUCTIONS),
+	CPUMF_EVENT_PTR(cf, PROBLEM_STATE_L1I_DIR_WRITES),
+	CPUMF_EVENT_PTR(cf, PROBLEM_STATE_L1I_PENALTY_CYCLES),
+	CPUMF_EVENT_PTR(cf, PROBLEM_STATE_L1D_DIR_WRITES),
+	CPUMF_EVENT_PTR(cf, PROBLEM_STATE_L1D_PENALTY_CYCLES),
+	CPUMF_EVENT_PTR(cf, L1D_DIR_WRITES),
+	CPUMF_EVENT_PTR(cf, L1D_PENALTY_CYCLES),
+	CPUMF_EVENT_PTR(cf, PRNG_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf, PRNG_CYCLES),
+	CPUMF_EVENT_PTR(cf, PRNG_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf, PRNG_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf, SHA_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf, SHA_CYCLES),
+	CPUMF_EVENT_PTR(cf, SHA_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf, SHA_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf, DEA_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf, DEA_CYCLES),
+	CPUMF_EVENT_PTR(cf, DEA_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf, DEA_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf, AES_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf, AES_CYCLES),
+	CPUMF_EVENT_PTR(cf, AES_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf, AES_BLOCKED_CYCLES),
+	NULL,
+};
+
+static struct attribute *cpumcf_z10_pmu_event_attr[] __initdata = {
+	CPUMF_EVENT_PTR(cf_z10, L1I_L2_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, L1D_L2_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, L1I_L3_LOCAL_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, L1D_L3_LOCAL_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, L1I_L3_REMOTE_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, L1D_L3_REMOTE_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, L1D_LMEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, L1I_LMEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, L1D_RO_EXCL_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, L1I_CACHELINE_INVALIDATES),
+	CPUMF_EVENT_PTR(cf_z10, ITLB1_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, DTLB1_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, TLB2_PTE_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, TLB2_CRSTE_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, TLB2_CRSTE_HPAGE_WRITES),
+	CPUMF_EVENT_PTR(cf_z10, ITLB1_MISSES),
+	CPUMF_EVENT_PTR(cf_z10, DTLB1_MISSES),
+	CPUMF_EVENT_PTR(cf_z10, L2C_STORES_SENT),
+	NULL,
+};
+
+static struct attribute *cpumcf_z196_pmu_event_attr[] __initdata = {
+	CPUMF_EVENT_PTR(cf_z196, L1D_L2_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1I_L2_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, DTLB1_MISSES),
+	CPUMF_EVENT_PTR(cf_z196, ITLB1_MISSES),
+	CPUMF_EVENT_PTR(cf_z196, L2C_STORES_SENT),
+	CPUMF_EVENT_PTR(cf_z196, L1D_OFFBOOK_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1D_ONBOOK_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1I_ONBOOK_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1D_RO_EXCL_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1D_OFFBOOK_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1I_OFFBOOK_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, DTLB1_HPAGE_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1D_LMEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1I_LMEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1I_OFFBOOK_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, DTLB1_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, ITLB1_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, TLB2_PTE_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, TLB2_CRSTE_HPAGE_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, TLB2_CRSTE_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1D_ONCHIP_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1D_OFFCHIP_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1I_ONCHIP_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_z196, L1I_OFFCHIP_L3_SOURCED_WRITES),
+	NULL,
+};
+
+static struct attribute *cpumcf_zec12_pmu_event_attr[] __initdata = {
+	CPUMF_EVENT_PTR(cf_zec12, DTLB1_MISSES),
+	CPUMF_EVENT_PTR(cf_zec12, ITLB1_MISSES),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_L2I_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_L2I_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_L2D_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, DTLB1_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_LMEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_LMEM_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_RO_EXCL_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, DTLB1_HPAGE_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, ITLB1_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, TLB2_PTE_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, TLB2_CRSTE_HPAGE_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, TLB2_CRSTE_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_ONCHIP_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_OFFCHIP_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_OFFBOOK_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_ONBOOK_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_OFFBOOK_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, TX_NC_TEND),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_ONCHIP_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_OFFCHIP_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_zec12, L1D_OFFBOOK_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_ONCHIP_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_OFFCHIP_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_OFFBOOK_L3_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_ONBOOK_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_OFFBOOK_L4_SOURCED_WRITES),
+	CPUMF_EVENT_PTR(cf_zec12, TX_C_TEND),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_ONCHIP_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_OFFCHIP_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_zec12, L1I_OFFBOOK_L3_SOURCED_WRITES_IV),
+	CPUMF_EVENT_PTR(cf_zec12, TX_NC_TABORT),
+	CPUMF_EVENT_PTR(cf_zec12, TX_C_TABORT_NO_SPECIAL),
+	CPUMF_EVENT_PTR(cf_zec12, TX_C_TABORT_SPECIAL),
+	NULL,
+};
+
+/* END: CPUM_CF COUNTER DEFINITIONS ===================================== */
+
+static struct attribute_group cpumsf_pmu_events_group = {
+	.name = "events",
+	.attrs = cpumcf_pmu_event_attr,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-63");
+
+static struct attribute *cpumsf_pmu_format_attr[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group cpumsf_pmu_format_group = {
+	.name = "format",
+	.attrs = cpumsf_pmu_format_attr,
+};
+
+static const struct attribute_group *cpumsf_pmu_attr_groups[] = {
+	&cpumsf_pmu_events_group,
+	&cpumsf_pmu_format_group,
+	NULL,
+};
+
+
+static __init struct attribute **merge_attr(struct attribute **a,
+					    struct attribute **b)
+{
+	struct attribute **new;
+	int j, i;
+
+	for (j = 0; a[j]; j++)
+		;
+	for (i = 0; b[i]; i++)
+		j++;
+	j++;
+
+	new = kmalloc(sizeof(struct attribute *) * j, GFP_KERNEL);
+	if (!new)
+		return NULL;
+	j = 0;
+	for (i = 0; a[i]; i++)
+		new[j++] = a[i];
+	for (i = 0; b[i]; i++)
+		new[j++] = b[i];
+	new[j] = NULL;
+
+	return new;
+}
+
+__init const struct attribute_group **cpumf_cf_event_group(void)
+{
+	struct attribute **combined, **model;
+	struct cpuid cpu_id;
+
+	get_cpu_id(&cpu_id);
+	switch (cpu_id.machine) {
+	case 0x2097:
+	case 0x2098:
+		model = cpumcf_z10_pmu_event_attr;
+		break;
+	case 0x2817:
+	case 0x2818:
+		model = cpumcf_z196_pmu_event_attr;
+		break;
+	case 0x2827:
+	case 0x2828:
+		model = cpumcf_zec12_pmu_event_attr;
+		break;
+	default:
+		model = NULL;
+		break;
+	};
+
+	if (!model)
+		goto out;
+
+	combined = merge_attr(cpumcf_pmu_event_attr, model);
+	if (combined)
+		cpumsf_pmu_events_group.attrs = combined;
+out:
+	return cpumsf_pmu_attr_groups;
+}
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 2343c21..4c1d336 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -16,6 +16,7 @@
 #include <linux/kvm_host.h>
 #include <linux/percpu.h>
 #include <linux/export.h>
+#include <linux/sysfs.h>
 #include <asm/irq.h>
 #include <asm/cpu_mf.h>
 #include <asm/lowcore.h>
@@ -172,3 +173,14 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
 	__store_trace(entry, head, S390_lowcore.thread_info,
 		      S390_lowcore.thread_info + THREAD_SIZE);
 }
+
+/* Perf defintions for PMU event attributes in sysfs */
+ssize_t cpumf_events_sysfs_show(struct device *dev,
+				struct device_attribute *attr, char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+	return sprintf(page, "event=0x%04llx,name=%s\n",
+		       pmu_attr->id, attr->attr.name);
+}
-- 
cgit v0.10.2


From 8c069ff4bd6063a3f15e606c882e03f75c7e7711 Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Thu, 12 Dec 2013 16:32:47 +0100
Subject: s390/perf: add support for the CPU-Measurement Sampling Facility

Introduce a perf PMU, "cpum_sf", to support the CPU-Measurement
Sampling Facility.  You can control the sampling facility through
this perf PMU interfaces.  Perf sampling events are created for
hardware samples.

For details about the CPU-Measurement Sampling Facility, see
"The Load-Program-Parameter and the CPU-Measurement Facilities" (SA23-2260).

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index f6dddea..d707abc 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -210,6 +210,20 @@ static inline int lsctl(struct hws_lsctl_request_block *req)
 
 /* Sampling control helper functions */
 
+#include <linux/time.h>
+
+static inline unsigned long freq_to_sample_rate(struct hws_qsi_info_block *qsi,
+						unsigned long freq)
+{
+	return (USEC_PER_SEC / freq) * qsi->cpu_speed;
+}
+
+static inline unsigned long sample_rate_to_freq(struct hws_qsi_info_block *qsi,
+						unsigned long rate)
+{
+	return USEC_PER_SEC * qsi->cpu_speed / rate;
+}
+
 #define SDB_TE_ALERT_REQ_MASK	0x4000000000000000UL
 #define SDB_TE_BUFFER_FULL_MASK 0x8000000000000000UL
 
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index 3418502..b4eea25 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -15,12 +15,13 @@
 #include <linux/device.h>
 #include <asm/cpu_mf.h>
 
-/* CPU-measurement counter facility */
-#define PERF_CPUM_CF_MAX_CTR		256
-
 /* Per-CPU flags for PMU states */
 #define PMU_F_RESERVED			0x1000
 #define PMU_F_ENABLED			0x2000
+#define PMU_F_IN_USE			0x4000
+#define PMU_F_ERR_IBE			0x0100
+#define PMU_F_ERR_LSDA			0x0200
+#define PMU_F_ERR_MASK			(PMU_F_ERR_IBE|PMU_F_ERR_LSDA)
 
 /* Perf defintions for PMU event attributes in sysfs */
 extern __init const struct attribute_group **cpumf_cf_event_group(void);
@@ -41,5 +42,15 @@ extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define perf_misc_flags(regs) perf_misc_flags(regs)
 
+/* Perf PMU definitions for the counter facility */
+#define PERF_CPUM_CF_MAX_CTR		256
+
+/* Perf PMU definitions for the sampling facility */
+#define PERF_CPUM_SF_MAX_CTR		1
+#define PERF_EVENT_CPUM_SF		0xB0000UL	/* Raw event ID */
+
+#define TEAR_REG(hwc)		((hwc)->last_tag)
+#define SAMPL_RATE(hwc)		((hwc)->event_base)
+
 #endif /* CONFIG_64BIT */
 #endif /* _ASM_S390_PERF_EVENT_H */
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 9f1e2ad..1b3ac09 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -60,7 +60,7 @@ obj-$(CONFIG_FTRACE_SYSCALLS)  += ftrace.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 
 ifdef CONFIG_64BIT
-obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_cpum_cf.o \
+obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_cpum_cf.o perf_cpum_sf.o \
 						perf_cpum_cf_events.o
 obj-y				+= runtime_instr.o cache.o
 endif
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
new file mode 100644
index 0000000..141eca0
--- /dev/null
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -0,0 +1,1024 @@
+/*
+ * Performance event support for the System z CPU-measurement Sampling Facility
+ *
+ * Copyright IBM Corp. 2013
+ * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+#define KMSG_COMPONENT	"cpum_sf"
+#define pr_fmt(fmt)	KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/kernel_stat.h>
+#include <linux/perf_event.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/export.h>
+#include <asm/cpu_mf.h>
+#include <asm/irq.h>
+#include <asm/debug.h>
+#include <asm/timex.h>
+
+/* Minimum number of sample-data-block-tables:
+ * At least one table is required for the sampling buffer structure.
+ * A single table contains up to 511 pointers to sample-data-blocks.
+ */
+#define CPUM_SF_MIN_SDBT    1
+
+/* Minimum number of sample-data-blocks:
+ * The minimum designates a single page for sample-data-block, i.e.,
+ * up to 126 sample-data-blocks with a size of 32 bytes (bsdes).
+ */
+#define CPUM_SF_MIN_SDB	    126
+
+/* Maximum number of sample-data-blocks:
+ * The maximum number designates approx. 256K per CPU including
+ * the given number of sample-data-blocks and taking the number
+ * of sample-data-block tables into account.
+ *
+ * Later, this number can be increased for extending the sampling
+ * buffer, for example, by factor 2 (512K) or 4 (1M).
+ */
+#define CPUM_SF_MAX_SDB	    6471
+
+struct sf_buffer {
+	unsigned long	 sdbt;	    /* Sample-data-block-table origin */
+	/* buffer characteristics (required for buffer increments) */
+	unsigned long num_sdb;	    /* Number of sample-data-blocks */
+	unsigned long	 tail;	    /* last sample-data-block-table */
+};
+
+struct cpu_hw_sf {
+	/* CPU-measurement sampling information block */
+	struct hws_qsi_info_block qsi;
+	struct hws_lsctl_request_block lsctl;
+	struct sf_buffer sfb;	    /* Sampling buffer */
+	unsigned int flags;	    /* Status flags */
+	struct perf_event *event;   /* Scheduled perf event */
+};
+static DEFINE_PER_CPU(struct cpu_hw_sf, cpu_hw_sf);
+
+/* Debug feature */
+static debug_info_t *sfdbg;
+
+/*
+ * sf_buffer_available() - Check for an allocated sampling buffer
+ */
+static int sf_buffer_available(struct cpu_hw_sf *cpuhw)
+{
+	return (cpuhw->sfb.sdbt) ? 1 : 0;
+}
+
+/*
+ * deallocate sampling facility buffer
+ */
+static void free_sampling_buffer(struct sf_buffer *sfb)
+{
+	unsigned long sdbt, *curr;
+
+	if (!sfb->sdbt)
+		return;
+
+	sdbt = sfb->sdbt;
+	curr = (unsigned long *) sdbt;
+
+	/* we'll free the SDBT after all SDBs are processed... */
+	while (1) {
+		if (!*curr || !sdbt)
+			break;
+
+		/* watch for link entry reset if found */
+		if (is_link_entry(curr)) {
+			curr = get_next_sdbt(curr);
+			if (sdbt)
+				free_page(sdbt);
+
+			/* we are done if we reach the origin */
+			if ((unsigned long) curr == sfb->sdbt)
+				break;
+			else
+				sdbt = (unsigned long) curr;
+		} else {
+			/* process SDB pointer */
+			if (*curr) {
+				free_page(*curr);
+				curr++;
+			}
+		}
+	}
+
+	debug_sprintf_event(sfdbg, 5,
+			    "free_sampling_buffer: freed sdbt=%0lx\n", sfb->sdbt);
+	memset(sfb, 0, sizeof(*sfb));
+}
+
+/*
+ * allocate_sampling_buffer() - allocate sampler memory
+ *
+ * Allocates and initializes a sampling buffer structure using the
+ * specified number of sample-data-blocks (SDB).  For each allocation,
+ * a 4K page is used.  The number of sample-data-block-tables (SDBT)
+ * are calculated from SDBs.
+ * Also set the ALERT_REQ mask in each SDBs trailer.
+ *
+ * Returns zero on success, non-zero otherwise.
+ */
+static int alloc_sampling_buffer(struct sf_buffer *sfb, unsigned long num_sdb)
+{
+	int j, k, rc;
+	unsigned long *sdbt, *tail, *trailer;
+	unsigned long sdb;
+	unsigned long num_sdbt, sdb_per_table;
+
+	if (sfb->sdbt)
+		return -EINVAL;
+	sfb->num_sdb = 0;
+
+	/* Compute the number of required sample-data-block-tables (SDBT) */
+	num_sdbt = num_sdb / ((PAGE_SIZE - 8) / 8);
+	if (num_sdbt < CPUM_SF_MIN_SDBT)
+		num_sdbt = CPUM_SF_MIN_SDBT;
+	sdb_per_table = (PAGE_SIZE - 8) / 8;
+
+	debug_sprintf_event(sfdbg, 4, "alloc_sampling_buffer: num_sdbt=%lu "
+			    "num_sdb=%lu sdb_per_table=%lu\n",
+			    num_sdbt, num_sdb, sdb_per_table);
+	sdbt = NULL;
+	tail = sdbt;
+
+	for (j = 0; j < num_sdbt; j++) {
+		sdbt = (unsigned long *) get_zeroed_page(GFP_KERNEL);
+		if (!sdbt) {
+			rc = -ENOMEM;
+			goto allocate_sdbt_error;
+		}
+
+		/* save origin of sample-data-block-table */
+		if (!sfb->sdbt)
+			sfb->sdbt = (unsigned long) sdbt;
+
+		/* link current page to tail of chain */
+		if (tail)
+			*tail = (unsigned long)(void *) sdbt + 1;
+
+		for (k = 0; k < num_sdb && k < sdb_per_table; k++) {
+			/* get and set SDB page */
+			sdb = get_zeroed_page(GFP_KERNEL);
+			if (!sdb) {
+				rc = -ENOMEM;
+				goto allocate_sdbt_error;
+			}
+			*sdbt = sdb;
+			trailer = trailer_entry_ptr(*sdbt);
+			*trailer = SDB_TE_ALERT_REQ_MASK;
+			sdbt++;
+		}
+		num_sdb -= k;
+		sfb->num_sdb += k;	/* count allocated sdb's */
+		tail = sdbt;
+	}
+
+	rc = 0;
+	if (tail)
+		*tail = sfb->sdbt + 1;
+	sfb->tail = (unsigned long) (void *)tail;
+
+allocate_sdbt_error:
+	if (rc)
+		free_sampling_buffer(sfb);
+	else
+		debug_sprintf_event(sfdbg, 4,
+			"alloc_sampling_buffer: tear=%0lx dear=%0lx\n",
+			sfb->sdbt, *(unsigned long *) sfb->sdbt);
+	return rc;
+}
+
+static int allocate_sdbt(struct cpu_hw_sf *cpuhw, const struct hw_perf_event *hwc)
+{
+	unsigned long n_sdb, freq;
+	unsigned long factor;
+
+	/* Calculate sampling buffers using 4K pages
+	 *
+	 *    1. Use frequency as input.  The samping buffer is designed for
+	 *	 a complete second.  This can be adjusted through the "factor"
+	 *	 variable.
+	 *	 In any case, alloc_sampling_buffer() sets the Alert Request
+	 *	 Control indicator to trigger measurement-alert to harvest
+	 *	 sample-data-blocks (sdb).
+	 *
+	 *    2. Compute the number of sample-data-blocks and ensure a minimum
+	 *	 of CPUM_SF_MIN_SDB.  Also ensure the upper limit does not
+	 *	 exceed CPUM_SF_MAX_SDB.  See also the remarks for these
+	 *	 symbolic constants.
+	 *
+	 *    3. Compute number of pages used for the sample-data-block-table
+	 *	 and ensure a minimum of CPUM_SF_MIN_SDBT (at minimum one table
+	 *	 to manage up to 511 sample-data-blocks).
+	 */
+	freq = sample_rate_to_freq(&cpuhw->qsi, SAMPL_RATE(hwc));
+	factor = 1;
+	n_sdb = DIV_ROUND_UP(freq, factor * ((PAGE_SIZE-64) / cpuhw->qsi.bsdes));
+	if (n_sdb < CPUM_SF_MIN_SDB)
+		n_sdb = CPUM_SF_MIN_SDB;
+
+	/* Return if there is already a sampling buffer allocated.
+	 * XXX Remove this later and check number of available and
+	 * required sdb's and, if necessary, increase the sampling buffer.
+	 */
+	if (sf_buffer_available(cpuhw))
+		return 0;
+
+	debug_sprintf_event(sfdbg, 3,
+			    "allocate_sdbt: rate=%lu f=%lu sdb=%lu/%i cpuhw=%p\n",
+			    SAMPL_RATE(hwc), freq, n_sdb, CPUM_SF_MAX_SDB, cpuhw);
+
+	return alloc_sampling_buffer(&cpuhw->sfb,
+			       min_t(unsigned long, n_sdb, CPUM_SF_MAX_SDB));
+}
+
+
+/* Number of perf events counting hardware events */
+static atomic_t num_events;
+/* Used to avoid races in calling reserve/release_cpumf_hardware */
+static DEFINE_MUTEX(pmc_reserve_mutex);
+
+/*
+ * sf_disable() - Switch off sampling facility
+ */
+static int sf_disable(void)
+{
+	struct hws_lsctl_request_block sreq;
+
+	memset(&sreq, 0, sizeof(sreq));
+	return lsctl(&sreq);
+}
+
+
+#define PMC_INIT      0
+#define PMC_RELEASE   1
+static void setup_pmc_cpu(void *flags)
+{
+	int err;
+	struct cpu_hw_sf *cpusf = &__get_cpu_var(cpu_hw_sf);
+
+	/* XXX Improve error handling and pass a flag in the *flags
+	 *     variable to indicate failures.  Alternatively, ignore
+	 *     (print) errors here and let the PMU functions fail if
+	 *     the per-cpu PMU_F_RESERVED flag is not.
+	 */
+	err = 0;
+	switch (*((int *) flags)) {
+	case PMC_INIT:
+		memset(cpusf, 0, sizeof(*cpusf));
+		err = qsi(&cpusf->qsi);
+		if (err)
+			break;
+		cpusf->flags |= PMU_F_RESERVED;
+		err = sf_disable();
+		if (err)
+			pr_err("Switching off the sampling facility failed "
+			       "with rc=%i\n", err);
+		debug_sprintf_event(sfdbg, 5,
+				    "setup_pmc_cpu: initialized: cpuhw=%p\n", cpusf);
+		break;
+	case PMC_RELEASE:
+		cpusf->flags &= ~PMU_F_RESERVED;
+		err = sf_disable();
+		if (err) {
+			pr_err("Switching off the sampling facility failed "
+			       "with rc=%i\n", err);
+		} else {
+			if (cpusf->sfb.sdbt)
+				free_sampling_buffer(&cpusf->sfb);
+		}
+		debug_sprintf_event(sfdbg, 5,
+				    "setup_pmc_cpu: released: cpuhw=%p\n", cpusf);
+		break;
+	}
+}
+
+static void release_pmc_hardware(void)
+{
+	int flags = PMC_RELEASE;
+
+	irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+	on_each_cpu(setup_pmc_cpu, &flags, 1);
+}
+
+static int reserve_pmc_hardware(void)
+{
+	int flags = PMC_INIT;
+
+	on_each_cpu(setup_pmc_cpu, &flags, 1);
+	irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+
+	return 0;
+}
+
+static void hw_perf_event_destroy(struct perf_event *event)
+{
+	/* Release PMC if this is the last perf event */
+	if (!atomic_add_unless(&num_events, -1, 1)) {
+		mutex_lock(&pmc_reserve_mutex);
+		if (atomic_dec_return(&num_events) == 0)
+			release_pmc_hardware();
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+}
+
+static void hw_init_period(struct hw_perf_event *hwc, u64 period)
+{
+	hwc->sample_period = period;
+	hwc->last_period = hwc->sample_period;
+	local64_set(&hwc->period_left, hwc->sample_period);
+}
+
+static void hw_reset_registers(struct hw_perf_event *hwc,
+			       unsigned long sdbt_origin)
+{
+	TEAR_REG(hwc) = sdbt_origin;	      /* (re)set to first sdb table */
+}
+
+static unsigned long hw_limit_rate(const struct hws_qsi_info_block *si,
+				   unsigned long rate)
+{
+	if (rate < si->min_sampl_rate)
+		return si->min_sampl_rate;
+	if (rate > si->max_sampl_rate)
+		return si->max_sampl_rate;
+	return rate;
+}
+
+static int __hw_perf_event_init(struct perf_event *event)
+{
+	struct cpu_hw_sf *cpuhw;
+	struct hws_qsi_info_block si;
+	struct perf_event_attr *attr = &event->attr;
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned long rate;
+	int cpu, err;
+
+	/* Reserve CPU-measurement sampling facility */
+	err = 0;
+	if (!atomic_inc_not_zero(&num_events)) {
+		mutex_lock(&pmc_reserve_mutex);
+		if (atomic_read(&num_events) == 0 && reserve_pmc_hardware())
+			err = -EBUSY;
+		else
+			atomic_inc(&num_events);
+		mutex_unlock(&pmc_reserve_mutex);
+	}
+	event->destroy = hw_perf_event_destroy;
+
+	if (err)
+		goto out;
+
+	/* Access per-CPU sampling information (query sampling info) */
+	/*
+	 * The event->cpu value can be -1 to count on every CPU, for example,
+	 * when attaching to a task.  If this is specified, use the query
+	 * sampling info from the current CPU, otherwise use event->cpu to
+	 * retrieve the per-CPU information.
+	 * Later, cpuhw indicates whether to allocate sampling buffers for a
+	 * particular CPU (cpuhw!=NULL) or each online CPU (cpuw==NULL).
+	 */
+	memset(&si, 0, sizeof(si));
+	cpuhw = NULL;
+	if (event->cpu == -1)
+		qsi(&si);
+	else {
+		/* Event is pinned to a particular CPU, retrieve the per-CPU
+		 * sampling structure for accessing the CPU-specific QSI.
+		 */
+		cpuhw = &per_cpu(cpu_hw_sf, event->cpu);
+		si = cpuhw->qsi;
+	}
+
+	/* Check sampling facility authorization and, if not authorized,
+	 * fall back to other PMUs.  It is safe to check any CPU because
+	 * the authorization is identical for all configured CPUs.
+	 */
+	if (!si.as) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	/* The sampling information (si) contains information about the
+	 * min/max sampling intervals and the CPU speed.  So calculate the
+	 * correct sampling interval and avoid the whole period adjust
+	 * feedback loop.
+	 */
+	rate = 0;
+	if (attr->freq) {
+		rate = freq_to_sample_rate(&si, attr->sample_freq);
+		rate = hw_limit_rate(&si, rate);
+		attr->freq = 0;
+		attr->sample_period = rate;
+	} else {
+		/* The min/max sampling rates specifies the valid range
+		 * of sample periods.  If the specified sample period is
+		 * out of range, limit the period to the range boundary.
+		 */
+		rate = hw_limit_rate(&si, hwc->sample_period);
+
+		/* The perf core maintains a maximum sample rate that is
+		 * configurable through the sysctl interface.  Ensure the
+		 * sampling rate does not exceed this value.  This also helps
+		 * to avoid throttling when pushing samples with
+		 * perf_event_overflow().
+		 */
+		if (sample_rate_to_freq(&si, rate) >
+		      sysctl_perf_event_sample_rate) {
+			err = -EINVAL;
+			debug_sprintf_event(sfdbg, 1, "Sampling rate exceeds maximum perf sample rate\n");
+			goto out;
+		}
+	}
+	SAMPL_RATE(hwc) = rate;
+	hw_init_period(hwc, SAMPL_RATE(hwc));
+
+	/* Allocate the per-CPU sampling buffer using the CPU information
+	 * from the event.  If the event is not pinned to a particular
+	 * CPU (event->cpu == -1; or cpuhw == NULL), allocate sampling
+	 * buffers for each online CPU.
+	 */
+	if (cpuhw)
+		/* Event is pinned to a particular CPU */
+		err = allocate_sdbt(cpuhw, hwc);
+	else {
+		/* Event is not pinned, allocate sampling buffer on
+		 * each online CPU
+		 */
+		for_each_online_cpu(cpu) {
+			cpuhw = &per_cpu(cpu_hw_sf, cpu);
+			err = allocate_sdbt(cpuhw, hwc);
+			if (err)
+				break;
+		}
+	}
+out:
+	return err;
+}
+
+static int cpumsf_pmu_event_init(struct perf_event *event)
+{
+	int err;
+
+	if (event->attr.type != PERF_TYPE_RAW)
+		return -ENOENT;
+
+	if (event->attr.config != PERF_EVENT_CPUM_SF)
+		return -ENOENT;
+
+	if (event->cpu >= nr_cpumask_bits ||
+	    (event->cpu >= 0 && !cpu_online(event->cpu)))
+		return -ENODEV;
+
+	err = __hw_perf_event_init(event);
+	if (unlikely(err))
+		if (event->destroy)
+			event->destroy(event);
+	return err;
+}
+
+static void cpumsf_pmu_enable(struct pmu *pmu)
+{
+	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	int err;
+
+	if (cpuhw->flags & PMU_F_ENABLED)
+		return;
+
+	if (cpuhw->flags & PMU_F_ERR_MASK)
+		return;
+
+	cpuhw->flags |= PMU_F_ENABLED;
+	barrier();
+
+	err = lsctl(&cpuhw->lsctl);
+	if (err) {
+		cpuhw->flags &= ~PMU_F_ENABLED;
+		pr_err("Loading sampling controls failed: op=%i err=%i\n",
+			1, err);
+		return;
+	}
+
+	debug_sprintf_event(sfdbg, 6, "pmu_enable: es=%i cs=%i tear=%p dear=%p\n",
+			    cpuhw->lsctl.es, cpuhw->lsctl.cs,
+			    (void *) cpuhw->lsctl.tear, (void *) cpuhw->lsctl.dear);
+}
+
+static void cpumsf_pmu_disable(struct pmu *pmu)
+{
+	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct hws_lsctl_request_block inactive;
+	struct hws_qsi_info_block si;
+	int err;
+
+	if (!(cpuhw->flags & PMU_F_ENABLED))
+		return;
+
+	if (cpuhw->flags & PMU_F_ERR_MASK)
+		return;
+
+	/* Switch off sampling activation control */
+	inactive = cpuhw->lsctl;
+	inactive.cs = 0;
+
+	err = lsctl(&inactive);
+	if (err) {
+		pr_err("Loading sampling controls failed: op=%i err=%i\n",
+			2, err);
+		return;
+	}
+
+	/* Save state of TEAR and DEAR register contents */
+	if (!qsi(&si)) {
+		/* TEAR/DEAR values are valid only if the sampling facility is
+		 * enabled.  Note that cpumsf_pmu_disable() might be called even
+		 * for a disabled sampling facility because cpumsf_pmu_enable()
+		 * controls the enable/disable state.
+		 */
+		if (si.es) {
+			cpuhw->lsctl.tear = si.tear;
+			cpuhw->lsctl.dear = si.dear;
+		}
+	} else
+		debug_sprintf_event(sfdbg, 3, "cpumsf_pmu_disable: "
+				    "qsi() failed with err=%i\n", err);
+
+	cpuhw->flags &= ~PMU_F_ENABLED;
+}
+
+/* perf_push_sample() - Push samples to perf
+ * @event:	The perf event
+ * @sample:	Hardware sample data
+ *
+ * Use the hardware sample data to create perf event sample.  The sample
+ * is the pushed to the event subsystem and the function checks for
+ * possible event overflows.  If an event overflow occurs, the PMU is
+ * stopped.
+ *
+ * Return non-zero if an event overflow occurred.
+ */
+static int perf_push_sample(struct perf_event *event,
+			    struct hws_data_entry *sample)
+{
+	int overflow;
+	struct pt_regs regs;
+	struct perf_sample_data data;
+
+	/* Skip samples that are invalid or for which the instruction address
+	 * is not predictable.	For the latter, the wait-state bit is set.
+	 */
+	if (sample->I || sample->W)
+		return 0;
+
+	perf_sample_data_init(&data, 0, event->hw.last_period);
+
+	memset(&regs, 0, sizeof(regs));
+	regs.psw.addr = sample->ia;
+	if (sample->T)
+		regs.psw.mask |= PSW_MASK_DAT;
+	if (sample->W)
+		regs.psw.mask |= PSW_MASK_WAIT;
+	if (sample->P)
+		regs.psw.mask |= PSW_MASK_PSTATE;
+	switch (sample->AS) {
+	case 0x0:
+		regs.psw.mask |= PSW_ASC_PRIMARY;
+		break;
+	case 0x1:
+		regs.psw.mask |= PSW_ASC_ACCREG;
+		break;
+	case 0x2:
+		regs.psw.mask |= PSW_ASC_SECONDARY;
+		break;
+	case 0x3:
+		regs.psw.mask |= PSW_ASC_HOME;
+		break;
+	}
+
+	overflow = 0;
+	if (perf_event_overflow(event, &data, &regs)) {
+		overflow = 1;
+		event->pmu->stop(event, 0);
+		debug_sprintf_event(sfdbg, 4, "perf_push_sample: PMU stopped"
+				    " because of an event overflow\n");
+	}
+	perf_event_update_userpage(event);
+
+	return overflow;
+}
+
+static void perf_event_count_update(struct perf_event *event, u64 count)
+{
+	local64_add(count, &event->count);
+}
+
+/* hw_collect_samples() - Walk through a sample-data-block and collect samples
+ * @event:	The perf event
+ * @sdbt:	Sample-data-block table
+ * @overflow:	Event overflow counter
+ *
+ * Walks through a sample-data-block and collects hardware sample-data that is
+ * pushed to the perf event subsystem.	The overflow reports the number of
+ * samples that has been discarded due to an event overflow.
+ */
+static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt,
+			       unsigned long long *overflow)
+{
+	struct hws_data_entry *sample;
+	unsigned long *trailer;
+
+	trailer = trailer_entry_ptr(*sdbt);
+	sample = (struct hws_data_entry *) *sdbt;
+	while ((unsigned long *) sample < trailer) {
+		/* Check for an empty sample */
+		if (!sample->def)
+			break;
+
+		/* Update perf event period */
+		perf_event_count_update(event, SAMPL_RATE(&event->hw));
+
+		/* Check for basic sampling mode */
+		if (sample->def == 0x0001) {
+			/* If an event overflow occurred, the PMU is stopped to
+			 * throttle event delivery.  Remaining sample data is
+			 * discarded.
+			 */
+			if (!*overflow)
+				*overflow = perf_push_sample(event, sample);
+			else
+				/* Count discarded samples */
+				*overflow += 1;
+		} else
+			/* Sample slot is not yet written or other record */
+			debug_sprintf_event(sfdbg, 5, "hw_collect_samples: "
+					    "Unknown sample data entry format:"
+					    " %i\n", sample->def);
+
+		/* Reset sample slot and advance to next sample */
+		sample->def = 0;
+		sample++;
+	}
+}
+
+/* hw_perf_event_update() - Process sampling buffer
+ * @event:	The perf event
+ * @flush_all:	Flag to also flush partially filled sample-data-blocks
+ *
+ * Processes the sampling buffer and create perf event samples.
+ * The sampling buffer position are retrieved and saved in the TEAR_REG
+ * register of the specified perf event.
+ *
+ * Only full sample-data-blocks are processed.	Specify the flash_all flag
+ * to also walk through partially filled sample-data-blocks.
+ *
+ */
+static void hw_perf_event_update(struct perf_event *event, int flush_all)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hws_trailer_entry *te;
+	unsigned long *sdbt;
+	unsigned long long event_overflow, sampl_overflow;
+	int done;
+
+	sdbt = (unsigned long *) TEAR_REG(hwc);
+	done = event_overflow = sampl_overflow = 0;
+	while (!done) {
+		/* Get the trailer entry of the sample-data-block */
+		te = (struct hws_trailer_entry *) trailer_entry_ptr(*sdbt);
+
+		/* Leave loop if no more work to do (block full indicator) */
+		if (!te->f) {
+			done = 1;
+			if (!flush_all)
+				break;
+		}
+
+		/* Check sample overflow count */
+		if (te->overflow) {
+			/* Increment sample overflow counter */
+			sampl_overflow += te->overflow;
+
+			/* XXX: If an sample overflow occurs, increase the
+			 *	sampling buffer.  Set a "realloc" flag because
+			 *	the sampler must be re-enabled for changing
+			 *	the sample-data-block-table content.
+			 */
+		}
+
+		/* Timestamps are valid for full sample-data-blocks only */
+		debug_sprintf_event(sfdbg, 6, "hw_perf_event_update: sdbt=%p "
+				    "overflow=%llu timestamp=0x%llx\n",
+				    sdbt, te->overflow,
+				    (te->f) ? te->timestamp : 0ULL);
+
+		/* Collect all samples from a single sample-data-block and
+		 * flag if an (perf) event overflow happened.  If so, the PMU
+		 * is stopped and remaining samples will be discarded.
+		 */
+		hw_collect_samples(event, sdbt, &event_overflow);
+
+		/* Reset trailer */
+		xchg(&te->overflow, 0);
+		xchg((unsigned char *) te, 0x40);
+
+		/* Advance to next sample-data-block */
+		sdbt++;
+		if (is_link_entry(sdbt))
+			sdbt = get_next_sdbt(sdbt);
+
+		/* Update event hardware registers */
+		TEAR_REG(hwc) = (unsigned long) sdbt;
+
+		/* Stop processing sample-data if all samples of the current
+		 * sample-data-block were flushed even if it was not full.
+		 */
+		if (flush_all && done)
+			break;
+
+		/* If an event overflow happened, discard samples by
+		 * processing any remaining sample-data-blocks.
+		 */
+		if (event_overflow)
+			flush_all = 1;
+	}
+
+	if (sampl_overflow || event_overflow)
+		debug_sprintf_event(sfdbg, 4, "hw_perf_event_update: "
+				    "overflow stats: sample=%llu event=%llu\n",
+				    sampl_overflow, event_overflow);
+}
+
+static void cpumsf_pmu_read(struct perf_event *event)
+{
+	/* Nothing to do ... updates are interrupt-driven */
+}
+
+/* Activate sampling control.
+ * Next call of pmu_enable() starts sampling.
+ */
+static void cpumsf_pmu_start(struct perf_event *event, int flags)
+{
+	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+
+	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+		return;
+
+	if (flags & PERF_EF_RELOAD)
+		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+
+	perf_pmu_disable(event->pmu);
+	event->hw.state = 0;
+	cpuhw->lsctl.cs = 1;
+	perf_pmu_enable(event->pmu);
+}
+
+/* Deactivate sampling control.
+ * Next call of pmu_enable() stops sampling.
+ */
+static void cpumsf_pmu_stop(struct perf_event *event, int flags)
+{
+	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+
+	if (event->hw.state & PERF_HES_STOPPED)
+		return;
+
+	perf_pmu_disable(event->pmu);
+	cpuhw->lsctl.cs = 0;
+	event->hw.state |= PERF_HES_STOPPED;
+
+	if ((flags & PERF_EF_UPDATE) && !(event->hw.state & PERF_HES_UPTODATE)) {
+		hw_perf_event_update(event, 1);
+		event->hw.state |= PERF_HES_UPTODATE;
+	}
+	perf_pmu_enable(event->pmu);
+}
+
+static int cpumsf_pmu_add(struct perf_event *event, int flags)
+{
+	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	int err;
+
+	if (cpuhw->flags & PMU_F_IN_USE)
+		return -EAGAIN;
+
+	if (!cpuhw->sfb.sdbt)
+		return -EINVAL;
+
+	err = 0;
+	perf_pmu_disable(event->pmu);
+
+	event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+	/* Set up sampling controls.  Always program the sampling register
+	 * using the SDB-table start.  Reset TEAR_REG event hardware register
+	 * that is used by hw_perf_event_update() to store the sampling buffer
+	 * position after samples have been flushed.
+	 */
+	cpuhw->lsctl.s = 0;
+	cpuhw->lsctl.h = 1;
+	cpuhw->lsctl.tear = cpuhw->sfb.sdbt;
+	cpuhw->lsctl.dear = *(unsigned long *) cpuhw->sfb.sdbt;
+	cpuhw->lsctl.interval = SAMPL_RATE(&event->hw);
+	hw_reset_registers(&event->hw, cpuhw->sfb.sdbt);
+
+	/* Ensure sampling functions are in the disabled state.  If disabled,
+	 * switch on sampling enable control. */
+	if (WARN_ON_ONCE(cpuhw->lsctl.es == 1)) {
+		err = -EAGAIN;
+		goto out;
+	}
+	cpuhw->lsctl.es = 1;
+
+	/* Set in_use flag and store event */
+	event->hw.idx = 0;	  /* only one sampling event per CPU supported */
+	cpuhw->event = event;
+	cpuhw->flags |= PMU_F_IN_USE;
+
+	if (flags & PERF_EF_START)
+		cpumsf_pmu_start(event, PERF_EF_RELOAD);
+out:
+	perf_event_update_userpage(event);
+	perf_pmu_enable(event->pmu);
+	return err;
+}
+
+static void cpumsf_pmu_del(struct perf_event *event, int flags)
+{
+	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+
+	perf_pmu_disable(event->pmu);
+	cpumsf_pmu_stop(event, PERF_EF_UPDATE);
+
+	cpuhw->lsctl.es = 0;
+	cpuhw->flags &= ~PMU_F_IN_USE;
+	cpuhw->event = NULL;
+
+	perf_event_update_userpage(event);
+	perf_pmu_enable(event->pmu);
+}
+
+static int cpumsf_pmu_event_idx(struct perf_event *event)
+{
+	return event->hw.idx;
+}
+
+CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC, PERF_EVENT_CPUM_SF);
+
+static struct attribute *cpumsf_pmu_events_attr[] = {
+	CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC),
+	NULL,
+};
+
+PMU_FORMAT_ATTR(event, "config:0-63");
+
+static struct attribute *cpumsf_pmu_format_attr[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group cpumsf_pmu_events_group = {
+	.name = "events",
+	.attrs = cpumsf_pmu_events_attr,
+};
+static struct attribute_group cpumsf_pmu_format_group = {
+	.name = "format",
+	.attrs = cpumsf_pmu_format_attr,
+};
+static const struct attribute_group *cpumsf_pmu_attr_groups[] = {
+	&cpumsf_pmu_events_group,
+	&cpumsf_pmu_format_group,
+	NULL,
+};
+
+static struct pmu cpumf_sampling = {
+	.pmu_enable   = cpumsf_pmu_enable,
+	.pmu_disable  = cpumsf_pmu_disable,
+
+	.event_init   = cpumsf_pmu_event_init,
+	.add	      = cpumsf_pmu_add,
+	.del	      = cpumsf_pmu_del,
+
+	.start	      = cpumsf_pmu_start,
+	.stop	      = cpumsf_pmu_stop,
+	.read	      = cpumsf_pmu_read,
+
+	.event_idx    = cpumsf_pmu_event_idx,
+	.attr_groups  = cpumsf_pmu_attr_groups,
+};
+
+static void cpumf_measurement_alert(struct ext_code ext_code,
+				    unsigned int alert, unsigned long unused)
+{
+	struct cpu_hw_sf *cpuhw;
+
+	if (!(alert & CPU_MF_INT_SF_MASK))
+		return;
+	inc_irq_stat(IRQEXT_CMS);
+	cpuhw = &__get_cpu_var(cpu_hw_sf);
+
+	/* Measurement alerts are shared and might happen when the PMU
+	 * is not reserved.  Ignore these alerts in this case. */
+	if (!(cpuhw->flags & PMU_F_RESERVED))
+		return;
+
+	/* The processing below must take care of multiple alert events that
+	 * might be indicated concurrently. */
+
+	/* Program alert request */
+	if (alert & CPU_MF_INT_SF_PRA) {
+		if (cpuhw->flags & PMU_F_IN_USE)
+			hw_perf_event_update(cpuhw->event, 0);
+		else
+			WARN_ON_ONCE(!(cpuhw->flags & PMU_F_IN_USE));
+	}
+
+	/* Report measurement alerts only for non-PRA codes */
+	if (alert != CPU_MF_INT_SF_PRA)
+		debug_sprintf_event(sfdbg, 6, "measurement alert: 0x%x\n", alert);
+
+	/* Sampling authorization change request */
+	if (alert & CPU_MF_INT_SF_SACA)
+		qsi(&cpuhw->qsi);
+
+	/* Loss of sample data due to high-priority machine activities */
+	if (alert & CPU_MF_INT_SF_LSDA) {
+		pr_err("Sample data was lost\n");
+		cpuhw->flags |= PMU_F_ERR_LSDA;
+		sf_disable();
+	}
+
+	/* Invalid sampling buffer entry */
+	if (alert & (CPU_MF_INT_SF_IAE|CPU_MF_INT_SF_ISE)) {
+		pr_err("A sampling buffer entry is incorrect (alert=0x%x)\n",
+		       alert);
+		cpuhw->flags |= PMU_F_ERR_IBE;
+		sf_disable();
+	}
+}
+
+static int __cpuinit cpumf_pmu_notifier(struct notifier_block *self,
+					unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (long) hcpu;
+	int flags;
+
+	/* Ignore the notification if no events are scheduled on the PMU.
+	 * This might be racy...
+	 */
+	if (!atomic_read(&num_events))
+		return NOTIFY_OK;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		flags = PMC_INIT;
+		smp_call_function_single(cpu, setup_pmc_cpu, &flags, 1);
+		break;
+	case CPU_DOWN_PREPARE:
+		flags = PMC_RELEASE;
+		smp_call_function_single(cpu, setup_pmc_cpu, &flags, 1);
+		break;
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static int __init init_cpum_sampling_pmu(void)
+{
+	int err;
+
+	if (!cpum_sf_avail())
+		return -ENODEV;
+
+	sfdbg = debug_register(KMSG_COMPONENT, 2, 1, 80);
+	if (!sfdbg)
+		pr_err("Registering for s390dbf failed\n");
+	debug_register_view(sfdbg, &debug_sprintf_view);
+
+	err = register_external_interrupt(0x1407, cpumf_measurement_alert);
+	if (err) {
+		pr_err("Failed to register for CPU-measurement alerts\n");
+		goto out;
+	}
+
+	err = perf_pmu_register(&cpumf_sampling, "cpum_sf", PERF_TYPE_RAW);
+	if (err) {
+		pr_err("Failed to register cpum_sf pmu\n");
+		unregister_external_interrupt(0x1407, cpumf_measurement_alert);
+		goto out;
+	}
+	perf_cpu_notifier(cpumf_pmu_notifier);
+out:
+	return err;
+}
+arch_initcall(init_cpum_sampling_pmu);
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 4c1d336..b9843ba 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -16,6 +16,7 @@
 #include <linux/kvm_host.h>
 #include <linux/percpu.h>
 #include <linux/export.h>
+#include <linux/spinlock.h>
 #include <linux/sysfs.h>
 #include <asm/irq.h>
 #include <asm/cpu_mf.h>
@@ -36,6 +37,8 @@ int perf_num_counters(void)
 
 	if (cpum_cf_avail())
 		num += PERF_CPUM_CF_MAX_CTR;
+	if (cpum_sf_avail())
+		num += PERF_CPUM_SF_MAX_CTR;
 
 	return num;
 }
@@ -93,24 +96,45 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
 			       : PERF_RECORD_MISC_KERNEL;
 }
 
-void perf_event_print_debug(void)
+void print_debug_cf(void)
 {
 	struct cpumf_ctr_info cf_info;
-	unsigned long flags;
-	int cpu;
-
-	if (!cpum_cf_avail())
-		return;
-
-	local_irq_save(flags);
+	int cpu = smp_processor_id();
 
-	cpu = smp_processor_id();
 	memset(&cf_info, 0, sizeof(cf_info));
 	if (!qctri(&cf_info))
 		pr_info("CPU[%i] CPUM_CF: ver=%u.%u A=%04x E=%04x C=%04x\n",
 			cpu, cf_info.cfvn, cf_info.csvn,
 			cf_info.auth_ctl, cf_info.enable_ctl, cf_info.act_ctl);
+}
+
+static void print_debug_sf(void)
+{
+	struct hws_qsi_info_block si;
+	int cpu = smp_processor_id();
+
+	memset(&si, 0, sizeof(si));
+	if (qsi(&si)) {
+		pr_err("CPU[%i]: CPM_SF: qsi failed\n");
+		return;
+	}
+
+	pr_info("CPU[%i]: CPM_SF: as=%i es=%i cs=%i bsdes=%i dsdes=%i"
+		" min=%i max=%i cpu_speed=%i tear=%p dear=%p\n",
+		cpu, si.as, si.es, si.cs, si.bsdes, si.dsdes,
+		si.min_sampl_rate, si.max_sampl_rate, si.cpu_speed,
+		si.tear, si.dear);
+}
+
+void perf_event_print_debug(void)
+{
+	unsigned long flags;
 
+	local_irq_save(flags);
+	if (cpum_cf_avail())
+		print_debug_cf();
+	if (cpum_sf_avail())
+		print_debug_sf();
 	local_irq_restore(flags);
 }
 
-- 
cgit v0.10.2


From 55baa2f831ae4a41da9617ab9e7cef5ebc991ec9 Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Thu, 12 Dec 2013 16:47:00 +0100
Subject: s390/perf: Improve PMU selection for PERF_COUNT_HW_CPU_CYCLES events

The cpum_cf (counter facility) PMU does not support sampling events.
With cpum_sf (sampling facility), a PMU for sampling CPU cycles is
available.

Make cpum_sf the "default" PMU for PERF_COUNT_HW_CPU_CYCLES sampling
events but use the more precise cpum_cf PMU for non-sampling events.

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 141eca0..52bf36e 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -468,11 +468,29 @@ static int cpumsf_pmu_event_init(struct perf_event *event)
 {
 	int err;
 
-	if (event->attr.type != PERF_TYPE_RAW)
-		return -ENOENT;
-
-	if (event->attr.config != PERF_EVENT_CPUM_SF)
+	/* No support for taken branch sampling */
+	if (has_branch_stack(event))
+		return -EOPNOTSUPP;
+
+	switch (event->attr.type) {
+	case PERF_TYPE_RAW:
+		if (event->attr.config != PERF_EVENT_CPUM_SF)
+			return -ENOENT;
+		break;
+	case PERF_TYPE_HARDWARE:
+		/* Support sampling of CPU cycles in addition to the
+		 * counter facility.  However, the counter facility
+		 * is more precise and, hence, restrict this PMU to
+		 * sampling events only.
+		 */
+		if (event->attr.config != PERF_COUNT_HW_CPU_CYCLES)
+			return -ENOENT;
+		if (!is_sampling_event(event))
+			return -ENOENT;
+		break;
+	default:
 		return -ENOENT;
+	}
 
 	if (event->cpu >= nr_cpumask_bits ||
 	    (event->cpu >= 0 && !cpu_online(event->cpu)))
-- 
cgit v0.10.2


From e28bb79d9935293a8eea5f3c771fde89db645ba7 Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Thu, 12 Dec 2013 16:52:48 +0100
Subject: s390/perf,oprofile: Share sampling facility

Introduce reserve/release functions to share the sampling facility
between perf and oprofile.
Also improve error handling for the sampling facility support in perf.

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index b4eea25..23d2dfa 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -52,5 +52,9 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define TEAR_REG(hwc)		((hwc)->last_tag)
 #define SAMPL_RATE(hwc)		((hwc)->event_base)
 
+/* Perf hardware reserve and release functions */
+int perf_reserve_sampling(void);
+void perf_release_sampling(void);
+
 #endif /* CONFIG_64BIT */
 #endif /* _ASM_S390_PERF_EVENT_H */
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 52bf36e..ae5e019 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -260,16 +260,12 @@ static int sf_disable(void)
 
 #define PMC_INIT      0
 #define PMC_RELEASE   1
+#define PMC_FAILURE   2
 static void setup_pmc_cpu(void *flags)
 {
 	int err;
 	struct cpu_hw_sf *cpusf = &__get_cpu_var(cpu_hw_sf);
 
-	/* XXX Improve error handling and pass a flag in the *flags
-	 *     variable to indicate failures.  Alternatively, ignore
-	 *     (print) errors here and let the PMU functions fail if
-	 *     the per-cpu PMU_F_RESERVED flag is not.
-	 */
 	err = 0;
 	switch (*((int *) flags)) {
 	case PMC_INIT:
@@ -299,6 +295,8 @@ static void setup_pmc_cpu(void *flags)
 				    "setup_pmc_cpu: released: cpuhw=%p\n", cpusf);
 		break;
 	}
+	if (err)
+		*((int *) flags) |= PMC_FAILURE;
 }
 
 static void release_pmc_hardware(void)
@@ -307,13 +305,22 @@ static void release_pmc_hardware(void)
 
 	irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
 	on_each_cpu(setup_pmc_cpu, &flags, 1);
+	perf_release_sampling();
 }
 
 static int reserve_pmc_hardware(void)
 {
 	int flags = PMC_INIT;
+	int err;
 
+	err = perf_reserve_sampling();
+	if (err)
+		return err;
 	on_each_cpu(setup_pmc_cpu, &flags, 1);
+	if (flags & PMC_FAILURE) {
+		release_pmc_hardware();
+		return -ENODEV;
+	}
 	irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
 
 	return 0;
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index b9843ba..4edcdfa 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -208,3 +208,33 @@ ssize_t cpumf_events_sysfs_show(struct device *dev,
 	return sprintf(page, "event=0x%04llx,name=%s\n",
 		       pmu_attr->id, attr->attr.name);
 }
+
+/* Reserve/release functions for sharing perf hardware */
+static DEFINE_SPINLOCK(perf_hw_owner_lock);
+static void *perf_sampling_owner;
+
+int perf_reserve_sampling(void)
+{
+	int err;
+
+	err = 0;
+	spin_lock(&perf_hw_owner_lock);
+	if (perf_sampling_owner) {
+		pr_warn("The sampling facility is already reserved by %p\n",
+			perf_sampling_owner);
+		err = -EBUSY;
+	} else
+		perf_sampling_owner = __builtin_return_address(0);
+	spin_unlock(&perf_hw_owner_lock);
+	return err;
+}
+EXPORT_SYMBOL(perf_reserve_sampling);
+
+void perf_release_sampling(void)
+{
+	spin_lock(&perf_hw_owner_lock);
+	WARN_ON(!perf_sampling_owner);
+	perf_sampling_owner = NULL;
+	spin_unlock(&perf_hw_owner_lock);
+}
+EXPORT_SYMBOL(perf_release_sampling);
diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c
index bbca76a..eb09587 100644
--- a/arch/s390/oprofile/hwsampler.c
+++ b/arch/s390/oprofile/hwsampler.c
@@ -41,6 +41,7 @@ static DEFINE_MUTEX(hws_sem_oom);
 
 static unsigned char hws_flush_all;
 static unsigned int hws_oom;
+static unsigned int hws_alert;
 static struct workqueue_struct *hws_wq;
 
 static unsigned int hws_state;
@@ -182,6 +183,9 @@ static void hws_ext_handler(struct ext_code ext_code,
 	if (!(param32 & CPU_MF_INT_SF_MASK))
 		return;
 
+	if (!hws_alert)
+		return;
+
 	inc_irq_stat(IRQEXT_CMS);
 	atomic_xchg(&cb->ext_params, atomic_read(&cb->ext_params) | param32);
 
@@ -941,6 +945,7 @@ int hwsampler_deallocate(void)
 		goto deallocate_exit;
 
 	irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+	hws_alert = 0;
 	deallocate_sdbt();
 
 	hws_state = HWS_DEALLOCATED;
@@ -1055,6 +1060,7 @@ int hwsampler_shutdown(void)
 
 		if (hws_state == HWS_STOPPED) {
 			irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+			hws_alert = 0;
 			deallocate_sdbt();
 		}
 		if (hws_wq) {
@@ -1129,6 +1135,7 @@ start_all_exit:
 	hws_oom = 1;
 	hws_flush_all = 0;
 	/* now let them in, 1407 CPUMF external interrupts */
+	hws_alert = 1;
 	irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
 
 	return 0;
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index 04e1b6a..9ffe645 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/oprofile.h>
+#include <linux/perf_event.h>
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
@@ -67,6 +68,21 @@ module_param_call(cpu_type, set_cpu_type, NULL, NULL, 0);
 MODULE_PARM_DESC(cpu_type, "Force legacy basic mode sampling"
 		           "(report cpu_type \"timer\"");
 
+static int __oprofile_hwsampler_start(void)
+{
+	int retval;
+
+	retval = hwsampler_allocate(oprofile_sdbt_blocks, oprofile_sdb_blocks);
+	if (retval)
+		return retval;
+
+	retval = hwsampler_start_all(oprofile_hw_interval);
+	if (retval)
+		hwsampler_deallocate();
+
+	return retval;
+}
+
 static int oprofile_hwsampler_start(void)
 {
 	int retval;
@@ -76,13 +92,13 @@ static int oprofile_hwsampler_start(void)
 	if (!hwsampler_running)
 		return timer_ops.start();
 
-	retval = hwsampler_allocate(oprofile_sdbt_blocks, oprofile_sdb_blocks);
+	retval = perf_reserve_sampling();
 	if (retval)
 		return retval;
 
-	retval = hwsampler_start_all(oprofile_hw_interval);
+	retval = __oprofile_hwsampler_start();
 	if (retval)
-		hwsampler_deallocate();
+		perf_release_sampling();
 
 	return retval;
 }
@@ -96,6 +112,7 @@ static void oprofile_hwsampler_stop(void)
 
 	hwsampler_stop_all();
 	hwsampler_deallocate();
+	perf_release_sampling();
 	return;
 }
 
-- 
cgit v0.10.2


From 99c64b6679c41d8238b154c1a462724d7101765c Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Fri, 13 Dec 2013 12:38:39 +0100
Subject: s390/perf: Add service level information for CPU-Measurement
 Facilities

Register a service level handler to report information about available
CPU-Measurement facilities.

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 4edcdfa..3bd2bf0 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -16,17 +16,19 @@
 #include <linux/kvm_host.h>
 #include <linux/percpu.h>
 #include <linux/export.h>
+#include <linux/seq_file.h>
 #include <linux/spinlock.h>
 #include <linux/sysfs.h>
 #include <asm/irq.h>
 #include <asm/cpu_mf.h>
 #include <asm/lowcore.h>
 #include <asm/processor.h>
+#include <asm/sysinfo.h>
 
 const char *perf_pmu_name(void)
 {
 	if (cpum_cf_avail() || cpum_sf_avail())
-		return "CPU-measurement facilities (CPUMF)";
+		return "CPU-Measurement Facilities (CPU-MF)";
 	return "pmu";
 }
 EXPORT_SYMBOL(perf_pmu_name);
@@ -138,6 +140,60 @@ void perf_event_print_debug(void)
 	local_irq_restore(flags);
 }
 
+/* Service level infrastructure */
+static void sl_print_counter(struct seq_file *m)
+{
+	struct cpumf_ctr_info ci;
+
+	memset(&ci, 0, sizeof(ci));
+	if (qctri(&ci))
+		return;
+
+	seq_printf(m, "CPU-MF: Counter facility: version=%u.%u "
+		   "authorization=%04x\n", ci.cfvn, ci.csvn, ci.auth_ctl);
+}
+
+static void sl_print_sampling(struct seq_file *m)
+{
+	struct hws_qsi_info_block si;
+
+	memset(&si, 0, sizeof(si));
+	if (qsi(&si))
+		return;
+
+	if (!si.as && !si.ad)
+		return;
+
+	seq_printf(m, "CPU-MF: Sampling facility: min_rate=%lu max_rate=%lu"
+		   " cpu_speed=%u\n", si.min_sampl_rate, si.max_sampl_rate,
+		   si.cpu_speed);
+	if (si.as)
+		seq_printf(m, "CPU-MF: Sampling facility: mode=basic"
+			   " sample_size=%u\n", si.bsdes);
+	if (si.ad)
+		seq_printf(m, "CPU-MF: Sampling facility: mode=diagnostic"
+			   " sample_size=%u\n", si.dsdes);
+}
+
+static void service_level_perf_print(struct seq_file *m,
+				     struct service_level *sl)
+{
+	if (cpum_cf_avail())
+		sl_print_counter(m);
+	if (cpum_sf_avail())
+		sl_print_sampling(m);
+}
+
+static struct service_level service_level_perf = {
+	.seq_print = service_level_perf_print,
+};
+
+static int __init service_level_perf_register(void)
+{
+	return register_service_level(&service_level_perf);
+}
+arch_initcall(service_level_perf_register);
+
 /* See also arch/s390/kernel/traps.c */
 static unsigned long __store_trace(struct perf_callchain_entry *entry,
 				   unsigned long sp,
-- 
cgit v0.10.2


From aa3b7c296732b4351dfdbfe70be6b38a0882be14 Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@linux.vnet.ibm.com>
Date: Thu, 12 Dec 2013 17:48:32 +0100
Subject: s390/pci: prevent inadvertently triggered bus scans

Initialization and scanning of the pci bus is omitted on older
machines without pci support or if pci=off was specified. Remember
the fact that we ran without pci support and prevent further bus
scans during resume from hibernate or after receiving hotplug
notifications.

Reported-by: Stefan Haberland <stefan.haberland@de.ibm.com>
Reviewed-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index c129ab2..2583466 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -144,6 +144,7 @@ int clp_disable_fh(struct zpci_dev *);
 void zpci_event_error(void *);
 void zpci_event_availability(void *);
 void zpci_rescan(void);
+bool zpci_is_enabled(void);
 #else /* CONFIG_PCI */
 static inline void zpci_event_error(void *e) {}
 static inline void zpci_event_availability(void *e) {}
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index bf7c73d..e3265b5 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -920,6 +920,7 @@ static void zpci_mem_exit(void)
 }
 
 static unsigned int s390_pci_probe;
+static unsigned int s390_pci_initialized;
 
 char * __init pcibios_setup(char *str)
 {
@@ -930,6 +931,11 @@ char * __init pcibios_setup(char *str)
 	return str;
 }
 
+bool zpci_is_enabled(void)
+{
+	return s390_pci_initialized;
+}
+
 static int __init pci_base_init(void)
 {
 	int rc;
@@ -961,6 +967,7 @@ static int __init pci_base_init(void)
 	if (rc)
 		goto out_find;
 
+	s390_pci_initialized = 1;
 	return 0;
 
 out_find:
@@ -978,5 +985,6 @@ subsys_initcall_sync(pci_base_init);
 
 void zpci_rescan(void)
 {
-	clp_rescan_pci_devices_simple();
+	if (zpci_is_enabled())
+		clp_rescan_pci_devices_simple();
 }
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 800f064..228787a 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -43,9 +43,8 @@ struct zpci_ccdf_avail {
 	u16 pec;			/* PCI event code */
 } __packed;
 
-void zpci_event_error(void *data)
+static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 {
-	struct zpci_ccdf_err *ccdf = data;
 	struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
 
 	zpci_err("error CCDF:\n");
@@ -58,9 +57,14 @@ void zpci_event_error(void *data)
 	       pci_name(zdev->pdev), ccdf->pec, ccdf->fid);
 }
 
-void zpci_event_availability(void *data)
+void zpci_event_error(void *data)
+{
+	if (zpci_is_enabled())
+		__zpci_event_error(data);
+}
+
+static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 {
-	struct zpci_ccdf_avail *ccdf = data;
 	struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
 	struct pci_dev *pdev = zdev ? zdev->pdev : NULL;
 	int ret;
@@ -115,3 +119,9 @@ void zpci_event_availability(void *data)
 		break;
 	}
 }
+
+void zpci_event_availability(void *data)
+{
+	if (zpci_is_enabled())
+		__zpci_event_availability(data);
+}
-- 
cgit v0.10.2


From 704268925d32a0457202371a61580af76b94c53a Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@linux.vnet.ibm.com>
Date: Thu, 12 Dec 2013 17:50:53 +0100
Subject: s390/pci: fix removal of nonexistent pci bus

If we remove a pci bus after receiving a hotplug notification we need
to check if the bus is actually present (creation of the pci bus
during an earlier notification may have been failed).

Reviewed-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 228787a..65ea105 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -112,6 +112,8 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 		clp_rescan_pci_devices();
 		break;
 	case 0x0308: /* Standby -> Reserved */
+		if (!zdev)
+			break;
 		pci_stop_root_bus(zdev->bus);
 		pci_remove_root_bus(zdev->bus);
 		break;
-- 
cgit v0.10.2


From 0c0c2776926018e7560b99e921467aea1115d03b Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@linux.vnet.ibm.com>
Date: Thu, 12 Dec 2013 17:53:11 +0100
Subject: s390/pci: set error state for unavailable functions

If we receive a notification that a pci function became unavailable we clean
up by removing the pci device. This can confuse the driver since the function
is already unaccessible. Improve this situation by setting an appropriate
error_state.

Reviewed-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 65ea105..7fc4c2c 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -102,8 +102,12 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
 
 		break;
 	case 0x0304: /* Configured -> Standby */
-		if (pdev)
+		if (pdev) {
+			/* Give the driver a hint that the function is
+			 * already unusable. */
+			pdev->error_state = pci_channel_io_perm_failure;
 			pci_stop_and_remove_bus_device(pdev);
+		}
 
 		zpci_disable_device(zdev);
 		zdev->state = ZPCI_FN_STATE_STANDBY;
-- 
cgit v0.10.2


From f7038b7c3f4924b18390c51c1ec1e49287cc87db Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@linux.vnet.ibm.com>
Date: Thu, 12 Dec 2013 17:53:59 +0100
Subject: s390/pci/dma: fix accounting of allocated_pages

allocated_pages sometimes are increased even if s390_dma_alloc fails
also this value is never decreased even if s390_dma_free is called.
This patch fixes these bugs.
Also remove the atomic64_t casts (the members are already of this type).

Reviewed-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 9b83d08..60c11a6 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -285,7 +285,7 @@ static dma_addr_t s390_dma_map_pages(struct device *dev, struct page *page,
 		flags |= ZPCI_TABLE_PROTECTED;
 
 	if (!dma_update_trans(zdev, pa, dma_addr, size, flags)) {
-		atomic64_add(nr_pages, (atomic64_t *) &zdev->fmb->mapped_pages);
+		atomic64_add(nr_pages, &zdev->fmb->mapped_pages);
 		return dma_addr + (offset & ~PAGE_MASK);
 	}
 
@@ -313,7 +313,7 @@ static void s390_dma_unmap_pages(struct device *dev, dma_addr_t dma_addr,
 		zpci_err_hex(&dma_addr, sizeof(dma_addr));
 	}
 
-	atomic64_add(npages, (atomic64_t *) &zdev->fmb->unmapped_pages);
+	atomic64_add(npages, &zdev->fmb->unmapped_pages);
 	iommu_page_index = (dma_addr - zdev->start_dma) >> PAGE_SHIFT;
 	dma_free_iommu(zdev, iommu_page_index, npages);
 }
@@ -332,7 +332,6 @@ static void *s390_dma_alloc(struct device *dev, size_t size,
 	if (!page)
 		return NULL;
 
-	atomic64_add(size / PAGE_SIZE, (atomic64_t *) &zdev->fmb->allocated_pages);
 	pa = page_to_phys(page);
 	memset((void *) pa, 0, size);
 
@@ -343,6 +342,7 @@ static void *s390_dma_alloc(struct device *dev, size_t size,
 		return NULL;
 	}
 
+	atomic64_add(size / PAGE_SIZE, &zdev->fmb->allocated_pages);
 	if (dma_handle)
 		*dma_handle = map;
 	return (void *) pa;
@@ -352,8 +352,11 @@ static void s390_dma_free(struct device *dev, size_t size,
 			  void *pa, dma_addr_t dma_handle,
 			  struct dma_attrs *attrs)
 {
-	s390_dma_unmap_pages(dev, dma_handle, PAGE_ALIGN(size),
-			     DMA_BIDIRECTIONAL, NULL);
+	struct zpci_dev *zdev = get_zdev(to_pci_dev(dev));
+
+	size = PAGE_ALIGN(size);
+	atomic64_sub(size / PAGE_SIZE, &zdev->fmb->allocated_pages);
+	s390_dma_unmap_pages(dev, dma_handle, size, DMA_BIDIRECTIONAL, NULL);
 	free_pages((unsigned long) pa, get_order(size));
 }
 
-- 
cgit v0.10.2


From 257608fb4112b4cabefd9e33a4fc2df6b64dca6a Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@linux.vnet.ibm.com>
Date: Thu, 12 Dec 2013 17:55:22 +0100
Subject: s390/pci: reenable per default

HW, FW and Linux support is in a better shape now - let's reenable
pci bus probing per default.

Acked-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index e3265b5..0820362 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -919,13 +919,13 @@ static void zpci_mem_exit(void)
 	kmem_cache_destroy(zdev_fmb_cache);
 }
 
-static unsigned int s390_pci_probe;
+static unsigned int s390_pci_probe = 1;
 static unsigned int s390_pci_initialized;
 
 char * __init pcibios_setup(char *str)
 {
-	if (!strcmp(str, "on")) {
-		s390_pci_probe = 1;
+	if (!strcmp(str, "off")) {
+		s390_pci_probe = 0;
 		return NULL;
 	}
 	return str;
-- 
cgit v0.10.2


From 69f239ed335a4b03265cae3ca930f3f166e42e35 Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Thu, 12 Dec 2013 17:03:48 +0100
Subject: s390/cpum_sf: Dynamically extend the sampling buffer if overflows
 occur

Improve the sampling buffer allocation and add a function to reallocate and
increase the sampling buffer structure.  The number of allocated buffer elements
(sample-data-blocks) are accounted.  You can control the minimum and maximum
number these sample-data-blocks through the cpum_sfb_size kernel parameter.

The number hardware sample overflows (if any) are also accounted and stored
per perf event.  During the PMU disable/enable calls, the accumulated overflow
counter is analyzed and, if necessary, the sampling buffer is dynamically
increased.

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index 23d2dfa..99d7f4e 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -49,6 +49,10 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define PERF_CPUM_SF_MAX_CTR		1
 #define PERF_EVENT_CPUM_SF		0xB0000UL	/* Raw event ID */
 
+#define REG_NONE		0
+#define REG_OVERFLOW		1
+#define OVERFLOW_REG(hwc)	((hwc)->extra_reg.config)
+#define SFB_ALLOC_REG(hwc)	((hwc)->extra_reg.alloc)
 #define TEAR_REG(hwc)		((hwc)->last_tag)
 #define SAMPL_RATE(hwc)		((hwc)->event_base)
 
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index ae5e019..ea16560 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -17,6 +17,8 @@
 #include <linux/percpu.h>
 #include <linux/notifier.h>
 #include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/moduleparam.h>
 #include <asm/cpu_mf.h>
 #include <asm/irq.h>
 #include <asm/debug.h>
@@ -26,34 +28,54 @@
  * At least one table is required for the sampling buffer structure.
  * A single table contains up to 511 pointers to sample-data-blocks.
  */
-#define CPUM_SF_MIN_SDBT    1
+#define CPUM_SF_MIN_SDBT	1
 
-/* Minimum number of sample-data-blocks:
- * The minimum designates a single page for sample-data-block, i.e.,
- * up to 126 sample-data-blocks with a size of 32 bytes (bsdes).
+/* Number of sample-data-blocks per sample-data-block-table (SDBT):
+ * The table contains SDB origin (8 bytes) and one SDBT origin that
+ * points to the next table.
  */
-#define CPUM_SF_MIN_SDB	    126
+#define CPUM_SF_SDB_PER_TABLE	((PAGE_SIZE - 8) / 8)
 
-/* Maximum number of sample-data-blocks:
- * The maximum number designates approx. 256K per CPU including
- * the given number of sample-data-blocks and taking the number
- * of sample-data-block tables into account.
+/* Maximum page offset for an SDBT table-link entry:
+ * If this page offset is reached, a table-link entry to the next SDBT
+ * must be added.
+ */
+#define CPUM_SF_SDBT_TL_OFFSET	(CPUM_SF_SDB_PER_TABLE * 8)
+static inline int require_table_link(const void *sdbt)
+{
+	return ((unsigned long) sdbt & ~PAGE_MASK) == CPUM_SF_SDBT_TL_OFFSET;
+}
+
+/* Minimum and maximum sampling buffer sizes:
+ *
+ * This number represents the maximum size of the sampling buffer
+ * taking the number of sample-data-block-tables into account.
  *
- * Later, this number can be increased for extending the sampling
- * buffer, for example, by factor 2 (512K) or 4 (1M).
+ * Sampling buffer size		Buffer characteristics
+ * ---------------------------------------------------
+ *	 64KB		    ==	  16 pages (4KB per page)
+ *				   1 page  for SDB-tables
+ *				  15 pages for SDBs
+ *
+ *  32MB		    ==	8192 pages (4KB per page)
+ *				  16 pages for SDB-tables
+ *				8176 pages for SDBs
  */
-#define CPUM_SF_MAX_SDB	    6471
+static unsigned long __read_mostly CPUM_SF_MIN_SDB = 15;
+static unsigned long __read_mostly CPUM_SF_MAX_SDB = 8176;
 
 struct sf_buffer {
-	unsigned long	 sdbt;	    /* Sample-data-block-table origin */
+	unsigned long	 *sdbt;	    /* Sample-data-block-table origin */
 	/* buffer characteristics (required for buffer increments) */
-	unsigned long num_sdb;	    /* Number of sample-data-blocks */
-	unsigned long	 tail;	    /* last sample-data-block-table */
+	unsigned long  num_sdb;	    /* Number of sample-data-blocks */
+	unsigned long num_sdbt;	    /* Number of sample-data-block-tables */
+	unsigned long	 *tail;	    /* last sample-data-block-table */
 };
 
 struct cpu_hw_sf {
 	/* CPU-measurement sampling information block */
 	struct hws_qsi_info_block qsi;
+	/* CPU-measurement sampling control block */
 	struct hws_lsctl_request_block lsctl;
 	struct sf_buffer sfb;	    /* Sampling buffer */
 	unsigned int flags;	    /* Status flags */
@@ -65,11 +87,22 @@ static DEFINE_PER_CPU(struct cpu_hw_sf, cpu_hw_sf);
 static debug_info_t *sfdbg;
 
 /*
+ * sf_disable() - Switch off sampling facility
+ */
+static int sf_disable(void)
+{
+	struct hws_lsctl_request_block sreq;
+
+	memset(&sreq, 0, sizeof(sreq));
+	return lsctl(&sreq);
+}
+
+/*
  * sf_buffer_available() - Check for an allocated sampling buffer
  */
 static int sf_buffer_available(struct cpu_hw_sf *cpuhw)
 {
-	return (cpuhw->sfb.sdbt) ? 1 : 0;
+	return !!cpuhw->sfb.sdbt;
 }
 
 /*
@@ -77,32 +110,32 @@ static int sf_buffer_available(struct cpu_hw_sf *cpuhw)
  */
 static void free_sampling_buffer(struct sf_buffer *sfb)
 {
-	unsigned long sdbt, *curr;
+	unsigned long *sdbt, *curr;
 
 	if (!sfb->sdbt)
 		return;
 
 	sdbt = sfb->sdbt;
-	curr = (unsigned long *) sdbt;
+	curr = sdbt;
 
-	/* we'll free the SDBT after all SDBs are processed... */
+	/* Free the SDBT after all SDBs are processed... */
 	while (1) {
 		if (!*curr || !sdbt)
 			break;
 
-		/* watch for link entry reset if found */
+		/* Process table-link entries */
 		if (is_link_entry(curr)) {
 			curr = get_next_sdbt(curr);
 			if (sdbt)
-				free_page(sdbt);
+				free_page((unsigned long) sdbt);
 
-			/* we are done if we reach the origin */
-			if ((unsigned long) curr == sfb->sdbt)
+			/* If the origin is reached, sampling buffer is freed */
+			if (curr == sfb->sdbt)
 				break;
 			else
-				sdbt = (unsigned long) curr;
+				sdbt = curr;
 		} else {
-			/* process SDB pointer */
+			/* Process SDB pointer */
 			if (*curr) {
 				free_page(*curr);
 				curr++;
@@ -111,10 +144,106 @@ static void free_sampling_buffer(struct sf_buffer *sfb)
 	}
 
 	debug_sprintf_event(sfdbg, 5,
-			    "free_sampling_buffer: freed sdbt=%0lx\n", sfb->sdbt);
+			    "free_sampling_buffer: freed sdbt=%p\n", sfb->sdbt);
 	memset(sfb, 0, sizeof(*sfb));
 }
 
+static int alloc_sample_data_block(unsigned long *sdbt, gfp_t gfp_flags)
+{
+	unsigned long sdb, *trailer;
+
+	/* Allocate and initialize sample-data-block */
+	sdb = get_zeroed_page(gfp_flags);
+	if (!sdb)
+		return -ENOMEM;
+	trailer = trailer_entry_ptr(sdb);
+	*trailer = SDB_TE_ALERT_REQ_MASK;
+
+	/* Link SDB into the sample-data-block-table */
+	*sdbt = sdb;
+
+	return 0;
+}
+
+/*
+ * realloc_sampling_buffer() - extend sampler memory
+ *
+ * Allocates new sample-data-blocks and adds them to the specified sampling
+ * buffer memory.
+ *
+ * Important: This modifies the sampling buffer and must be called when the
+ *	      sampling facility is disabled.
+ *
+ * Returns zero on success, non-zero otherwise.
+ */
+static int realloc_sampling_buffer(struct sf_buffer *sfb,
+				   unsigned long num_sdb, gfp_t gfp_flags)
+{
+	int i, rc;
+	unsigned long *new, *tail;
+
+	if (!sfb->sdbt || !sfb->tail)
+		return -EINVAL;
+
+	if (!is_link_entry(sfb->tail))
+		return -EINVAL;
+
+	/* Append to the existing sampling buffer, overwriting the table-link
+	 * register.
+	 * The tail variables always points to the "tail" (last and table-link)
+	 * entry in an SDB-table.
+	 */
+	tail = sfb->tail;
+
+	/* Do a sanity check whether the table-link entry points to
+	 * the sampling buffer origin.
+	 */
+	if (sfb->sdbt != get_next_sdbt(tail)) {
+		debug_sprintf_event(sfdbg, 3, "realloc_sampling_buffer: "
+				    "sampling buffer is not linked: origin=%p"
+				    "tail=%p\n",
+				    (void *) sfb->sdbt, (void *) tail);
+		return -EINVAL;
+	}
+
+	/* Allocate remaining SDBs */
+	rc = 0;
+	for (i = 0; i < num_sdb; i++) {
+		/* Allocate a new SDB-table if it is full. */
+		if (require_table_link(tail)) {
+			new = (unsigned long *) get_zeroed_page(gfp_flags);
+			if (!new) {
+				rc = -ENOMEM;
+				break;
+			}
+			sfb->num_sdbt++;
+			/* Link current page to tail of chain */
+			*tail = (unsigned long)(void *) new + 1;
+			tail = new;
+		}
+
+		/* Allocate a new sample-data-block.
+		 * If there is not enough memory, stop the realloc process
+		 * and simply use what was allocated.  If this is a temporary
+		 * issue, a new realloc call (if required) might succeed.
+		 */
+		rc = alloc_sample_data_block(tail, gfp_flags);
+		if (rc)
+			break;
+		sfb->num_sdb++;
+		tail++;
+	}
+
+	/* Link sampling buffer to its origin */
+	*tail = (unsigned long) sfb->sdbt + 1;
+	sfb->tail = tail;
+
+	debug_sprintf_event(sfdbg, 4, "realloc_sampling_buffer: new buffer"
+			    " settings: sdbt=%lu sdb=%lu\n",
+			    sfb->num_sdbt, sfb->num_sdb);
+	return rc;
+}
+
 /*
  * allocate_sampling_buffer() - allocate sampler memory
  *
@@ -128,75 +257,74 @@ static void free_sampling_buffer(struct sf_buffer *sfb)
  */
 static int alloc_sampling_buffer(struct sf_buffer *sfb, unsigned long num_sdb)
 {
-	int j, k, rc;
-	unsigned long *sdbt, *tail, *trailer;
-	unsigned long sdb;
-	unsigned long num_sdbt, sdb_per_table;
+	int rc;
 
 	if (sfb->sdbt)
 		return -EINVAL;
+
+	/* Allocate the sample-data-block-table origin */
+	sfb->sdbt = (unsigned long *) get_zeroed_page(GFP_KERNEL);
+	if (!sfb->sdbt)
+		return -ENOMEM;
 	sfb->num_sdb = 0;
+	sfb->num_sdbt = 1;
 
-	/* Compute the number of required sample-data-block-tables (SDBT) */
-	num_sdbt = num_sdb / ((PAGE_SIZE - 8) / 8);
-	if (num_sdbt < CPUM_SF_MIN_SDBT)
-		num_sdbt = CPUM_SF_MIN_SDBT;
-	sdb_per_table = (PAGE_SIZE - 8) / 8;
-
-	debug_sprintf_event(sfdbg, 4, "alloc_sampling_buffer: num_sdbt=%lu "
-			    "num_sdb=%lu sdb_per_table=%lu\n",
-			    num_sdbt, num_sdb, sdb_per_table);
-	sdbt = NULL;
-	tail = sdbt;
-
-	for (j = 0; j < num_sdbt; j++) {
-		sdbt = (unsigned long *) get_zeroed_page(GFP_KERNEL);
-		if (!sdbt) {
-			rc = -ENOMEM;
-			goto allocate_sdbt_error;
-		}
+	/* Link the table origin to point to itself to prepare for
+	 * realloc_sampling_buffer() invocation.
+	 */
+	sfb->tail = sfb->sdbt;
+	*sfb->tail = (unsigned long)(void *) sfb->sdbt + 1;
 
-		/* save origin of sample-data-block-table */
-		if (!sfb->sdbt)
-			sfb->sdbt = (unsigned long) sdbt;
+	/* Allocate requested number of sample-data-blocks */
+	rc = realloc_sampling_buffer(sfb, num_sdb, GFP_KERNEL);
+	if (rc) {
+		free_sampling_buffer(sfb);
+		debug_sprintf_event(sfdbg, 4, "alloc_sampling_buffer: "
+			"realloc_sampling_buffer failed with rc=%i\n", rc);
+	} else
+		debug_sprintf_event(sfdbg, 4,
+			"alloc_sampling_buffer: tear=%p dear=%p\n",
+			sfb->sdbt, (void *) *sfb->sdbt);
+	return rc;
+}
 
-		/* link current page to tail of chain */
-		if (tail)
-			*tail = (unsigned long)(void *) sdbt + 1;
+static void sfb_set_limits(unsigned long min, unsigned long max)
+{
+	CPUM_SF_MIN_SDB = min;
+	CPUM_SF_MAX_SDB = max;
+}
 
-		for (k = 0; k < num_sdb && k < sdb_per_table; k++) {
-			/* get and set SDB page */
-			sdb = get_zeroed_page(GFP_KERNEL);
-			if (!sdb) {
-				rc = -ENOMEM;
-				goto allocate_sdbt_error;
-			}
-			*sdbt = sdb;
-			trailer = trailer_entry_ptr(*sdbt);
-			*trailer = SDB_TE_ALERT_REQ_MASK;
-			sdbt++;
-		}
-		num_sdb -= k;
-		sfb->num_sdb += k;	/* count allocated sdb's */
-		tail = sdbt;
-	}
+static unsigned long sfb_pending_allocs(struct sf_buffer *sfb,
+					struct hw_perf_event *hwc)
+{
+	if (!sfb->sdbt)
+		return SFB_ALLOC_REG(hwc);
+	if (SFB_ALLOC_REG(hwc) > sfb->num_sdb)
+		return SFB_ALLOC_REG(hwc) - sfb->num_sdb;
+	return 0;
+}
 
-	rc = 0;
-	if (tail)
-		*tail = sfb->sdbt + 1;
-	sfb->tail = (unsigned long) (void *)tail;
+static int sfb_has_pending_allocs(struct sf_buffer *sfb,
+				   struct hw_perf_event *hwc)
+{
+	return sfb_pending_allocs(sfb, hwc) > 0;
+}
 
-allocate_sdbt_error:
-	if (rc)
-		free_sampling_buffer(sfb);
-	else
-		debug_sprintf_event(sfdbg, 4,
-			"alloc_sampling_buffer: tear=%0lx dear=%0lx\n",
-			sfb->sdbt, *(unsigned long *) sfb->sdbt);
-	return rc;
+static void sfb_account_allocs(unsigned long num, struct hw_perf_event *hwc)
+{
+	/* Limit the number SDBs to not exceed the maximum */
+	num = min_t(unsigned long, num, CPUM_SF_MAX_SDB - SFB_ALLOC_REG(hwc));
+	if (num)
+		SFB_ALLOC_REG(hwc) += num;
 }
 
-static int allocate_sdbt(struct cpu_hw_sf *cpuhw, const struct hw_perf_event *hwc)
+static void sfb_init_allocs(unsigned long num, struct hw_perf_event *hwc)
+{
+	SFB_ALLOC_REG(hwc) = 0;
+	sfb_account_allocs(num, hwc);
+}
+
+static int allocate_sdbt(struct cpu_hw_sf *cpuhw, struct hw_perf_event *hwc)
 {
 	unsigned long n_sdb, freq;
 	unsigned long factor;
@@ -225,39 +353,133 @@ static int allocate_sdbt(struct cpu_hw_sf *cpuhw, const struct hw_perf_event *hw
 	if (n_sdb < CPUM_SF_MIN_SDB)
 		n_sdb = CPUM_SF_MIN_SDB;
 
-	/* Return if there is already a sampling buffer allocated.
-	 * XXX Remove this later and check number of available and
-	 * required sdb's and, if necessary, increase the sampling buffer.
+	/* If there is already a sampling buffer allocated, it is very likely
+	 * that the sampling facility is enabled too.  If the event to be
+	 * initialized requires a greater sampling buffer, the allocation must
+	 * be postponed.  Changing the sampling buffer requires the sampling
+	 * facility to be in the disabled state.  So, account the number of
+	 * required SDBs and let cpumsf_pmu_enable() resize the buffer just
+	 * before the event is started.
 	 */
+	sfb_init_allocs(n_sdb, hwc);
 	if (sf_buffer_available(cpuhw))
 		return 0;
 
 	debug_sprintf_event(sfdbg, 3,
-			    "allocate_sdbt: rate=%lu f=%lu sdb=%lu/%i cpuhw=%p\n",
+			    "allocate_sdbt: rate=%lu f=%lu sdb=%lu/%lu cpuhw=%p\n",
 			    SAMPL_RATE(hwc), freq, n_sdb, CPUM_SF_MAX_SDB, cpuhw);
 
 	return alloc_sampling_buffer(&cpuhw->sfb,
-			       min_t(unsigned long, n_sdb, CPUM_SF_MAX_SDB));
+				     sfb_pending_allocs(&cpuhw->sfb, hwc));
 }
 
+static unsigned long min_percent(unsigned int percent, unsigned long base,
+				 unsigned long min)
+{
+	return min_t(unsigned long, min, DIV_ROUND_UP(percent * base, 100));
+}
 
-/* Number of perf events counting hardware events */
-static atomic_t num_events;
-/* Used to avoid races in calling reserve/release_cpumf_hardware */
-static DEFINE_MUTEX(pmc_reserve_mutex);
+static unsigned long compute_sfb_extent(unsigned long ratio, unsigned long base)
+{
+	/* Use a percentage-based approach to extend the sampling facility
+	 * buffer.  Accept up to 5% sample data loss.
+	 * Vary the extents between 1% to 5% of the current number of
+	 * sample-data-blocks.
+	 */
+	if (ratio <= 5)
+		return 0;
+	if (ratio <= 25)
+		return min_percent(1, base, 1);
+	if (ratio <= 50)
+		return min_percent(1, base, 1);
+	if (ratio <= 75)
+		return min_percent(2, base, 2);
+	if (ratio <= 100)
+		return min_percent(3, base, 3);
+	if (ratio <= 250)
+		return min_percent(4, base, 4);
+
+	return min_percent(5, base, 8);
+}
 
-/*
- * sf_disable() - Switch off sampling facility
+static void sfb_account_overflows(struct cpu_hw_sf *cpuhw,
+				  struct hw_perf_event *hwc)
+{
+	unsigned long ratio, num;
+
+	if (!OVERFLOW_REG(hwc))
+		return;
+
+	/* The sample_overflow contains the average number of sample data
+	 * that has been lost because sample-data-blocks were full.
+	 *
+	 * Calculate the total number of sample data entries that has been
+	 * discarded.  Then calculate the ratio of lost samples to total samples
+	 * per second in percent.
+	 */
+	ratio = DIV_ROUND_UP(100 * OVERFLOW_REG(hwc) * cpuhw->sfb.num_sdb,
+			     sample_rate_to_freq(&cpuhw->qsi, SAMPL_RATE(hwc)));
+
+	/* Compute number of sample-data-blocks */
+	num = compute_sfb_extent(ratio, cpuhw->sfb.num_sdb);
+	if (num)
+		sfb_account_allocs(num, hwc);
+
+	debug_sprintf_event(sfdbg, 5, "sfb: overflow: overflow=%llu ratio=%lu"
+			    " num=%lu\n", OVERFLOW_REG(hwc), ratio, num);
+	OVERFLOW_REG(hwc) = 0;
+}
+
+/* extend_sampling_buffer() - Extend sampling buffer
+ * @sfb:	Sampling buffer structure (for local CPU)
+ * @hwc:	Perf event hardware structure
+ *
+ * Use this function to extend the sampling buffer based on the overflow counter
+ * and postponed allocation extents stored in the specified Perf event hardware.
+ *
+ * Important: This function disables the sampling facility in order to safely
+ *	      change the sampling buffer structure.  Do not call this function
+ *	      when the PMU is active.
  */
-static int sf_disable(void)
+static void extend_sampling_buffer(struct sf_buffer *sfb,
+				   struct hw_perf_event *hwc)
 {
-	struct hws_lsctl_request_block sreq;
+	unsigned long num, num_old;
+	int rc;
 
-	memset(&sreq, 0, sizeof(sreq));
-	return lsctl(&sreq);
+	num = sfb_pending_allocs(sfb, hwc);
+	if (!num)
+		return;
+	num_old = sfb->num_sdb;
+
+	/* Disable the sampling facility to reset any states and also
+	 * clear pending measurement alerts.
+	 */
+	sf_disable();
+
+	/* Extend the sampling buffer.
+	 * This memory allocation typically happens in an atomic context when
+	 * called by perf.  Because this is a reallocation, it is fine if the
+	 * new SDB-request cannot be satisfied immediately.
+	 */
+	rc = realloc_sampling_buffer(sfb, num, GFP_ATOMIC);
+	if (rc)
+		debug_sprintf_event(sfdbg, 5, "sfb: extend: realloc "
+				    "failed with rc=%i\n", rc);
+
+	if (sfb_has_pending_allocs(sfb, hwc))
+		debug_sprintf_event(sfdbg, 5, "sfb: extend: "
+				    "req=%lu alloc=%lu remaining=%lu\n",
+				    num, sfb->num_sdb - num_old,
+				    sfb_pending_allocs(sfb, hwc));
 }
 
 
+/* Number of perf events counting hardware events */
+static atomic_t num_events;
+/* Used to avoid races in calling reserve/release_cpumf_hardware */
+static DEFINE_MUTEX(pmc_reserve_mutex);
+
 #define PMC_INIT      0
 #define PMC_RELEASE   1
 #define PMC_FAILURE   2
@@ -345,19 +567,17 @@ static void hw_init_period(struct hw_perf_event *hwc, u64 period)
 }
 
 static void hw_reset_registers(struct hw_perf_event *hwc,
-			       unsigned long sdbt_origin)
+			       unsigned long *sdbt_origin)
 {
-	TEAR_REG(hwc) = sdbt_origin;	      /* (re)set to first sdb table */
+	/* (Re)set to first sample-data-block-table */
+	TEAR_REG(hwc) = (unsigned long) sdbt_origin;
 }
 
 static unsigned long hw_limit_rate(const struct hws_qsi_info_block *si,
 				   unsigned long rate)
 {
-	if (rate < si->min_sampl_rate)
-		return si->min_sampl_rate;
-	if (rate > si->max_sampl_rate)
-		return si->max_sampl_rate;
-	return rate;
+	return clamp_t(unsigned long, rate,
+		       si->min_sampl_rate, si->max_sampl_rate);
 }
 
 static int __hw_perf_event_init(struct perf_event *event)
@@ -448,6 +668,10 @@ static int __hw_perf_event_init(struct perf_event *event)
 	SAMPL_RATE(hwc) = rate;
 	hw_init_period(hwc, SAMPL_RATE(hwc));
 
+	/* Initialize sample data overflow accounting */
+	hwc->extra_reg.reg = REG_OVERFLOW;
+	OVERFLOW_REG(hwc) = 0;
+
 	/* Allocate the per-CPU sampling buffer using the CPU information
 	 * from the event.  If the event is not pinned to a particular
 	 * CPU (event->cpu == -1; or cpuhw == NULL), allocate sampling
@@ -513,6 +737,7 @@ static int cpumsf_pmu_event_init(struct perf_event *event)
 static void cpumsf_pmu_enable(struct pmu *pmu)
 {
 	struct cpu_hw_sf *cpuhw = &__get_cpu_var(cpu_hw_sf);
+	struct hw_perf_event *hwc;
 	int err;
 
 	if (cpuhw->flags & PMU_F_ENABLED)
@@ -521,6 +746,26 @@ static void cpumsf_pmu_enable(struct pmu *pmu)
 	if (cpuhw->flags & PMU_F_ERR_MASK)
 		return;
 
+	/* Check whether to extent the sampling buffer.
+	 *
+	 * Two conditions trigger an increase of the sampling buffer for a
+	 * perf event:
+	 *    1. Postponed buffer allocations from the event initialization.
+	 *    2. Sampling overflows that contribute to pending allocations.
+	 *
+	 * Note that the extend_sampling_buffer() function disables the sampling
+	 * facility, but it can be fully re-enabled using sampling controls that
+	 * have been saved in cpumsf_pmu_disable().
+	 */
+	if (cpuhw->event) {
+		hwc = &cpuhw->event->hw;
+		/* Account number of overflow-designated buffer extents */
+		sfb_account_overflows(cpuhw, hwc);
+		if (sfb_has_pending_allocs(&cpuhw->sfb, hwc))
+			extend_sampling_buffer(&cpuhw->sfb, hwc);
+	}
+
+	/* (Re)enable the PMU and sampling facility */
 	cpuhw->flags |= PMU_F_ENABLED;
 	barrier();
 
@@ -632,8 +877,6 @@ static int perf_push_sample(struct perf_event *event,
 	if (perf_event_overflow(event, &data, &regs)) {
 		overflow = 1;
 		event->pmu->stop(event, 0);
-		debug_sprintf_event(sfdbg, 4, "perf_push_sample: PMU stopped"
-				    " because of an event overflow\n");
 	}
 	perf_event_update_userpage(event);
 
@@ -710,11 +953,11 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 	struct hw_perf_event *hwc = &event->hw;
 	struct hws_trailer_entry *te;
 	unsigned long *sdbt;
-	unsigned long long event_overflow, sampl_overflow;
+	unsigned long long event_overflow, sampl_overflow, num_sdb;
 	int done;
 
 	sdbt = (unsigned long *) TEAR_REG(hwc);
-	done = event_overflow = sampl_overflow = 0;
+	done = event_overflow = sampl_overflow = num_sdb = 0;
 	while (!done) {
 		/* Get the trailer entry of the sample-data-block */
 		te = (struct hws_trailer_entry *) trailer_entry_ptr(*sdbt);
@@ -726,17 +969,13 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 				break;
 		}
 
-		/* Check sample overflow count */
-		if (te->overflow) {
-			/* Increment sample overflow counter */
-			sampl_overflow += te->overflow;
-
-			/* XXX: If an sample overflow occurs, increase the
-			 *	sampling buffer.  Set a "realloc" flag because
-			 *	the sampler must be re-enabled for changing
-			 *	the sample-data-block-table content.
+		/* Check the sample overflow count */
+		if (te->overflow)
+			/* Account sample overflows and, if a particular limit
+			 * is reached, extend the sampling buffer.
+			 * For details, see sfb_account_overflows().
 			 */
-		}
+			sampl_overflow += te->overflow;
 
 		/* Timestamps are valid for full sample-data-blocks only */
 		debug_sprintf_event(sfdbg, 6, "hw_perf_event_update: sdbt=%p "
@@ -749,6 +988,7 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 		 * is stopped and remaining samples will be discarded.
 		 */
 		hw_collect_samples(event, sdbt, &event_overflow);
+		num_sdb++;
 
 		/* Reset trailer */
 		xchg(&te->overflow, 0);
@@ -775,6 +1015,10 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 			flush_all = 1;
 	}
 
+	/* Account sample overflows in the event hardware structure */
+	if (sampl_overflow)
+		OVERFLOW_REG(hwc) = DIV_ROUND_UP(OVERFLOW_REG(hwc) +
+						 sampl_overflow, 1 + num_sdb);
 	if (sampl_overflow || event_overflow)
 		debug_sprintf_event(sfdbg, 4, "hw_perf_event_update: "
 				    "overflow stats: sample=%llu event=%llu\n",
@@ -849,7 +1093,7 @@ static int cpumsf_pmu_add(struct perf_event *event, int flags)
 	 */
 	cpuhw->lsctl.s = 0;
 	cpuhw->lsctl.h = 1;
-	cpuhw->lsctl.tear = cpuhw->sfb.sdbt;
+	cpuhw->lsctl.tear = (unsigned long) cpuhw->sfb.sdbt;
 	cpuhw->lsctl.dear = *(unsigned long *) cpuhw->sfb.sdbt;
 	cpuhw->lsctl.interval = SAMPL_RATE(&event->hw);
 	hw_reset_registers(&event->hw, cpuhw->sfb.sdbt);
@@ -1018,6 +1262,48 @@ static int __cpuinit cpumf_pmu_notifier(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
+static int param_get_sfb_size(char *buffer, const struct kernel_param *kp)
+{
+	if (!cpum_sf_avail())
+		return -ENODEV;
+	return sprintf(buffer, "%lu,%lu", CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB);
+}
+
+static int param_set_sfb_size(const char *val, const struct kernel_param *kp)
+{
+	int rc;
+	unsigned long min, max;
+
+	if (!cpum_sf_avail())
+		return -ENODEV;
+	if (!val || !strlen(val))
+		return -EINVAL;
+
+	/* Valid parameter values: "min,max" or "max" */
+	min = CPUM_SF_MIN_SDB;
+	max = CPUM_SF_MAX_SDB;
+	if (strchr(val, ','))
+		rc = (sscanf(val, "%lu,%lu", &min, &max) == 2) ? 0 : -EINVAL;
+	else
+		rc = kstrtoul(val, 10, &max);
+
+	if (min < 2 || min >= max || max > get_num_physpages())
+		rc = -EINVAL;
+	if (rc)
+		return rc;
+
+	sfb_set_limits(min, max);
+	pr_info("Changed sampling buffer settings: min=%lu max=%lu\n",
+		CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB);
+	return 0;
+}
+
+#define param_check_sfb_size(name, p) __param_check(name, p, void)
+static struct kernel_param_ops param_ops_sfb_size = {
+	.set = param_set_sfb_size,
+	.get = param_get_sfb_size,
+};
+
 static int __init init_cpum_sampling_pmu(void)
 {
 	int err;
@@ -1047,3 +1333,4 @@ out:
 	return err;
 }
 arch_initcall(init_cpum_sampling_pmu);
+core_param(cpum_sfb_size, CPUM_SF_MAX_SDB, sfb_size, 0640);
-- 
cgit v0.10.2


From fcc77f507333776eaa336ab4ff49c23422f53703 Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Thu, 12 Dec 2013 17:26:51 +0100
Subject: s390/cpum_sf: Atomically reset trailer entry fields of
 sample-data-blocks

Ensure to reset the sample-data-block full indicator and the overflow counter
at the same time.  This must be done atomically because the sampling hardware
is still active while full sample-data-block is processed.

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index d707abc..b0b3059 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -115,10 +115,15 @@ struct hws_data_entry {
 } __packed;
 
 struct hws_trailer_entry {
-	unsigned int f:1;	    /* 0 - Block Full Indicator 	 */
-	unsigned int a:1;	    /* 1 - Alert request control	 */
-	unsigned int t:1;	    /* 2 - Timestamp format		 */
-	unsigned long long:61;	    /* 3 - 63: Reserved 		 */
+	union {
+		struct {
+			unsigned int f:1;	/* 0 - Block Full Indicator   */
+			unsigned int a:1;	/* 1 - Alert request control  */
+			unsigned int t:1;	/* 2 - Timestamp format	      */
+			unsigned long long:61;	/* 3 - 63: Reserved	      */
+		};
+		unsigned long long flags;	/* 0 - 63: All indicators     */
+	};
 	unsigned long long overflow;	 /* 64 - sample Overflow count	      */
 	unsigned long long timestamp;	 /* 16 - time-stamp		      */
 	unsigned long long timestamp1;	 /*				      */
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index ea16560..9202f28 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -953,7 +953,7 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 	struct hw_perf_event *hwc = &event->hw;
 	struct hws_trailer_entry *te;
 	unsigned long *sdbt;
-	unsigned long long event_overflow, sampl_overflow, num_sdb;
+	unsigned long long event_overflow, sampl_overflow, num_sdb, te_flags;
 	int done;
 
 	sdbt = (unsigned long *) TEAR_REG(hwc);
@@ -990,9 +990,13 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 		hw_collect_samples(event, sdbt, &event_overflow);
 		num_sdb++;
 
-		/* Reset trailer */
-		xchg(&te->overflow, 0);
-		xchg((unsigned char *) te, 0x40);
+		/* Reset trailer (using compare-double-and-swap) */
+		do {
+			te_flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK;
+			te_flags |= SDB_TE_ALERT_REQ_MASK;
+		} while (!cmpxchg_double(&te->flags, &te->overflow,
+					 te->flags, te->overflow,
+					 te_flags, 0ULL));
 
 		/* Advance to next sample-data-block */
 		sdbt++;
-- 
cgit v0.10.2


From 443d4beb823d4dccaaf964b59df9dd38b4d6aae7 Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Thu, 12 Dec 2013 17:38:50 +0100
Subject: s390/cpum_sf: Add helper to read TOD from trailer entries

The trailer entry contains a timestamp of the time when the sample-data-block
became full.  The timestamp specifies a TOD (time-of-day) value in either the
STCK or STCKE format.

Provide a helper function to return the TOD value depending on the setting of
time format indicator.

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index b0b3059..09dc5fa 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -125,8 +125,7 @@ struct hws_trailer_entry {
 		unsigned long long flags;	/* 0 - 63: All indicators     */
 	};
 	unsigned long long overflow;	 /* 64 - sample Overflow count	      */
-	unsigned long long timestamp;	 /* 16 - time-stamp		      */
-	unsigned long long timestamp1;	 /*				      */
+	unsigned char timestamp[16];	 /* 16 - 31 timestamp		      */
 	unsigned long long reserved1;	 /* 32 -Reserved		      */
 	unsigned long long reserved2;	 /*				      */
 	unsigned long long progusage1;	 /* 48 - reserved for programming use */
@@ -232,6 +231,17 @@ static inline unsigned long sample_rate_to_freq(struct hws_qsi_info_block *qsi,
 #define SDB_TE_ALERT_REQ_MASK	0x4000000000000000UL
 #define SDB_TE_BUFFER_FULL_MASK 0x8000000000000000UL
 
+/* Return TOD timestamp contained in an trailer entry */
+static inline unsigned long long trailer_timestamp(struct hws_trailer_entry *te)
+{
+	/* TOD in STCKE format */
+	if (te->t)
+		return *((unsigned long long *) &te->timestamp[1]);
+
+	/* TOD in STCK format */
+	return *((unsigned long long *) &te->timestamp[0]);
+}
+
 /* Return pointer to trailer entry of an sample data block */
 static inline unsigned long *trailer_entry_ptr(unsigned long v)
 {
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 9202f28..3ab7e67 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -981,7 +981,7 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 		debug_sprintf_event(sfdbg, 6, "hw_perf_event_update: sdbt=%p "
 				    "overflow=%llu timestamp=0x%llx\n",
 				    sdbt, te->overflow,
-				    (te->f) ? te->timestamp : 0ULL);
+				    (te->f) ? trailer_timestamp(te) : 0ULL);
 
 		/* Collect all samples from a single sample-data-block and
 		 * flag if an (perf) event overflow happened.  If so, the PMU
-- 
cgit v0.10.2


From 443e802bab16916f9a51a34f2213f4dee6e8762c Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Thu, 12 Dec 2013 17:54:57 +0100
Subject: s390/cpum_sf: Detect KVM guest samples

The host-program-parameter (hpp) value of basic sample-data-entries designates
a SIE control block that is set by the LPP instruction in sie64a().
Non-zero values indicate guest samples, a value of zero indicates a host sample.

For perf samples, host and guest samples are distinguished using particular
PERF_MISC_* flags.  The perf layer calls perf_misc_flags() to set the flags
based on the pt_regs content.  For each sample-data-entry, the cpum_sf PMU
creates a pt_regs structure with the sample-data information.  An additional
flag structure is added to easily distinguish between host and guest samples.

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index 99d7f4e..7667bde 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -42,6 +42,12 @@ extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define perf_misc_flags(regs) perf_misc_flags(regs)
 
+/* Perf pt_regs extension for sample-data-entry indicators */
+struct perf_sf_sde_regs {
+	unsigned char in_guest:1;	  /* guest sample */
+	unsigned long reserved:63;	  /* reserved */
+};
+
 /* Perf PMU definitions for the counter facility */
 #define PERF_CPUM_CF_MAX_CTR		256
 
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 3ab7e67..d611fac 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -840,6 +840,7 @@ static int perf_push_sample(struct perf_event *event,
 {
 	int overflow;
 	struct pt_regs regs;
+	struct perf_sf_sde_regs *sde_regs;
 	struct perf_sample_data data;
 
 	/* Skip samples that are invalid or for which the instruction address
@@ -850,7 +851,16 @@ static int perf_push_sample(struct perf_event *event,
 
 	perf_sample_data_init(&data, 0, event->hw.last_period);
 
+	/* Setup pt_regs to look like an CPU-measurement external interrupt
+	 * using the Program Request Alert code.  The regs.int_parm_long
+	 * field which is unused contains additional sample-data-entry related
+	 * indicators.
+	 */
 	memset(&regs, 0, sizeof(regs));
+	regs.int_code = 0x1407;
+	regs.int_parm = CPU_MF_INT_SF_PRA;
+	sde_regs = (struct perf_sf_sde_regs *) &regs.int_parm_long;
+
 	regs.psw.addr = sample->ia;
 	if (sample->T)
 		regs.psw.mask |= PSW_MASK_DAT;
@@ -873,6 +883,16 @@ static int perf_push_sample(struct perf_event *event,
 		break;
 	}
 
+	/* The host-program-parameter (hpp) contains the sie control
+	 * block that is set by sie64a() in entry64.S.	Check if hpp
+	 * refers to a valid control block and set sde_regs flags
+	 * accordingly.  This would allow to use hpp values for other
+	 * purposes too.
+	 * For now, simply use a non-zero value as guest indicator.
+	 */
+	if (sample->hpp)
+		sde_regs->in_guest = 1;
+
 	overflow = 0;
 	if (perf_event_overflow(event, &data, &regs)) {
 		overflow = 1;
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 3bd2bf0..60a6826 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -1,7 +1,7 @@
 /*
  * Performance event support for s390x
  *
- *  Copyright IBM Corp. 2012
+ *  Copyright IBM Corp. 2012, 2013
  *  Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  *
  * This program is free software; you can redistribute it and/or modify
@@ -89,8 +89,31 @@ static unsigned long perf_misc_guest_flags(struct pt_regs *regs)
 					: PERF_RECORD_MISC_GUEST_KERNEL;
 }
 
+static unsigned long perf_misc_flags_sf(struct pt_regs *regs)
+{
+	struct perf_sf_sde_regs *sde_regs;
+	unsigned long flags;
+
+	sde_regs = (struct perf_sf_sde_regs *) &regs->int_parm_long;
+	if (sde_regs->in_guest)
+		flags = user_mode(regs) ? PERF_RECORD_MISC_GUEST_USER
+					: PERF_RECORD_MISC_GUEST_KERNEL;
+	else
+		flags = user_mode(regs) ? PERF_RECORD_MISC_USER
+					: PERF_RECORD_MISC_KERNEL;
+	return flags;
+}
+
 unsigned long perf_misc_flags(struct pt_regs *regs)
 {
+	/* Check if the cpum_sf PMU has created the pt_regs structure.
+	 * In this case, perf misc flags can be easily extracted.  Otherwise,
+	 * do regular checks on the pt_regs content.
+	 */
+	if (regs->int_code == 0x1407 && regs->int_parm == CPU_MF_INT_SF_PRA)
+		if (!regs->gprs[15])
+			return perf_misc_flags_sf(regs);
+
 	if (is_in_guest(regs))
 		return perf_misc_guest_flags(regs);
 
-- 
cgit v0.10.2


From dd127b3b977b81eab58d1d7ee037195cf0bbeba7 Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Thu, 12 Dec 2013 18:05:20 +0100
Subject: s390/cpum_sf: Filter perf events based event->attr.exclude_* settings

Introduce the perf_exclude_event() function to filter perf samples
according to event->attr.exclude_* settings.   During event initialization,
reset event exclude settings that are not supported.

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index d611fac..28fa2f2 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -723,10 +723,19 @@ static int cpumsf_pmu_event_init(struct perf_event *event)
 		return -ENOENT;
 	}
 
+	/* Check online status of the CPU to which the event is pinned */
 	if (event->cpu >= nr_cpumask_bits ||
 	    (event->cpu >= 0 && !cpu_online(event->cpu)))
 		return -ENODEV;
 
+	/* Force reset of idle/hv excludes regardless of what the
+	 * user requested.
+	 */
+	if (event->attr.exclude_hv)
+		event->attr.exclude_hv = 0;
+	if (event->attr.exclude_idle)
+		event->attr.exclude_idle = 0;
+
 	err = __hw_perf_event_init(event);
 	if (unlikely(err))
 		if (event->destroy)
@@ -824,6 +833,29 @@ static void cpumsf_pmu_disable(struct pmu *pmu)
 	cpuhw->flags &= ~PMU_F_ENABLED;
 }
 
+/* perf_exclude_event() - Filter event
+ * @event:	The perf event
+ * @regs:	pt_regs structure
+ * @sde_regs:	Sample-data-entry (sde) regs structure
+ *
+ * Filter perf events according to their exclude specification.
+ *
+ * Return non-zero if the event shall be excluded.
+ */
+static int perf_exclude_event(struct perf_event *event, struct pt_regs *regs,
+			      struct perf_sf_sde_regs *sde_regs)
+{
+	if (event->attr.exclude_user && user_mode(regs))
+		return 1;
+	if (event->attr.exclude_kernel && !user_mode(regs))
+		return 1;
+	if (event->attr.exclude_guest && sde_regs->in_guest)
+		return 1;
+	if (event->attr.exclude_host && !sde_regs->in_guest)
+		return 1;
+	return 0;
+}
+
 /* perf_push_sample() - Push samples to perf
  * @event:	The perf event
  * @sample:	Hardware sample data
@@ -894,12 +926,14 @@ static int perf_push_sample(struct perf_event *event,
 		sde_regs->in_guest = 1;
 
 	overflow = 0;
+	if (perf_exclude_event(event, &regs, sde_regs))
+		goto out;
 	if (perf_event_overflow(event, &data, &regs)) {
 		overflow = 1;
 		event->pmu->stop(event, 0);
 	}
 	perf_event_update_userpage(event);
-
+out:
 	return overflow;
 }
 
-- 
cgit v0.10.2


From 7e75fc3ff4cffd90684816d69838f8730ac3e072 Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Fri, 13 Dec 2013 11:42:44 +0100
Subject: s390/cpum_sf: Add raw data sampling to support the
 diagnostic-sampling function

Also support the diagnostic-sampling function in addition to the basic-sampling
function.  Diagnostic-sampling data entries contain hardware model specific
sampling data and additional programs are required to analyze the data.

To deliver diagnostic-sampling, as well, as basis-sampling data entries to user
space, introduce support for sampling "raw data".  If this particular perf
sampling type (PERF_SAMPLE_RAW) is used, sampling data entries are copied
to user space.  External programs can then analyze these data.

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index 09dc5fa..cb700d5 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -59,13 +59,15 @@ struct cpumf_ctr_info {
 /* QUERY SAMPLING INFORMATION block */
 struct hws_qsi_info_block {	    /* Bit(s) */
 	unsigned int b0_13:14;	    /* 0-13: zeros			 */
-	unsigned int as:1;	    /* 14: sampling authorisation control*/
-	unsigned int b15_21:7;	    /* 15-21: zeros			 */
-	unsigned int es:1;	    /* 22: sampling enable control	 */
-	unsigned int b23_29:7;	    /* 23-29: zeros			 */
-	unsigned int cs:1;	    /* 30: sampling activation control	 */
-	unsigned int:1; 	    /* 31: reserved			 */
-	unsigned int bsdes:16;	    /* 4-5: size of basic sampling entry      */
+	unsigned int as:1;	    /* 14: basic-sampling authorization	 */
+	unsigned int ad:1;	    /* 15: diag-sampling authorization	 */
+	unsigned int b16_21:6;	    /* 16-21: zeros			 */
+	unsigned int es:1;	    /* 22: basic-sampling enable control */
+	unsigned int ed:1;	    /* 23: diag-sampling enable control	 */
+	unsigned int b24_29:6;	    /* 24-29: zeros			 */
+	unsigned int cs:1;	    /* 30: basic-sampling activation control */
+	unsigned int cd:1;	    /* 31: diag-sampling activation control */
+	unsigned int bsdes:16;	    /* 4-5: size of basic sampling entry */
 	unsigned int dsdes:16;	    /* 6-7: size of diagnostic sampling entry */
 	unsigned long min_sampl_rate; /* 8-15: minimum sampling interval */
 	unsigned long max_sampl_rate; /* 16-23: maximum sampling interval*/
@@ -82,10 +84,11 @@ struct hws_lsctl_request_block {
 	unsigned int s:1;	    /* 0: maximum buffer indicator	 */
 	unsigned int h:1;	    /* 1: part. level reserved for VM use*/
 	unsigned long long b2_53:52;/* 2-53: zeros			 */
-	unsigned int es:1;	    /* 54: sampling enable control	 */
-	unsigned int b55_61:7;	    /* 55-61: - zeros			 */
-	unsigned int cs:1;	    /* 62: sampling activation control	 */
-	unsigned int b63:1;	    /* 63: zero 			 */
+	unsigned int es:1;	    /* 54: basic-sampling enable control */
+	unsigned int ed:1;	    /* 55: diag-sampling enable control	 */
+	unsigned int b56_61:6;	    /* 56-61: - zeros			 */
+	unsigned int cs:1;	    /* 62: basic-sampling activation control */
+	unsigned int cd:1;	    /* 63: diag-sampling activation control  */
 	unsigned long interval;     /* 8-15: sampling interval		 */
 	unsigned long tear;	    /* 16-23: TEAR contents		 */
 	unsigned long dear;	    /* 24-31: DEAR contents		 */
@@ -96,8 +99,7 @@ struct hws_lsctl_request_block {
 	unsigned long rsvrd4;	    /* reserved 			 */
 } __packed;
 
-
-struct hws_data_entry {
+struct hws_basic_entry {
 	unsigned int def:16;	    /* 0-15  Data Entry Format		 */
 	unsigned int R:4;	    /* 16-19 reserved			 */
 	unsigned int U:4;	    /* 20-23 Number of unique instruct.  */
@@ -114,6 +116,18 @@ struct hws_data_entry {
 	unsigned long long hpp;     /* Host Program Parameter		 */
 } __packed;
 
+struct hws_diag_entry {
+	unsigned int def:16;	    /* 0-15  Data Entry Format		 */
+	unsigned int R:14;	    /* 16-19 and 20-30 reserved		 */
+	unsigned int I:1;	    /* 31 entry valid or invalid	 */
+	u8	     data[];	    /* Machine-dependent sample data	 */
+} __packed;
+
+struct hws_combined_entry {
+	struct hws_basic_entry	basic;	/* Basic-sampling data entry */
+	struct hws_diag_entry	diag;	/* Diagnostic-sampling data entry */
+} __packed;
+
 struct hws_trailer_entry {
 	union {
 		struct {
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index 7667bde..bd4573f 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -52,15 +52,39 @@ struct perf_sf_sde_regs {
 #define PERF_CPUM_CF_MAX_CTR		256
 
 /* Perf PMU definitions for the sampling facility */
-#define PERF_CPUM_SF_MAX_CTR		1
-#define PERF_EVENT_CPUM_SF		0xB0000UL	/* Raw event ID */
+#define PERF_CPUM_SF_MAX_CTR		2
+#define PERF_EVENT_CPUM_SF		0xB0000UL /* Event: Basic-sampling */
+#define PERF_EVENT_CPUM_SF_DIAG		0xBD000UL /* Event: Combined-sampling */
+#define PERF_CPUM_SF_BASIC_MODE		0x0001	  /* Basic-sampling flag */
+#define PERF_CPUM_SF_DIAG_MODE		0x0002	  /* Diagnostic-sampling flag */
+#define PERF_CPUM_SF_MODE_MASK		(PERF_CPUM_SF_BASIC_MODE| \
+					 PERF_CPUM_SF_DIAG_MODE)
 
 #define REG_NONE		0
 #define REG_OVERFLOW		1
 #define OVERFLOW_REG(hwc)	((hwc)->extra_reg.config)
 #define SFB_ALLOC_REG(hwc)	((hwc)->extra_reg.alloc)
+#define RAWSAMPLE_REG(hwc)	((hwc)->config)
 #define TEAR_REG(hwc)		((hwc)->last_tag)
 #define SAMPL_RATE(hwc)		((hwc)->event_base)
+#define SAMPL_FLAGS(hwc)	((hwc)->config_base)
+#define SAMPL_DIAG_MODE(hwc)	(SAMPL_FLAGS(hwc) & PERF_CPUM_SF_DIAG_MODE)
+
+/* Structure for sampling data entries to be passed as perf raw sample data
+ * to user space.  Note that raw sample data must be aligned and, thus, might
+ * be padded with zeros.
+ */
+struct sf_raw_sample {
+#define SF_RAW_SAMPLE_BASIC	PERF_CPUM_SF_BASIC_MODE
+#define SF_RAW_SAMPLE_DIAG	PERF_CPUM_SF_DIAG_MODE
+	u64			format;
+	u32			 size;	  /* Size of sf_raw_sample */
+	u16			bsdes;	  /* Basic-sampling data entry size */
+	u16			dsdes;	  /* Diagnostic-sampling data entry size */
+	struct hws_basic_entry	basic;	  /* Basic-sampling data entry */
+	struct hws_diag_entry	 diag;	  /* Diagnostic-sampling data entry */
+	u8		    padding[];	  /* Padding to next multiple of 8 */
+} __packed;
 
 /* Perf hardware reserve and release functions */
 int perf_reserve_sampling(void);
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 28fa2f2..b4ec058 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -17,6 +17,7 @@
 #include <linux/percpu.h>
 #include <linux/notifier.h>
 #include <linux/export.h>
+#include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/moduleparam.h>
 #include <asm/cpu_mf.h>
@@ -31,8 +32,8 @@
 #define CPUM_SF_MIN_SDBT	1
 
 /* Number of sample-data-blocks per sample-data-block-table (SDBT):
- * The table contains SDB origin (8 bytes) and one SDBT origin that
- * points to the next table.
+ * A table contains SDB pointers (8 bytes) and one table-link entry
+ * that points to the origin of the next SDBT.
  */
 #define CPUM_SF_SDB_PER_TABLE	((PAGE_SIZE - 8) / 8)
 
@@ -48,8 +49,11 @@ static inline int require_table_link(const void *sdbt)
 
 /* Minimum and maximum sampling buffer sizes:
  *
- * This number represents the maximum size of the sampling buffer
- * taking the number of sample-data-block-tables into account.
+ * This number represents the maximum size of the sampling buffer taking
+ * the number of sample-data-block-tables into account.  Note that these
+ * numbers apply to the basic-sampling function only.
+ * The maximum number of SDBs is increased by CPUM_SF_SDB_DIAG_FACTOR if
+ * the diagnostic-sampling function is active.
  *
  * Sampling buffer size		Buffer characteristics
  * ---------------------------------------------------
@@ -63,6 +67,7 @@ static inline int require_table_link(const void *sdbt)
  */
 static unsigned long __read_mostly CPUM_SF_MIN_SDB = 15;
 static unsigned long __read_mostly CPUM_SF_MAX_SDB = 8176;
+static unsigned long __read_mostly CPUM_SF_SDB_DIAG_FACTOR = 1;
 
 struct sf_buffer {
 	unsigned long	 *sdbt;	    /* Sample-data-block-table origin */
@@ -290,8 +295,20 @@ static int alloc_sampling_buffer(struct sf_buffer *sfb, unsigned long num_sdb)
 
 static void sfb_set_limits(unsigned long min, unsigned long max)
 {
+	struct hws_qsi_info_block si;
+
 	CPUM_SF_MIN_SDB = min;
 	CPUM_SF_MAX_SDB = max;
+
+	memset(&si, 0, sizeof(si));
+	if (!qsi(&si))
+		CPUM_SF_SDB_DIAG_FACTOR = DIV_ROUND_UP(si.dsdes, si.bsdes);
+}
+
+static unsigned long sfb_max_limit(struct hw_perf_event *hwc)
+{
+	return SAMPL_DIAG_MODE(hwc) ? CPUM_SF_MAX_SDB * CPUM_SF_SDB_DIAG_FACTOR
+				    : CPUM_SF_MAX_SDB;
 }
 
 static unsigned long sfb_pending_allocs(struct sf_buffer *sfb,
@@ -312,8 +329,8 @@ static int sfb_has_pending_allocs(struct sf_buffer *sfb,
 
 static void sfb_account_allocs(unsigned long num, struct hw_perf_event *hwc)
 {
-	/* Limit the number SDBs to not exceed the maximum */
-	num = min_t(unsigned long, num, CPUM_SF_MAX_SDB - SFB_ALLOC_REG(hwc));
+	/* Limit the number of SDBs to not exceed the maximum */
+	num = min_t(unsigned long, num, sfb_max_limit(hwc) - SFB_ALLOC_REG(hwc));
 	if (num)
 		SFB_ALLOC_REG(hwc) += num;
 }
@@ -324,32 +341,89 @@ static void sfb_init_allocs(unsigned long num, struct hw_perf_event *hwc)
 	sfb_account_allocs(num, hwc);
 }
 
-static int allocate_sdbt(struct cpu_hw_sf *cpuhw, struct hw_perf_event *hwc)
+static size_t event_sample_size(struct hw_perf_event *hwc)
+{
+	struct sf_raw_sample *sfr = (struct sf_raw_sample *) RAWSAMPLE_REG(hwc);
+	size_t sample_size;
+
+	/* The sample size depends on the sampling function: The basic-sampling
+	 * function must be always enabled, diagnostic-sampling function is
+	 * optional.
+	 */
+	sample_size = sfr->bsdes;
+	if (SAMPL_DIAG_MODE(hwc))
+		sample_size += sfr->dsdes;
+
+	return sample_size;
+}
+
+static void deallocate_buffers(struct cpu_hw_sf *cpuhw)
+{
+	if (cpuhw->sfb.sdbt)
+		free_sampling_buffer(&cpuhw->sfb);
+}
+
+static int allocate_buffers(struct cpu_hw_sf *cpuhw, struct hw_perf_event *hwc)
 {
-	unsigned long n_sdb, freq;
-	unsigned long factor;
+	unsigned long n_sdb, freq, factor;
+	size_t sfr_size, sample_size;
+	struct sf_raw_sample *sfr;
+
+	/* Allocate raw sample buffer
+	 *
+	 *    The raw sample buffer is used to temporarily store sampling data
+	 *    entries for perf raw sample processing.  The buffer size mainly
+	 *    depends on the size of diagnostic-sampling data entries which is
+	 *    machine-specific.  The exact size calculation includes:
+	 *	1. The first 4 bytes of diagnostic-sampling data entries are
+	 *	   already reflected in the sf_raw_sample structure.  Subtract
+	 *	   these bytes.
+	 *	2. The perf raw sample data must be 8-byte aligned (u64) and
+	 *	   perf's internal data size must be considered too.  So add
+	 *	   an additional u32 for correct alignment and subtract before
+	 *	   allocating the buffer.
+	 *	3. Store the raw sample buffer pointer in the perf event
+	 *	   hardware structure.
+	 */
+	sfr_size = ALIGN((sizeof(*sfr) - sizeof(sfr->diag) + cpuhw->qsi.dsdes) +
+			 sizeof(u32), sizeof(u64));
+	sfr_size -= sizeof(u32);
+	sfr = kzalloc(sfr_size, GFP_KERNEL);
+	if (!sfr)
+		return -ENOMEM;
+	sfr->size = sfr_size;
+	sfr->bsdes = cpuhw->qsi.bsdes;
+	sfr->dsdes = cpuhw->qsi.dsdes;
+	RAWSAMPLE_REG(hwc) = (unsigned long) sfr;
 
 	/* Calculate sampling buffers using 4K pages
 	 *
-	 *    1. Use frequency as input.  The samping buffer is designed for
-	 *	 a complete second.  This can be adjusted through the "factor"
-	 *	 variable.
+	 *    1. Determine the sample data size which depends on the used
+	 *	 sampling functions, for example, basic-sampling or
+	 *	 basic-sampling with diagnostic-sampling.
+	 *
+	 *    2. Use the sampling frequency as input.  The sampling buffer is
+	 *	 designed for almost one second.  This can be adjusted through
+	 *	 the "factor" variable.
 	 *	 In any case, alloc_sampling_buffer() sets the Alert Request
-	 *	 Control indicator to trigger measurement-alert to harvest
+	 *	 Control indicator to trigger a measurement-alert to harvest
 	 *	 sample-data-blocks (sdb).
 	 *
-	 *    2. Compute the number of sample-data-blocks and ensure a minimum
+	 *    3. Compute the number of sample-data-blocks and ensure a minimum
 	 *	 of CPUM_SF_MIN_SDB.  Also ensure the upper limit does not
-	 *	 exceed CPUM_SF_MAX_SDB.  See also the remarks for these
-	 *	 symbolic constants.
+	 *	 exceed a "calculated" maximum.  The symbolic maximum is
+	 *	 designed for basic-sampling only and needs to be increased if
+	 *	 diagnostic-sampling is active.
+	 *	 See also the remarks for these symbolic constants.
 	 *
-	 *    3. Compute number of pages used for the sample-data-block-table
-	 *	 and ensure a minimum of CPUM_SF_MIN_SDBT (at minimum one table
-	 *	 to manage up to 511 sample-data-blocks).
+	 *    4. Compute the number of sample-data-block-tables (SDBT) and
+	 *	 ensure a minimum of CPUM_SF_MIN_SDBT (one table can manage up
+	 *	 to 511 SDBs).
 	 */
+	sample_size = event_sample_size(hwc);
 	freq = sample_rate_to_freq(&cpuhw->qsi, SAMPL_RATE(hwc));
 	factor = 1;
-	n_sdb = DIV_ROUND_UP(freq, factor * ((PAGE_SIZE-64) / cpuhw->qsi.bsdes));
+	n_sdb = DIV_ROUND_UP(freq, factor * ((PAGE_SIZE-64) / sample_size));
 	if (n_sdb < CPUM_SF_MIN_SDB)
 		n_sdb = CPUM_SF_MIN_SDB;
 
@@ -366,8 +440,10 @@ static int allocate_sdbt(struct cpu_hw_sf *cpuhw, struct hw_perf_event *hwc)
 		return 0;
 
 	debug_sprintf_event(sfdbg, 3,
-			    "allocate_sdbt: rate=%lu f=%lu sdb=%lu/%lu cpuhw=%p\n",
-			    SAMPL_RATE(hwc), freq, n_sdb, CPUM_SF_MAX_SDB, cpuhw);
+			    "allocate_buffers: rate=%lu f=%lu sdb=%lu/%lu"
+			    " sample_size=%lu cpuhw=%p\n",
+			    SAMPL_RATE(hwc), freq, n_sdb, sfb_max_limit(hwc),
+			    sample_size, cpuhw);
 
 	return alloc_sampling_buffer(&cpuhw->sfb,
 				     sfb_pending_allocs(&cpuhw->sfb, hwc));
@@ -509,10 +585,8 @@ static void setup_pmc_cpu(void *flags)
 		if (err) {
 			pr_err("Switching off the sampling facility failed "
 			       "with rc=%i\n", err);
-		} else {
-			if (cpusf->sfb.sdbt)
-				free_sampling_buffer(&cpusf->sfb);
-		}
+		} else
+			deallocate_buffers(cpusf);
 		debug_sprintf_event(sfdbg, 5,
 				    "setup_pmc_cpu: released: cpuhw=%p\n", cpusf);
 		break;
@@ -550,6 +624,10 @@ static int reserve_pmc_hardware(void)
 
 static void hw_perf_event_destroy(struct perf_event *event)
 {
+	/* Free raw sample buffer */
+	if (RAWSAMPLE_REG(&event->hw))
+		kfree((void *) RAWSAMPLE_REG(&event->hw));
+
 	/* Release PMC if this is the last perf event */
 	if (!atomic_add_unless(&num_events, -1, 1)) {
 		mutex_lock(&pmc_reserve_mutex);
@@ -569,8 +647,15 @@ static void hw_init_period(struct hw_perf_event *hwc, u64 period)
 static void hw_reset_registers(struct hw_perf_event *hwc,
 			       unsigned long *sdbt_origin)
 {
+	struct sf_raw_sample *sfr;
+
 	/* (Re)set to first sample-data-block-table */
 	TEAR_REG(hwc) = (unsigned long) sdbt_origin;
+
+	/* (Re)set raw sampling buffer register */
+	sfr = (struct sf_raw_sample *) RAWSAMPLE_REG(hwc);
+	memset(&sfr->basic, 0, sizeof(sfr->basic));
+	memset(&sfr->diag, 0, sfr->dsdes);
 }
 
 static unsigned long hw_limit_rate(const struct hws_qsi_info_block *si,
@@ -634,6 +719,20 @@ static int __hw_perf_event_init(struct perf_event *event)
 		goto out;
 	}
 
+	/* Always enable basic sampling */
+	SAMPL_FLAGS(hwc) = PERF_CPUM_SF_BASIC_MODE;
+
+	/* Check if diagnostic sampling is requested.  Deny if the required
+	 * sampling authorization is missing.
+	 */
+	if (attr->config == PERF_EVENT_CPUM_SF_DIAG) {
+		if (!si.ad) {
+			err = -EPERM;
+			goto out;
+		}
+		SAMPL_FLAGS(hwc) |= PERF_CPUM_SF_DIAG_MODE;
+	}
+
 	/* The sampling information (si) contains information about the
 	 * min/max sampling intervals and the CPU speed.  So calculate the
 	 * correct sampling interval and avoid the whole period adjust
@@ -679,14 +778,14 @@ static int __hw_perf_event_init(struct perf_event *event)
 	 */
 	if (cpuhw)
 		/* Event is pinned to a particular CPU */
-		err = allocate_sdbt(cpuhw, hwc);
+		err = allocate_buffers(cpuhw, hwc);
 	else {
 		/* Event is not pinned, allocate sampling buffer on
 		 * each online CPU
 		 */
 		for_each_online_cpu(cpu) {
 			cpuhw = &per_cpu(cpu_hw_sf, cpu);
-			err = allocate_sdbt(cpuhw, hwc);
+			err = allocate_buffers(cpuhw, hwc);
 			if (err)
 				break;
 		}
@@ -705,7 +804,8 @@ static int cpumsf_pmu_event_init(struct perf_event *event)
 
 	switch (event->attr.type) {
 	case PERF_TYPE_RAW:
-		if (event->attr.config != PERF_EVENT_CPUM_SF)
+		if ((event->attr.config != PERF_EVENT_CPUM_SF) &&
+		    (event->attr.config != PERF_EVENT_CPUM_SF_DIAG))
 			return -ENOENT;
 		break;
 	case PERF_TYPE_HARDWARE:
@@ -786,8 +886,9 @@ static void cpumsf_pmu_enable(struct pmu *pmu)
 		return;
 	}
 
-	debug_sprintf_event(sfdbg, 6, "pmu_enable: es=%i cs=%i tear=%p dear=%p\n",
-			    cpuhw->lsctl.es, cpuhw->lsctl.cs,
+	debug_sprintf_event(sfdbg, 6, "pmu_enable: es=%i cs=%i ed=%i cd=%i "
+			    "tear=%p dear=%p\n", cpuhw->lsctl.es, cpuhw->lsctl.cs,
+			    cpuhw->lsctl.ed, cpuhw->lsctl.cd,
 			    (void *) cpuhw->lsctl.tear, (void *) cpuhw->lsctl.dear);
 }
 
@@ -807,6 +908,7 @@ static void cpumsf_pmu_disable(struct pmu *pmu)
 	/* Switch off sampling activation control */
 	inactive = cpuhw->lsctl;
 	inactive.cs = 0;
+	inactive.cd = 0;
 
 	err = lsctl(&inactive);
 	if (err) {
@@ -867,21 +969,19 @@ static int perf_exclude_event(struct perf_event *event, struct pt_regs *regs,
  *
  * Return non-zero if an event overflow occurred.
  */
-static int perf_push_sample(struct perf_event *event,
-			    struct hws_data_entry *sample)
+static int perf_push_sample(struct perf_event *event, struct sf_raw_sample *sfr)
 {
 	int overflow;
 	struct pt_regs regs;
 	struct perf_sf_sde_regs *sde_regs;
 	struct perf_sample_data data;
+	struct perf_raw_record raw;
 
-	/* Skip samples that are invalid or for which the instruction address
-	 * is not predictable.	For the latter, the wait-state bit is set.
-	 */
-	if (sample->I || sample->W)
-		return 0;
-
+	/* Setup perf sample */
 	perf_sample_data_init(&data, 0, event->hw.last_period);
+	raw.size = sfr->size;
+	raw.data = sfr;
+	data.raw = &raw;
 
 	/* Setup pt_regs to look like an CPU-measurement external interrupt
 	 * using the Program Request Alert code.  The regs.int_parm_long
@@ -893,14 +993,14 @@ static int perf_push_sample(struct perf_event *event,
 	regs.int_parm = CPU_MF_INT_SF_PRA;
 	sde_regs = (struct perf_sf_sde_regs *) &regs.int_parm_long;
 
-	regs.psw.addr = sample->ia;
-	if (sample->T)
+	regs.psw.addr = sfr->basic.ia;
+	if (sfr->basic.T)
 		regs.psw.mask |= PSW_MASK_DAT;
-	if (sample->W)
+	if (sfr->basic.W)
 		regs.psw.mask |= PSW_MASK_WAIT;
-	if (sample->P)
+	if (sfr->basic.P)
 		regs.psw.mask |= PSW_MASK_PSTATE;
-	switch (sample->AS) {
+	switch (sfr->basic.AS) {
 	case 0x0:
 		regs.psw.mask |= PSW_ASC_PRIMARY;
 		break;
@@ -922,7 +1022,7 @@ static int perf_push_sample(struct perf_event *event,
 	 * purposes too.
 	 * For now, simply use a non-zero value as guest indicator.
 	 */
-	if (sample->hpp)
+	if (sfr->basic.hpp)
 		sde_regs->in_guest = 1;
 
 	overflow = 0;
@@ -942,51 +1042,155 @@ static void perf_event_count_update(struct perf_event *event, u64 count)
 	local64_add(count, &event->count);
 }
 
+static int sample_format_is_valid(struct hws_combined_entry *sample,
+				   unsigned int flags)
+{
+	if (likely(flags & PERF_CPUM_SF_BASIC_MODE))
+		/* Only basic-sampling data entries with data-entry-format
+		 * version of 0x0001 can be processed.
+		 */
+		if (sample->basic.def != 0x0001)
+			return 0;
+	if (flags & PERF_CPUM_SF_DIAG_MODE)
+		/* The data-entry-format number of diagnostic-sampling data
+		 * entries can vary.  Because diagnostic data is just passed
+		 * through, do only a sanity check on the DEF.
+		 */
+		if (sample->diag.def < 0x8001)
+			return 0;
+	return 1;
+}
+
+static int sample_is_consistent(struct hws_combined_entry *sample,
+				unsigned long flags)
+{
+	/* This check applies only to basic-sampling data entries of potentially
+	 * combined-sampling data entries.  Invalid entries cannot be processed
+	 * by the PMU and, thus, do not deliver an associated
+	 * diagnostic-sampling data entry.
+	 */
+	if (unlikely(!(flags & PERF_CPUM_SF_BASIC_MODE)))
+		return 0;
+	/*
+	 * Samples are skipped, if they are invalid or for which the
+	 * instruction address is not predictable, i.e., the wait-state bit is
+	 * set.
+	 */
+	if (sample->basic.I || sample->basic.W)
+		return 0;
+	return 1;
+}
+
+static void reset_sample_slot(struct hws_combined_entry *sample,
+			      unsigned long flags)
+{
+	if (likely(flags & PERF_CPUM_SF_BASIC_MODE))
+		sample->basic.def = 0;
+	if (flags & PERF_CPUM_SF_DIAG_MODE)
+		sample->diag.def = 0;
+}
+
+static void sfr_store_sample(struct sf_raw_sample *sfr,
+			     struct hws_combined_entry *sample)
+{
+	if (likely(sfr->format & PERF_CPUM_SF_BASIC_MODE))
+		sfr->basic = sample->basic;
+	if (sfr->format & PERF_CPUM_SF_DIAG_MODE)
+		memcpy(&sfr->diag, &sample->diag, sfr->dsdes);
+}
+
+static void debug_sample_entry(struct hws_combined_entry *sample,
+			       struct hws_trailer_entry *te,
+			       unsigned long flags)
+{
+	debug_sprintf_event(sfdbg, 4, "hw_collect_samples: Found unknown "
+			    "sampling data entry: te->f=%i basic.def=%04x (%p)"
+			    " diag.def=%04x (%p)\n", te->f,
+			    sample->basic.def, &sample->basic,
+			    (flags & PERF_CPUM_SF_DIAG_MODE)
+					? sample->diag.def : 0xFFFF,
+			    (flags & PERF_CPUM_SF_DIAG_MODE)
+					?  &sample->diag : NULL);
+}
+
 /* hw_collect_samples() - Walk through a sample-data-block and collect samples
  * @event:	The perf event
  * @sdbt:	Sample-data-block table
  * @overflow:	Event overflow counter
  *
- * Walks through a sample-data-block and collects hardware sample-data that is
- * pushed to the perf event subsystem.	The overflow reports the number of
- * samples that has been discarded due to an event overflow.
+ * Walks through a sample-data-block and collects sampling data entries that are
+ * then pushed to the perf event subsystem.  Depending on the sampling function,
+ * there can be either basic-sampling or combined-sampling data entries.  A
+ * combined-sampling data entry consists of a basic- and a diagnostic-sampling
+ * data entry.	The sampling function is determined by the flags in the perf
+ * event hardware structure.  The function always works with a combined-sampling
+ * data entry but ignores the the diagnostic portion if it is not available.
+ *
+ * Note that the implementation focuses on basic-sampling data entries and, if
+ * such an entry is not valid, the entire combined-sampling data entry is
+ * ignored.
+ *
+ * The overflow variables counts the number of samples that has been discarded
+ * due to a perf event overflow.
  */
 static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt,
 			       unsigned long long *overflow)
 {
-	struct hws_data_entry *sample;
-	unsigned long *trailer;
+	unsigned long flags = SAMPL_FLAGS(&event->hw);
+	struct hws_combined_entry *sample;
+	struct hws_trailer_entry *te;
+	struct sf_raw_sample *sfr;
+	size_t sample_size;
+
+	/* Prepare and initialize raw sample data */
+	sfr = (struct sf_raw_sample *) RAWSAMPLE_REG(&event->hw);
+	sfr->format = flags & PERF_CPUM_SF_MODE_MASK;
 
-	trailer = trailer_entry_ptr(*sdbt);
-	sample = (struct hws_data_entry *) *sdbt;
-	while ((unsigned long *) sample < trailer) {
+	sample_size = event_sample_size(&event->hw);
+	te = (struct hws_trailer_entry *) trailer_entry_ptr(*sdbt);
+	sample = (struct hws_combined_entry *) *sdbt;
+	while ((unsigned long *) sample < (unsigned long *) te) {
 		/* Check for an empty sample */
-		if (!sample->def)
+		if (!sample->basic.def)
 			break;
 
 		/* Update perf event period */
 		perf_event_count_update(event, SAMPL_RATE(&event->hw));
 
-		/* Check for basic sampling mode */
-		if (sample->def == 0x0001) {
+		/* Check sampling data entry */
+		if (sample_format_is_valid(sample, flags)) {
 			/* If an event overflow occurred, the PMU is stopped to
 			 * throttle event delivery.  Remaining sample data is
 			 * discarded.
 			 */
-			if (!*overflow)
-				*overflow = perf_push_sample(event, sample);
-			else
+			if (!*overflow) {
+				if (sample_is_consistent(sample, flags)) {
+					/* Deliver sample data to perf */
+					sfr_store_sample(sfr, sample);
+					*overflow = perf_push_sample(event, sfr);
+				}
+			} else
 				/* Count discarded samples */
 				*overflow += 1;
-		} else
-			/* Sample slot is not yet written or other record */
-			debug_sprintf_event(sfdbg, 5, "hw_collect_samples: "
-					    "Unknown sample data entry format:"
-					    " %i\n", sample->def);
+		} else {
+			debug_sample_entry(sample, te, flags);
+			/* Sample slot is not yet written or other record.
+			 *
+			 * This condition can occur if the buffer was reused
+			 * from a combined basic- and diagnostic-sampling.
+			 * If only basic-sampling is then active, entries are
+			 * written into the larger diagnostic entries.
+			 * This is typically the case for sample-data-blocks
+			 * that are not full.  Stop processing if the first
+			 * invalid format was detected.
+			 */
+			if (!te->f)
+				break;
+		}
 
 		/* Reset sample slot and advance to next sample */
-		sample->def = 0;
-		sample++;
+		reset_sample_slot(sample, flags);
+		sample += sample_size;
 	}
 }
 
@@ -1104,6 +1308,8 @@ static void cpumsf_pmu_start(struct perf_event *event, int flags)
 	perf_pmu_disable(event->pmu);
 	event->hw.state = 0;
 	cpuhw->lsctl.cs = 1;
+	if (SAMPL_DIAG_MODE(&event->hw))
+		cpuhw->lsctl.cd = 1;
 	perf_pmu_enable(event->pmu);
 }
 
@@ -1119,6 +1325,7 @@ static void cpumsf_pmu_stop(struct perf_event *event, int flags)
 
 	perf_pmu_disable(event->pmu);
 	cpuhw->lsctl.cs = 0;
+	cpuhw->lsctl.cd = 0;
 	event->hw.state |= PERF_HES_STOPPED;
 
 	if ((flags & PERF_EF_UPDATE) && !(event->hw.state & PERF_HES_UPTODATE)) {
@@ -1158,11 +1365,13 @@ static int cpumsf_pmu_add(struct perf_event *event, int flags)
 
 	/* Ensure sampling functions are in the disabled state.  If disabled,
 	 * switch on sampling enable control. */
-	if (WARN_ON_ONCE(cpuhw->lsctl.es == 1)) {
+	if (WARN_ON_ONCE(cpuhw->lsctl.es == 1 || cpuhw->lsctl.ed == 1)) {
 		err = -EAGAIN;
 		goto out;
 	}
 	cpuhw->lsctl.es = 1;
+	if (SAMPL_DIAG_MODE(&event->hw))
+		cpuhw->lsctl.ed = 1;
 
 	/* Set in_use flag and store event */
 	event->hw.idx = 0;	  /* only one sampling event per CPU supported */
@@ -1185,6 +1394,7 @@ static void cpumsf_pmu_del(struct perf_event *event, int flags)
 	cpumsf_pmu_stop(event, PERF_EF_UPDATE);
 
 	cpuhw->lsctl.es = 0;
+	cpuhw->lsctl.ed = 0;
 	cpuhw->flags &= ~PMU_F_IN_USE;
 	cpuhw->event = NULL;
 
@@ -1198,9 +1408,11 @@ static int cpumsf_pmu_event_idx(struct perf_event *event)
 }
 
 CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC, PERF_EVENT_CPUM_SF);
+CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC_DIAG, PERF_EVENT_CPUM_SF_DIAG);
 
 static struct attribute *cpumsf_pmu_events_attr[] = {
 	CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC),
+	CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG),
 	NULL,
 };
 
@@ -1351,8 +1563,9 @@ static int param_set_sfb_size(const char *val, const struct kernel_param *kp)
 		return rc;
 
 	sfb_set_limits(min, max);
-	pr_info("Changed sampling buffer settings: min=%lu max=%lu\n",
-		CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB);
+	pr_info("The sampling buffer limits have changed to: "
+		"min=%lu max=%lu (diag=x%lu)\n",
+		CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB, CPUM_SF_SDB_DIAG_FACTOR);
 	return 0;
 }
 
@@ -1362,13 +1575,38 @@ static struct kernel_param_ops param_ops_sfb_size = {
 	.get = param_get_sfb_size,
 };
 
+#define RS_INIT_FAILURE_QSI	  0x0001
+#define RS_INIT_FAILURE_BSDES	  0x0002
+#define RS_INIT_FAILURE_ALRT	  0x0003
+#define RS_INIT_FAILURE_PERF	  0x0004
+static void __init pr_cpumsf_err(unsigned int reason)
+{
+	pr_err("Sampling facility support for perf is not available: "
+	       "reason=%04x\n", reason);
+}
+
 static int __init init_cpum_sampling_pmu(void)
 {
+	struct hws_qsi_info_block si;
 	int err;
 
 	if (!cpum_sf_avail())
 		return -ENODEV;
 
+	memset(&si, 0, sizeof(si));
+	if (qsi(&si)) {
+		pr_cpumsf_err(RS_INIT_FAILURE_QSI);
+		return -ENODEV;
+	}
+
+	if (si.bsdes != sizeof(struct hws_basic_entry)) {
+		pr_cpumsf_err(RS_INIT_FAILURE_BSDES);
+		return -EINVAL;
+	}
+
+	if (si.ad)
+		sfb_set_limits(CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB);
+
 	sfdbg = debug_register(KMSG_COMPONENT, 2, 1, 80);
 	if (!sfdbg)
 		pr_err("Registering for s390dbf failed\n");
@@ -1376,13 +1614,13 @@ static int __init init_cpum_sampling_pmu(void)
 
 	err = register_external_interrupt(0x1407, cpumf_measurement_alert);
 	if (err) {
-		pr_err("Failed to register for CPU-measurement alerts\n");
+		pr_cpumsf_err(RS_INIT_FAILURE_ALRT);
 		goto out;
 	}
 
 	err = perf_pmu_register(&cpumf_sampling, "cpum_sf", PERF_TYPE_RAW);
 	if (err) {
-		pr_err("Failed to register cpum_sf pmu\n");
+		pr_cpumsf_err(RS_INIT_FAILURE_PERF);
 		unregister_external_interrupt(0x1407, cpumf_measurement_alert);
 		goto out;
 	}
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 60a6826..91aa215 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -139,16 +139,21 @@ static void print_debug_sf(void)
 	int cpu = smp_processor_id();
 
 	memset(&si, 0, sizeof(si));
-	if (qsi(&si)) {
-		pr_err("CPU[%i]: CPM_SF: qsi failed\n");
+	if (qsi(&si))
 		return;
-	}
 
-	pr_info("CPU[%i]: CPM_SF: as=%i es=%i cs=%i bsdes=%i dsdes=%i"
-		" min=%i max=%i cpu_speed=%i tear=%p dear=%p\n",
-		cpu, si.as, si.es, si.cs, si.bsdes, si.dsdes,
-		si.min_sampl_rate, si.max_sampl_rate, si.cpu_speed,
-		si.tear, si.dear);
+	pr_info("CPU[%i] CPUM_SF: basic=%i diag=%i min=%i max=%i cpu_speed=%i\n",
+		cpu, si.as, si.ad, si.min_sampl_rate, si.max_sampl_rate,
+		si.cpu_speed);
+
+	if (si.as)
+		pr_info("CPU[%i] CPUM_SF: Basic-sampling: a=%i e=%i c=%i"
+			" bsdes=%i tear=%p dear=%p\n", cpu,
+			si.as, si.es, si.cs, si.bsdes, si.tear, si.dear);
+	if (si.ad)
+		pr_info("CPU[%i] CPUM_SF: Diagnostic-sampling: a=%i e=%i c=%i"
+			" dsdes=%i tear=%p dear=%p\n", cpu,
+			si.ad, si.ed, si.cd, si.dsdes, si.tear, si.dear);
 }
 
 void perf_event_print_debug(void)
diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c
index eb09587..a32c967 100644
--- a/arch/s390/oprofile/hwsampler.c
+++ b/arch/s390/oprofile/hwsampler.c
@@ -799,7 +799,7 @@ static void worker_on_interrupt(unsigned int cpu)
 static void add_samples_to_oprofile(unsigned int cpu, unsigned long *sdbt,
 		unsigned long *dear)
 {
-	struct hws_data_entry *sample_data_ptr;
+	struct hws_basic_entry *sample_data_ptr;
 	unsigned long *trailer;
 
 	trailer = trailer_entry_ptr(*sdbt);
@@ -809,7 +809,7 @@ static void add_samples_to_oprofile(unsigned int cpu, unsigned long *sdbt,
 		trailer = dear;
 	}
 
-	sample_data_ptr = (struct hws_data_entry *)(*sdbt);
+	sample_data_ptr = (struct hws_basic_entry *)(*sdbt);
 
 	while ((unsigned long *)sample_data_ptr < trailer) {
 		struct pt_regs *regs = NULL;
-- 
cgit v0.10.2


From d7528862cf035994972c2c6f42c927db78f2f3a2 Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Fri, 13 Dec 2013 12:45:01 +0100
Subject: s390/cpum_sf: Add flag to process full SDBs only

Add the PERF_CPUM_SF_FULL_BLOCKS flag to process only sample-data-blocks that
have the block-full-indicator bit set.  Sample-data-blocks that are partially
filled are discarded.  Use this flag if the sampling buffer is likely to be
shared among perf events that use different sampling modes.  In such
environments, flushing sample-data-blocks that are not completely filled, might
cause invalid-data-formats.

Setting PERF_CPUM_SF_FULL_BLOCKS prevents potentially invalid sampling data to
be processed but, in contrast, also discards valid samples in partially filled
sample-data-blocks.  Note that sample-data-blocks might not become full for
small sampling frequencies or for workload that is scheduled for tiny intervals.

To sample with the PERF_CPUM_SF_FULL_BLOCKS flag, set the perf->attr.config1
to 0x0004.  For example:

	perf record -e cpum_sf/config=0xB000,config1=0x0004/

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index bd4573f..159a8ec 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -59,6 +59,7 @@ struct perf_sf_sde_regs {
 #define PERF_CPUM_SF_DIAG_MODE		0x0002	  /* Diagnostic-sampling flag */
 #define PERF_CPUM_SF_MODE_MASK		(PERF_CPUM_SF_BASIC_MODE| \
 					 PERF_CPUM_SF_DIAG_MODE)
+#define PERF_CPUM_SF_FULL_BLOCKS	0x0004	  /* Process full SDBs only */
 
 #define REG_NONE		0
 #define REG_OVERFLOW		1
@@ -69,6 +70,7 @@ struct perf_sf_sde_regs {
 #define SAMPL_RATE(hwc)		((hwc)->event_base)
 #define SAMPL_FLAGS(hwc)	((hwc)->config_base)
 #define SAMPL_DIAG_MODE(hwc)	(SAMPL_FLAGS(hwc) & PERF_CPUM_SF_DIAG_MODE)
+#define SDB_FULL_BLOCKS(hwc)	(SAMPL_FLAGS(hwc) & PERF_CPUM_SF_FULL_BLOCKS)
 
 /* Structure for sampling data entries to be passed as perf raw sample data
  * to user space.  Note that raw sample data must be aligned and, thus, might
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index b4ec058..3c3bc8d 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -733,6 +733,10 @@ static int __hw_perf_event_init(struct perf_event *event)
 		SAMPL_FLAGS(hwc) |= PERF_CPUM_SF_DIAG_MODE;
 	}
 
+	/* Check and set other sampling flags */
+	if (attr->config1 & PERF_CPUM_SF_FULL_BLOCKS)
+		SAMPL_FLAGS(hwc) |= PERF_CPUM_SF_FULL_BLOCKS;
+
 	/* The sampling information (si) contains information about the
 	 * min/max sampling intervals and the CPU speed.  So calculate the
 	 * correct sampling interval and avoid the whole period adjust
@@ -1203,8 +1207,10 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt,
  * register of the specified perf event.
  *
  * Only full sample-data-blocks are processed.	Specify the flash_all flag
- * to also walk through partially filled sample-data-blocks.
- *
+ * to also walk through partially filled sample-data-blocks.  It is ignored
+ * if PERF_CPUM_SF_FULL_BLOCKS is set.	The PERF_CPUM_SF_FULL_BLOCKS flag
+ * enforces the processing of full sample-data-blocks only (trailer entries
+ * with the block-full-indicator bit set).
  */
 static void hw_perf_event_update(struct perf_event *event, int flush_all)
 {
@@ -1214,6 +1220,9 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all)
 	unsigned long long event_overflow, sampl_overflow, num_sdb, te_flags;
 	int done;
 
+	if (flush_all && SDB_FULL_BLOCKS(hwc))
+		flush_all = 0;
+
 	sdbt = (unsigned long *) TEAR_REG(hwc);
 	done = event_overflow = sampl_overflow = num_sdb = 0;
 	while (!done) {
-- 
cgit v0.10.2


From 74bd0d859dc3536b01c892abfa9f87620e4bca2f Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@linux.vnet.ibm.com>
Date: Mon, 16 Dec 2013 10:51:54 +0100
Subject: s390/cio: fix unlocked access of online member

Make sure that access to the online member of a ccw device is
guarded by the ccwlock.

Reported-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Reviewed-by: Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index e4a7ab2..4a0734f 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -333,9 +333,9 @@ int ccw_device_set_offline(struct ccw_device *cdev)
 		if (ret != 0)
 			return ret;
 	}
-	cdev->online = 0;
 	spin_lock_irq(cdev->ccwlock);
 	sch = to_subchannel(cdev->dev.parent);
+	cdev->online = 0;
 	/* Wait until a final state or DISCONNECTED is reached */
 	while (!dev_fsm_final_state(cdev) &&
 	       cdev->private->state != DEV_STATE_DISCONNECTED) {
@@ -446,7 +446,10 @@ int ccw_device_set_online(struct ccw_device *cdev)
 		ret = cdev->drv->set_online(cdev);
 	if (ret)
 		goto rollback;
+
+	spin_lock_irq(cdev->ccwlock);
 	cdev->online = 1;
+	spin_unlock_irq(cdev->ccwlock);
 	return 0;
 
 rollback:
@@ -1745,8 +1748,7 @@ ccw_device_probe (struct device *dev)
 	return 0;
 }
 
-static int
-ccw_device_remove (struct device *dev)
+static int ccw_device_remove(struct device *dev)
 {
 	struct ccw_device *cdev = to_ccwdev(dev);
 	struct ccw_driver *cdrv = cdev->drv;
@@ -1754,9 +1756,10 @@ ccw_device_remove (struct device *dev)
 
 	if (cdrv->remove)
 		cdrv->remove(cdev);
+
+	spin_lock_irq(cdev->ccwlock);
 	if (cdev->online) {
 		cdev->online = 0;
-		spin_lock_irq(cdev->ccwlock);
 		ret = ccw_device_offline(cdev);
 		spin_unlock_irq(cdev->ccwlock);
 		if (ret == 0)
@@ -1769,10 +1772,12 @@ ccw_device_remove (struct device *dev)
 				      cdev->private->dev_id.devno);
 		/* Give up reference obtained in ccw_device_set_online(). */
 		put_device(&cdev->dev);
+		spin_lock_irq(cdev->ccwlock);
 	}
 	ccw_device_set_timeout(cdev, 0);
 	cdev->drv = NULL;
 	cdev->private->int_class = IRQIO_CIO;
+	spin_unlock_irq(cdev->ccwlock);
 	return 0;
 }
 
-- 
cgit v0.10.2


From 00381eeb47ef6b3b70d2a17c89a8205b6f1aa00a Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@linux.vnet.ibm.com>
Date: Mon, 16 Dec 2013 10:54:13 +0100
Subject: s390/cio: use device_lock to synchronize calls to the ccw driver

When calling set_{on,off}line of a ccw device driver we hold the
module reference of the owner. This is pretty useless - we don't
want to prevent module unloading but driver unbinding. Use the
driver core's device_lock instead.

Reviewed-by: Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index 4a0734f..e9d7835 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -549,17 +549,12 @@ static ssize_t online_store (struct device *dev, struct device_attribute *attr,
 	if (!dev_fsm_final_state(cdev) &&
 	    cdev->private->state != DEV_STATE_DISCONNECTED) {
 		ret = -EAGAIN;
-		goto out_onoff;
+		goto out;
 	}
 	/* Prevent conflict between pending work and on-/offline processing.*/
 	if (work_pending(&cdev->private->todo_work)) {
 		ret = -EAGAIN;
-		goto out_onoff;
-	}
-
-	if (cdev->drv && !try_module_get(cdev->drv->driver.owner)) {
-		ret = -EINVAL;
-		goto out_onoff;
+		goto out;
 	}
 	if (!strncmp(buf, "force\n", count)) {
 		force = 1;
@@ -571,6 +566,8 @@ static ssize_t online_store (struct device *dev, struct device_attribute *attr,
 	}
 	if (ret)
 		goto out;
+
+	device_lock(dev);
 	switch (i) {
 	case 0:
 		ret = online_store_handle_offline(cdev);
@@ -581,10 +578,9 @@ static ssize_t online_store (struct device *dev, struct device_attribute *attr,
 	default:
 		ret = -EINVAL;
 	}
+	device_unlock(dev);
+
 out:
-	if (cdev->drv)
-		module_put(cdev->drv->driver.owner);
-out_onoff:
 	atomic_set(&cdev->private->onoff, 0);
 	return (ret < 0) ? ret : count;
 }
-- 
cgit v0.10.2


From d5b877ffb9aa04a6fb6b6eae6dc19ca163d568a8 Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@linux.vnet.ibm.com>
Date: Mon, 16 Dec 2013 10:56:46 +0100
Subject: s390/cio: use device_lock to synchronize calls to the ccwgroup driver

When calling set_{on,off}line of a ccwgroup device driver we hold
the module reference of the owner. This is pretty useless - we don't
want to prevent module unloading but driver unbinding. Use the
driver core's device_lock instead.

Reviewed-by: Peter Oberparleiter <oberpar@linux.vnet.ibm.com>
Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c
index 959135a..fd3367a1 100644
--- a/drivers/s390/cio/ccwgroup.c
+++ b/drivers/s390/cio/ccwgroup.c
@@ -128,14 +128,14 @@ static ssize_t ccwgroup_online_store(struct device *dev,
 				     const char *buf, size_t count)
 {
 	struct ccwgroup_device *gdev = to_ccwgroupdev(dev);
-	struct ccwgroup_driver *gdrv = to_ccwgroupdrv(dev->driver);
 	unsigned long value;
 	int ret;
 
-	if (!dev->driver)
-		return -EINVAL;
-	if (!try_module_get(gdrv->driver.owner))
-		return -EINVAL;
+	device_lock(dev);
+	if (!dev->driver) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	ret = kstrtoul(buf, 0, &value);
 	if (ret)
@@ -148,7 +148,7 @@ static ssize_t ccwgroup_online_store(struct device *dev,
 	else
 		ret = -EINVAL;
 out:
-	module_put(gdrv->driver.owner);
+	device_unlock(dev);
 	return (ret == 0) ? count : ret;
 }
 
-- 
cgit v0.10.2


From 61aa4884b70cdf3b2d373e18ebbbada43789eade Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Fri, 1 Nov 2013 10:08:20 +0100
Subject: s390: use IS_ENABLED to check if a CONFIG is set to y or m

This is shorter and should be used instead of the longer form
which checks for both possible config options.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index e5b43c9..9532fe2 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -74,7 +74,7 @@ _TIF_TRACE    = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
 	.endm
 
 	.macro LPP newpp
-#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+#if IS_ENABLED(CONFIG_KVM)
 	tm	__LC_MACHINE_FLAGS+6,0x20	# MACHINE_FLAG_LPP
 	jz	.+8
 	.insn	s,0xb2800000,\newpp
@@ -82,7 +82,7 @@ _TIF_TRACE    = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
 	.endm
 
 	.macro	HANDLE_SIE_INTERCEPT scratch,reason
-#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+#if IS_ENABLED(CONFIG_KVM)
 	tmhh	%r8,0x0001		# interrupting from user ?
 	jnz	.+62
 	lgr	\scratch,%r9
@@ -946,7 +946,7 @@ cleanup_idle_insn:
 	.quad	__critical_end - __critical_start
 
 
-#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+#if IS_ENABLED(CONFIG_KVM)
 /*
  * sie64a calling convention:
  * %r2 pointer to sie control block
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 91aa215..a76d602 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -60,7 +60,7 @@ static bool is_in_guest(struct pt_regs *regs)
 {
 	if (user_mode(regs))
 		return false;
-#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+#if IS_ENABLED(CONFIG_KVM)
 	return instruction_pointer(regs) == (unsigned long) &sie_exit;
 #else
 	return false;
diff --git a/arch/s390/kernel/s390_ksyms.c b/arch/s390/kernel/s390_ksyms.c
index 3bac589..9f60467 100644
--- a/arch/s390/kernel/s390_ksyms.c
+++ b/arch/s390/kernel/s390_ksyms.c
@@ -5,7 +5,7 @@
 #ifdef CONFIG_FUNCTION_TRACER
 EXPORT_SYMBOL(_mcount);
 #endif
-#if defined(CONFIG_KVM) || defined(CONFIG_KVM_MODULE)
+#if IS_ENABLED(CONFIG_KVM)
 EXPORT_SYMBOL(sie64a);
 EXPORT_SYMBOL(sie_exit);
 #endif
-- 
cgit v0.10.2


From 553873e1df63a20559ac9c336765dc7055cfc3d4 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Mon, 9 Dec 2013 17:14:23 +0100
Subject: tools/: Convert to new topic libraries

Move debugfs.* to api/fs/. We have a common tools/lib/api/ place where
the Makefile lives and then we place the headers in subdirs.

For example, all the fs-related stuff goes to tools/lib/api/fs/ from
which we get libapikfs.a (acme got almost the naming he wanted :-)) and
we link it into the tools which need it - in this case perf and
tools/vm/page-types.

acme:

"Looking at the implementation, I think some tools can even link
directly to the .o files, avoiding the .a file altogether.

But that is just an optimization/finer granularity tools/lib/
cherrypicking that toolers can make use of."

Fixup documentation cleaning target while at it.

Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Robert Richter <rric@kernel.org>
Cc: Stanislav Fomichev <stfomichev@yandex-team.ru>
Cc: Stephane Eranian <eranian@google.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386605664-24041-2-git-send-email-bp@alien8.de
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/Makefile b/tools/Makefile
index a9b0200..927cd46 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -39,10 +39,10 @@ cpupower: FORCE
 cgroup firewire guest usb virtio vm net: FORCE
 	$(call descend,$@)
 
-liblk: FORCE
-	$(call descend,lib/lk)
+libapikfs: FORCE
+	$(call descend,lib/api)
 
-perf: liblk FORCE
+perf: libapikfs FORCE
 	$(call descend,$@)
 
 selftests: FORCE
@@ -80,10 +80,10 @@ cpupower_clean:
 cgroup_clean firewire_clean lguest_clean usb_clean virtio_clean vm_clean net_clean:
 	$(call descend,$(@:_clean=),clean)
 
-liblk_clean:
-	$(call descend,lib/lk,clean)
+libapikfs_clean:
+	$(call descend,lib/api,clean)
 
-perf_clean: liblk_clean
+perf_clean: libapikfs_clean
 	$(call descend,$(@:_clean=),clean)
 
 selftests_clean:
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
new file mode 100644
index 0000000..ed2f51e
--- /dev/null
+++ b/tools/lib/api/Makefile
@@ -0,0 +1,42 @@
+include ../../scripts/Makefile.include
+include ../../perf/config/utilities.mak		# QUIET_CLEAN
+
+CC = $(CROSS_COMPILE)gcc
+AR = $(CROSS_COMPILE)ar
+
+# guard against environment variables
+LIB_H=
+LIB_OBJS=
+
+LIB_H += fs/debugfs.h
+
+LIB_OBJS += $(OUTPUT)fs/debugfs.o
+
+LIBFILE = libapikfs.a
+
+CFLAGS = -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) -fPIC
+EXTLIBS = -lelf -lpthread -lrt -lm
+ALL_CFLAGS = $(CFLAGS) $(BASIC_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
+ALL_LDFLAGS = $(LDFLAGS)
+
+RM = rm -f
+
+$(LIBFILE): $(LIB_OBJS)
+	$(QUIET_AR)$(RM) $@ && $(AR) rcs $(OUTPUT)$@ $(LIB_OBJS)
+
+$(LIB_OBJS): $(LIB_H)
+
+libapi_dirs:
+	$(QUIET_MKDIR)mkdir -p $(OUTPUT)fs/
+
+$(OUTPUT)%.o: %.c libapi_dirs
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
+$(OUTPUT)%.s: %.c libapi_dirs
+	$(QUIET_CC)$(CC) -S $(ALL_CFLAGS) $<
+$(OUTPUT)%.o: %.S libapi_dirs
+	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
+
+clean:
+	$(call QUIET_CLEAN, libapi) $(RM) $(LIB_OBJS) $(LIBFILE)
+
+.PHONY: clean
diff --git a/tools/lib/api/fs/debugfs.c b/tools/lib/api/fs/debugfs.c
new file mode 100644
index 0000000..7c43479
--- /dev/null
+++ b/tools/lib/api/fs/debugfs.c
@@ -0,0 +1,100 @@
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdbool.h>
+#include <sys/vfs.h>
+#include <sys/mount.h>
+#include <linux/kernel.h>
+
+#include "debugfs.h"
+
+char debugfs_mountpoint[PATH_MAX + 1] = "/sys/kernel/debug";
+
+static const char * const debugfs_known_mountpoints[] = {
+	"/sys/kernel/debug/",
+	"/debug/",
+	0,
+};
+
+static bool debugfs_found;
+
+/* find the path to the mounted debugfs */
+const char *debugfs_find_mountpoint(void)
+{
+	const char * const *ptr;
+	char type[100];
+	FILE *fp;
+
+	if (debugfs_found)
+		return (const char *)debugfs_mountpoint;
+
+	ptr = debugfs_known_mountpoints;
+	while (*ptr) {
+		if (debugfs_valid_mountpoint(*ptr) == 0) {
+			debugfs_found = true;
+			strcpy(debugfs_mountpoint, *ptr);
+			return debugfs_mountpoint;
+		}
+		ptr++;
+	}
+
+	/* give up and parse /proc/mounts */
+	fp = fopen("/proc/mounts", "r");
+	if (fp == NULL)
+		return NULL;
+
+	while (fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n",
+		      debugfs_mountpoint, type) == 2) {
+		if (strcmp(type, "debugfs") == 0)
+			break;
+	}
+	fclose(fp);
+
+	if (strcmp(type, "debugfs") != 0)
+		return NULL;
+
+	debugfs_found = true;
+
+	return debugfs_mountpoint;
+}
+
+/* verify that a mountpoint is actually a debugfs instance */
+
+int debugfs_valid_mountpoint(const char *debugfs)
+{
+	struct statfs st_fs;
+
+	if (statfs(debugfs, &st_fs) < 0)
+		return -ENOENT;
+	else if (st_fs.f_type != (long) DEBUGFS_MAGIC)
+		return -ENOENT;
+
+	return 0;
+}
+
+/* mount the debugfs somewhere if it's not mounted */
+char *debugfs_mount(const char *mountpoint)
+{
+	/* see if it's already mounted */
+	if (debugfs_find_mountpoint())
+		goto out;
+
+	/* if not mounted and no argument */
+	if (mountpoint == NULL) {
+		/* see if environment variable set */
+		mountpoint = getenv(PERF_DEBUGFS_ENVIRONMENT);
+		/* if no environment variable, use default */
+		if (mountpoint == NULL)
+			mountpoint = "/sys/kernel/debug";
+	}
+
+	if (mount(NULL, mountpoint, "debugfs", 0, NULL) < 0)
+		return NULL;
+
+	/* save the mountpoint */
+	debugfs_found = true;
+	strncpy(debugfs_mountpoint, mountpoint, sizeof(debugfs_mountpoint));
+out:
+	return debugfs_mountpoint;
+}
diff --git a/tools/lib/api/fs/debugfs.h b/tools/lib/api/fs/debugfs.h
new file mode 100644
index 0000000..f19d3df
--- /dev/null
+++ b/tools/lib/api/fs/debugfs.h
@@ -0,0 +1,29 @@
+#ifndef __API_DEBUGFS_H__
+#define __API_DEBUGFS_H__
+
+#define _STR(x) #x
+#define STR(x) _STR(x)
+
+/*
+ * On most systems <limits.h> would have given us this, but  not on some systems
+ * (e.g. GNU/Hurd).
+ */
+#ifndef PATH_MAX
+#define PATH_MAX 4096
+#endif
+
+#ifndef DEBUGFS_MAGIC
+#define DEBUGFS_MAGIC          0x64626720
+#endif
+
+#ifndef PERF_DEBUGFS_ENVIRONMENT
+#define PERF_DEBUGFS_ENVIRONMENT "PERF_DEBUGFS_DIR"
+#endif
+
+const char *debugfs_find_mountpoint(void);
+int debugfs_valid_mountpoint(const char *debugfs);
+char *debugfs_mount(const char *mountpoint);
+
+extern char debugfs_mountpoint[];
+
+#endif /* __API_DEBUGFS_H__ */
diff --git a/tools/lib/lk/Makefile b/tools/lib/lk/Makefile
deleted file mode 100644
index 3dba0a4..0000000
--- a/tools/lib/lk/Makefile
+++ /dev/null
@@ -1,38 +0,0 @@
-include ../../scripts/Makefile.include
-
-CC = $(CROSS_COMPILE)gcc
-AR = $(CROSS_COMPILE)ar
-
-# guard against environment variables
-LIB_H=
-LIB_OBJS=
-
-LIB_H += debugfs.h
-
-LIB_OBJS += $(OUTPUT)debugfs.o
-
-LIBFILE = liblk.a
-
-CFLAGS = -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) -fPIC
-EXTLIBS = -lelf -lpthread -lrt -lm
-ALL_CFLAGS = $(CFLAGS) $(BASIC_CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
-ALL_LDFLAGS = $(LDFLAGS)
-
-RM = rm -f
-
-$(LIBFILE): $(LIB_OBJS)
-	$(QUIET_AR)$(RM) $@ && $(AR) rcs $(OUTPUT)$@ $(LIB_OBJS)
-
-$(LIB_OBJS): $(LIB_H)
-
-$(OUTPUT)%.o: %.c
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
-$(OUTPUT)%.s: %.c
-	$(QUIET_CC)$(CC) -S $(ALL_CFLAGS) $<
-$(OUTPUT)%.o: %.S
-	$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
-
-clean:
-	$(RM) $(LIB_OBJS) $(LIBFILE)
-
-.PHONY: clean
diff --git a/tools/lib/lk/debugfs.c b/tools/lib/lk/debugfs.c
deleted file mode 100644
index 7c43479..0000000
--- a/tools/lib/lk/debugfs.c
+++ /dev/null
@@ -1,100 +0,0 @@
-#include <errno.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <stdbool.h>
-#include <sys/vfs.h>
-#include <sys/mount.h>
-#include <linux/kernel.h>
-
-#include "debugfs.h"
-
-char debugfs_mountpoint[PATH_MAX + 1] = "/sys/kernel/debug";
-
-static const char * const debugfs_known_mountpoints[] = {
-	"/sys/kernel/debug/",
-	"/debug/",
-	0,
-};
-
-static bool debugfs_found;
-
-/* find the path to the mounted debugfs */
-const char *debugfs_find_mountpoint(void)
-{
-	const char * const *ptr;
-	char type[100];
-	FILE *fp;
-
-	if (debugfs_found)
-		return (const char *)debugfs_mountpoint;
-
-	ptr = debugfs_known_mountpoints;
-	while (*ptr) {
-		if (debugfs_valid_mountpoint(*ptr) == 0) {
-			debugfs_found = true;
-			strcpy(debugfs_mountpoint, *ptr);
-			return debugfs_mountpoint;
-		}
-		ptr++;
-	}
-
-	/* give up and parse /proc/mounts */
-	fp = fopen("/proc/mounts", "r");
-	if (fp == NULL)
-		return NULL;
-
-	while (fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n",
-		      debugfs_mountpoint, type) == 2) {
-		if (strcmp(type, "debugfs") == 0)
-			break;
-	}
-	fclose(fp);
-
-	if (strcmp(type, "debugfs") != 0)
-		return NULL;
-
-	debugfs_found = true;
-
-	return debugfs_mountpoint;
-}
-
-/* verify that a mountpoint is actually a debugfs instance */
-
-int debugfs_valid_mountpoint(const char *debugfs)
-{
-	struct statfs st_fs;
-
-	if (statfs(debugfs, &st_fs) < 0)
-		return -ENOENT;
-	else if (st_fs.f_type != (long) DEBUGFS_MAGIC)
-		return -ENOENT;
-
-	return 0;
-}
-
-/* mount the debugfs somewhere if it's not mounted */
-char *debugfs_mount(const char *mountpoint)
-{
-	/* see if it's already mounted */
-	if (debugfs_find_mountpoint())
-		goto out;
-
-	/* if not mounted and no argument */
-	if (mountpoint == NULL) {
-		/* see if environment variable set */
-		mountpoint = getenv(PERF_DEBUGFS_ENVIRONMENT);
-		/* if no environment variable, use default */
-		if (mountpoint == NULL)
-			mountpoint = "/sys/kernel/debug";
-	}
-
-	if (mount(NULL, mountpoint, "debugfs", 0, NULL) < 0)
-		return NULL;
-
-	/* save the mountpoint */
-	debugfs_found = true;
-	strncpy(debugfs_mountpoint, mountpoint, sizeof(debugfs_mountpoint));
-out:
-	return debugfs_mountpoint;
-}
diff --git a/tools/lib/lk/debugfs.h b/tools/lib/lk/debugfs.h
deleted file mode 100644
index 935c59b..0000000
--- a/tools/lib/lk/debugfs.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef __LK_DEBUGFS_H__
-#define __LK_DEBUGFS_H__
-
-#define _STR(x) #x
-#define STR(x) _STR(x)
-
-/*
- * On most systems <limits.h> would have given us this, but  not on some systems
- * (e.g. GNU/Hurd).
- */
-#ifndef PATH_MAX
-#define PATH_MAX 4096
-#endif
-
-#ifndef DEBUGFS_MAGIC
-#define DEBUGFS_MAGIC          0x64626720
-#endif
-
-#ifndef PERF_DEBUGFS_ENVIRONMENT
-#define PERF_DEBUGFS_ENVIRONMENT "PERF_DEBUGFS_DIR"
-#endif
-
-const char *debugfs_find_mountpoint(void);
-int debugfs_valid_mountpoint(const char *debugfs);
-char *debugfs_mount(const char *mountpoint);
-
-extern char debugfs_mountpoint[];
-
-#endif /* __LK_DEBUGFS_H__ */
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index fad6107..97a2145 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -86,7 +86,7 @@ FLEX    = flex
 BISON   = bison
 STRIP   = strip
 
-LK_DIR          = $(srctree)/tools/lib/lk/
+LIB_DIR          = $(srctree)/tools/lib/api/
 TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/
 
 # include config/Makefile by default and rule out
@@ -127,20 +127,20 @@ strip-libs = $(filter-out -l%,$(1))
 ifneq ($(OUTPUT),)
   TE_PATH=$(OUTPUT)
 ifneq ($(subdir),)
-  LK_PATH=$(OUTPUT)/../lib/lk/
+  LIB_PATH=$(OUTPUT)/../lib/api/
 else
-  LK_PATH=$(OUTPUT)
+  LIB_PATH=$(OUTPUT)
 endif
 else
   TE_PATH=$(TRACE_EVENT_DIR)
-  LK_PATH=$(LK_DIR)
+  LIB_PATH=$(LIB_DIR)
 endif
 
 LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
 export LIBTRACEEVENT
 
-LIBLK = $(LK_PATH)liblk.a
-export LIBLK
+LIBAPIKFS = $(LIB_PATH)libapikfs.a
+export LIBAPIKFS
 
 # python extension build directories
 PYTHON_EXTBUILD     := $(OUTPUT)python_ext_build/
@@ -151,7 +151,7 @@ export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP
 python-clean := $(call QUIET_CLEAN, python) $(RM) -r $(PYTHON_EXTBUILD) $(OUTPUT)python/perf.so
 
 PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
-PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBLK)
+PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBAPIKFS)
 
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
 	$(QUIET_GEN)CFLAGS='$(CFLAGS)' $(PYTHON_WORD) util/setup.py \
@@ -441,7 +441,7 @@ BUILTIN_OBJS += $(OUTPUT)builtin-inject.o
 BUILTIN_OBJS += $(OUTPUT)tests/builtin-test.o
 BUILTIN_OBJS += $(OUTPUT)builtin-mem.o
 
-PERFLIBS = $(LIB_FILE) $(LIBLK) $(LIBTRACEEVENT)
+PERFLIBS = $(LIB_FILE) $(LIBAPIKFS) $(LIBTRACEEVENT)
 
 # We choose to avoid "if .. else if .. else .. endif endif"
 # because maintaining the nesting to match is a pain.  If
@@ -730,19 +730,19 @@ $(LIBTRACEEVENT)-clean:
 install-traceevent-plugins: $(LIBTRACEEVENT)
 	$(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) install_plugins
 
-LIBLK_SOURCES = $(wildcard $(LK_PATH)*.[ch])
+LIBAPIKFS_SOURCES = $(wildcard $(LIB_PATH)fs/*.[ch])
 
 # if subdir is set, we've been called from above so target has been built
 # already
-$(LIBLK): $(LIBLK_SOURCES)
+$(LIBAPIKFS): $(LIBAPIKFS_SOURCES)
 ifeq ($(subdir),)
-	$(QUIET_SUBDIR0)$(LK_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) liblk.a
+	$(QUIET_SUBDIR0)$(LIB_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) libapikfs.a
 endif
 
-$(LIBLK)-clean:
+$(LIBAPIKFS)-clean:
 ifeq ($(subdir),)
-	$(call QUIET_CLEAN, liblk)
-	@$(MAKE) -C $(LK_DIR) O=$(OUTPUT) clean >/dev/null
+	$(call QUIET_CLEAN, libapikfs)
+	@$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null
 endif
 
 help:
@@ -881,12 +881,11 @@ config-clean:
 	$(call QUIET_CLEAN, config)
 	@$(MAKE) -C config/feature-checks clean >/dev/null
 
-clean: $(LIBTRACEEVENT)-clean $(LIBLK)-clean config-clean
+clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean
 	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
-	$(call QUIET_CLEAN, Documentation)
-	@$(MAKE) -C Documentation O=$(OUTPUT) clean >/dev/null
+	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
 	$(python-clean)
 
 #
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index c6fa3cb..154b397 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -13,7 +13,7 @@
 #include "util/parse-options.h"
 #include "util/trace-event.h"
 #include "util/debug.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include "util/tool.h"
 #include "util/stat.h"
 #include "util/top.h"
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 6ea9e85..c98ccb5 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -37,7 +37,7 @@
 #include "util/strfilter.h"
 #include "util/symbol.h"
 #include "util/debug.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include "util/parse-options.h"
 #include "util/probe-finder.h"
 #include "util/probe-event.h"
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 8b38b4e..431798a 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -13,7 +13,7 @@
 #include "util/quote.h"
 #include "util/run-command.h"
 #include "util/parse-events.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include <pthread.h>
 
 const char perf_usage_string[] =
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 3cbd104..e4ce8ae 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -3,7 +3,7 @@
 #include "evsel.h"
 #include "evlist.h"
 #include "fs.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include "tests.h"
 #include <linux/hw_breakpoint.h>
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 0b31cee..da31829 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -7,7 +7,7 @@
  * Released under the GPL v2. (and only v2, not any later version)
  */
 #include "util.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include <poll.h>
 #include "cpumap.h"
 #include "thread_map.h"
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 7b510fd..01ff4cf 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -9,7 +9,7 @@
 
 #include <byteswap.h>
 #include <linux/bitops.h>
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include <traceevent/event-parse.h>
 #include <linux/hw_breakpoint.h>
 #include <linux/perf_event.h>
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 969cb8f..094c28b 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -10,7 +10,7 @@
 #include "symbol.h"
 #include "cache.h"
 #include "header.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include "parse-events-bison.h"
 #define YY_EXTRA_TYPE int
 #include "parse-events-flex.h"
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index d7cff57..544ac18 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -40,7 +40,7 @@
 #include "color.h"
 #include "symbol.h"
 #include "thread.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include "trace-event.h"	/* For __maybe_unused */
 #include "probe-event.h"
 #include "probe-finder.h"
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 58ea5ca..d0aee4b 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -25,7 +25,7 @@ cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter'
 build_lib = getenv('PYTHON_EXTBUILD_LIB')
 build_tmp = getenv('PYTHON_EXTBUILD_TMP')
 libtraceevent = getenv('LIBTRACEEVENT')
-liblk = getenv('LIBLK')
+libapikfs = getenv('LIBAPIKFS')
 
 ext_sources = [f.strip() for f in file('util/python-ext-sources')
 				if len(f.strip()) > 0 and f[0] != '#']
@@ -34,7 +34,7 @@ perf = Extension('perf',
 		  sources = ext_sources,
 		  include_dirs = ['util/include'],
 		  extra_compile_args = cflags,
-		  extra_objects = [libtraceevent, liblk],
+		  extra_objects = [libtraceevent, libapikfs],
                  )
 
 setup(name='perf',
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index f3c9e55..c354b95 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -38,7 +38,7 @@
 
 #include "../perf.h"
 #include "trace-event.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include "evsel.h"
 
 #define VERSION "0.5"
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index a1eea3e..9a2c268 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -71,7 +71,7 @@
 #include <linux/magic.h>
 #include "types.h"
 #include <sys/ttydefaults.h>
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 #include <termios.h>
 #include <linux/bitops.h>
 
diff --git a/tools/vm/Makefile b/tools/vm/Makefile
index 24e9ddd..3d907da 100644
--- a/tools/vm/Makefile
+++ b/tools/vm/Makefile
@@ -2,21 +2,21 @@
 #
 TARGETS=page-types slabinfo
 
-LK_DIR = ../lib/lk
-LIBLK = $(LK_DIR)/liblk.a
+LIB_DIR = ../lib/api
+LIBS = $(LIB_DIR)/libapikfs.a
 
 CC = $(CROSS_COMPILE)gcc
 CFLAGS = -Wall -Wextra -I../lib/
-LDFLAGS = $(LIBLK)
+LDFLAGS = $(LIBS)
 
-$(TARGETS): liblk
+$(TARGETS): $(LIBS)
 
-liblk:
-	make -C $(LK_DIR)
+$(LIBS):
+	make -C $(LIB_DIR)
 
 %: %.c
 	$(CC) $(CFLAGS) -o $@ $< $(LDFLAGS)
 
 clean:
 	$(RM) page-types slabinfo
-	make -C ../lib/lk clean
+	make -C $(LIB_DIR) clean
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index d5e9d6d..f9be24d 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -36,7 +36,7 @@
 #include <sys/statfs.h>
 #include "../../include/uapi/linux/magic.h"
 #include "../../include/uapi/linux/kernel-page-flags.h"
-#include <lk/debugfs.h>
+#include <api/fs/debugfs.h>
 
 #ifndef MAX_PATH
 # define MAX_PATH 256
-- 
cgit v0.10.2


From 8b6dcca017aa53fe13066411a653b5997c158a2c Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <stfomichev@yandex-team.ru>
Date: Mon, 2 Dec 2013 18:37:33 +0400
Subject: perf timechart: Add backtrace support to CPU info

Add backtrace info to the CPU usage timechart.

Signed-off-by: Stanislav Fomichev <stfomichev@yandex-team.ru>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ramkumar Ramachandra <artagnon@gmail.com>
Link: http://lkml.kernel.org/r/1385995056-20158-2-git-send-email-stfomichev@yandex-team.ru
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 0bda620..d955095 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -837,8 +837,14 @@ static void draw_cpu_usage(struct timechart *tchart)
 		while (c) {
 			sample = c->samples;
 			while (sample) {
-				if (sample->type == TYPE_RUNNING)
-					svg_process(sample->cpu, sample->start_time, sample->end_time, "sample", c->comm);
+				if (sample->type == TYPE_RUNNING) {
+					svg_process(sample->cpu,
+						    sample->start_time,
+						    sample->end_time,
+						    "sample",
+						    c->comm,
+						    sample->backtrace);
+				}
 
 				sample = sample->next;
 			}
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 8b79d3a..740f032 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -285,7 +285,7 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq)
 	fprintf(svgfile, "</g>\n");
 }
 
-void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name)
+void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name, const char *backtrace)
 {
 	double width;
 
@@ -295,6 +295,8 @@ void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name
 
 	fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), cpu2y(cpu));
 	fprintf(svgfile, "<title>%s %s</title>\n", name, time_to_string(end - start));
+	if (backtrace)
+		fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace);
 	fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
 		time2pixels(end)-time2pixels(start), SLOT_MULT+SLOT_HEIGHT, type);
 	width = time2pixels(end)-time2pixels(start);
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index fad79ce..7db6ae9 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -11,7 +11,7 @@ extern void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *back
 extern void svg_cpu_box(int cpu, u64 max_frequency, u64 turbo_frequency);
 
 
-extern void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name);
+extern void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name, const char *backtrace);
 extern void svg_cstate(int cpu, u64 start, u64 end, int type);
 extern void svg_pstate(int cpu, u64 start, u64 end, u64 freq);
 
-- 
cgit v0.10.2


From de996228dedc74d9e72b749bbc8225f5e2bf19d8 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <stfomichev@yandex-team.ru>
Date: Mon, 2 Dec 2013 18:37:34 +0400
Subject: perf timechart: Print pid along the name

Add PID to the figures of CPU usage timechart.

Signed-off-by: Stanislav Fomichev <stfomichev@yandex-team.ru>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ramkumar Ramachandra <artagnon@gmail.com>
Link: http://lkml.kernel.org/r/1385995056-20158-3-git-send-email-stfomichev@yandex-team.ru
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index d955095..99fe363 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -841,6 +841,7 @@ static void draw_cpu_usage(struct timechart *tchart)
 					svg_process(sample->cpu,
 						    sample->start_time,
 						    sample->end_time,
+						    p->pid,
 						    "sample",
 						    c->comm,
 						    sample->backtrace);
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 740f032..927851d 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -285,7 +285,7 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq)
 	fprintf(svgfile, "</g>\n");
 }
 
-void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name, const char *backtrace)
+void svg_process(int cpu, u64 start, u64 end, int pid, const char *type, const char *name, const char *backtrace)
 {
 	double width;
 
@@ -294,7 +294,7 @@ void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name
 
 
 	fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), cpu2y(cpu));
-	fprintf(svgfile, "<title>%s %s</title>\n", name, time_to_string(end - start));
+	fprintf(svgfile, "<title>%d %s running %s</title>\n", pid, name, time_to_string(end - start));
 	if (backtrace)
 		fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace);
 	fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index 7db6ae9..8b77ca6 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -11,7 +11,7 @@ extern void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *back
 extern void svg_cpu_box(int cpu, u64 max_frequency, u64 turbo_frequency);
 
 
-extern void svg_process(int cpu, u64 start, u64 end, const char *type, const char *name, const char *backtrace);
+extern void svg_process(int cpu, u64 start, u64 end, int pid, const char *type, const char *name, const char *backtrace);
 extern void svg_cstate(int cpu, u64 start, u64 end, int type);
 extern void svg_pstate(int cpu, u64 start, u64 end, u64 freq);
 
-- 
cgit v0.10.2


From 58b9a18ecd251cbd6e666ad792023ab77c7d100e Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <stfomichev@yandex-team.ru>
Date: Mon, 2 Dec 2013 18:37:35 +0400
Subject: perf timechart: Get number of CPUs from perf header

Print all CPUs, even if there were no events (use perf header to get
number of CPUs).

This is required to support topology in the next patch.

Signed-off-by: Stanislav Fomichev <stfomichev@yandex-team.ru>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ramkumar Ramachandra <artagnon@gmail.com>
Link: http://lkml.kernel.org/r/1385995056-20158-4-git-send-email-stfomichev@yandex-team.ru
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 99fe363..db9c4c1 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -531,12 +531,10 @@ static int process_sample_event(struct perf_tool *tool,
 			tchart->last_time = sample->time;
 	}
 
-	if (sample->cpu > tchart->numcpus)
-		tchart->numcpus = sample->cpu;
-
 	if (evsel->handler != NULL) {
 		tracepoint_handler f = evsel->handler;
-		return f(tchart, evsel, sample, cat_backtrace(event, sample, machine));
+		return f(tchart, evsel, sample,
+			 cat_backtrace(event, sample, machine));
 	}
 
 	return 0;
@@ -1038,8 +1036,6 @@ static void write_svg_file(struct timechart *tchart, const char *filename)
 	int count;
 	int thresh = TIME_THRESH;
 
-	tchart->numcpus++;
-
 	if (tchart->power_only)
 		tchart->proc_num = 0;
 
@@ -1069,6 +1065,25 @@ static void write_svg_file(struct timechart *tchart, const char *filename)
 	svg_close();
 }
 
+static int process_header(struct perf_file_section *section __maybe_unused,
+			  struct perf_header *ph,
+			  int feat,
+			  int fd __maybe_unused,
+			  void *data)
+{
+	struct timechart *tchart = data;
+
+	switch (feat) {
+	case HEADER_NRCPUS:
+		tchart->numcpus = ph->env.nr_cpus_avail;
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 static int __cmd_timechart(struct timechart *tchart, const char *output_name)
 {
 	const struct perf_evsel_str_handler power_tracepoints[] = {
@@ -1094,6 +1109,11 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
 	if (session == NULL)
 		return -ENOMEM;
 
+	(void)perf_header__process_sections(&session->header,
+					    perf_data_file__fd(session->file),
+					    tchart,
+					    process_header);
+
 	if (!perf_session__has_traces(session, "timechart record"))
 		goto out_delete;
 
-- 
cgit v0.10.2


From c507999790438cde78b5618fa64daefd697035af Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <stfomichev@yandex-team.ru>
Date: Mon, 2 Dec 2013 18:37:36 +0400
Subject: perf timechart: Add support for topology

Add -t switch to sort CPUs topologically.

Signed-off-by: Stanislav Fomichev <stfomichev@yandex-team.ru>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ramkumar Ramachandra <artagnon@gmail.com>
Link: http://lkml.kernel.org/r/1385995056-20158-5-git-send-email-stfomichev@yandex-team.ru
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index 271dd4e..367c1be 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -59,6 +59,9 @@ $ perf timechart
 -n::
 --proc-num::
         Print task info for at least given number of tasks.
+-t::
+--topology::
+        Sort CPUs according to topology.
 
 RECORD OPTIONS
 --------------
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index db9c4c1..8bde57c 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -58,7 +58,8 @@ struct timechart {
 				first_time, last_time;
 	bool			power_only,
 				tasks_only,
-				with_backtrace;
+				with_backtrace,
+				topology;
 };
 
 struct per_pidcomm;
@@ -1077,6 +1078,18 @@ static int process_header(struct perf_file_section *section __maybe_unused,
 	case HEADER_NRCPUS:
 		tchart->numcpus = ph->env.nr_cpus_avail;
 		break;
+
+	case HEADER_CPU_TOPOLOGY:
+		if (!tchart->topology)
+			break;
+
+		if (svg_build_topology_map(ph->env.sibling_cores,
+					   ph->env.nr_sibling_cores,
+					   ph->env.sibling_threads,
+					   ph->env.nr_sibling_threads))
+			fprintf(stderr, "problem building topology\n");
+		break;
+
 	default:
 		break;
 	}
@@ -1267,6 +1280,8 @@ int cmd_timechart(int argc, const char **argv,
 		    "Look for files with symbols relative to this directory"),
 	OPT_INTEGER('n', "proc-num", &tchart.proc_num,
 		    "min. number of tasks to print"),
+	OPT_BOOLEAN('t', "topology", &tchart.topology,
+		    "sort CPUs according to topology"),
 	OPT_END()
 	};
 	const char * const timechart_usage[] = {
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 927851d..9468136 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -17,8 +17,11 @@
 #include <stdlib.h>
 #include <unistd.h>
 #include <string.h>
+#include <linux/bitops.h>
 
+#include "perf.h"
 #include "svghelper.h"
+#include "cpumap.h"
 
 static u64 first_time, last_time;
 static u64 turbo_frequency, max_freq;
@@ -39,9 +42,14 @@ static double cpu2slot(int cpu)
 	return 2 * cpu + 1;
 }
 
+static int *topology_map;
+
 static double cpu2y(int cpu)
 {
-	return cpu2slot(cpu) * SLOT_MULT;
+	if (topology_map)
+		return cpu2slot(topology_map[cpu]) * SLOT_MULT;
+	else
+		return cpu2slot(cpu) * SLOT_MULT;
 }
 
 static double time2pixels(u64 __time)
@@ -275,7 +283,7 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq)
 		time2pixels(last_time)-time2pixels(first_time),
 		cpu2y(cpu), SLOT_MULT+SLOT_HEIGHT);
 
-	sprintf(cpu_string, "CPU %i", (int)cpu+1);
+	sprintf(cpu_string, "CPU %i", (int)cpu);
 	fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\">%s</text>\n",
 		10+time2pixels(first_time), cpu2y(cpu) + SLOT_HEIGHT/2, cpu_string);
 
@@ -568,3 +576,123 @@ void svg_close(void)
 		svgfile = NULL;
 	}
 }
+
+#define cpumask_bits(maskp) ((maskp)->bits)
+typedef struct { DECLARE_BITMAP(bits, MAX_NR_CPUS); } cpumask_t;
+
+struct topology {
+	cpumask_t *sib_core;
+	int sib_core_nr;
+	cpumask_t *sib_thr;
+	int sib_thr_nr;
+};
+
+static void scan_thread_topology(int *map, struct topology *t, int cpu, int *pos)
+{
+	int i;
+	int thr;
+
+	for (i = 0; i < t->sib_thr_nr; i++) {
+		if (!test_bit(cpu, cpumask_bits(&t->sib_thr[i])))
+			continue;
+
+		for_each_set_bit(thr,
+				 cpumask_bits(&t->sib_thr[i]),
+				 MAX_NR_CPUS)
+			if (map[thr] == -1)
+				map[thr] = (*pos)++;
+	}
+}
+
+static void scan_core_topology(int *map, struct topology *t)
+{
+	int pos = 0;
+	int i;
+	int cpu;
+
+	for (i = 0; i < t->sib_core_nr; i++)
+		for_each_set_bit(cpu,
+				 cpumask_bits(&t->sib_core[i]),
+				 MAX_NR_CPUS)
+			scan_thread_topology(map, t, cpu, &pos);
+}
+
+static int str_to_bitmap(char *s, cpumask_t *b)
+{
+	int i;
+	int ret = 0;
+	struct cpu_map *m;
+	int c;
+
+	m = cpu_map__new(s);
+	if (!m)
+		return -1;
+
+	for (i = 0; i < m->nr; i++) {
+		c = m->map[i];
+		if (c >= MAX_NR_CPUS) {
+			ret = -1;
+			break;
+		}
+
+		set_bit(c, cpumask_bits(b));
+	}
+
+	cpu_map__delete(m);
+
+	return ret;
+}
+
+int svg_build_topology_map(char *sib_core, int sib_core_nr,
+			   char *sib_thr, int sib_thr_nr)
+{
+	int i;
+	struct topology t;
+
+	t.sib_core_nr = sib_core_nr;
+	t.sib_thr_nr = sib_thr_nr;
+	t.sib_core = calloc(sib_core_nr, sizeof(cpumask_t));
+	t.sib_thr = calloc(sib_thr_nr, sizeof(cpumask_t));
+
+	if (!t.sib_core || !t.sib_thr) {
+		fprintf(stderr, "topology: no memory\n");
+		goto exit;
+	}
+
+	for (i = 0; i < sib_core_nr; i++) {
+		if (str_to_bitmap(sib_core, &t.sib_core[i])) {
+			fprintf(stderr, "topology: can't parse siblings map\n");
+			goto exit;
+		}
+
+		sib_core += strlen(sib_core) + 1;
+	}
+
+	for (i = 0; i < sib_thr_nr; i++) {
+		if (str_to_bitmap(sib_thr, &t.sib_thr[i])) {
+			fprintf(stderr, "topology: can't parse siblings map\n");
+			goto exit;
+		}
+
+		sib_thr += strlen(sib_thr) + 1;
+	}
+
+	topology_map = malloc(sizeof(int) * MAX_NR_CPUS);
+	if (!topology_map) {
+		fprintf(stderr, "topology: no memory\n");
+		goto exit;
+	}
+
+	for (i = 0; i < MAX_NR_CPUS; i++)
+		topology_map[i] = -1;
+
+	scan_core_topology(topology_map, &t);
+
+	return 0;
+
+exit:
+	free(t.sib_core);
+	free(t.sib_thr);
+
+	return -1;
+}
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index 8b77ca6..1df4fb6 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -23,6 +23,8 @@ extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, cha
 extern void svg_interrupt(u64 start, int row, const char *backtrace);
 extern void svg_text(int Yslot, u64 start, const char *text);
 extern void svg_close(void);
+extern int svg_build_topology_map(char *sib_core, int sib_core_nr,
+				  char *sib_thr, int sib_thr_nr);
 
 extern int svg_page_width;
 
-- 
cgit v0.10.2


From 631d34b5626a8de828f3ab8da54013293097e678 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 16 Dec 2013 16:57:43 -0300
Subject: perf symbols: Remove needless static binary_type array

There are no references to that array anywhere, it is only used to try
a series of "binary" types in turn, always setting dso->data_type till
one can be used.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-4mw7xrbs12tln6v2uthg7sqc@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 436922f..e7f4449 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -161,7 +161,7 @@ static int open_dso(struct dso *dso, struct machine *machine)
 
 int dso__data_fd(struct dso *dso, struct machine *machine)
 {
-	static enum dso_binary_type binary_type_data[] = {
+	enum dso_binary_type binary_type_data[] = {
 		DSO_BINARY_TYPE__BUILD_ID_CACHE,
 		DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
 		DSO_BINARY_TYPE__NOT_FOUND,
-- 
cgit v0.10.2


From ee4e9625c8d4ec3a35322a882f7b6e035d2a1ad5 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 16 Dec 2013 17:03:18 -0300
Subject: perf symbols: Clarify method to get DSO binary_type filename

Using dso__binary_type_file() make it look like this function will
return a file, not just its filename, so rename it to:

	dso__read_binary_type_filename()

to make its purpose clear, just like we have:

	dso__read_running_kernel_build_id()

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-vkf3upzrfrxtr01wueej4xw4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index e7f4449..eef1662 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -28,8 +28,9 @@ char dso__symtab_origin(const struct dso *dso)
 	return origin[dso->symtab_type];
 }
 
-int dso__binary_type_file(const struct dso *dso, enum dso_binary_type type,
-			  char *root_dir, char *filename, size_t size)
+int dso__read_binary_type_filename(const struct dso *dso,
+				   enum dso_binary_type type,
+				   char *root_dir, char *filename, size_t size)
 {
 	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
 	int ret = 0;
@@ -137,19 +138,18 @@ int dso__binary_type_file(const struct dso *dso, enum dso_binary_type type,
 
 static int open_dso(struct dso *dso, struct machine *machine)
 {
-	char *root_dir = (char *) "";
-	char *name;
 	int fd;
+	char *root_dir = (char *)"";
+	char *name = malloc(PATH_MAX);
 
-	name = malloc(PATH_MAX);
 	if (!name)
 		return -ENOMEM;
 
 	if (machine)
 		root_dir = machine->root_dir;
 
-	if (dso__binary_type_file(dso, dso->data_type,
-				  root_dir, name, PATH_MAX)) {
+	if (dso__read_binary_type_filename(dso, dso->data_type,
+					    root_dir, name, PATH_MAX)) {
 		free(name);
 		return -EINVAL;
 	}
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index e1cc506..aa33847 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -128,8 +128,8 @@ void dso__read_running_kernel_build_id(struct dso *dso,
 int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir);
 
 char dso__symtab_origin(const struct dso *dso);
-int dso__binary_type_file(const struct dso *dso, enum dso_binary_type type,
-			  char *root_dir, char *filename, size_t size);
+int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
+				   char *root_dir, char *filename, size_t size);
 
 int dso__data_fd(struct dso *dso, struct machine *machine);
 ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 61eb1cd..9ee4b80 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1258,8 +1258,8 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 
 		enum dso_binary_type symtab_type = binary_type_symtab[i];
 
-		if (dso__binary_type_file(dso, symtab_type,
-					  root_dir, name, PATH_MAX))
+		if (dso__read_binary_type_filename(dso, symtab_type,
+						   root_dir, name, PATH_MAX))
 			continue;
 
 		/* Name is now the name of the next image to try */
-- 
cgit v0.10.2


From c0e30763f7ef9c7b7ff663204c9439bdbcac72ca Mon Sep 17 00:00:00 2001
From: Javier Lopez <jlopex@cozybit.com>
Date: Mon, 16 Dec 2013 10:01:07 -0800
Subject: mac80211_hwsim: Fix NULL pointer dereference

mac80211_hwsim was crashing when receiving tx information from user
space. Crash happens because txi->rate_driver_data[0] is pointing to a
non valid memory address.

This code path is only used by wmediumd and wmediumd doesn't provide
multiple channel support, so we can pass the channel struct
(data2->channel) directly to mac80211_hwsim_monitor_ack function.

Signed-off-by: Javier Lopez <jlopex@cozybit.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index c72438b..a1b32ee 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -2011,7 +2011,7 @@ static int hwsim_tx_info_frame_received_nl(struct sk_buff *skb_2,
 	   (hwsim_flags & HWSIM_TX_STAT_ACK)) {
 		if (skb->len >= 16) {
 			hdr = (struct ieee80211_hdr *) skb->data;
-			mac80211_hwsim_monitor_ack(txi->rate_driver_data[0],
+			mac80211_hwsim_monitor_ack(data2->channel,
 						   hdr->addr2);
 		}
 		txi->flags |= IEEE80211_TX_STAT_ACK;
-- 
cgit v0.10.2


From 277d916fc2e959c3f106904116bb4f7b1148d47a Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@openwrt.org>
Date: Mon, 16 Dec 2013 21:39:50 +0100
Subject: mac80211: move "bufferable MMPDU" check to fix AP mode scan

The check needs to apply to both multicast and unicast packets,
otherwise probe requests on AP mode scans are sent through the multicast
buffer queue, which adds long delays (often longer than the scanning
interval).

Cc: stable@vger.kernel.org
Signed-off-by: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index c558b24..ca7fa7f 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -463,7 +463,6 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 {
 	struct sta_info *sta = tx->sta;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data;
 	struct ieee80211_local *local = tx->local;
 
 	if (unlikely(!sta))
@@ -474,15 +473,6 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 		     !(info->flags & IEEE80211_TX_CTL_NO_PS_BUFFER))) {
 		int ac = skb_get_queue_mapping(tx->skb);
 
-		/* only deauth, disassoc and action are bufferable MMPDUs */
-		if (ieee80211_is_mgmt(hdr->frame_control) &&
-		    !ieee80211_is_deauth(hdr->frame_control) &&
-		    !ieee80211_is_disassoc(hdr->frame_control) &&
-		    !ieee80211_is_action(hdr->frame_control)) {
-			info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER;
-			return TX_CONTINUE;
-		}
-
 		ps_dbg(sta->sdata, "STA %pM aid %d: PS buffer for AC %d\n",
 		       sta->sta.addr, sta->sta.aid, ac);
 		if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER)
@@ -525,9 +515,22 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 static ieee80211_tx_result debug_noinline
 ieee80211_tx_h_ps_buf(struct ieee80211_tx_data *tx)
 {
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data;
+
 	if (unlikely(tx->flags & IEEE80211_TX_PS_BUFFERED))
 		return TX_CONTINUE;
 
+	/* only deauth, disassoc and action are bufferable MMPDUs */
+	if (ieee80211_is_mgmt(hdr->frame_control) &&
+	    !ieee80211_is_deauth(hdr->frame_control) &&
+	    !ieee80211_is_disassoc(hdr->frame_control) &&
+	    !ieee80211_is_action(hdr->frame_control)) {
+		if (tx->flags & IEEE80211_TX_UNICAST)
+			info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER;
+		return TX_CONTINUE;
+	}
+
 	if (tx->flags & IEEE80211_TX_UNICAST)
 		return ieee80211_tx_h_unicast_ps_buf(tx);
 	else
-- 
cgit v0.10.2


From 1bc5ad168f441f6f8bfd944288a5f7b4963ac1f6 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 17 Dec 2013 03:21:25 -0800
Subject: Bluetooth: Fix HCI User Channel permission check in hci_sock_sendmsg

The HCI User Channel is an admin operation which enforces CAP_NET_ADMIN
when binding the socket. Problem now is that it then requires also
CAP_NET_RAW when calling into hci_sock_sendmsg. This is not intended
and just an oversight since general HCI sockets (which do not require
special permission to bind) and HCI User Channel share the same code
path here.

Remove the extra CAP_NET_RAW check for HCI User Channel write operation
since the permission check has already been enforced when binding the
socket. This also makes it possible to open HCI User Channel from a
privileged process and then hand the file descriptor to an unprivilged
process.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Tested-by: Samuel Ortiz <sameo@linux.intel.com>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>

diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 71f0be1..73bf644 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -942,8 +942,22 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	bt_cb(skb)->pkt_type = *((unsigned char *) skb->data);
 	skb_pull(skb, 1);
 
-	if (hci_pi(sk)->channel == HCI_CHANNEL_RAW &&
-	    bt_cb(skb)->pkt_type == HCI_COMMAND_PKT) {
+	if (hci_pi(sk)->channel == HCI_CHANNEL_USER) {
+		/* No permission check is needed for user channel
+		 * since that gets enforced when binding the socket.
+		 *
+		 * However check that the packet type is valid.
+		 */
+		if (bt_cb(skb)->pkt_type != HCI_COMMAND_PKT &&
+		    bt_cb(skb)->pkt_type != HCI_ACLDATA_PKT &&
+		    bt_cb(skb)->pkt_type != HCI_SCODATA_PKT) {
+			err = -EINVAL;
+			goto drop;
+		}
+
+		skb_queue_tail(&hdev->raw_q, skb);
+		queue_work(hdev->workqueue, &hdev->tx_work);
+	} else if (bt_cb(skb)->pkt_type == HCI_COMMAND_PKT) {
 		u16 opcode = get_unaligned_le16(skb->data);
 		u16 ogf = hci_opcode_ogf(opcode);
 		u16 ocf = hci_opcode_ocf(opcode);
@@ -974,14 +988,6 @@ static int hci_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 			goto drop;
 		}
 
-		if (hci_pi(sk)->channel == HCI_CHANNEL_USER &&
-		    bt_cb(skb)->pkt_type != HCI_COMMAND_PKT &&
-		    bt_cb(skb)->pkt_type != HCI_ACLDATA_PKT &&
-		    bt_cb(skb)->pkt_type != HCI_SCODATA_PKT) {
-			err = -EINVAL;
-			goto drop;
-		}
-
 		skb_queue_tail(&hdev->raw_q, skb);
 		queue_work(hdev->workqueue, &hdev->tx_work);
 	}
-- 
cgit v0.10.2


From 7fd565e27547c913b83b46d94662103be81a88ec Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Mon, 16 Dec 2013 21:20:23 +0100
Subject: perf/x86: enable Haswell Celeron RAPL support

Enable RAPL support for Haswell Celeron (model 69).

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: ak@linux.intel.com
Cc: acme@redhat.com
Cc: jolsa@redhat.com
Cc: zheng.z.yan@intel.com
Cc: bp@alien8.de
Cc: vincent.weaver@maine.edu
Cc: maria.n.dimakopoulou@gmail.com
Cc: peterz@infradead.org
Link: http://lkml.kernel.org/r/1387225224-27799-2-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index bf8e4a7..0e3754e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -615,6 +615,7 @@ static int __init rapl_pmu_init(void)
 	case 42: /* Sandy Bridge */
 	case 58: /* Ivy Bridge */
 	case 60: /* Haswell */
+	case 69: /* Haswell-Celeron */
 		rapl_cntr_mask = RAPL_IDX_CLN;
 		rapl_pmu_events_group.attrs = rapl_events_cln_attr;
 		break;
-- 
cgit v0.10.2


From bad7192b842c83e580747ca57104dd51fe08c223 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 27 Nov 2013 13:54:38 +0000
Subject: perf: Fix PERF_EVENT_IOC_PERIOD to force-reset the period

Vince Weaver reports that, on all architectures apart from ARM,
PERF_EVENT_IOC_PERIOD doesn't actually update the period until the next
event fires. This is counter-intuitive behaviour and is better dealt
with in the core code.

This patch ensures that the period is forcefully reset when dealing with
such a request in the core code. A subsequent patch removes the
equivalent hack from the ARM back-end.

Reported-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Link: http://lkml.kernel.org/r/1385560479-11014-1-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 403b781..89d34f9 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3527,7 +3527,7 @@ static void perf_event_for_each(struct perf_event *event,
 static int perf_event_period(struct perf_event *event, u64 __user *arg)
 {
 	struct perf_event_context *ctx = event->ctx;
-	int ret = 0;
+	int ret = 0, active;
 	u64 value;
 
 	if (!is_sampling_event(event))
@@ -3551,6 +3551,20 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 		event->attr.sample_period = value;
 		event->hw.sample_period = value;
 	}
+
+	active = (event->state == PERF_EVENT_STATE_ACTIVE);
+	if (active) {
+		perf_pmu_disable(ctx->pmu);
+		event->pmu->stop(event, PERF_EF_UPDATE);
+	}
+
+	local64_set(&event->hw.period_left, 0);
+
+	if (active) {
+		event->pmu->start(event, PERF_EF_RELOAD);
+		perf_pmu_enable(ctx->pmu);
+	}
+
 unlock:
 	raw_spin_unlock_irq(&ctx->lock);
 
-- 
cgit v0.10.2


From 9450d14fb959336803e5209119eb422b667b96aa Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Wed, 27 Nov 2013 13:54:39 +0000
Subject: Revert "ARM: 7556/1: perf: fix updated event period in response to
 PERF_EVENT_IOC_PERIOD"

This reverts commit 3581fe0ef37ce12ac7a4f74831168352ae848edc.

Fixes to the handling of PERF_EVENT_IOC_PERIOD in the core code mean
we no longer have to play this horrible game.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1385560479-11014-2-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index bc3f2ef..789d846 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -99,10 +99,6 @@ int armpmu_event_set_period(struct perf_event *event)
 	s64 period = hwc->sample_period;
 	int ret = 0;
 
-	/* The period may have been changed by PERF_EVENT_IOC_PERIOD */
-	if (unlikely(period != hwc->last_period))
-		left = period - (hwc->last_period - left);
-
 	if (unlikely(left <= -period)) {
 		left = period;
 		local64_set(&hwc->period_left, left);
-- 
cgit v0.10.2


From 1bd53a7efdc988163ec4c25f656df38dbe500632 Mon Sep 17 00:00:00 2001
From: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Date: Thu, 12 Dec 2013 15:23:23 +0800
Subject: sched/numa: Drop sysctl_numa_balancing_settle_count sysctl

commit 887c290e (sched/numa: Decide whether to favour task or group weights
based on swap candidate relationships) drop the check against
sysctl_numa_balancing_settle_count, this patch remove the sysctl.

Signed-off-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Link: http://lkml.kernel.org/r/1386833006-6600-1-git-send-email-liwanp@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 26b7ee4..6d48640 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -428,11 +428,6 @@ rate for each task.
 numa_balancing_scan_size_mb is how many megabytes worth of pages are
 scanned for a given scan.
 
-numa_balancing_settle_count is how many scan periods must complete before
-the schedule balancer stops pushing the task towards a preferred node. This
-gives the scheduler a chance to place the task on an alternative node if the
-preferred node is overloaded.
-
 numa_balancing_migrate_deferred is how many page migrations get skipped
 unconditionally, after a page migration is skipped because a page is shared
 with other tasks. This reduces page migration overhead, and determines
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 41467f8..31e0193 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -48,7 +48,6 @@ extern unsigned int sysctl_numa_balancing_scan_delay;
 extern unsigned int sysctl_numa_balancing_scan_period_min;
 extern unsigned int sysctl_numa_balancing_scan_period_max;
 extern unsigned int sysctl_numa_balancing_scan_size;
-extern unsigned int sysctl_numa_balancing_settle_count;
 
 #ifdef CONFIG_SCHED_DEBUG
 extern unsigned int sysctl_sched_migration_cost;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a9185f7..fcb6c17 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -872,15 +872,6 @@ static unsigned int task_scan_max(struct task_struct *p)
 	return max(smin, smax);
 }
 
-/*
- * Once a preferred node is selected the scheduler balancer will prefer moving
- * a task to that node for sysctl_numa_balancing_settle_count number of PTE
- * scans. This will give the process the chance to accumulate more faults on
- * the preferred node but still allow the scheduler to move the task again if
- * the nodes CPUs are overloaded.
- */
-unsigned int sysctl_numa_balancing_settle_count __read_mostly = 4;
-
 static void account_numa_enqueue(struct rq *rq, struct task_struct *p)
 {
 	rq->nr_numa_running += (p->numa_preferred_nid != -1);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 34a6047..c8da99f 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -385,13 +385,6 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 	{
-		.procname       = "numa_balancing_settle_count",
-		.data           = &sysctl_numa_balancing_settle_count,
-		.maxlen         = sizeof(unsigned int),
-		.mode           = 0644,
-		.proc_handler   = proc_dointvec,
-	},
-	{
 		.procname       = "numa_balancing_migrate_deferred",
 		.data           = &sysctl_numa_balancing_migrate_deferred,
 		.maxlen         = sizeof(unsigned int),
-- 
cgit v0.10.2


From de1b301a19754778ddd9f908d266ffe1c010b2cf Mon Sep 17 00:00:00 2001
From: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Date: Thu, 12 Dec 2013 15:23:24 +0800
Subject: sched/numa: Use wrapper function task_node to get node which task is
 on

Use wrapper function task_node to get node which task is on.

Signed-off-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1386833006-6600-2-git-send-email-liwanp@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 5c34d18..374fe04 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -139,7 +139,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 		0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
 #endif
 #ifdef CONFIG_NUMA_BALANCING
-	SEQ_printf(m, " %d", cpu_to_node(task_cpu(p)));
+	SEQ_printf(m, " %d", task_node(p));
 #endif
 #ifdef CONFIG_CGROUP_SCHED
 	SEQ_printf(m, " %s", task_group_path(task_group(p)));
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fcb6c17..ebdb08b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1202,7 +1202,7 @@ static int task_numa_migrate(struct task_struct *p)
 	 * elsewhere, so there is no point in (re)trying.
 	 */
 	if (unlikely(!sd)) {
-		p->numa_preferred_nid = cpu_to_node(task_cpu(p));
+		p->numa_preferred_nid = task_node(p);
 		return -EINVAL;
 	}
 
@@ -1269,7 +1269,7 @@ static void numa_migrate_preferred(struct task_struct *p)
 	p->numa_migrate_retry = jiffies + HZ;
 
 	/* Success if task is already running on preferred CPU */
-	if (cpu_to_node(task_cpu(p)) == p->numa_preferred_nid)
+	if (task_node(p) == p->numa_preferred_nid)
 		return;
 
 	/* Otherwise, try migrate to a CPU on the preferred node */
-- 
cgit v0.10.2


From 82897b4fd3920ffd2456731d4f2ae1406558ef4c Mon Sep 17 00:00:00 2001
From: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Date: Thu, 12 Dec 2013 15:23:25 +0800
Subject: sched/numa: Use wrapper function task_faults_idx to calculate index
 in group_faults

Use wrapper function task_faults_idx to calculate index in group_faults.

Signed-off-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Rik van Riel <riel@redhat.com>
Link: http://lkml.kernel.org/r/1386833006-6600-3-git-send-email-liwanp@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ebdb08b..37892d7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -921,7 +921,8 @@ static inline unsigned long group_faults(struct task_struct *p, int nid)
 	if (!p->numa_group)
 		return 0;
 
-	return p->numa_group->faults[2*nid] + p->numa_group->faults[2*nid+1];
+	return p->numa_group->faults[task_faults_idx(nid, 0)] +
+		p->numa_group->faults[task_faults_idx(nid, 1)];
 }
 
 /*
-- 
cgit v0.10.2


From e777b63bbd589248eb151a3191ee92331a701385 Mon Sep 17 00:00:00 2001
From: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Date: Thu, 12 Dec 2013 15:23:26 +0800
Subject: sched/numa: Fix period_slot recalculation

The original code is as intended and was meant to scale the difference
between the NUMA_PERIOD_THRESHOLD and local/remote ratio when adjusting
the scan period. The period_slot recalculation can be dropped.

Signed-off-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: David Rientjes <rientjes@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Rik van Riel <riel@redhat.com>
Link: http://lkml.kernel.org/r/1386833006-6600-4-git-send-email-liwanp@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 37892d7..4316af2 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1342,7 +1342,6 @@ static void update_task_scan_period(struct task_struct *p,
 		 * scanning faster if shared accesses dominate as it may
 		 * simply bounce migrations uselessly
 		 */
-		period_slot = DIV_ROUND_UP(diff, NUMA_PERIOD_SLOTS);
 		ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared));
 		diff = (diff * ratio) / NUMA_PERIOD_SLOTS;
 	}
-- 
cgit v0.10.2


From 91f30a17024ff0d8345e11228af33ee938b13426 Mon Sep 17 00:00:00 2001
From: Chuansheng Liu <chuansheng.liu@intel.com>
Date: Wed, 4 Dec 2013 13:58:13 +0800
Subject: mutexes: Give more informative mutex warning in the !lock->owner case

When mutex debugging is enabled and an imbalanced mutex_unlock()
is called, we get the following, slightly confusing warning:

  [  364.208284] DEBUG_LOCKS_WARN_ON(lock->owner != current)

But in that case the warning is due to an imbalanced mutex_unlock() call,
and the lock->owner is NULL - so the message is misleading.

So improve the message by testing for this case specifically:

   DEBUG_LOCKS_WARN_ON(!lock->owner)

Signed-off-by: Liu, Chuansheng <chuansheng.liu@intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1386136693.3650.48.camel@cliu38-desktop-build
[ Improved the changelog, changed the patch to use !lock->owner consistently. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 7e3443f..faf6f5b 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -75,7 +75,12 @@ void debug_mutex_unlock(struct mutex *lock)
 		return;
 
 	DEBUG_LOCKS_WARN_ON(lock->magic != lock);
-	DEBUG_LOCKS_WARN_ON(lock->owner != current);
+
+	if (!lock->owner)
+		DEBUG_LOCKS_WARN_ON(!lock->owner);
+	else
+		DEBUG_LOCKS_WARN_ON(lock->owner != current);
+
 	DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next);
 	mutex_clear_owner(lock);
 }
-- 
cgit v0.10.2


From 657eb17d87852c42b55c4b06d5425baa08b2ddb3 Mon Sep 17 00:00:00 2001
From: Mathy Vanhoef <vanhoefm@gmail.com>
Date: Thu, 28 Nov 2013 12:21:45 +0100
Subject: ath9k_htc: properly set MAC address and BSSID mask

Pick the MAC address of the first virtual interface as the new hardware MAC
address. Set BSSID mask according to this MAC address. This fixes CVE-2013-4579.

Signed-off-by: Mathy Vanhoef <vanhoefm@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>

diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
index 9a2657f..608d739 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
@@ -127,21 +127,26 @@ static void ath9k_htc_bssid_iter(void *data, u8 *mac, struct ieee80211_vif *vif)
 	struct ath9k_vif_iter_data *iter_data = data;
 	int i;
 
-	for (i = 0; i < ETH_ALEN; i++)
-		iter_data->mask[i] &= ~(iter_data->hw_macaddr[i] ^ mac[i]);
+	if (iter_data->hw_macaddr != NULL) {
+		for (i = 0; i < ETH_ALEN; i++)
+			iter_data->mask[i] &= ~(iter_data->hw_macaddr[i] ^ mac[i]);
+	} else {
+		iter_data->hw_macaddr = mac;
+	}
 }
 
-static void ath9k_htc_set_bssid_mask(struct ath9k_htc_priv *priv,
+static void ath9k_htc_set_mac_bssid_mask(struct ath9k_htc_priv *priv,
 				     struct ieee80211_vif *vif)
 {
 	struct ath_common *common = ath9k_hw_common(priv->ah);
 	struct ath9k_vif_iter_data iter_data;
 
 	/*
-	 * Use the hardware MAC address as reference, the hardware uses it
-	 * together with the BSSID mask when matching addresses.
+	 * Pick the MAC address of the first interface as the new hardware
+	 * MAC address. The hardware will use it together with the BSSID mask
+	 * when matching addresses.
 	 */
-	iter_data.hw_macaddr = common->macaddr;
+	iter_data.hw_macaddr = NULL;
 	memset(&iter_data.mask, 0xff, ETH_ALEN);
 
 	if (vif)
@@ -153,6 +158,10 @@ static void ath9k_htc_set_bssid_mask(struct ath9k_htc_priv *priv,
 		ath9k_htc_bssid_iter, &iter_data);
 
 	memcpy(common->bssidmask, iter_data.mask, ETH_ALEN);
+
+	if (iter_data.hw_macaddr)
+		memcpy(common->macaddr, iter_data.hw_macaddr, ETH_ALEN);
+
 	ath_hw_setbssidmask(common);
 }
 
@@ -1063,7 +1072,7 @@ static int ath9k_htc_add_interface(struct ieee80211_hw *hw,
 		goto out;
 	}
 
-	ath9k_htc_set_bssid_mask(priv, vif);
+	ath9k_htc_set_mac_bssid_mask(priv, vif);
 
 	priv->vif_slot |= (1 << avp->index);
 	priv->nvifs++;
@@ -1128,7 +1137,7 @@ static void ath9k_htc_remove_interface(struct ieee80211_hw *hw,
 
 	ath9k_htc_set_opmode(priv);
 
-	ath9k_htc_set_bssid_mask(priv, vif);
+	ath9k_htc_set_mac_bssid_mask(priv, vif);
 
 	/*
 	 * Stop ANI only if there are no associated station interfaces.
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index 74f452c..21aa09e 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -965,8 +965,9 @@ void ath9k_calculate_iter_data(struct ieee80211_hw *hw,
 	struct ath_common *common = ath9k_hw_common(ah);
 
 	/*
-	 * Use the hardware MAC address as reference, the hardware uses it
-	 * together with the BSSID mask when matching addresses.
+	 * Pick the MAC address of the first interface as the new hardware
+	 * MAC address. The hardware will use it together with the BSSID mask
+	 * when matching addresses.
 	 */
 	memset(iter_data, 0, sizeof(*iter_data));
 	memset(&iter_data->mask, 0xff, ETH_ALEN);
-- 
cgit v0.10.2


From 9278db6279e28d4d433bc8a848e10b4ece8793ed Mon Sep 17 00:00:00 2001
From: Larry Finger <Larry.Finger@lwfinger.net>
Date: Wed, 11 Dec 2013 17:13:10 -0600
Subject: rtlwifi: pci: Fix oops on driver unload

On Fedora systems, unloading rtl8192ce causes an oops. This patch fixes the
problem reported at https://bugzilla.redhat.com/show_bug.cgi?id=852761.

Signed-off-by: Larry Finger <Larry.Finger@lwfinger.net>
Cc: Stable <stable@vger.kernel.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>

diff --git a/drivers/net/wireless/rtlwifi/pci.c b/drivers/net/wireless/rtlwifi/pci.c
index 0f49444..5a53195 100644
--- a/drivers/net/wireless/rtlwifi/pci.c
+++ b/drivers/net/wireless/rtlwifi/pci.c
@@ -740,6 +740,8 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
 	};
 	int index = rtlpci->rx_ring[rx_queue_idx].idx;
 
+	if (rtlpci->driver_is_goingto_unload)
+		return;
 	/*RX NORMAL PKT */
 	while (count--) {
 		/*rx descriptor */
@@ -1636,6 +1638,7 @@ static void rtl_pci_stop(struct ieee80211_hw *hw)
 	 */
 	set_hal_stop(rtlhal);
 
+	rtlpci->driver_is_goingto_unload = true;
 	rtlpriv->cfg->ops->disable_interrupt(hw);
 	cancel_work_sync(&rtlpriv->works.lps_change_work);
 
@@ -1653,7 +1656,6 @@ static void rtl_pci_stop(struct ieee80211_hw *hw)
 	ppsc->rfchange_inprogress = true;
 	spin_unlock_irqrestore(&rtlpriv->locks.rf_ps_lock, flags);
 
-	rtlpci->driver_is_goingto_unload = true;
 	rtlpriv->cfg->ops->hw_disable(hw);
 	/* some things are not needed if firmware not available */
 	if (!rtlpriv->max_fw_size)
-- 
cgit v0.10.2


From 73f0b56a1ff64e7fb6c3a62088804bab93bcedc2 Mon Sep 17 00:00:00 2001
From: Sujith Manoharan <c_manoha@qca.qualcomm.com>
Date: Mon, 16 Dec 2013 07:04:59 +0530
Subject: ath9k: Fix interrupt handling for the AR9002 family

This patch adds a driver workaround for a HW issue.

A race condition in the HW results in missing interrupts,
which can be avoided by a read/write with the ISR register.
All chips in the AR9002 series are affected by this bug - AR9003
and above do not have this problem.

Cc: stable@vger.kernel.org
Cc: Felix Fietkau <nbd@openwrt.org>
Signed-off-by: Sujith Manoharan <c_manoha@qca.qualcomm.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>

diff --git a/drivers/net/wireless/ath/ath9k/ar9002_mac.c b/drivers/net/wireless/ath/ath9k/ar9002_mac.c
index 8d78253..a366d6b 100644
--- a/drivers/net/wireless/ath/ath9k/ar9002_mac.c
+++ b/drivers/net/wireless/ath/ath9k/ar9002_mac.c
@@ -76,9 +76,16 @@ static bool ar9002_hw_get_isr(struct ath_hw *ah, enum ath9k_int *masked)
 				mask2 |= ATH9K_INT_CST;
 			if (isr2 & AR_ISR_S2_TSFOOR)
 				mask2 |= ATH9K_INT_TSFOOR;
+
+			if (!(pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED)) {
+				REG_WRITE(ah, AR_ISR_S2, isr2);
+				isr &= ~AR_ISR_BCNMISC;
+			}
 		}
 
-		isr = REG_READ(ah, AR_ISR_RAC);
+		if (pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED)
+			isr = REG_READ(ah, AR_ISR_RAC);
+
 		if (isr == 0xffffffff) {
 			*masked = 0;
 			return false;
@@ -97,11 +104,23 @@ static bool ar9002_hw_get_isr(struct ath_hw *ah, enum ath9k_int *masked)
 
 			*masked |= ATH9K_INT_TX;
 
-			s0_s = REG_READ(ah, AR_ISR_S0_S);
+			if (pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED) {
+				s0_s = REG_READ(ah, AR_ISR_S0_S);
+				s1_s = REG_READ(ah, AR_ISR_S1_S);
+			} else {
+				s0_s = REG_READ(ah, AR_ISR_S0);
+				REG_WRITE(ah, AR_ISR_S0, s0_s);
+				s1_s = REG_READ(ah, AR_ISR_S1);
+				REG_WRITE(ah, AR_ISR_S1, s1_s);
+
+				isr &= ~(AR_ISR_TXOK |
+					 AR_ISR_TXDESC |
+					 AR_ISR_TXERR |
+					 AR_ISR_TXEOL);
+			}
+
 			ah->intr_txqs |= MS(s0_s, AR_ISR_S0_QCU_TXOK);
 			ah->intr_txqs |= MS(s0_s, AR_ISR_S0_QCU_TXDESC);
-
-			s1_s = REG_READ(ah, AR_ISR_S1_S);
 			ah->intr_txqs |= MS(s1_s, AR_ISR_S1_QCU_TXERR);
 			ah->intr_txqs |= MS(s1_s, AR_ISR_S1_QCU_TXEOL);
 		}
@@ -114,13 +133,15 @@ static bool ar9002_hw_get_isr(struct ath_hw *ah, enum ath9k_int *masked)
 		*masked |= mask2;
 	}
 
-	if (AR_SREV_9100(ah))
-		return true;
-
-	if (isr & AR_ISR_GENTMR) {
+	if (!AR_SREV_9100(ah) && (isr & AR_ISR_GENTMR)) {
 		u32 s5_s;
 
-		s5_s = REG_READ(ah, AR_ISR_S5_S);
+		if (pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED) {
+			s5_s = REG_READ(ah, AR_ISR_S5_S);
+		} else {
+			s5_s = REG_READ(ah, AR_ISR_S5);
+		}
+
 		ah->intr_gen_timer_trigger =
 				MS(s5_s, AR_ISR_S5_GENTIMER_TRIG);
 
@@ -133,8 +154,21 @@ static bool ar9002_hw_get_isr(struct ath_hw *ah, enum ath9k_int *masked)
 		if ((s5_s & AR_ISR_S5_TIM_TIMER) &&
 		    !(pCap->hw_caps & ATH9K_HW_CAP_AUTOSLEEP))
 			*masked |= ATH9K_INT_TIM_TIMER;
+
+		if (!(pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED)) {
+			REG_WRITE(ah, AR_ISR_S5, s5_s);
+			isr &= ~AR_ISR_GENTMR;
+		}
 	}
 
+	if (!(pCap->hw_caps & ATH9K_HW_CAP_RAC_SUPPORTED)) {
+		REG_WRITE(ah, AR_ISR, isr);
+		REG_READ(ah, AR_ISR);
+	}
+
+	if (AR_SREV_9100(ah))
+		return true;
+
 	if (sync_cause) {
 		ath9k_debug_sync_cause(common, sync_cause);
 		fatal_int =
-- 
cgit v0.10.2


From e57a2dffbc7e28cef5f4659b98a9d5595010ab4d Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <stfomichev@yandex-team.ru>
Date: Tue, 17 Dec 2013 19:53:49 +0400
Subject: perf timechart: Add --highlight option

This option highlights tasks (using different color) that run more than
given duration or tasks with given name.

Signed-off-by: Stanislav Fomichev <stfomichev@yandex-team.ru>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ramkumar Ramachandra <artagnon@gmail.com>
Link: http://lkml.kernel.org/r/20131217155349.GA13021@stfomichev-desktop
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index 367c1be..bc5990c 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -56,12 +56,25 @@ $ perf timechart
 
   Written 10.2 seconds of trace to output.svg.
 
+Record system-wide timechart:
+
+  $ perf timechart record
+
+  then generate timechart and highlight 'gcc' tasks:
+
+  $ perf timechart --highlight gcc
+
 -n::
 --proc-num::
         Print task info for at least given number of tasks.
 -t::
 --topology::
         Sort CPUs according to topology.
+--highlight=<duration_nsecs|task_name>::
+	Highlight tasks (using different color) that run more than given
+	duration or tasks with given name. If number is given it's interpreted
+	as number of nanoseconds. If non-numeric string is given it's
+	interpreted as task name.
 
 RECORD OPTIONS
 --------------
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 8bde57c..20d4212 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -841,7 +841,6 @@ static void draw_cpu_usage(struct timechart *tchart)
 						    sample->start_time,
 						    sample->end_time,
 						    p->pid,
-						    "sample",
 						    c->comm,
 						    sample->backtrace);
 				}
@@ -1252,6 +1251,23 @@ parse_process(const struct option *opt __maybe_unused, const char *arg,
 	return 0;
 }
 
+static int
+parse_highlight(const struct option *opt __maybe_unused, const char *arg,
+		int __maybe_unused unset)
+{
+	unsigned long duration = strtoul(arg, NULL, 0);
+
+	if (svg_highlight || svg_highlight_name)
+		return -1;
+
+	if (duration)
+		svg_highlight = duration;
+	else
+		svg_highlight_name = strdup(arg);
+
+	return 0;
+}
+
 int cmd_timechart(int argc, const char **argv,
 		  const char *prefix __maybe_unused)
 {
@@ -1270,6 +1286,9 @@ int cmd_timechart(int argc, const char **argv,
 	OPT_STRING('i', "input", &input_name, "file", "input file name"),
 	OPT_STRING('o', "output", &output_name, "file", "output file name"),
 	OPT_INTEGER('w', "width", &svg_page_width, "page width"),
+	OPT_CALLBACK(0, "highlight", NULL, "duration or task name",
+		      "highlight tasks. Pass duration in ns or process name.",
+		       parse_highlight),
 	OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
 	OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
 		    "output processes data only"),
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 9468136..56a84f2 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -31,6 +31,8 @@ static u64 turbo_frequency, max_freq;
 #define SLOT_HEIGHT 25.0
 
 int svg_page_width = 1000;
+u64 svg_highlight;
+const char *svg_highlight_name;
 
 #define MIN_TEXT_SIZE 0.01
 
@@ -112,6 +114,7 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end)
 	fprintf(svgfile, "      rect.process  { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:1;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.process2 { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.sample   { fill:rgb(  0,  0,255); fill-opacity:0.8; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
+	fprintf(svgfile, "      rect.sample_hi{ fill:rgb(255,128,  0); fill-opacity:0.8; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.blocked  { fill:rgb(255,  0,  0); fill-opacity:0.5; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.waiting  { fill:rgb(224,214,  0); fill-opacity:0.8; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.WAITING  { fill:rgb(255,214, 48); fill-opacity:0.6; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
@@ -155,17 +158,24 @@ void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 {
 	double text_size;
+	const char *type;
+
 	if (!svgfile)
 		return;
 
+	if (svg_highlight && end - start > svg_highlight)
+		type = "sample_hi";
+	else
+		type = "sample";
 	fprintf(svgfile, "<g>\n");
 
 	fprintf(svgfile, "<title>#%d running %s</title>\n",
 		cpu, time_to_string(end - start));
 	if (backtrace)
 		fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace);
-	fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"sample\"/>\n",
-		time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT);
+	fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"%s\"/>\n",
+		time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT,
+		type);
 
 	text_size = (time2pixels(end)-time2pixels(start));
 	if (cpu > 9)
@@ -293,13 +303,20 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq)
 	fprintf(svgfile, "</g>\n");
 }
 
-void svg_process(int cpu, u64 start, u64 end, int pid, const char *type, const char *name, const char *backtrace)
+void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const char *backtrace)
 {
 	double width;
+	const char *type;
 
 	if (!svgfile)
 		return;
 
+	if (svg_highlight && end - start >= svg_highlight)
+		type = "sample_hi";
+	else if (svg_highlight_name && strstr(name, svg_highlight_name))
+		type = "sample_hi";
+	else
+		type = "sample";
 
 	fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), cpu2y(cpu));
 	fprintf(svgfile, "<title>%d %s running %s</title>\n", pid, name, time_to_string(end - start));
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index 1df4fb6..f7b4d6e 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -11,7 +11,7 @@ extern void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *back
 extern void svg_cpu_box(int cpu, u64 max_frequency, u64 turbo_frequency);
 
 
-extern void svg_process(int cpu, u64 start, u64 end, int pid, const char *type, const char *name, const char *backtrace);
+extern void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const char *backtrace);
 extern void svg_cstate(int cpu, u64 start, u64 end, int type);
 extern void svg_pstate(int cpu, u64 start, u64 end, u64 freq);
 
@@ -27,5 +27,7 @@ extern int svg_build_topology_map(char *sib_core, int sib_core_nr,
 				  char *sib_thr, int sib_thr_nr);
 
 extern int svg_page_width;
+extern u64 svg_highlight;
+extern const char *svg_highlight_name;
 
 #endif /* __PERF_SVGHELPER_H */
-- 
cgit v0.10.2


From 5f70619d67b99310be9aaf850293b7fd7f31d160 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 17 Dec 2013 16:14:07 -0300
Subject: perf symbols: Use consistent name for the DSO binary type member

It was called "data_type", but in this context "data" is way too vague,
it could mean the "data" ELF segment, or something else.

Since we have dso__read_binary_type_filename() and the values this field
receives are all DSO__BINARY_TYPE_<FOO> we may as well call it
"binary_type" for consistency sake.

It also seems more appropriate since it determines if we can do
operations like annotation and DWARF unwinding, that needs more than
just the symtab, requiring access to ELF text segments, CFI ELF
sections, etc.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-2lkbqrn23uc2uvnn9w9in379@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index eef1662..4ddeecb 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -148,7 +148,7 @@ static int open_dso(struct dso *dso, struct machine *machine)
 	if (machine)
 		root_dir = machine->root_dir;
 
-	if (dso__read_binary_type_filename(dso, dso->data_type,
+	if (dso__read_binary_type_filename(dso, dso->binary_type,
 					    root_dir, name, PATH_MAX)) {
 		free(name);
 		return -EINVAL;
@@ -168,19 +168,19 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
 	};
 	int i = 0;
 
-	if (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND)
+	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND)
 		return open_dso(dso, machine);
 
 	do {
 		int fd;
 
-		dso->data_type = binary_type_data[i++];
+		dso->binary_type = binary_type_data[i++];
 
 		fd = open_dso(dso, machine);
 		if (fd >= 0)
 			return fd;
 
-	} while (dso->data_type != DSO_BINARY_TYPE__NOT_FOUND);
+	} while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND);
 
 	return -EINVAL;
 }
@@ -475,7 +475,7 @@ struct dso *dso__new(const char *name)
 			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
 		dso->cache = RB_ROOT;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
-		dso->data_type   = DSO_BINARY_TYPE__NOT_FOUND;
+		dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->loaded = 0;
 		dso->rel = 0;
 		dso->sorted_by_name = 0;
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index aa33847..cd7d6f0 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -83,7 +83,7 @@ struct dso {
 	enum dso_kernel_type	kernel;
 	enum dso_swap_type	needs_swap;
 	enum dso_binary_type	symtab_type;
-	enum dso_binary_type	data_type;
+	enum dso_binary_type	binary_type;
 	u8		 adjust_symbols:1;
 	u8		 has_build_id:1;
 	u8		 has_srcline:1;
@@ -159,14 +159,14 @@ size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp);
 
 static inline bool dso__is_vmlinux(struct dso *dso)
 {
-	return dso->data_type == DSO_BINARY_TYPE__VMLINUX ||
-	       dso->data_type == DSO_BINARY_TYPE__GUEST_VMLINUX;
+	return dso->binary_type == DSO_BINARY_TYPE__VMLINUX ||
+	       dso->binary_type == DSO_BINARY_TYPE__GUEST_VMLINUX;
 }
 
 static inline bool dso__is_kcore(struct dso *dso)
 {
-	return dso->data_type == DSO_BINARY_TYPE__KCORE ||
-	       dso->data_type == DSO_BINARY_TYPE__GUEST_KCORE;
+	return dso->binary_type == DSO_BINARY_TYPE__KCORE ||
+	       dso->binary_type == DSO_BINARY_TYPE__GUEST_KCORE;
 }
 
 void dso__free_a2l(struct dso *dso);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 9ee4b80..923d000 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1089,9 +1089,9 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	 * dso__data_read_addr().
 	 */
 	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
-		dso->data_type = DSO_BINARY_TYPE__GUEST_KCORE;
+		dso->binary_type = DSO_BINARY_TYPE__GUEST_KCORE;
 	else
-		dso->data_type = DSO_BINARY_TYPE__KCORE;
+		dso->binary_type = DSO_BINARY_TYPE__KCORE;
 	dso__set_long_name(dso, strdup(kcore_filename), true);
 
 	close(fd);
@@ -1368,9 +1368,9 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 
 	if (err > 0) {
 		if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
-			dso->data_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
+			dso->binary_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
 		else
-			dso->data_type = DSO_BINARY_TYPE__VMLINUX;
+			dso->binary_type = DSO_BINARY_TYPE__VMLINUX;
 		dso__set_long_name(dso, vmlinux, vmlinux_allocated);
 		dso__set_loaded(dso, map->type);
 		pr_debug("Using %s for symbols\n", symfs_vmlinux);
-- 
cgit v0.10.2


From f23b24f1bf90b56cfaeb2a1c9b77c46efe8916a6 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 17 Dec 2013 09:02:36 +0900
Subject: tools lib traceevent: Get rid of die() in some string conversion
 functions

Those functions stringify filter arguments.

As caller of those functions handles NULL string properly, it seems that
it's enough to return NULL rather than calling die().

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/878uvkgx9f.fsf@sejong.aot.lge.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index 9303c55..e2842b9 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -1361,8 +1361,10 @@ enum pevent_errno pevent_filter_add_filter_str(struct event_filter *filter,
 		if (ret >= 0 && pevent->test_filters) {
 			char *test;
 			test = pevent_filter_make_string(filter, event->event->id);
-			printf(" '%s: %s'\n", event->event->name, test);
-			free(test);
+			if (test) {
+				printf(" '%s: %s'\n", event->event->name, test);
+				free(test);
+			}
 		}
 	}
 
@@ -2050,7 +2052,6 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 	int left_val = -1;
 	int right_val = -1;
 	int val;
-	int len;
 
 	switch (arg->op.type) {
 	case FILTER_OP_AND:
@@ -2097,11 +2098,7 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 				default:
 					break;
 				}
-				str = malloc_or_die(6);
-				if (val)
-					strcpy(str, "TRUE");
-				else
-					strcpy(str, "FALSE");
+				asprintf(&str, val ? "TRUE" : "FALSE");
 				break;
 			}
 		}
@@ -2119,10 +2116,7 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 			break;
 		}
 
-		len = strlen(left) + strlen(right) + strlen(op) + 10;
-		str = malloc_or_die(len);
-		snprintf(str, len, "(%s) %s (%s)",
-			 left, op, right);
+		asprintf(&str, "(%s) %s (%s)", left, op, right);
 		break;
 
 	case FILTER_OP_NOT:
@@ -2138,16 +2132,10 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 			right_val = 0;
 		if (right_val >= 0) {
 			/* just return the opposite */
-			str = malloc_or_die(6);
-			if (right_val)
-				strcpy(str, "FALSE");
-			else
-				strcpy(str, "TRUE");
+			asprintf(&str, right_val ? "FALSE" : "TRUE");
 			break;
 		}
-		len = strlen(right) + strlen(op) + 3;
-		str = malloc_or_die(len);
-		snprintf(str, len, "%s(%s)", op, right);
+		asprintf(&str, "%s(%s)", op, right);
 		break;
 
 	default:
@@ -2161,11 +2149,9 @@ static char *op_to_str(struct event_filter *filter, struct filter_arg *arg)
 
 static char *val_to_str(struct event_filter *filter, struct filter_arg *arg)
 {
-	char *str;
-
-	str = malloc_or_die(30);
+	char *str = NULL;
 
-	snprintf(str, 30, "%lld", arg->value.val);
+	asprintf(&str, "%lld", arg->value.val);
 
 	return str;
 }
@@ -2181,7 +2167,6 @@ static char *exp_to_str(struct event_filter *filter, struct filter_arg *arg)
 	char *rstr;
 	char *op;
 	char *str = NULL;
-	int len;
 
 	lstr = arg_to_str(filter, arg->exp.left);
 	rstr = arg_to_str(filter, arg->exp.right);
@@ -2220,12 +2205,11 @@ static char *exp_to_str(struct event_filter *filter, struct filter_arg *arg)
 		op = "^";
 		break;
 	default:
-		die("oops in exp");
+		op = "[ERROR IN EXPRESSION TYPE]";
+		break;
 	}
 
-	len = strlen(op) + strlen(lstr) + strlen(rstr) + 4;
-	str = malloc_or_die(len);
-	snprintf(str, len, "%s %s %s", lstr, op, rstr);
+	asprintf(&str, "%s %s %s", lstr, op, rstr);
 out:
 	free(lstr);
 	free(rstr);
@@ -2239,7 +2223,6 @@ static char *num_to_str(struct event_filter *filter, struct filter_arg *arg)
 	char *rstr;
 	char *str = NULL;
 	char *op = NULL;
-	int len;
 
 	lstr = arg_to_str(filter, arg->num.left);
 	rstr = arg_to_str(filter, arg->num.right);
@@ -2270,10 +2253,7 @@ static char *num_to_str(struct event_filter *filter, struct filter_arg *arg)
 		if (!op)
 			op = "<=";
 
-		len = strlen(lstr) + strlen(op) + strlen(rstr) + 4;
-		str = malloc_or_die(len);
-		sprintf(str, "%s %s %s", lstr, op, rstr);
-
+		asprintf(&str, "%s %s %s", lstr, op, rstr);
 		break;
 
 	default:
@@ -2291,7 +2271,6 @@ static char *str_to_str(struct event_filter *filter, struct filter_arg *arg)
 {
 	char *str = NULL;
 	char *op = NULL;
-	int len;
 
 	switch (arg->str.type) {
 	case FILTER_CMP_MATCH:
@@ -2309,12 +2288,8 @@ static char *str_to_str(struct event_filter *filter, struct filter_arg *arg)
 		if (!op)
 			op = "!~";
 
-		len = strlen(arg->str.field->name) + strlen(op) +
-			strlen(arg->str.val) + 6;
-		str = malloc_or_die(len);
-		snprintf(str, len, "%s %s \"%s\"",
-			 arg->str.field->name,
-			 op, arg->str.val);
+		asprintf(&str, "%s %s \"%s\"",
+			 arg->str.field->name, op, arg->str.val);
 		break;
 
 	default:
@@ -2326,15 +2301,11 @@ static char *str_to_str(struct event_filter *filter, struct filter_arg *arg)
 
 static char *arg_to_str(struct event_filter *filter, struct filter_arg *arg)
 {
-	char *str;
+	char *str = NULL;
 
 	switch (arg->type) {
 	case FILTER_ARG_BOOLEAN:
-		str = malloc_or_die(6);
-		if (arg->boolean.value)
-			strcpy(str, "TRUE");
-		else
-			strcpy(str, "FALSE");
+		asprintf(&str, arg->boolean.value ? "TRUE" : "FALSE");
 		return str;
 
 	case FILTER_ARG_OP:
@@ -2369,7 +2340,7 @@ static char *arg_to_str(struct event_filter *filter, struct filter_arg *arg)
  *
  * Returns a string that displays the filter contents.
  *  This string must be freed with free(str).
- *  NULL is returned if no filter is found.
+ *  NULL is returned if no filter is found or allocation failed.
  */
 char *
 pevent_filter_make_string(struct event_filter *filter, int event_id)
-- 
cgit v0.10.2


From 45c2aff645c82da7b1574dad5062993cf451c699 Mon Sep 17 00:00:00 2001
From: Gao feng <gaofeng@cn.fujitsu.com>
Date: Mon, 16 Dec 2013 14:59:22 +0800
Subject: netfilter: nfnetlink_log: unset nf_loggers for netns when unloading
 module

Steven Rostedt and Arnaldo Carvalho de Melo reported a panic
when access the files /proc/sys/net/netfilter/nf_log/*.

This problem will occur when we do:

 echo nfnetlink_log > /proc/sys/net/netfilter/nf_log/any_file
 rmmod nfnetlink_log

and then access the files.

Since the nf_loggers of netns hasn't been unset, it will point
to the memory that has been freed.

This bug is introduced by commit 9368a53c ("netfilter: nfnetlink_log:
add net namespace support for nfnetlink_log").

[17261.822047] BUG: unable to handle kernel paging request at ffffffffa0d49090
[17261.822056] IP: [<ffffffff8157aba0>] nf_log_proc_dostring+0xf0/0x1d0
[...]
[17261.822226] Call Trace:
[17261.822235]  [<ffffffff81297b98>] ? security_capable+0x18/0x20
[17261.822240]  [<ffffffff8106fa09>] ? ns_capable+0x29/0x50
[17261.822247]  [<ffffffff8163d25f>] ? net_ctl_permissions+0x1f/0x90
[17261.822254]  [<ffffffff81216613>] proc_sys_call_handler+0xb3/0xc0
[17261.822258]  [<ffffffff81216651>] proc_sys_read+0x11/0x20
[17261.822265]  [<ffffffff811a80de>] vfs_read+0x9e/0x170
[17261.822270]  [<ffffffff811a8c09>] SyS_read+0x49/0xa0
[17261.822276]  [<ffffffff810e6496>] ? __audit_syscall_exit+0x1f6/0x2a0
[17261.822283]  [<ffffffff81656e99>] system_call_fastpath+0x16/0x1b
[17261.822285] Code: cc 81 4d 63 e4 4c 89 45 88 48 89 4d 90 e8 19 03 0d 00 4b 8b 84 e5 28 08 00 00 48 8b 4d 90 4c 8b 45 88 48 85 c0 0f 84 a8 00 00 00 <48> 8b 40 10 48 89 43 08 48 89 df 4c 89 f2 31 f6 e8 4b 35 af ff
[17261.822329] RIP  [<ffffffff8157aba0>] nf_log_proc_dostring+0xf0/0x1d0
[17261.822334]  RSP <ffff880274d3fe28>
[17261.822336] CR2: ffffffffa0d49090
[17261.822340] ---[ end trace a14ce54c0897a90d ]---

Reported-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 3c4b69e..a155d19 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -1053,6 +1053,7 @@ static void __net_exit nfnl_log_net_exit(struct net *net)
 #ifdef CONFIG_PROC_FS
 	remove_proc_entry("nfnetlink_log", net->nf.proc_netfilter);
 #endif
+	nf_log_unset(net, &nfulnl_logger);
 }
 
 static struct pernet_operations nfnl_log_net_ops = {
-- 
cgit v0.10.2


From 3482fb5e0c1c20ce0dbcfc5ca3b6558a8c455b10 Mon Sep 17 00:00:00 2001
From: "Luck, Tony" <tony.luck@intel.com>
Date: Wed, 6 Nov 2013 13:30:36 -0800
Subject: ACPI, APEI, EINJ: Changes to the ACPI/APEI/EINJ debugfs interface

When I added support for ACPI5 I made the assumption that
injected processor errors would just need to know the APICID,
memory errors just the address and mask, and PCIe errors just the
segment/bus/device/function. So I had the code check the type of injection
and multiplex the "param1" value appropriately.

This was not a good assumption :-(

There are injection scenarios where we need to specify more than one of
these items. E.g. injecting a cache error we need to specify an APICID
of the cpu that owns the cache, and also an address (so that we can trip
the error by accessing the address).

Add a "flags" file to give the user direct access to specify which items
are valid in the ACPI SET_ERROR_TYPE_WITH_ADDRESS structure. Also add
new files param3 and param4 to hold all these values.

For backwards compatability with old injection scripts we maintain the
old behaviour if flags remains set at zero (or is reset to 0).

Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>

diff --git a/Documentation/acpi/apei/einj.txt b/Documentation/acpi/apei/einj.txt
index a58b63d..f51861b 100644
--- a/Documentation/acpi/apei/einj.txt
+++ b/Documentation/acpi/apei/einj.txt
@@ -45,11 +45,22 @@ directory apei/einj. The following files are provided.
   injection. Before this, please specify all necessary error
   parameters.
 
+- flags
+  Present for kernel version 3.13 and above. Used to specify which
+  of param{1..4} are valid and should be used by BIOS during injection.
+  Value is a bitmask as specified in ACPI5.0 spec for the
+  SET_ERROR_TYPE_WITH_ADDRESS data structure:
+	Bit 0 - Processor APIC field valid (see param3 below)
+	Bit 1 - Memory address and mask valid (param1 and param2)
+	Bit 2 - PCIe (seg,bus,dev,fn) valid (param4 below)
+  If set to zero, legacy behaviour is used where the type of injection
+  specifies just one bit set, and param1 is multiplexed.
+
 - param1
   This file is used to set the first error parameter value. Effect of
   parameter depends on error_type specified. For example, if error
   type is memory related type, the param1 should be a valid physical
-  memory address.
+  memory address. [Unless "flag" is set - see above]
 
 - param2
   This file is used to set the second error parameter value. Effect of
@@ -58,6 +69,12 @@ directory apei/einj. The following files are provided.
   address mask. Linux requires page or narrower granularity, say,
   0xfffffffffffff000.
 
+- param3
+  Used when the 0x1 bit is set in "flag" to specify the APIC id
+
+- param4
+  Used when the 0x4 bit is set in "flag" to specify target PCIe device
+
 - notrigger
   The EINJ mechanism is a two step process. First inject the error, then
   perform some actions to trigger it. Setting "notrigger" to 1 skips the
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
index fb57d03..c76674e 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj.c
@@ -416,7 +416,8 @@ out:
 	return rc;
 }
 
-static int __einj_error_inject(u32 type, u64 param1, u64 param2)
+static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
+			       u64 param3, u64 param4)
 {
 	struct apei_exec_context ctx;
 	u64 val, trigger_paddr, timeout = FIRMWARE_TIMEOUT;
@@ -446,6 +447,12 @@ static int __einj_error_inject(u32 type, u64 param1, u64 param2)
 				break;
 			}
 			v5param->flags = vendor_flags;
+		} else if (flags) {
+				v5param->flags = flags;
+				v5param->memory_address = param1;
+				v5param->memory_address_range = param2;
+				v5param->apicid = param3;
+				v5param->pcie_sbdf = param4;
 		} else {
 			switch (type) {
 			case ACPI_EINJ_PROCESSOR_CORRECTABLE:
@@ -514,11 +521,17 @@ static int __einj_error_inject(u32 type, u64 param1, u64 param2)
 }
 
 /* Inject the specified hardware error */
-static int einj_error_inject(u32 type, u64 param1, u64 param2)
+static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2,
+			     u64 param3, u64 param4)
 {
 	int rc;
 	unsigned long pfn;
 
+	/* If user manually set "flags", make sure it is legal */
+	if (flags && (flags &
+		~(SETWA_FLAGS_APICID|SETWA_FLAGS_MEM|SETWA_FLAGS_PCIE_SBDF)))
+		return -EINVAL;
+
 	/*
 	 * We need extra sanity checks for memory errors.
 	 * Other types leap directly to injection.
@@ -532,7 +545,7 @@ static int einj_error_inject(u32 type, u64 param1, u64 param2)
 	if (type & ACPI5_VENDOR_BIT) {
 		if (vendor_flags != SETWA_FLAGS_MEM)
 			goto inject;
-	} else if (!(type & MEM_ERROR_MASK))
+	} else if (!(type & MEM_ERROR_MASK) && !(flags & SETWA_FLAGS_MEM))
 		goto inject;
 
 	/*
@@ -546,15 +559,18 @@ static int einj_error_inject(u32 type, u64 param1, u64 param2)
 
 inject:
 	mutex_lock(&einj_mutex);
-	rc = __einj_error_inject(type, param1, param2);
+	rc = __einj_error_inject(type, flags, param1, param2, param3, param4);
 	mutex_unlock(&einj_mutex);
 
 	return rc;
 }
 
 static u32 error_type;
+static u32 error_flags;
 static u64 error_param1;
 static u64 error_param2;
+static u64 error_param3;
+static u64 error_param4;
 static struct dentry *einj_debug_dir;
 
 static int available_error_type_show(struct seq_file *m, void *v)
@@ -648,7 +664,8 @@ static int error_inject_set(void *data, u64 val)
 	if (!error_type)
 		return -EINVAL;
 
-	return einj_error_inject(error_type, error_param1, error_param2);
+	return einj_error_inject(error_type, error_flags, error_param1, error_param2,
+		error_param3, error_param4);
 }
 
 DEFINE_SIMPLE_ATTRIBUTE(error_inject_fops, NULL,
@@ -729,6 +746,10 @@ static int __init einj_init(void)
 	rc = -ENOMEM;
 	einj_param = einj_get_parameter_address();
 	if ((param_extension || acpi5) && einj_param) {
+		fentry = debugfs_create_x32("flags", S_IRUSR | S_IWUSR,
+					    einj_debug_dir, &error_flags);
+		if (!fentry)
+			goto err_unmap;
 		fentry = debugfs_create_x64("param1", S_IRUSR | S_IWUSR,
 					    einj_debug_dir, &error_param1);
 		if (!fentry)
@@ -737,6 +758,14 @@ static int __init einj_init(void)
 					    einj_debug_dir, &error_param2);
 		if (!fentry)
 			goto err_unmap;
+		fentry = debugfs_create_x64("param3", S_IRUSR | S_IWUSR,
+					    einj_debug_dir, &error_param3);
+		if (!fentry)
+			goto err_unmap;
+		fentry = debugfs_create_x64("param4", S_IRUSR | S_IWUSR,
+					    einj_debug_dir, &error_param4);
+		if (!fentry)
+			goto err_unmap;
 
 		fentry = debugfs_create_x32("notrigger", S_IRUSR | S_IWUSR,
 					    einj_debug_dir, &notrigger);
-- 
cgit v0.10.2


From 85328240c625f322af9f69c7b60e619717101d77 Mon Sep 17 00:00:00 2001
From: John Fastabend <john.r.fastabend@intel.com>
Date: Tue, 26 Nov 2013 06:33:52 +0000
Subject: net: allow netdev_all_upper_get_next_dev_rcu with rtnl lock held

It is useful to be able to walk all upper devices when bringing
a device online where the RTNL lock is held. In this case it
is safe to walk the all_adj_list because the RTNL lock is used
to protect the write side as well.

This patch adds a check to see if the rtnl lock is held before
throwing a warning in netdev_all_upper_get_next_dev_rcu().

Also because we now have a call site for lockdep_rtnl_is_held()
outside COFIG_LOCK_PROVING an inline definition returning 1 is
needed. Similar to the rcu_read_lock_is_held().

Fixes: 2a47fa45d4df ("ixgbe: enable l2 forwarding acceleration for macvlans")
CC: Veaceslav Falico <vfalico@redhat.com>
Reported-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 939428a..8e3e66a 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -24,6 +24,11 @@ extern int rtnl_trylock(void);
 extern int rtnl_is_locked(void);
 #ifdef CONFIG_PROVE_LOCKING
 extern int lockdep_rtnl_is_held(void);
+#else
+static inline int lockdep_rtnl_is_held(void)
+{
+	return 1;
+}
 #endif /* #ifdef CONFIG_PROVE_LOCKING */
 
 /**
diff --git a/net/core/dev.c b/net/core/dev.c
index ba3b7ea..4fc1722 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4500,7 +4500,7 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
 {
 	struct netdev_adjacent *upper;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held());
 
 	upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
 
-- 
cgit v0.10.2


From 9e6c3b63399dd424d33a34e08b77f2cab0b84cdc Mon Sep 17 00:00:00 2001
From: David Ertman <davidx.m.ertman@intel.com>
Date: Sat, 14 Dec 2013 07:18:18 +0000
Subject: e1000e: fix compiler warnings

This patch is to fix a compiler warning of __bad_udelay due to a value
of >999 being passed as a parameter to udelay() in the function
e1000e_phy_has_link_generic().  This affects the gcc compiler when
it is given a flag of -O3 and the icc compiler.

This patch is also making the change from mdelay() to msleep() in the
same function, since it was determined though code inspection that this
function is never called in atomic context.

Signed-off-by: David Ertman <davidx.m.ertman@intel.com>
Acked-by: Bruce Allan <bruce.w.allan@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c
index da2be59..20e71f4 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.c
+++ b/drivers/net/ethernet/intel/e1000e/phy.c
@@ -1757,19 +1757,23 @@ s32 e1000e_phy_has_link_generic(struct e1000_hw *hw, u32 iterations,
 		 * it across the board.
 		 */
 		ret_val = e1e_rphy(hw, MII_BMSR, &phy_status);
-		if (ret_val)
+		if (ret_val) {
 			/* If the first read fails, another entity may have
 			 * ownership of the resources, wait and try again to
 			 * see if they have relinquished the resources yet.
 			 */
-			udelay(usec_interval);
+			if (usec_interval >= 1000)
+				msleep(usec_interval / 1000);
+			else
+				udelay(usec_interval);
+		}
 		ret_val = e1e_rphy(hw, MII_BMSR, &phy_status);
 		if (ret_val)
 			break;
 		if (phy_status & BMSR_LSTATUS)
 			break;
 		if (usec_interval >= 1000)
-			mdelay(usec_interval / 1000);
+			msleep(usec_interval / 1000);
 		else
 			udelay(usec_interval);
 	}
-- 
cgit v0.10.2


From 918a4308bad24a8c40a9e569fb7b3a6295ec7757 Mon Sep 17 00:00:00 2001
From: David Ertman <davidx.m.ertman@intel.com>
Date: Sat, 14 Dec 2013 07:30:39 +0000
Subject: e1000e: fix compiler warning (maybe-unitialized variable)

This patch is to fix a compiler warning of maybe-uininitialized-variable
that is generated from gcc when the -O3 flag is used.  In the function
e1000_reset_hw_80003es2lan(), the variable krmn_reg_data is first given
a value by being passed to a register read function as a
pass-by-reference parameter.  But, the return value of that read
function was never checked to see if the read failed and the variable
not given an initial value.  The compiler was smart enough to spot
this.  This patch is to check the return value for that read function
and return it, if an error occurs, without trying to utilize the value
in kmrn_reg_data.

Signed-off-by: David Ertman <davidx.m.ertman@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.c b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
index 895450e..ff2d806 100644
--- a/drivers/net/ethernet/intel/e1000e/80003es2lan.c
+++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
@@ -718,8 +718,11 @@ static s32 e1000_reset_hw_80003es2lan(struct e1000_hw *hw)
 	e1000_release_phy_80003es2lan(hw);
 
 	/* Disable IBIST slave mode (far-end loopback) */
-	e1000_read_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
-					&kum_reg_data);
+	ret_val =
+	    e1000_read_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
+					    &kum_reg_data);
+	if (ret_val)
+		return ret_val;
 	kum_reg_data |= E1000_KMRNCTRLSTA_IBIST_DISABLE;
 	e1000_write_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
 					 kum_reg_data);
-- 
cgit v0.10.2


From 7509963c703b71eebccc421585e7f48ebbbd3f38 Mon Sep 17 00:00:00 2001
From: David Ertman <davidx.m.ertman@intel.com>
Date: Tue, 17 Dec 2013 04:42:42 +0000
Subject: e1000e: Fix a compile flag mis-match for suspend/resume

This patch addresses a mis-match between the declaration and usage of
the e1000_suspend and e1000_resume functions.  Previously, these
functions were declared in a CONFIG_PM_SLEEP wrapper, and then utilized
within a CONFIG_PM wrapper.  Both the declaration and usage will now be
contained within CONFIG_PM wrappers.

Signed-off-by: Dave Ertman <davidx.m.ertman@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 8d3945a..c30d41d 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -6174,7 +6174,7 @@ static int __e1000_resume(struct pci_dev *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_PM
 static int e1000_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -6193,7 +6193,7 @@ static int e1000_resume(struct device *dev)
 
 	return __e1000_resume(pdev);
 }
-#endif /* CONFIG_PM_SLEEP */
+#endif /* CONFIG_PM */
 
 #ifdef CONFIG_PM_RUNTIME
 static int e1000_runtime_suspend(struct device *dev)
-- 
cgit v0.10.2


From 8f48f5bc759d6f945ff0c3b2bf2a1d5971e561ba Mon Sep 17 00:00:00 2001
From: Don Skidmore <donald.c.skidmore@intel.com>
Date: Fri, 22 Nov 2013 04:27:23 +0000
Subject: ixgbe: fix for unused variable warning with certain config

If CONFIG_PCI_IOV isn't defined we get an "unused variable" warining so
now wrap the variable declaration like it's usage already was.

Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index d6f0c0d..72084f7 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -291,7 +291,9 @@ static int ixgbe_pci_sriov_disable(struct pci_dev *dev)
 {
 	struct ixgbe_adapter *adapter = pci_get_drvdata(dev);
 	int err;
+#ifdef CONFIG_PCI_IOV
 	u32 current_flags = adapter->flags;
+#endif
 
 	err = ixgbe_disable_sriov(adapter);
 
-- 
cgit v0.10.2


From 57dee992df244ccce6a6a3a88a43160e285da5d8 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Date: Sat, 14 Dec 2013 15:07:32 +0900
Subject: clocksource: sh_cmt: Add clk_prepare/unprepare support

Prepare the clock at probe time, as there is no other appropriate place
in the driver where we're allowed to sleep.

Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c
index 0965e98..940341a 100644
--- a/drivers/clocksource/sh_cmt.c
+++ b/drivers/clocksource/sh_cmt.c
@@ -634,12 +634,18 @@ static int sh_cmt_clock_event_next(unsigned long delta,
 
 static void sh_cmt_clock_event_suspend(struct clock_event_device *ced)
 {
-	pm_genpd_syscore_poweroff(&ced_to_sh_cmt(ced)->pdev->dev);
+	struct sh_cmt_priv *p = ced_to_sh_cmt(ced);
+
+	pm_genpd_syscore_poweroff(&p->pdev->dev);
+	clk_unprepare(p->clk);
 }
 
 static void sh_cmt_clock_event_resume(struct clock_event_device *ced)
 {
-	pm_genpd_syscore_poweron(&ced_to_sh_cmt(ced)->pdev->dev);
+	struct sh_cmt_priv *p = ced_to_sh_cmt(ced);
+
+	clk_prepare(p->clk);
+	pm_genpd_syscore_poweron(&p->pdev->dev);
 }
 
 static void sh_cmt_register_clockevent(struct sh_cmt_priv *p,
@@ -737,6 +743,10 @@ static int sh_cmt_setup(struct sh_cmt_priv *p, struct platform_device *pdev)
 		goto err2;
 	}
 
+	ret = clk_prepare(p->clk);
+	if (ret < 0)
+		goto err3;
+
 	if (res2 && (resource_size(res2) == 4)) {
 		/* assume both CMSTR and CMCSR to be 32-bit */
 		p->read_control = sh_cmt_read32;
@@ -773,19 +783,21 @@ static int sh_cmt_setup(struct sh_cmt_priv *p, struct platform_device *pdev)
 			      cfg->clocksource_rating);
 	if (ret) {
 		dev_err(&p->pdev->dev, "registration failed\n");
-		goto err3;
+		goto err4;
 	}
 	p->cs_enabled = false;
 
 	ret = setup_irq(irq, &p->irqaction);
 	if (ret) {
 		dev_err(&p->pdev->dev, "failed to request irq %d\n", irq);
-		goto err3;
+		goto err4;
 	}
 
 	platform_set_drvdata(pdev, p);
 
 	return 0;
+err4:
+	clk_unprepare(p->clk);
 err3:
 	clk_put(p->clk);
 err2:
-- 
cgit v0.10.2


From d80512f87474f2dfd67ef931737659acce20fe69 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Mon, 16 Dec 2013 14:31:26 +0100
Subject: s390/smp: improve setup of possible cpu mask

Since under z/VM we cannot have more than 64 cpus, make sure the
cpu_possible_mask does not contain more bits.
This avoids wasting memory for dynamic per-cpu allocations if
CONFIG_NR_CPUS is larger than 64.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 1e1a03d..e9f3125 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -135,7 +135,6 @@ config S390
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UID16 if 32BIT
 	select HAVE_VIRT_CPU_ACCOUNTING
-	select INIT_ALL_POSSIBLE
 	select KTIME_SCALAR if 32BIT
 	select MODULES_USE_ELF_RELA
 	select OLD_SIGACTION
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index ac9bed8..1607793 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -31,6 +31,7 @@ extern void smp_yield(void);
 extern void smp_stop_cpu(void);
 extern void smp_cpu_set_polarization(int cpu, int val);
 extern int smp_cpu_get_polarization(int cpu);
+extern void smp_fill_possible_mask(void);
 
 #else /* CONFIG_SMP */
 
@@ -50,6 +51,7 @@ static inline int smp_vcpu_scheduled(int cpu) { return 1; }
 static inline void smp_yield_cpu(int cpu) { }
 static inline void smp_yield(void) { }
 static inline void smp_stop_cpu(void) { }
+static inline void smp_fill_possible_mask(void) { }
 
 #endif /* CONFIG_SMP */
 
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 4444875..0f3d44e 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -1023,6 +1023,7 @@ void __init setup_arch(char **cmdline_p)
 	setup_vmcoreinfo();
 	setup_lowcore();
 
+	smp_fill_possible_mask();
         cpu_init();
 	s390_init_cpu_topology();
 
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index dc4a534..9587047 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -721,18 +721,14 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 	return 0;
 }
 
-static int __init setup_possible_cpus(char *s)
-{
-	int max, cpu;
+static unsigned int setup_possible_cpus __initdata;
 
-	if (kstrtoint(s, 0, &max) < 0)
-		return 0;
-	init_cpu_possible(cpumask_of(0));
-	for (cpu = 1; cpu < max && cpu < nr_cpu_ids; cpu++)
-		set_cpu_possible(cpu, true);
+static int __init _setup_possible_cpus(char *s)
+{
+	get_option(&s, &setup_possible_cpus);
 	return 0;
 }
-early_param("possible_cpus", setup_possible_cpus);
+early_param("possible_cpus", _setup_possible_cpus);
 
 #ifdef CONFIG_HOTPLUG_CPU
 
@@ -775,6 +771,17 @@ void __noreturn cpu_die(void)
 
 #endif /* CONFIG_HOTPLUG_CPU */
 
+void __init smp_fill_possible_mask(void)
+{
+	unsigned int possible, cpu;
+
+	possible = setup_possible_cpus;
+	if (!possible)
+		possible = MACHINE_IS_VM ? 64 : nr_cpu_ids;
+	for (cpu = 0; cpu < possible && cpu < nr_cpu_ids; cpu++)
+		set_cpu_possible(cpu, true);
+}
+
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	/* request the 0x1201 emergency signal external interrupt */
-- 
cgit v0.10.2


From 36d9f4d3b68c7035ead3850dc85f310a579ed0eb Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Wed, 18 Dec 2013 14:36:18 +0100
Subject: s390/3270: fix allocation of tty3270_screen structure

The tty3270_alloc_screen function is called from tty3270_install with
swapped arguments, the number of columns instead of rows and vice versa.
The number of rows is typically smaller than the number of columns which
makes the screen array too big but the individual cell arrays for the
lines too small. Creating lines longer than the number of rows will
clobber the memory after the end of the cell array.
The fix is simple, call tty3270_alloc_screen with the correct argument
order.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/drivers/s390/char/tty3270.c b/drivers/s390/char/tty3270.c
index 3f4ca4e..34629ea 100644
--- a/drivers/s390/char/tty3270.c
+++ b/drivers/s390/char/tty3270.c
@@ -942,7 +942,7 @@ static int tty3270_install(struct tty_driver *driver, struct tty_struct *tty)
 		return rc;
 	}
 
-	tp->screen = tty3270_alloc_screen(tp->view.cols, tp->view.rows);
+	tp->screen = tty3270_alloc_screen(tp->view.rows, tp->view.cols);
 	if (IS_ERR(tp->screen)) {
 		rc = PTR_ERR(tp->screen);
 		raw3270_put_view(&tp->view);
-- 
cgit v0.10.2


From 9efe4f2992025c3a4027c60bf36ae9d710ca3781 Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Tue, 17 Dec 2013 13:41:31 +0100
Subject: s390/mm: optimize randomize_et_dyn for !PF_RANDOMIZE

Skip the call to brk_rnd() if the PF_RANDOMIZE flag is not set for
the process. This avoids the costly get_random_int() call. Modify
arch_randomize_brk() as well to make it look like randomize_et_dyn().

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 7ed0d4e..dd14532 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -261,20 +261,18 @@ static inline unsigned long brk_rnd(void)
 
 unsigned long arch_randomize_brk(struct mm_struct *mm)
 {
-	unsigned long ret = PAGE_ALIGN(mm->brk + brk_rnd());
+	unsigned long ret;
 
-	if (ret < mm->brk)
-		return mm->brk;
-	return ret;
+	ret = PAGE_ALIGN(mm->brk + brk_rnd());
+	return (ret > mm->brk) ? ret : mm->brk;
 }
 
 unsigned long randomize_et_dyn(unsigned long base)
 {
-	unsigned long ret = PAGE_ALIGN(base + brk_rnd());
+	unsigned long ret;
 
 	if (!(current->flags & PF_RANDOMIZE))
 		return base;
-	if (ret < base)
-		return base;
-	return ret;
+	ret = PAGE_ALIGN(base + brk_rnd());
+	return (ret > base) ? ret : base;
 }
-- 
cgit v0.10.2


From 91f3e3eaba4413e76ce8e12e3ef10525a889142f Mon Sep 17 00:00:00 2001
From: Ingo Tuchscherer <ingo.tuchscherer@de.ibm.com>
Date: Wed, 20 Nov 2013 10:47:13 +0100
Subject: s390/zcrypt: add support for EP11 coprocessor cards

This feature extends the generic cryptographic device driver (zcrypt)
with a new capability to service EP11 requests for the Crypto Express4S
card in EP11 (Enterprise PKCS#11 mode) coprocessor mode.

Signed-off-by: Ingo Tuchscherer <ingo.tuchscherer@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/Documentation/kmsg/s390/zcrypt b/Documentation/kmsg/s390/zcrypt
new file mode 100644
index 0000000..7fb2087
--- /dev/null
+++ b/Documentation/kmsg/s390/zcrypt
@@ -0,0 +1,20 @@
+/*?
+ * Text: "Cryptographic device %x failed and was set offline\n"
+ * Severity: Error
+ * Parameter:
+ *   @1: device index
+ * Description:
+ * A cryptographic device failed to process a cryptographic request.
+ * The cryptographic device driver could not correct the error and
+ * set the device offline. The application that issued the
+ * request received an indication that the request has failed.
+ * User action:
+ * Use the lszcrypt command to confirm that the cryptographic
+ * hardware is still configured to your LPAR or z/VM guest virtual
+ * machine. If the device is available to your Linux instance the
+ * command output contains a line that begins with 'card<device index>',
+ * where <device index> is the two-digit decimal number in the message text.
+ * After ensuring that the device is available, use the chzcrypt command to
+ * set it online again.
+ * If the error persists, contact your support organization.
+ */
diff --git a/arch/s390/include/uapi/asm/zcrypt.h b/arch/s390/include/uapi/asm/zcrypt.h
index e83fc11..f2b18ea 100644
--- a/arch/s390/include/uapi/asm/zcrypt.h
+++ b/arch/s390/include/uapi/asm/zcrypt.h
@@ -154,6 +154,67 @@ struct ica_xcRB {
 	unsigned short	priority_window;
 	unsigned int	status;
 } __attribute__((packed));
+
+/**
+ * struct ep11_cprb - EP11 connectivity programming request block
+ * @cprb_len:		CPRB header length [0x0020]
+ * @cprb_ver_id:	CPRB version id.   [0x04]
+ * @pad_000:		Alignment pad bytes
+ * @flags:		Admin cmd [0x80] or functional cmd [0x00]
+ * @func_id:		Function id / subtype [0x5434]
+ * @source_id:		Source id [originator id]
+ * @target_id:		Target id [usage/ctrl domain id]
+ * @ret_code:		Return code
+ * @reserved1:		Reserved
+ * @reserved2:		Reserved
+ * @payload_len:	Payload length
+ */
+struct ep11_cprb {
+	uint16_t	cprb_len;
+	unsigned char	cprb_ver_id;
+	unsigned char	pad_000[2];
+	unsigned char	flags;
+	unsigned char	func_id[2];
+	uint32_t	source_id;
+	uint32_t	target_id;
+	uint32_t	ret_code;
+	uint32_t	reserved1;
+	uint32_t	reserved2;
+	uint32_t	payload_len;
+} __attribute__((packed));
+
+/**
+ * struct ep11_target_dev - EP11 target device list
+ * @ap_id:	AP device id
+ * @dom_id:	Usage domain id
+ */
+struct ep11_target_dev {
+	uint16_t ap_id;
+	uint16_t dom_id;
+};
+
+/**
+ * struct ep11_urb - EP11 user request block
+ * @targets_num:	Number of target adapters
+ * @targets:		Addr to target adapter list
+ * @weight:		Level of request priority
+ * @req_no:		Request id/number
+ * @req_len:		Request length
+ * @req:		Addr to request block
+ * @resp_len:		Response length
+ * @resp:		Addr to response block
+ */
+struct ep11_urb {
+	uint16_t		targets_num;
+	uint64_t		targets;
+	uint64_t		weight;
+	uint64_t		req_no;
+	uint64_t		req_len;
+	uint64_t		req;
+	uint64_t		resp_len;
+	uint64_t		resp;
+} __attribute__((packed));
+
 #define AUTOSELECT ((unsigned int)0xFFFFFFFF)
 
 #define ZCRYPT_IOCTL_MAGIC 'z'
@@ -183,6 +244,9 @@ struct ica_xcRB {
  *   ZSECSENDCPRB
  *     Send an arbitrary CPRB to a crypto card.
  *
+ *   ZSENDEP11CPRB
+ *     Send an arbitrary EP11 CPRB to an EP11 coprocessor crypto card.
+ *
  *   Z90STAT_STATUS_MASK
  *     Return an 64 element array of unsigned chars for the status of
  *     all devices.
@@ -256,6 +320,7 @@ struct ica_xcRB {
 #define ICARSAMODEXPO	_IOC(_IOC_READ|_IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x05, 0)
 #define ICARSACRT	_IOC(_IOC_READ|_IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x06, 0)
 #define ZSECSENDCPRB	_IOC(_IOC_READ|_IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x81, 0)
+#define ZSENDEP11CPRB	_IOC(_IOC_READ|_IOC_WRITE, ZCRYPT_IOCTL_MAGIC, 0x04, 0)
 
 /* New status calls */
 #define Z90STAT_TOTALCOUNT	_IOR(ZCRYPT_IOCTL_MAGIC, 0x40, int)
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 02300dc..ab3baa7 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -591,7 +591,13 @@ static int ap_init_queue(ap_qid_t qid)
 		if (rc != -ENODEV && rc != -EBUSY)
 			break;
 		if (i < AP_MAX_RESET - 1) {
-			udelay(5);
+			/* Time we are waiting until we give up (0.7sec * 90).
+			 * Since the actual request (in progress) will not
+			 * interrupted immediately for the reset command,
+			 * we have to be patient. In worst case we have to
+			 * wait 60sec + reset time (some msec).
+			 */
+			schedule_timeout(AP_RESET_TIMEOUT);
 			status = ap_test_queue(qid, &dummy, &dummy);
 		}
 	}
@@ -992,6 +998,28 @@ static ssize_t ap_domain_show(struct bus_type *bus, char *buf)
 
 static BUS_ATTR(ap_domain, 0444, ap_domain_show, NULL);
 
+static ssize_t ap_control_domain_mask_show(struct bus_type *bus, char *buf)
+{
+	if (ap_configuration != NULL) { /* QCI not supported */
+		if (test_facility(76)) { /* format 1 - 256 bit domain field */
+			return snprintf(buf, PAGE_SIZE,
+				"0x%08x%08x%08x%08x%08x%08x%08x%08x\n",
+			ap_configuration->adm[0], ap_configuration->adm[1],
+			ap_configuration->adm[2], ap_configuration->adm[3],
+			ap_configuration->adm[4], ap_configuration->adm[5],
+			ap_configuration->adm[6], ap_configuration->adm[7]);
+		} else { /* format 0 - 16 bit domain field */
+			return snprintf(buf, PAGE_SIZE, "%08x%08x\n",
+			ap_configuration->adm[0], ap_configuration->adm[1]);
+		  }
+	} else {
+		return snprintf(buf, PAGE_SIZE, "not supported\n");
+	  }
+}
+
+static BUS_ATTR(ap_control_domain_mask, 0444,
+		ap_control_domain_mask_show, NULL);
+
 static ssize_t ap_config_time_show(struct bus_type *bus, char *buf)
 {
 	return snprintf(buf, PAGE_SIZE, "%d\n", ap_config_time);
@@ -1077,6 +1105,7 @@ static BUS_ATTR(poll_timeout, 0644, poll_timeout_show, poll_timeout_store);
 
 static struct bus_attribute *const ap_bus_attrs[] = {
 	&bus_attr_ap_domain,
+	&bus_attr_ap_control_domain_mask,
 	&bus_attr_config_time,
 	&bus_attr_poll_thread,
 	&bus_attr_ap_interrupts,
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index 685f6cc0..6405ae2 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -33,7 +33,7 @@
 #define AP_DEVICES 64		/* Number of AP devices. */
 #define AP_DOMAINS 16		/* Number of AP domains. */
 #define AP_MAX_RESET 90		/* Maximum number of resets. */
-#define AP_RESET_TIMEOUT (HZ/2)	/* Time in ticks for reset timeouts. */
+#define AP_RESET_TIMEOUT (HZ*0.7)	/* Time in ticks for reset timeouts. */
 #define AP_CONFIG_TIME 30	/* Time in seconds between AP bus rescans. */
 #define AP_POLL_TIME 1		/* Time in ticks between receive polls. */
 
@@ -125,6 +125,8 @@ static inline int ap_test_bit(unsigned int *ptr, unsigned int nr)
 #define AP_FUNC_CRT4K 2
 #define AP_FUNC_COPRO 3
 #define AP_FUNC_ACCEL 4
+#define AP_FUNC_EP11  5
+#define AP_FUNC_APXA  6
 
 /*
  * AP reset flag states
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index 31cfaa5..4b824b1 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -44,6 +44,8 @@
 #include "zcrypt_debug.h"
 #include "zcrypt_api.h"
 
+#include "zcrypt_msgtype6.h"
+
 /*
  * Module description.
  */
@@ -554,9 +556,9 @@ static long zcrypt_send_cprb(struct ica_xcRB *xcRB)
 	spin_lock_bh(&zcrypt_device_lock);
 	list_for_each_entry(zdev, &zcrypt_device_list, list) {
 		if (!zdev->online || !zdev->ops->send_cprb ||
-		    (xcRB->user_defined != AUTOSELECT &&
-			AP_QID_DEVICE(zdev->ap_dev->qid) != xcRB->user_defined)
-		    )
+		   (zdev->ops->variant == MSGTYPE06_VARIANT_EP11) ||
+		   (xcRB->user_defined != AUTOSELECT &&
+		    AP_QID_DEVICE(zdev->ap_dev->qid) != xcRB->user_defined))
 			continue;
 		zcrypt_device_get(zdev);
 		get_device(&zdev->ap_dev->device);
@@ -581,6 +583,90 @@ static long zcrypt_send_cprb(struct ica_xcRB *xcRB)
 	return -ENODEV;
 }
 
+struct ep11_target_dev_list {
+	unsigned short		targets_num;
+	struct ep11_target_dev	*targets;
+};
+
+static bool is_desired_ep11dev(unsigned int dev_qid,
+			       struct ep11_target_dev_list dev_list)
+{
+	int n;
+
+	for (n = 0; n < dev_list.targets_num; n++, dev_list.targets++) {
+		if ((AP_QID_DEVICE(dev_qid) == dev_list.targets->ap_id) &&
+		    (AP_QID_QUEUE(dev_qid) == dev_list.targets->dom_id)) {
+			return true;
+		}
+	}
+	return false;
+}
+
+static long zcrypt_send_ep11_cprb(struct ep11_urb *xcrb)
+{
+	struct zcrypt_device *zdev;
+	bool autoselect = false;
+	int rc;
+	struct ep11_target_dev_list ep11_dev_list = {
+		.targets_num	=  0x00,
+		.targets	=  NULL,
+	};
+
+	ep11_dev_list.targets_num = (unsigned short) xcrb->targets_num;
+
+	/* empty list indicates autoselect (all available targets) */
+	if (ep11_dev_list.targets_num == 0)
+		autoselect = true;
+	else {
+		ep11_dev_list.targets = kcalloc((unsigned short)
+						xcrb->targets_num,
+						sizeof(struct ep11_target_dev),
+						GFP_KERNEL);
+		if (!ep11_dev_list.targets)
+			return -ENOMEM;
+
+		if (copy_from_user(ep11_dev_list.targets,
+				   (struct ep11_target_dev *)xcrb->targets,
+				   xcrb->targets_num *
+				   sizeof(struct ep11_target_dev)))
+			return -EFAULT;
+	}
+
+	spin_lock_bh(&zcrypt_device_lock);
+	list_for_each_entry(zdev, &zcrypt_device_list, list) {
+		/* check if device is eligible */
+		if (!zdev->online ||
+		    zdev->ops->variant != MSGTYPE06_VARIANT_EP11)
+			continue;
+
+		/* check if device is selected as valid target */
+		if (!is_desired_ep11dev(zdev->ap_dev->qid, ep11_dev_list) &&
+		    !autoselect)
+			continue;
+
+		zcrypt_device_get(zdev);
+		get_device(&zdev->ap_dev->device);
+		zdev->request_count++;
+		__zcrypt_decrease_preference(zdev);
+		if (try_module_get(zdev->ap_dev->drv->driver.owner)) {
+			spin_unlock_bh(&zcrypt_device_lock);
+			rc = zdev->ops->send_ep11_cprb(zdev, xcrb);
+			spin_lock_bh(&zcrypt_device_lock);
+			module_put(zdev->ap_dev->drv->driver.owner);
+		} else {
+			rc = -EAGAIN;
+		  }
+		zdev->request_count--;
+		__zcrypt_increase_preference(zdev);
+		put_device(&zdev->ap_dev->device);
+		zcrypt_device_put(zdev);
+		spin_unlock_bh(&zcrypt_device_lock);
+		return rc;
+	}
+	spin_unlock_bh(&zcrypt_device_lock);
+	return -ENODEV;
+}
+
 static long zcrypt_rng(char *buffer)
 {
 	struct zcrypt_device *zdev;
@@ -784,6 +870,23 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd,
 			return -EFAULT;
 		return rc;
 	}
+	case ZSENDEP11CPRB: {
+		struct ep11_urb __user *uxcrb = (void __user *)arg;
+		struct ep11_urb xcrb;
+		if (copy_from_user(&xcrb, uxcrb, sizeof(xcrb)))
+			return -EFAULT;
+		do {
+			rc = zcrypt_send_ep11_cprb(&xcrb);
+		} while (rc == -EAGAIN);
+		/* on failure: retry once again after a requested rescan */
+		if ((rc == -ENODEV) && (zcrypt_process_rescan()))
+			do {
+				rc = zcrypt_send_ep11_cprb(&xcrb);
+			} while (rc == -EAGAIN);
+		if (copy_to_user(uxcrb, &xcrb, sizeof(xcrb)))
+			return -EFAULT;
+		return rc;
+	}
 	case Z90STAT_STATUS_MASK: {
 		char status[AP_DEVICES];
 		zcrypt_status_mask(status);
diff --git a/drivers/s390/crypto/zcrypt_api.h b/drivers/s390/crypto/zcrypt_api.h
index 8963291..b3d496b 100644
--- a/drivers/s390/crypto/zcrypt_api.h
+++ b/drivers/s390/crypto/zcrypt_api.h
@@ -74,6 +74,7 @@ struct ica_z90_status {
 #define ZCRYPT_CEX2A		6
 #define ZCRYPT_CEX3C		7
 #define ZCRYPT_CEX3A		8
+#define ZCRYPT_CEX4	       10
 
 /**
  * Large random numbers are pulled in 4096 byte chunks from the crypto cards
@@ -89,6 +90,7 @@ struct zcrypt_ops {
 	long (*rsa_modexpo_crt)(struct zcrypt_device *,
 				struct ica_rsa_modexpo_crt *);
 	long (*send_cprb)(struct zcrypt_device *, struct ica_xcRB *);
+	long (*send_ep11_cprb)(struct zcrypt_device *, struct ep11_urb *);
 	long (*rng)(struct zcrypt_device *, char *);
 	struct list_head list;		/* zcrypt ops list. */
 	struct module *owner;
diff --git a/drivers/s390/crypto/zcrypt_cex4.c b/drivers/s390/crypto/zcrypt_cex4.c
index ce12263..569f8b1 100644
--- a/drivers/s390/crypto/zcrypt_cex4.c
+++ b/drivers/s390/crypto/zcrypt_cex4.c
@@ -30,7 +30,12 @@
 #define CEX4A_MAX_MESSAGE_SIZE	MSGTYPE50_CRB3_MAX_MSG_SIZE
 #define CEX4C_MAX_MESSAGE_SIZE	MSGTYPE06_MAX_MSG_SIZE
 
-#define CEX4_CLEANUP_TIME	(15*HZ)
+/* Waiting time for requests to be processed.
+ * Currently there are some types of request which are not deterministic.
+ * But the maximum time limit managed by the stomper code is set to 60sec.
+ * Hence we have to wait at least that time period.
+ */
+#define CEX4_CLEANUP_TIME	(61*HZ)
 
 static struct ap_device_id zcrypt_cex4_ids[] = {
 	{ AP_DEVICE(AP_DEVICE_TYPE_CEX4)  },
@@ -101,6 +106,19 @@ static int zcrypt_cex4_probe(struct ap_device *ap_dev)
 			zdev->speed_rating = CEX4C_SPEED_RATING;
 			zdev->ops = zcrypt_msgtype_request(MSGTYPE06_NAME,
 							   MSGTYPE06_VARIANT_DEFAULT);
+		} else if (ap_test_bit(&ap_dev->functions, AP_FUNC_EP11)) {
+			zdev = zcrypt_device_alloc(CEX4C_MAX_MESSAGE_SIZE);
+			if (!zdev)
+				return -ENOMEM;
+			zdev->type_string = "CEX4P";
+			zdev->user_space_type = ZCRYPT_CEX4;
+			zdev->min_mod_size = CEX4C_MIN_MOD_SIZE;
+			zdev->max_mod_size = CEX4C_MAX_MOD_SIZE;
+			zdev->max_exp_bit_length = CEX4C_MAX_MOD_SIZE;
+			zdev->short_crt = 0;
+			zdev->speed_rating = CEX4C_SPEED_RATING;
+			zdev->ops = zcrypt_msgtype_request(MSGTYPE06_NAME,
+							MSGTYPE06_VARIANT_EP11);
 		}
 		break;
 	}
diff --git a/drivers/s390/crypto/zcrypt_error.h b/drivers/s390/crypto/zcrypt_error.h
index 0079b66..7b23f43 100644
--- a/drivers/s390/crypto/zcrypt_error.h
+++ b/drivers/s390/crypto/zcrypt_error.h
@@ -106,15 +106,15 @@ static inline int convert_error(struct zcrypt_device *zdev,
 	//   REP88_ERROR_MESSAGE_TYPE		// '20' CEX2A
 		/*
 		 * To sent a message of the wrong type is a bug in the
-		 * device driver. Warn about it, disable the device
+		 * device driver. Send error msg, disable the device
 		 * and then repeat the request.
 		 */
-		WARN_ON(1);
 		atomic_set(&zcrypt_rescan_req, 1);
 		zdev->online = 0;
+		pr_err("Cryptographic device %x failed and was set offline\n",
+		       zdev->ap_dev->qid);
 		ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%drc%d",
-			       zdev->ap_dev->qid,
-			       zdev->online, ehdr->reply_code);
+			zdev->ap_dev->qid, zdev->online, ehdr->reply_code);
 		return -EAGAIN;
 	case REP82_ERROR_TRANSPORT_FAIL:
 	case REP82_ERROR_MACHINE_FAILURE:
@@ -122,15 +122,17 @@ static inline int convert_error(struct zcrypt_device *zdev,
 		/* If a card fails disable it and repeat the request. */
 		atomic_set(&zcrypt_rescan_req, 1);
 		zdev->online = 0;
+		pr_err("Cryptographic device %x failed and was set offline\n",
+		       zdev->ap_dev->qid);
 		ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%drc%d",
-			       zdev->ap_dev->qid,
-			       zdev->online, ehdr->reply_code);
+			zdev->ap_dev->qid, zdev->online, ehdr->reply_code);
 		return -EAGAIN;
 	default:
 		zdev->online = 0;
+		pr_err("Cryptographic device %x failed and was set offline\n",
+		       zdev->ap_dev->qid);
 		ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%drc%d",
-			       zdev->ap_dev->qid,
-			       zdev->online, ehdr->reply_code);
+			zdev->ap_dev->qid, zdev->online, ehdr->reply_code);
 		return -EAGAIN;	/* repeat the request on a different device. */
 	}
 }
diff --git a/drivers/s390/crypto/zcrypt_msgtype50.c b/drivers/s390/crypto/zcrypt_msgtype50.c
index 7c522f3..334e282 100644
--- a/drivers/s390/crypto/zcrypt_msgtype50.c
+++ b/drivers/s390/crypto/zcrypt_msgtype50.c
@@ -25,6 +25,9 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#define KMSG_COMPONENT "zcrypt"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/init.h>
@@ -332,6 +335,11 @@ static int convert_type80(struct zcrypt_device *zdev,
 	if (t80h->len < sizeof(*t80h) + outputdatalength) {
 		/* The result is too short, the CEX2A card may not do that.. */
 		zdev->online = 0;
+		pr_err("Cryptographic device %x failed and was set offline\n",
+		       zdev->ap_dev->qid);
+		ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%drc%d",
+			       zdev->ap_dev->qid, zdev->online, t80h->code);
+
 		return -EAGAIN;	/* repeat the request on a different device. */
 	}
 	if (zdev->user_space_type == ZCRYPT_CEX2A)
@@ -359,6 +367,10 @@ static int convert_response(struct zcrypt_device *zdev,
 				      outputdata, outputdatalength);
 	default: /* Unknown response type, this should NEVER EVER happen */
 		zdev->online = 0;
+		pr_err("Cryptographic device %x failed and was set offline\n",
+		       zdev->ap_dev->qid);
+		ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%dfail",
+			       zdev->ap_dev->qid, zdev->online);
 		return -EAGAIN;	/* repeat the request on a different device. */
 	}
 }
diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c
index 7d97fa5..57bfda1 100644
--- a/drivers/s390/crypto/zcrypt_msgtype6.c
+++ b/drivers/s390/crypto/zcrypt_msgtype6.c
@@ -25,6 +25,9 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#define KMSG_COMPONENT "zcrypt"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/err.h>
@@ -50,6 +53,7 @@ struct response_type {
 };
 #define PCIXCC_RESPONSE_TYPE_ICA  0
 #define PCIXCC_RESPONSE_TYPE_XCRB 1
+#define PCIXCC_RESPONSE_TYPE_EP11 2
 
 MODULE_AUTHOR("IBM Corporation");
 MODULE_DESCRIPTION("Cryptographic Coprocessor (message type 6), " \
@@ -358,6 +362,91 @@ static int XCRB_msg_to_type6CPRB_msgX(struct zcrypt_device *zdev,
 	return 0;
 }
 
+static int xcrb_msg_to_type6_ep11cprb_msgx(struct zcrypt_device *zdev,
+				       struct ap_message *ap_msg,
+				       struct ep11_urb *xcRB)
+{
+	unsigned int lfmt;
+
+	static struct type6_hdr static_type6_ep11_hdr = {
+		.type		=  0x06,
+		.rqid		= {0x00, 0x01},
+		.function_code	= {0x00, 0x00},
+		.agent_id[0]	=  0x58,	/* {'X'} */
+		.agent_id[1]	=  0x43,	/* {'C'} */
+		.offset1	=  0x00000058,
+	};
+
+	struct {
+		struct type6_hdr hdr;
+		struct ep11_cprb cprbx;
+		unsigned char	pld_tag;	/* fixed value 0x30 */
+		unsigned char	pld_lenfmt;	/* payload length format */
+	} __packed * msg = ap_msg->message;
+
+	struct pld_hdr {
+		unsigned char	func_tag;	/* fixed value 0x4 */
+		unsigned char	func_len;	/* fixed value 0x4 */
+		unsigned int	func_val;	/* function ID	   */
+		unsigned char	dom_tag;	/* fixed value 0x4 */
+		unsigned char	dom_len;	/* fixed value 0x4 */
+		unsigned int	dom_val;	/* domain id	   */
+	} __packed * payload_hdr;
+
+	/* length checks */
+	ap_msg->length = sizeof(struct type6_hdr) + xcRB->req_len;
+	if (CEIL4(xcRB->req_len) > MSGTYPE06_MAX_MSG_SIZE -
+				   (sizeof(struct type6_hdr)))
+		return -EINVAL;
+
+	if (CEIL4(xcRB->resp_len) > MSGTYPE06_MAX_MSG_SIZE -
+				    (sizeof(struct type86_fmt2_msg)))
+		return -EINVAL;
+
+	/* prepare type6 header */
+	msg->hdr = static_type6_ep11_hdr;
+	msg->hdr.ToCardLen1   = xcRB->req_len;
+	msg->hdr.FromCardLen1 = xcRB->resp_len;
+
+	/* Import CPRB data from the ioctl input parameter */
+	if (copy_from_user(&(msg->cprbx.cprb_len),
+			   (char *)xcRB->req, xcRB->req_len)) {
+		return -EFAULT;
+	}
+
+	/*
+	 The target domain field within the cprb body/payload block will be
+	 replaced by the usage domain for non-management commands only.
+	 Therefore we check the first bit of the 'flags' parameter for
+	 management command indication.
+	   0 - non managment command
+	   1 - management command
+	*/
+	if (!((msg->cprbx.flags & 0x80) == 0x80)) {
+		msg->cprbx.target_id = (unsigned int)
+					AP_QID_QUEUE(zdev->ap_dev->qid);
+
+		if ((msg->pld_lenfmt & 0x80) == 0x80) { /*ext.len.fmt 2 or 3*/
+			switch (msg->pld_lenfmt & 0x03) {
+			case 1:
+				lfmt = 2;
+				break;
+			case 2:
+				lfmt = 3;
+				break;
+			default:
+				return -EINVAL;
+			}
+		} else {
+			lfmt = 1; /* length format #1 */
+		  }
+		payload_hdr = (struct pld_hdr *)((&(msg->pld_lenfmt))+lfmt);
+		payload_hdr->dom_val = (unsigned int)
+					AP_QID_QUEUE(zdev->ap_dev->qid);
+	}
+	return 0;
+}
+
 /**
  * Copy results from a type 86 ICA reply message back to user space.
  *
@@ -377,6 +466,12 @@ struct type86x_reply {
 	char text[0];
 } __packed;
 
+struct type86_ep11_reply {
+	struct type86_hdr hdr;
+	struct type86_fmt2_ext fmt2;
+	struct ep11_cprb cprbx;
+} __packed;
+
 static int convert_type86_ica(struct zcrypt_device *zdev,
 			  struct ap_message *reply,
 			  char __user *outputdata,
@@ -440,6 +535,11 @@ static int convert_type86_ica(struct zcrypt_device *zdev,
 		if (service_rc == 8 && service_rs == 72)
 			return -EINVAL;
 		zdev->online = 0;
+		pr_err("Cryptographic device %x failed and was set offline\n",
+		       zdev->ap_dev->qid);
+		ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%drc%d",
+			       zdev->ap_dev->qid, zdev->online,
+			       msg->hdr.reply_code);
 		return -EAGAIN;	/* repeat the request on a different device. */
 	}
 	data = msg->text;
@@ -503,6 +603,33 @@ static int convert_type86_xcrb(struct zcrypt_device *zdev,
 	return 0;
 }
 
+/**
+ * Copy results from a type 86 EP11 XCRB reply message back to user space.
+ *
+ * @zdev: crypto device pointer
+ * @reply: reply AP message.
+ * @xcRB: pointer to EP11 user request block
+ *
+ * Returns 0 on success or -EINVAL, -EFAULT, -EAGAIN in case of an error.
+ */
+static int convert_type86_ep11_xcrb(struct zcrypt_device *zdev,
+				    struct ap_message *reply,
+				    struct ep11_urb *xcRB)
+{
+	struct type86_fmt2_msg *msg = reply->message;
+	char *data = reply->message;
+
+	if (xcRB->resp_len < msg->fmt2.count1)
+		return -EINVAL;
+
+	/* Copy response CPRB to user */
+	if (copy_to_user((char *)xcRB->resp,
+			 data + msg->fmt2.offset1, msg->fmt2.count1))
+		return -EFAULT;
+	xcRB->resp_len = msg->fmt2.count1;
+	return 0;
+}
+
 static int convert_type86_rng(struct zcrypt_device *zdev,
 			  struct ap_message *reply,
 			  char *buffer)
@@ -551,6 +678,10 @@ static int convert_response_ica(struct zcrypt_device *zdev,
 		 * response */
 	default: /* Unknown response type, this should NEVER EVER happen */
 		zdev->online = 0;
+		pr_err("Cryptographic device %x failed and was set offline\n",
+		       zdev->ap_dev->qid);
+		ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%dfail",
+			       zdev->ap_dev->qid, zdev->online);
 		return -EAGAIN;	/* repeat the request on a different device. */
 	}
 }
@@ -579,10 +710,40 @@ static int convert_response_xcrb(struct zcrypt_device *zdev,
 	default: /* Unknown response type, this should NEVER EVER happen */
 		xcRB->status = 0x0008044DL; /* HDD_InvalidParm */
 		zdev->online = 0;
+		pr_err("Cryptographic device %x failed and was set offline\n",
+		       zdev->ap_dev->qid);
+		ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%dfail",
+			       zdev->ap_dev->qid, zdev->online);
 		return -EAGAIN;	/* repeat the request on a different device. */
 	}
 }
 
+static int convert_response_ep11_xcrb(struct zcrypt_device *zdev,
+	struct ap_message *reply, struct ep11_urb *xcRB)
+{
+	struct type86_ep11_reply *msg = reply->message;
+
+	/* Response type byte is the second byte in the response. */
+	switch (((unsigned char *)reply->message)[1]) {
+	case TYPE82_RSP_CODE:
+	case TYPE87_RSP_CODE:
+		return convert_error(zdev, reply);
+	case TYPE86_RSP_CODE:
+		if (msg->hdr.reply_code)
+			return convert_error(zdev, reply);
+		if (msg->cprbx.cprb_ver_id == 0x04)
+			return convert_type86_ep11_xcrb(zdev, reply, xcRB);
+	/* Fall through, no break, incorrect cprb version is an unknown resp.*/
+	default: /* Unknown response type, this should NEVER EVER happen */
+		zdev->online = 0;
+		pr_err("Cryptographic device %x failed and was set offline\n",
+		       zdev->ap_dev->qid);
+		ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%dfail",
+			       zdev->ap_dev->qid, zdev->online);
+		return -EAGAIN; /* repeat the request on a different device. */
+	}
+}
+
 static int convert_response_rng(struct zcrypt_device *zdev,
 				 struct ap_message *reply,
 				 char *data)
@@ -602,6 +763,10 @@ static int convert_response_rng(struct zcrypt_device *zdev,
 		 * response */
 	default: /* Unknown response type, this should NEVER EVER happen */
 		zdev->online = 0;
+		pr_err("Cryptographic device %x failed and was set offline\n",
+		       zdev->ap_dev->qid);
+		ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%dfail",
+			       zdev->ap_dev->qid, zdev->online);
 		return -EAGAIN;	/* repeat the request on a different device. */
 	}
 }
@@ -657,6 +822,51 @@ out:
 	complete(&(resp_type->work));
 }
 
+/**
+ * This function is called from the AP bus code after a crypto request
+ * "msg" has finished with the reply message "reply".
+ * It is called from tasklet context.
+ * @ap_dev: pointer to the AP device
+ * @msg: pointer to the AP message
+ * @reply: pointer to the AP reply message
+ */
+static void zcrypt_msgtype6_receive_ep11(struct ap_device *ap_dev,
+					 struct ap_message *msg,
+					 struct ap_message *reply)
+{
+	static struct error_hdr error_reply = {
+		.type = TYPE82_RSP_CODE,
+		.reply_code = REP82_ERROR_MACHINE_FAILURE,
+	};
+	struct response_type *resp_type =
+		(struct response_type *)msg->private;
+	struct type86_ep11_reply *t86r;
+	int length;
+
+	/* Copy the reply message to the request message buffer. */
+	if (IS_ERR(reply)) {
+		memcpy(msg->message, &error_reply, sizeof(error_reply));
+		goto out;
+	}
+	t86r = reply->message;
+	if (t86r->hdr.type == TYPE86_RSP_CODE &&
+	    t86r->cprbx.cprb_ver_id == 0x04) {
+		switch (resp_type->type) {
+		case PCIXCC_RESPONSE_TYPE_EP11:
+			length = t86r->fmt2.offset1 + t86r->fmt2.count1;
+			length = min(MSGTYPE06_MAX_MSG_SIZE, length);
+			memcpy(msg->message, reply->message, length);
+			break;
+		default:
+			memcpy(msg->message, &error_reply, sizeof(error_reply));
+		}
+	} else {
+		memcpy(msg->message, reply->message, sizeof(error_reply));
+	  }
+out:
+	complete(&(resp_type->work));
+}
+
 static atomic_t zcrypt_step = ATOMIC_INIT(0);
 
 /**
@@ -782,6 +992,46 @@ out_free:
 }
 
 /**
+ * The request distributor calls this function if it picked the CEX4P
+ * device to handle a send_ep11_cprb request.
+ * @zdev: pointer to zcrypt_device structure that identifies the
+ *	  CEX4P device to the request distributor
+ * @xcRB: pointer to the ep11 user request block
+ */
+static long zcrypt_msgtype6_send_ep11_cprb(struct zcrypt_device *zdev,
+						struct ep11_urb *xcrb)
+{
+	struct ap_message ap_msg;
+	struct response_type resp_type = {
+		.type = PCIXCC_RESPONSE_TYPE_EP11,
+	};
+	int rc;
+
+	ap_init_message(&ap_msg);
+	ap_msg.message = kmalloc(MSGTYPE06_MAX_MSG_SIZE, GFP_KERNEL);
+	if (!ap_msg.message)
+		return -ENOMEM;
+	ap_msg.receive = zcrypt_msgtype6_receive_ep11;
+	ap_msg.psmid = (((unsigned long long) current->pid) << 32) +
+				atomic_inc_return(&zcrypt_step);
+	ap_msg.private = &resp_type;
+	rc = xcrb_msg_to_type6_ep11cprb_msgx(zdev, &ap_msg, xcrb);
+	if (rc)
+		goto out_free;
+	init_completion(&resp_type.work);
+	ap_queue_message(zdev->ap_dev, &ap_msg);
+	rc = wait_for_completion_interruptible(&resp_type.work);
+	if (rc == 0)
+		rc = convert_response_ep11_xcrb(zdev, &ap_msg, xcrb);
+	else /* Signal pending. */
+		ap_cancel_message(zdev->ap_dev, &ap_msg);
+
+out_free:
+	kzfree(ap_msg.message);
+	return rc;
+}
+
+/**
  * The request distributor calls this function if it picked the PCIXCC/CEX2C
  * device to generate random data.
  * @zdev: pointer to zcrypt_device structure that identifies the
@@ -839,10 +1089,19 @@ static struct zcrypt_ops zcrypt_msgtype6_ops = {
 	.rng = zcrypt_msgtype6_rng,
 };
 
+static struct zcrypt_ops zcrypt_msgtype6_ep11_ops = {
+	.owner = THIS_MODULE,
+	.variant = MSGTYPE06_VARIANT_EP11,
+	.rsa_modexpo = NULL,
+	.rsa_modexpo_crt = NULL,
+	.send_ep11_cprb = zcrypt_msgtype6_send_ep11_cprb,
+};
+
 int __init zcrypt_msgtype6_init(void)
 {
 	zcrypt_msgtype_register(&zcrypt_msgtype6_norng_ops);
 	zcrypt_msgtype_register(&zcrypt_msgtype6_ops);
+	zcrypt_msgtype_register(&zcrypt_msgtype6_ep11_ops);
 	return 0;
 }
 
@@ -850,6 +1109,7 @@ void __exit zcrypt_msgtype6_exit(void)
 {
 	zcrypt_msgtype_unregister(&zcrypt_msgtype6_norng_ops);
 	zcrypt_msgtype_unregister(&zcrypt_msgtype6_ops);
+	zcrypt_msgtype_unregister(&zcrypt_msgtype6_ep11_ops);
 }
 
 module_init(zcrypt_msgtype6_init);
diff --git a/drivers/s390/crypto/zcrypt_msgtype6.h b/drivers/s390/crypto/zcrypt_msgtype6.h
index 1e500d3..2072475 100644
--- a/drivers/s390/crypto/zcrypt_msgtype6.h
+++ b/drivers/s390/crypto/zcrypt_msgtype6.h
@@ -32,6 +32,7 @@
 #define MSGTYPE06_NAME			"zcrypt_msgtype6"
 #define MSGTYPE06_VARIANT_DEFAULT	0
 #define MSGTYPE06_VARIANT_NORNG		1
+#define MSGTYPE06_VARIANT_EP11		2
 
 #define MSGTYPE06_MAX_MSG_SIZE		(12*1024)
 
@@ -99,6 +100,7 @@ struct type86_hdr {
 } __packed;
 
 #define TYPE86_RSP_CODE 0x86
+#define TYPE87_RSP_CODE 0x87
 #define TYPE86_FMT2	0x02
 
 struct type86_fmt2_ext {
diff --git a/drivers/s390/crypto/zcrypt_pcica.c b/drivers/s390/crypto/zcrypt_pcica.c
index f2b71d8..7a743f4 100644
--- a/drivers/s390/crypto/zcrypt_pcica.c
+++ b/drivers/s390/crypto/zcrypt_pcica.c
@@ -24,6 +24,9 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#define KMSG_COMPONENT "zcrypt"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/init.h>
@@ -199,6 +202,10 @@ static int convert_type84(struct zcrypt_device *zdev,
 	if (t84h->len < sizeof(*t84h) + outputdatalength) {
 		/* The result is too short, the PCICA card may not do that.. */
 		zdev->online = 0;
+		pr_err("Cryptographic device %x failed and was set offline\n",
+		       zdev->ap_dev->qid);
+		ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%drc%d",
+			       zdev->ap_dev->qid, zdev->online, t84h->code);
 		return -EAGAIN;	/* repeat the request on a different device. */
 	}
 	BUG_ON(t84h->len > PCICA_MAX_RESPONSE_SIZE);
@@ -223,6 +230,10 @@ static int convert_response(struct zcrypt_device *zdev,
 				      outputdata, outputdatalength);
 	default: /* Unknown response type, this should NEVER EVER happen */
 		zdev->online = 0;
+		pr_err("Cryptographic device %x failed and was set offline\n",
+		       zdev->ap_dev->qid);
+		ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%dfail",
+			       zdev->ap_dev->qid, zdev->online);
 		return -EAGAIN;	/* repeat the request on a different device. */
 	}
 }
diff --git a/drivers/s390/crypto/zcrypt_pcicc.c b/drivers/s390/crypto/zcrypt_pcicc.c
index 0d90a43..4d14c04 100644
--- a/drivers/s390/crypto/zcrypt_pcicc.c
+++ b/drivers/s390/crypto/zcrypt_pcicc.c
@@ -24,6 +24,9 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#define KMSG_COMPONENT "zcrypt"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/gfp.h>
@@ -372,6 +375,11 @@ static int convert_type86(struct zcrypt_device *zdev,
 		if (service_rc == 8 && service_rs == 72)
 			return -EINVAL;
 		zdev->online = 0;
+		pr_err("Cryptographic device %x failed and was set offline\n",
+		       zdev->ap_dev->qid);
+		ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%drc%d",
+			       zdev->ap_dev->qid, zdev->online,
+			       msg->hdr.reply_code);
 		return -EAGAIN;	/* repeat the request on a different device. */
 	}
 	data = msg->text;
@@ -425,6 +433,10 @@ static int convert_response(struct zcrypt_device *zdev,
 		/* no break, incorrect cprb version is an unknown response */
 	default: /* Unknown response type, this should NEVER EVER happen */
 		zdev->online = 0;
+		pr_err("Cryptographic device %x failed and was set offline\n",
+		       zdev->ap_dev->qid);
+		ZCRYPT_DBF_DEV(DBF_ERR, zdev, "dev%04xo%dfail",
+			       zdev->ap_dev->qid, zdev->online);
 		return -EAGAIN;	/* repeat the request on a different device. */
 	}
 }
-- 
cgit v0.10.2


From 2037be53b2bceac3c2e648b8ff3fd62e21af2d35 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung.kim@lge.com>
Date: Wed, 18 Dec 2013 14:21:09 +0900
Subject: perf sort: Compare addresses if no symbol info

If a hist entry doesn't have symbol information, compare it with its
address.  Currently it only compares its level or whether it's NULL.

This can lead to an undesired result like an overhead exceeds 100%
especially when callchain accumulation is enabled by later patch.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Rodrigo Campos <rodrigo@sdfg.com.ar>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1387344086-12744-2-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 8b0bb1f..68a4fd2 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -161,6 +161,11 @@ struct sort_entry sort_dso = {
 
 /* --sort symbol */
 
+static int64_t _sort__addr_cmp(u64 left_ip, u64 right_ip)
+{
+	return (int64_t)(right_ip - left_ip);
+}
+
 static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
 {
 	u64 ip_l, ip_r;
@@ -183,7 +188,7 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
 	int64_t ret;
 
 	if (!left->ms.sym && !right->ms.sym)
-		return right->level - left->level;
+		return _sort__addr_cmp(left->ip, right->ip);
 
 	/*
 	 * comparing symbol address alone is not enough since it's a
@@ -372,7 +377,7 @@ sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
 	struct addr_map_symbol *from_r = &right->branch_info->from;
 
 	if (!from_l->sym && !from_r->sym)
-		return right->level - left->level;
+		return _sort__addr_cmp(from_l->addr, from_r->addr);
 
 	return _sort__sym_cmp(from_l->sym, from_r->sym);
 }
@@ -384,7 +389,7 @@ sort__sym_to_cmp(struct hist_entry *left, struct hist_entry *right)
 	struct addr_map_symbol *to_r = &right->branch_info->to;
 
 	if (!to_l->sym && !to_r->sym)
-		return right->level - left->level;
+		return _sort__addr_cmp(to_l->addr, to_r->addr);
 
 	return _sort__sym_cmp(to_l->sym, to_r->sym);
 }
-- 
cgit v0.10.2


From 68f6d0224b2a19a4da4a12a5081f01776e5150df Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung.kim@lge.com>
Date: Wed, 18 Dec 2013 14:21:10 +0900
Subject: perf sort: Do not compare dso again

The commit 09600e0f9ebb ("perf tools: Compare dso's also when comparing
symbols") added a comparison of dso when comparing symbol.

But if the sort key already has dso, it doesn't need to do it again
since entries have a different dso already filtered out.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Rodrigo Campos <rodrigo@sdfg.com.ar>
Link: http://lkml.kernel.org/r/1387344086-12744-3-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 68a4fd2..635cd8f 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -13,6 +13,7 @@ int		have_ignore_callees = 0;
 int		sort__need_collapse = 0;
 int		sort__has_parent = 0;
 int		sort__has_sym = 0;
+int		sort__has_dso = 0;
 enum sort_mode	sort__mode = SORT_MODE__NORMAL;
 
 enum sort_type	sort__first_dimension;
@@ -194,9 +195,11 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
 	 * comparing symbol address alone is not enough since it's a
 	 * relative address within a dso.
 	 */
-	ret = sort__dso_cmp(left, right);
-	if (ret != 0)
-		return ret;
+	if (!sort__has_dso) {
+		ret = sort__dso_cmp(left, right);
+		if (ret != 0)
+			return ret;
+	}
 
 	return _sort__sym_cmp(left->ms.sym, right->ms.sym);
 }
@@ -1061,6 +1064,8 @@ int sort_dimension__add(const char *tok)
 			sort__has_parent = 1;
 		} else if (sd->entry == &sort_sym) {
 			sort__has_sym = 1;
+		} else if (sd->entry == &sort_dso) {
+			sort__has_dso = 1;
 		}
 
 		__sort_dimension__add(sd, i);
-- 
cgit v0.10.2


From f1cbf78d175e6202a29f53a7f915520e40a37baf Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung.kim@lge.com>
Date: Wed, 18 Dec 2013 14:21:11 +0900
Subject: perf hists: Do not pass period and weight to add_hist_entry()

The @entry argument already has the info so no need to pass them.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Rodrigo Campos <rodrigo@sdfg.com.ar>
Link: http://lkml.kernel.org/r/1387344086-12744-4-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 822903e..63234e3 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -342,15 +342,15 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 }
 
 static struct hist_entry *add_hist_entry(struct hists *hists,
-				      struct hist_entry *entry,
-				      struct addr_location *al,
-				      u64 period,
-				      u64 weight)
+					 struct hist_entry *entry,
+					 struct addr_location *al)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct hist_entry *he;
 	int64_t cmp;
+	u64 period = entry->stat.period;
+	u64 weight = entry->stat.weight;
 
 	p = &hists->entries_in->rb_node;
 
@@ -437,7 +437,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 		.transaction = transaction,
 	};
 
-	return add_hist_entry(hists, &entry, al, period, weight);
+	return add_hist_entry(hists, &entry, al);
 }
 
 int64_t
-- 
cgit v0.10.2


From bf19b82e7cf033319525a9eab12216b59c41c519 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung.kim@lge.com>
Date: Thu, 12 Dec 2013 16:36:17 +0900
Subject: tools lib traceevent: Introduce pevent_filter_strerror()

The pevent_filter_strerror() function is for receiving actual error
message from pevent_errno value.  To do that, add a static buffer to
event_filter for saving internal error message

If a failed function saved other information in the static buffer
returns the information, otherwise returns generic error message.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1386833777-3790-15-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 22566c2..2ce565a 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -5230,22 +5230,7 @@ int pevent_strerror(struct pevent *pevent __maybe_unused,
 
 	idx = errnum - __PEVENT_ERRNO__START - 1;
 	msg = pevent_error_str[idx];
-
-	switch (errnum) {
-	case PEVENT_ERRNO__MEM_ALLOC_FAILED:
-	case PEVENT_ERRNO__PARSE_EVENT_FAILED:
-	case PEVENT_ERRNO__READ_ID_FAILED:
-	case PEVENT_ERRNO__READ_FORMAT_FAILED:
-	case PEVENT_ERRNO__READ_PRINT_FAILED:
-	case PEVENT_ERRNO__OLD_FTRACE_ARG_FAILED:
-	case PEVENT_ERRNO__INVALID_ARG_TYPE:
-		snprintf(buf, buflen, "%s", msg);
-		break;
-
-	default:
-		/* cannot reach here */
-		break;
-	}
+	snprintf(buf, buflen, "%s", msg);
 
 	return 0;
 }
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 3ad784f..cf5db90 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -851,10 +851,13 @@ struct filter_type {
 	struct filter_arg	*filter;
 };
 
+#define PEVENT_FILTER_ERROR_BUFSZ  1024
+
 struct event_filter {
 	struct pevent		*pevent;
 	int			filters;
 	struct filter_type	*event_filters;
+	char			error_buffer[PEVENT_FILTER_ERROR_BUFSZ];
 };
 
 struct event_filter *pevent_filter_alloc(struct pevent *pevent);
@@ -874,10 +877,12 @@ enum filter_trivial_type {
 enum pevent_errno pevent_filter_add_filter_str(struct event_filter *filter,
 					       const char *filter_str);
 
-
 enum pevent_errno pevent_filter_match(struct event_filter *filter,
 				      struct pevent_record *record);
 
+int pevent_filter_strerror(struct event_filter *filter, enum pevent_errno err,
+			   char *buf, size_t buflen);
+
 int pevent_event_filtered(struct event_filter *filter,
 			  int event_id);
 
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index e2842b9..b502344 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -38,55 +38,31 @@ struct event_list {
 	struct event_format	*event;
 };
 
-#define MAX_ERR_STR_SIZE 256
-
-static void show_error(char **error_str, const char *fmt, ...)
+static void show_error(char *error_buf, const char *fmt, ...)
 {
 	unsigned long long index;
 	const char *input;
-	char *error;
 	va_list ap;
 	int len;
 	int i;
 
-	if (!error_str)
-		return;
-
 	input = pevent_get_input_buf();
 	index = pevent_get_input_buf_ptr();
 	len = input ? strlen(input) : 0;
 
-	error = malloc(MAX_ERR_STR_SIZE + (len*2) + 3);
-	if (error == NULL) {
-		/*
-		 * Maybe it's due to len is too long.
-		 * Retry without the input buffer part.
-		 */
-		len = 0;
-
-		error = malloc(MAX_ERR_STR_SIZE);
-		if (error == NULL) {
-			/* no memory */
-			*error_str = NULL;
-			return;
-		}
-	}
-
 	if (len) {
-		strcpy(error, input);
-		error[len] = '\n';
+		strcpy(error_buf, input);
+		error_buf[len] = '\n';
 		for (i = 1; i < len && i < index; i++)
-			error[len+i] = ' ';
-		error[len + i] = '^';
-		error[len + i + 1] = '\n';
+			error_buf[len+i] = ' ';
+		error_buf[len + i] = '^';
+		error_buf[len + i + 1] = '\n';
 		len += i+2;
 	}
 
 	va_start(ap, fmt);
-	vsnprintf(error + len, MAX_ERR_STR_SIZE, fmt, ap);
+	vsnprintf(error_buf + len, PEVENT_FILTER_ERROR_BUFSZ - len, fmt, ap);
 	va_end(ap);
-
-	*error_str = error;
 }
 
 static void free_token(char *token)
@@ -370,7 +346,7 @@ static void free_events(struct event_list *events)
 
 static enum pevent_errno
 create_arg_item(struct event_format *event, const char *token,
-		enum event_type type, struct filter_arg **parg, char **error_str)
+		enum event_type type, struct filter_arg **parg, char *error_str)
 {
 	struct format_field *field;
 	struct filter_arg *arg;
@@ -474,7 +450,7 @@ create_arg_cmp(enum filter_exp_type etype)
 }
 
 static enum pevent_errno
-add_right(struct filter_arg *op, struct filter_arg *arg, char **error_str)
+add_right(struct filter_arg *op, struct filter_arg *arg, char *error_str)
 {
 	struct filter_arg *left;
 	char *str;
@@ -786,7 +762,7 @@ enum filter_vals {
 
 static enum pevent_errno
 reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
-		struct filter_arg *arg, char **error_str)
+		struct filter_arg *arg, char *error_str)
 {
 	struct filter_arg *other_child;
 	struct filter_arg **ptr;
@@ -838,7 +814,7 @@ reparent_op_arg(struct filter_arg *parent, struct filter_arg *old_child,
 
 /* Returns either filter_vals (success) or pevent_errno (failfure) */
 static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
-		    char **error_str)
+		    char *error_str)
 {
 	int lval, rval;
 
@@ -938,7 +914,7 @@ static int test_arg(struct filter_arg *parent, struct filter_arg *arg,
 
 /* Remove any unknown event fields */
 static int collapse_tree(struct filter_arg *arg,
-			 struct filter_arg **arg_collapsed, char **error_str)
+			 struct filter_arg **arg_collapsed, char *error_str)
 {
 	int ret;
 
@@ -973,7 +949,7 @@ static int collapse_tree(struct filter_arg *arg,
 
 static enum pevent_errno
 process_filter(struct event_format *event, struct filter_arg **parg,
-	       char **error_str, int not)
+	       char *error_str, int not)
 {
 	enum event_type type;
 	char *token = NULL;
@@ -1211,7 +1187,7 @@ process_filter(struct event_format *event, struct filter_arg **parg,
 
 static enum pevent_errno
 process_event(struct event_format *event, const char *filter_str,
-	      struct filter_arg **parg, char **error_str)
+	      struct filter_arg **parg, char *error_str)
 {
 	int ret;
 
@@ -1236,7 +1212,7 @@ process_event(struct event_format *event, const char *filter_str,
 
 static enum pevent_errno
 filter_event(struct event_filter *filter, struct event_format *event,
-	     const char *filter_str, char **error_str)
+	     const char *filter_str, char *error_str)
 {
 	struct filter_type *filter_type;
 	struct filter_arg *arg;
@@ -1268,13 +1244,21 @@ filter_event(struct event_filter *filter, struct event_format *event,
 	return 0;
 }
 
+static void filter_init_error_buf(struct event_filter *filter)
+{
+	/* clear buffer to reset show error */
+	pevent_buffer_init("", 0);
+	filter->error_buffer[0] = '\0';
+}
+
 /**
  * pevent_filter_add_filter_str - add a new filter
  * @filter: the event filter to add to
  * @filter_str: the filter string that contains the filter
  *
  * Returns 0 if the filter was successfully added or a
- * negative error code.
+ * negative error code.  Use pevent_filter_strerror() to see
+ * actual error message in case of error.
  */
 enum pevent_errno pevent_filter_add_filter_str(struct event_filter *filter,
 					       const char *filter_str)
@@ -1291,10 +1275,8 @@ enum pevent_errno pevent_filter_add_filter_str(struct event_filter *filter,
 	enum pevent_errno rtn = 0; /* PEVENT_ERRNO__SUCCESS */
 	int len;
 	int ret;
-	char *error_str = NULL;
 
-	/* clear buffer to reset show error */
-	pevent_buffer_init("", 0);
+	filter_init_error_buf(filter);
 
 	filter_start = strchr(filter_str, ':');
 	if (filter_start)
@@ -1353,7 +1335,7 @@ enum pevent_errno pevent_filter_add_filter_str(struct event_filter *filter,
 	/* filter starts here */
 	for (event = events; event; event = event->next) {
 		ret = filter_event(filter, event->event, filter_start,
-				   &error_str);
+				   filter->error_buffer);
 		/* Failures are returned if a parse error happened */
 		if (ret < 0)
 			rtn = ret;
@@ -1382,6 +1364,32 @@ static void free_filter_type(struct filter_type *filter_type)
 }
 
 /**
+ * pevent_filter_strerror - fill error message in a buffer
+ * @filter: the event filter contains error
+ * @err: the error code
+ * @buf: the buffer to be filled in
+ * @buflen: the size of the buffer
+ *
+ * Returns 0 if message was filled successfully, -1 if error
+ */
+int pevent_filter_strerror(struct event_filter *filter, enum pevent_errno err,
+			   char *buf, size_t buflen)
+{
+	if (err <= __PEVENT_ERRNO__START || err >= __PEVENT_ERRNO__END)
+		return -1;
+
+	if (strlen(filter->error_buffer) > 0) {
+		size_t len = snprintf(buf, buflen, "%s", filter->error_buffer);
+
+		if (len > buflen)
+			return -1;
+		return 0;
+	}
+
+	return pevent_strerror(filter->pevent, err, buf, buflen);
+}
+
+/**
  * pevent_filter_remove_event - remove a filter for an event
  * @filter: the event filter to remove from
  * @event_id: the event to remove a filter for
@@ -2027,6 +2035,8 @@ enum pevent_errno pevent_filter_match(struct event_filter *filter,
 	int ret;
 	enum pevent_errno err = 0;
 
+	filter_init_error_buf(filter);
+
 	if (!filter->filters)
 		return PEVENT_ERRNO__NO_FILTER;
 
-- 
cgit v0.10.2


From bbca4d39175a96b882def1628e8b532998750dfa Mon Sep 17 00:00:00 2001
From: Gerhard Sittig <gsi@denx.de>
Date: Tue, 10 Dec 2013 10:51:08 +0100
Subject: powerpc/512x: dts: remove misplaced IRQ spec from 'soc' node (5125)

the 'soc' node in the MPC5125 "tower" board .dts has an '#interrupt-cells'
property although this node is not an interrupt controller

remove this erroneously placed property because starting with v3.13-rc1
lookup and resolution of 'interrupts' specs for peripherals gets misled
(tries to use the 'soc' as the interrupt parent which fails), emits
'no irq domain found' WARN() messages and breaks the boot process

[ best viewed with 'git diff -U5' to have DT node names in the context ]

Cc: Anatolij Gustschin <agust@denx.de>
Cc: linuxppc-dev@lists.ozlabs.org
Cc: devicetree@vger.kernel.org
Signed-off-by: Gerhard Sittig <gsi@denx.de>
Signed-off-by: Anatolij Gustschin <agust@denx.de>

diff --git a/arch/powerpc/boot/dts/mpc5125twr.dts b/arch/powerpc/boot/dts/mpc5125twr.dts
index 4177b62..0a0fe92 100644
--- a/arch/powerpc/boot/dts/mpc5125twr.dts
+++ b/arch/powerpc/boot/dts/mpc5125twr.dts
@@ -58,7 +58,6 @@
 		compatible = "fsl,mpc5121-immr";
 		#address-cells = <1>;
 		#size-cells = <1>;
-		#interrupt-cells = <2>;
 		ranges = <0x0 0x80000000 0x400000>;
 		reg = <0x80000000 0x400000>;
 		bus-frequency = <66000000>;	// 66 MHz ips bus
-- 
cgit v0.10.2


From 71a06c59d19a57c8dd2972ebee88030f5b0c700e Mon Sep 17 00:00:00 2001
From: dingtianhong <dingtianhong@huawei.com>
Date: Fri, 13 Dec 2013 17:29:19 +0800
Subject: bonding: protect port for bond_3ad_adapter_speed_changed()

Jay Vosburgh said that the bond_3ad_adapter_speed_changed is
called with RTNL only, and the function will modify the port's
information with no further locking, it will not mutex against
bond state machine and incoming LACPDU which do not hold RTNL,
So I add __get_state_machine_lock to protect the port.

But it is not a critical bug, it exist since day one, and till
now it has never been hit and reported, because changes to
speed is very rare, and will not occur critical problem.

The comment in the function is very old, cleanup it.

Suggested-by: Jay Vosburgh <fubar@us.ibm.com>
Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 187b1b7..6405ce3 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -2201,20 +2201,25 @@ void bond_3ad_adapter_speed_changed(struct slave *slave)
 
 	port = &(SLAVE_AD_INFO(slave).port);
 
-	// if slave is null, the whole port is not initialized
+	/* if slave is null, the whole port is not initialized */
 	if (!port->slave) {
 		pr_warning("Warning: %s: speed changed for uninitialized port on %s\n",
 			   slave->bond->dev->name, slave->dev->name);
 		return;
 	}
 
+	__get_state_machine_lock(port);
+
 	port->actor_admin_port_key &= ~AD_SPEED_KEY_BITS;
 	port->actor_oper_port_key = port->actor_admin_port_key |=
 		(__get_link_speed(port) << 1);
 	pr_debug("Port %d changed speed\n", port->actor_port_number);
-	// there is no need to reselect a new aggregator, just signal the
-	// state machines to reinitialize
+	/* there is no need to reselect a new aggregator, just signal the
+	 * state machines to reinitialize
+	 */
 	port->sm_vars |= AD_PORT_BEGIN;
+
+	__release_state_machine_lock(port);
 }
 
 /**
-- 
cgit v0.10.2


From bca44a7341924ec92ee7a1ba085c8f0745aeb74e Mon Sep 17 00:00:00 2001
From: dingtianhong <dingtianhong@huawei.com>
Date: Fri, 13 Dec 2013 17:29:24 +0800
Subject: bonding: protect port for bond_3ad_adapter_duplex_changed()

Jay Vosburgh said that the bond_3ad_adapter_duplex_changed is
called with RTNL only, and the function will modify the port's
information with no further locking, it will not mutex against
bond state machine and incoming LACPDU which do not hold RTNL,
So I add __get_state_machine_lock to protect the port.

But it is not a critical bug, it exist since day one, and till
now it has never been hit and reported, because changes to
speed is very rare, and will not occur critical problem.

The comments in the function is very old, cleanup it.

Suggested-by: Jay Vosburgh <fubar@us.ibm.com>
Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index 6405ce3..e851a67 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -2234,20 +2234,25 @@ void bond_3ad_adapter_duplex_changed(struct slave *slave)
 
 	port = &(SLAVE_AD_INFO(slave).port);
 
-	// if slave is null, the whole port is not initialized
+	/* if slave is null, the whole port is not initialized */
 	if (!port->slave) {
 		pr_warning("%s: Warning: duplex changed for uninitialized port on %s\n",
 			   slave->bond->dev->name, slave->dev->name);
 		return;
 	}
 
+	__get_state_machine_lock(port);
+
 	port->actor_admin_port_key &= ~AD_DUPLEX_KEY_BITS;
 	port->actor_oper_port_key = port->actor_admin_port_key |=
 		__get_duplex(port);
 	pr_debug("Port %d changed duplex\n", port->actor_port_number);
-	// there is no need to reselect a new aggregator, just signal the
-	// state machines to reinitialize
+	/* there is no need to reselect a new aggregator, just signal the
+	 * state machines to reinitialize
+	 */
 	port->sm_vars |= AD_PORT_BEGIN;
+
+	__release_state_machine_lock(port);
 }
 
 /**
-- 
cgit v0.10.2


From 108db7363736ceafdbc6fc708aa770939eb9906a Mon Sep 17 00:00:00 2001
From: dingtianhong <dingtianhong@huawei.com>
Date: Fri, 13 Dec 2013 17:29:29 +0800
Subject: bonding: protect port for bond_3ad_handle_link_change()

The bond_3ad_handle_link_change is called with RTNL only,
and the function will modify the port's information with
no further locking, it will not mutex against bond state
machine and incoming LACPDU which do not hold RTNL, So I
add __get_state_machine_lock to protect the port.

But it is not a critical bug, it exist since day one, and till
now it has never been hit and reported, because changes to
speed is very rare, and will not occur critical problem.

The comments in the function is very old, cleanup it and
add a new pr_debug to debug the port message.

Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index e851a67..4ced594 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -2268,15 +2268,21 @@ void bond_3ad_handle_link_change(struct slave *slave, char link)
 
 	port = &(SLAVE_AD_INFO(slave).port);
 
-	// if slave is null, the whole port is not initialized
+	/* if slave is null, the whole port is not initialized */
 	if (!port->slave) {
 		pr_warning("Warning: %s: link status changed for uninitialized port on %s\n",
 			   slave->bond->dev->name, slave->dev->name);
 		return;
 	}
 
-	// on link down we are zeroing duplex and speed since some of the adaptors(ce1000.lan) report full duplex/speed instead of N/A(duplex) / 0(speed)
-	// on link up we are forcing recheck on the duplex and speed since some of he adaptors(ce1000.lan) report
+	__get_state_machine_lock(port);
+	/* on link down we are zeroing duplex and speed since
+	 * some of the adaptors(ce1000.lan) report full duplex/speed
+	 * instead of N/A(duplex) / 0(speed).
+	 *
+	 * on link up we are forcing recheck on the duplex and speed since
+	 * some of he adaptors(ce1000.lan) report.
+	 */
 	if (link == BOND_LINK_UP) {
 		port->is_enabled = true;
 		port->actor_admin_port_key &= ~AD_DUPLEX_KEY_BITS;
@@ -2292,10 +2298,15 @@ void bond_3ad_handle_link_change(struct slave *slave, char link)
 		port->actor_oper_port_key = (port->actor_admin_port_key &=
 					     ~AD_SPEED_KEY_BITS);
 	}
-	//BOND_PRINT_DBG(("Port %d changed link status to %s", port->actor_port_number, ((link == BOND_LINK_UP)?"UP":"DOWN")));
-	// there is no need to reselect a new aggregator, just signal the
-	// state machines to reinitialize
+	pr_debug("Port %d changed link status to %s",
+		port->actor_port_number,
+		(link == BOND_LINK_UP) ? "UP" : "DOWN");
+	/* there is no need to reselect a new aggregator, just signal the
+	 * state machines to reinitialize
+	 */
 	port->sm_vars |= AD_PORT_BEGIN;
+
+	__release_state_machine_lock(port);
 }
 
 /*
-- 
cgit v0.10.2


From a81d8762d71396f69d27187a909fcc69f1a7be75 Mon Sep 17 00:00:00 2001
From: Mugunthan V N <mugunthanvnm@ti.com>
Date: Fri, 13 Dec 2013 18:42:55 +0530
Subject: drivers: net cpsw: Enable In Band mode in cpsw for 10 mbps

This patch adds support for enabling In Band mode in 10 mbps speed.
RGMII supports 1 Gig and 100 mbps mode for Forced mode of operation.
For 10mbps mode it should be configured to in band mode so that link
status, duplexity and speed are determined from the RGMII input data
stream

Signed-off-by: Mugunthan V N <mugunthanvnm@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 5120d9c..614f284 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -740,6 +740,8 @@ static void _cpsw_adjust_link(struct cpsw_slave *slave,
 		/* set speed_in input in case RMII mode is used in 100Mbps */
 		if (phy->speed == 100)
 			mac_control |= BIT(15);
+		else if (phy->speed == 10)
+			mac_control |= BIT(18); /* In Band mode */
 
 		*link = true;
 	} else {
-- 
cgit v0.10.2


From 0e3da5bb8da45890b1dc413404e0f978ab71173e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Timo=20Ter=C3=A4s?= <timo.teras@iki.fi>
Date: Mon, 16 Dec 2013 11:02:09 +0200
Subject: ip_gre: fix msg_name parsing for recvfrom/recvmsg
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ipgre_header_parse() needs to parse the tunnel's ip header and it
uses mac_header to locate the iphdr. This got broken when gre tunneling
was refactored as mac_header is no longer updated to point to iphdr.
Introduce skb_pop_mac_header() helper to do the mac_header assignment
and use it in ipgre_rcv() to fix msg_name parsing.

Bug introduced in commit c54419321455 (GRE: Refactor GRE tunneling code.)

Cc: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: Timo Teräs <timo.teras@iki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 215b5ea..6aae838 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1638,6 +1638,11 @@ static inline void skb_set_mac_header(struct sk_buff *skb, const int offset)
 	skb->mac_header += offset;
 }
 
+static inline void skb_pop_mac_header(struct sk_buff *skb)
+{
+	skb->mac_header = skb->network_header;
+}
+
 static inline void skb_probe_transport_header(struct sk_buff *skb,
 					      const int offset_hint)
 {
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index d7aea4c..e560ef3 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -217,6 +217,7 @@ static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi)
 				  iph->saddr, iph->daddr, tpi->key);
 
 	if (tunnel) {
+		skb_pop_mac_header(skb);
 		ip_tunnel_rcv(tunnel, skb, tpi, log_ecn_error);
 		return PACKET_RCVD;
 	}
-- 
cgit v0.10.2


From 3b3878926c7679765635ed2803dd694a8658042d Mon Sep 17 00:00:00 2001
From: Peter Korsgaard <peter@korsgaard.com>
Date: Mon, 16 Dec 2013 11:35:32 +0100
Subject: dm9601: add support for dm9621a based dongle

dm9621a is functionally identical to dm9620, so the existing handling can
directly be used.

Thanks to Davicom for sending me a dongle.

Signed-off-by: Peter Korsgaard <peter@korsgaard.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index c6867f9..8e88572 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -594,6 +594,10 @@ static const struct usb_device_id products[] = {
 	 USB_DEVICE(0x0a46, 0x9620),	/* DM9620 USB to Fast Ethernet Adapter */
 	 .driver_info = (unsigned long)&dm9601_info,
 	 },
+	{
+	 USB_DEVICE(0x0a46, 0x9621),	/* DM9621A USB to Fast Ethernet Adapter */
+	 .driver_info = (unsigned long)&dm9601_info,
+	},
 	{},			// END
 };
 
-- 
cgit v0.10.2


From 407900cfb54bdb2cfa228010b6697305f66b2948 Mon Sep 17 00:00:00 2001
From: Peter Korsgaard <peter@korsgaard.com>
Date: Mon, 16 Dec 2013 11:35:33 +0100
Subject: dm9601: fix reception of full size ethernet frames on dm9620/dm9621a

dm9620/dm9621a require room for 4 byte padding even in dm9601 (3 byte
header) mode.

Cc: <stable@vger.kernel.org>
Signed-off-by: Peter Korsgaard <peter@korsgaard.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index 8e88572..aca0285 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -364,7 +364,12 @@ static int dm9601_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->net->ethtool_ops = &dm9601_ethtool_ops;
 	dev->net->hard_header_len += DM_TX_OVERHEAD;
 	dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len;
-	dev->rx_urb_size = dev->net->mtu + ETH_HLEN + DM_RX_OVERHEAD;
+
+	/* dm9620/21a require room for 4 byte padding, even in dm9601
+	 * mode, so we need +1 to be able to receive full size
+	 * ethernet frames.
+	 */
+	dev->rx_urb_size = dev->net->mtu + ETH_HLEN + DM_RX_OVERHEAD + 1;
 
 	dev->mii.dev = dev->net;
 	dev->mii.mdio_read = dm9601_mdio_read;
-- 
cgit v0.10.2


From cabd0e3a3861d45569b8f91633c98fc48d820cdb Mon Sep 17 00:00:00 2001
From: Peter Korsgaard <peter@korsgaard.com>
Date: Mon, 16 Dec 2013 11:35:34 +0100
Subject: dm9601: make it clear that dm9620/dm9621a are also supported

The driver nowadays also support dm9620/dm9621a based USB 2.0 ethernet
adapters, so adjust module/driver description and Kconfig help text to
match.

Signed-off-by: Peter Korsgaard <peter@korsgaard.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index 85e4a016..47b0f73 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -276,12 +276,12 @@ config USB_NET_CDC_MBIM
 	  module will be called cdc_mbim.
 
 config USB_NET_DM9601
-	tristate "Davicom DM9601 based USB 1.1 10/100 ethernet devices"
+	tristate "Davicom DM96xx based USB 10/100 ethernet devices"
 	depends on USB_USBNET
 	select CRC32
 	help
-	  This option adds support for Davicom DM9601 based USB 1.1
-	  10/100 Ethernet adapters.
+	  This option adds support for Davicom DM9601/DM9620/DM9621A
+	  based USB 10/100 Ethernet adapters.
 
 config USB_NET_SR9700
 	tristate "CoreChip-sz SR9700 based USB 1.1 10/100 ethernet devices"
diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index aca0285..ca99c35 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -1,5 +1,5 @@
 /*
- * Davicom DM9601 USB 1.1 10/100Mbps ethernet devices
+ * Davicom DM96xx USB 10/100Mbps ethernet devices
  *
  * Peter Korsgaard <jacmet@sunsite.dk>
  *
@@ -548,7 +548,7 @@ static int dm9601_link_reset(struct usbnet *dev)
 }
 
 static const struct driver_info dm9601_info = {
-	.description	= "Davicom DM9601 USB Ethernet",
+	.description	= "Davicom DM96xx USB 10/100 Ethernet",
 	.flags		= FLAG_ETHER | FLAG_LINK_INTR,
 	.bind		= dm9601_bind,
 	.rx_fixup	= dm9601_rx_fixup,
@@ -621,5 +621,5 @@ static struct usb_driver dm9601_driver = {
 module_usb_driver(dm9601_driver);
 
 MODULE_AUTHOR("Peter Korsgaard <jacmet@sunsite.dk>");
-MODULE_DESCRIPTION("Davicom DM9601 USB 1.1 ethernet devices");
+MODULE_DESCRIPTION("Davicom DM96xx USB 10/100 ethernet devices");
 MODULE_LICENSE("GPL");
-- 
cgit v0.10.2


From 4263c86dca5198da6bd3ad826d0b2304fbe25776 Mon Sep 17 00:00:00 2001
From: Peter Korsgaard <peter@korsgaard.com>
Date: Mon, 16 Dec 2013 11:35:35 +0100
Subject: dm9601: work around tx fifo sync issue on dm962x

Certain dm962x revisions contain an bug, where if a USB bulk transfer retry
(E.G. if bulk crc mismatch) happens right after a transfer with odd or
maxpacket length, the internal tx hardware fifo gets out of sync causing
the interface to stop working.

Work around it by adding up to 3 bytes of padding to ensure this situation
cannot trigger.

This workaround also means we never pass multiple-of-maxpacket size skb's
to usbnet, so the length adjustment to handle usbnet's padding of those can
be removed.

Cc: <stable@vger.kernel.org>
Reported-by: Joseph Chang <joseph_chang@davicom.com.tw>
Signed-off-by: Peter Korsgaard <peter@korsgaard.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index ca99c35..14aa48f 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -473,7 +473,7 @@ static int dm9601_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 static struct sk_buff *dm9601_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
 				       gfp_t flags)
 {
-	int len;
+	int len, pad;
 
 	/* format:
 	   b1: packet length low
@@ -481,12 +481,23 @@ static struct sk_buff *dm9601_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
 	   b3..n: packet data
 	*/
 
-	len = skb->len;
+	len = skb->len + DM_TX_OVERHEAD;
+
+	/* workaround for dm962x errata with tx fifo getting out of
+	 * sync if a USB bulk transfer retry happens right after a
+	 * packet with odd / maxpacket length by adding up to 3 bytes
+	 * padding.
+	 */
+	while ((len & 1) || !(len % dev->maxpacket))
+		len++;
 
-	if (skb_headroom(skb) < DM_TX_OVERHEAD) {
+	len -= DM_TX_OVERHEAD; /* hw header doesn't count as part of length */
+	pad = len - skb->len;
+
+	if (skb_headroom(skb) < DM_TX_OVERHEAD || skb_tailroom(skb) < pad) {
 		struct sk_buff *skb2;
 
-		skb2 = skb_copy_expand(skb, DM_TX_OVERHEAD, 0, flags);
+		skb2 = skb_copy_expand(skb, DM_TX_OVERHEAD, pad, flags);
 		dev_kfree_skb_any(skb);
 		skb = skb2;
 		if (!skb)
@@ -495,10 +506,10 @@ static struct sk_buff *dm9601_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
 
 	__skb_push(skb, DM_TX_OVERHEAD);
 
-	/* usbnet adds padding if length is a multiple of packet size
-	   if so, adjust length value in header */
-	if ((skb->len % dev->maxpacket) == 0)
-		len++;
+	if (pad) {
+		memset(skb->data + skb->len, 0, pad);
+		__skb_put(skb, pad);
+	}
 
 	skb->data[0] = len;
 	skb->data[1] = len >> 8;
-- 
cgit v0.10.2


From 4df98e76cde7c64b5606d82584c65dda4151bd6a Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Mon, 16 Dec 2013 12:36:44 +0100
Subject: ipv6: pmtudisc setting not respected with UFO/CORK

Sockets marked with IPV6_PMTUDISC_PROBE (or later IPV6_PMTUDISC_INTERFACE)
don't respect this setting when the outgoing interface supports UFO.

We had the same problem in IPv4, which was fixed in commit
daba287b299ec7a2c61ae3a714920e90e8396ad5 ("ipv4: fix DO and PROBE pmtu
mode regarding local fragmentation with UFO/CORK").

Also IPV6_DONTFRAG mode did not care about already corked data, thus
it may generate a fragmented frame even if this socket option was
specified. It also did not care about the length of the ipv6 header and
possible options.

In the error path allow the user to receive the pmtu notifications via
both, rxpmtu method or error queue. The user may opted in for both,
so deliver the notification to both error handlers (the handlers check
if the error needs to be enqueued).

Also report back consistent pmtu values when sending on an already
cork-appended socket.

Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 4acdb63..e6f9319 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1193,11 +1193,35 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 
 	fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
 			(opt ? opt->opt_nflen : 0);
-	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr);
+	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen -
+		     sizeof(struct frag_hdr);
 
 	if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
-		if (cork->length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) {
-			ipv6_local_error(sk, EMSGSIZE, fl6, mtu-exthdrlen);
+		unsigned int maxnonfragsize, headersize;
+
+		headersize = sizeof(struct ipv6hdr) +
+			     (opt ? opt->tot_len : 0) +
+			     (dst_allfrag(&rt->dst) ?
+			      sizeof(struct frag_hdr) : 0) +
+			     rt->rt6i_nfheader_len;
+
+		maxnonfragsize = (np->pmtudisc >= IPV6_PMTUDISC_DO) ?
+				 mtu : sizeof(struct ipv6hdr) + IPV6_MAXPLEN;
+
+		/* dontfrag active */
+		if ((cork->length + length > mtu - headersize) && dontfrag &&
+		    (sk->sk_protocol == IPPROTO_UDP ||
+		     sk->sk_protocol == IPPROTO_RAW)) {
+			ipv6_local_rxpmtu(sk, fl6, mtu - headersize +
+						   sizeof(struct ipv6hdr));
+			goto emsgsize;
+		}
+
+		if (cork->length + length > maxnonfragsize - headersize) {
+emsgsize:
+			ipv6_local_error(sk, EMSGSIZE, fl6,
+					 mtu - headersize +
+					 sizeof(struct ipv6hdr));
 			return -EMSGSIZE;
 		}
 	}
@@ -1222,12 +1246,6 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 	 * --yoshfuji
 	 */
 
-	if ((length > mtu) && dontfrag && (sk->sk_protocol == IPPROTO_UDP ||
-					   sk->sk_protocol == IPPROTO_RAW)) {
-		ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen);
-		return -EMSGSIZE;
-	}
-
 	skb = skb_peek_tail(&sk->sk_write_queue);
 	cork->length += length;
 	if (((length > mtu) ||
-- 
cgit v0.10.2


From 58a4782449c5882f61882396ef18cc34c7dc1269 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 16 Dec 2013 06:31:23 -0800
Subject: ipv6: sit: update mtu check to take care of gso packets

While testing my changes for TSO support in SIT devices,
I was using sit0 tunnel which appears to include nopmtudisc flag.

But using :

ip tun add sittun mode sit remote $REMOTE_IPV4 local $LOCAL_IPV4 \
   dev $IFACE

We get a tunnel which rejects too long packets because of the mtu check
which is not yet GSO aware.

erd:~# ip tunnel
sittun: ipv6/ip  remote 10.246.17.84  local 10.246.17.83  ttl inherit  6rd-prefix 2002::/16
sit0: ipv6/ip  remote any  local any  ttl 64  nopmtudisc 6rd-prefix 2002::/16

This patch is based on an excellent report from
Michal Shmidt.

In the future, we probably want to extend the MTU check to do the
right thing for GSO packets...

Fixes: ("61c1db7fae21 ipv6: sit: add GSO/TSO support")
Reported-by: Michal Schmidt <mschmidt@redhat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Tested-by: Michal Schmidt <mschmidt@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 366fbba..a710fde 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -924,7 +924,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		if (tunnel->parms.iph.daddr && skb_dst(skb))
 			skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
 
-		if (skb->len > mtu) {
+		if (skb->len > mtu && !skb_is_gso(skb)) {
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
 			ip_rt_put(rt);
 			goto tx_error;
-- 
cgit v0.10.2


From 7306006f103567fcf595d23dd741da0b8642f4c5 Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@linux.intel.com>
Date: Wed, 18 Dec 2013 15:52:13 -0800
Subject: x86, realmode: Pointer walk cleanups, pull out invariant use of
 __pa()

The pointer arithmetic in this function was really bizarre, where in
fact all we really wanted was a simple pointer array walk.  Use the
much more idiomatic construction for that (*ptr++).

Factor an invariant use of __pa() out of the relocation loop.  At
least on 64 bits it seems gcc isn't capable of doing that
automatically.

Change the scope of a couple of variables to make it extra obvious
that they are extremely local temp variables.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Link: http://lkml.kernel.org/n/tip-rd908t9c8kvcojdabtmm94mb@git.kernel.org

diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index a44f457..bad628a 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -29,12 +29,10 @@ void __init reserve_real_mode(void)
 void __init setup_real_mode(void)
 {
 	u16 real_mode_seg;
-	u32 *rel;
+	const u32 *rel;
 	u32 count;
-	u32 *ptr;
-	u16 *seg;
-	int i;
 	unsigned char *base;
+	unsigned long phys_base;
 	struct trampoline_header *trampoline_header;
 	size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob);
 #ifdef CONFIG_X86_64
@@ -46,23 +44,23 @@ void __init setup_real_mode(void)
 
 	memcpy(base, real_mode_blob, size);
 
-	real_mode_seg = __pa(base) >> 4;
+	phys_base = __pa(base);
+	real_mode_seg = phys_base >> 4;
+
 	rel = (u32 *) real_mode_relocs;
 
 	/* 16-bit segment relocations. */
-	count = rel[0];
-	rel = &rel[1];
-	for (i = 0; i < count; i++) {
-		seg = (u16 *) (base + rel[i]);
+	count = *rel++;
+	while (count--) {
+		u16 *seg = (u16 *) (base + *rel++);
 		*seg = real_mode_seg;
 	}
 
 	/* 32-bit linear relocations. */
-	count = rel[i];
-	rel =  &rel[i + 1];
-	for (i = 0; i < count; i++) {
-		ptr = (u32 *) (base + rel[i]);
-		*ptr += __pa(base);
+	count = *rel++;
+	while (count--) {
+		u32 *ptr = (u32 *) (base + *rel++);
+		*ptr += phys_base;
 	}
 
 	/* Must be perfomed *after* relocation. */
-- 
cgit v0.10.2


From 40979d327c99b20a938b2672d7e506f8fc41ddcc Mon Sep 17 00:00:00 2001
From: Chen Gang <gang.chen.5i5j@gmail.com>
Date: Thu, 19 Dec 2013 16:03:40 +0800
Subject: metag: topology: export 'cpu_core_map'

We need to export 'cpu_core_map' since the topology_core_cpumask macro
refers to it and is used by certain kernel modules.

Found in allmodconfig build:
  ERROR: "cpu_core_map" [drivers/staging/lustre/lustre/libcfs/libcfs.ko] undefined!

Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com>
Signed-off-by: James Hogan <james.hogan@imgtec.com>

diff --git a/arch/metag/kernel/topology.c b/arch/metag/kernel/topology.c
index bec3dec..4ba59570 100644
--- a/arch/metag/kernel/topology.c
+++ b/arch/metag/kernel/topology.c
@@ -19,6 +19,7 @@
 DEFINE_PER_CPU(struct cpuinfo_metag, cpu_data);
 
 cpumask_t cpu_core_map[NR_CPUS];
+EXPORT_SYMBOL(cpu_core_map);
 
 static cpumask_t cpu_coregroup_map(unsigned int cpu)
 {
-- 
cgit v0.10.2


From f3d815cb854b2f6262ade56a4d91a1ed3f1e50c4 Mon Sep 17 00:00:00 2001
From: Lans Zhang <jia.zhang@windriver.com>
Date: Fri, 6 Dec 2013 12:18:30 +0800
Subject: x86/mm/numa: Fix 32-bit kernel NUMA boot

When booting a 32-bit x86 kernel on a NUMA machine, node data
cannot be allocated from local node if the account of memory for
node 0 covers the low memory space entirely:

  [    0.000000] Initmem setup node 0 [mem 0x00000000-0x83fffffff]
  [    0.000000]   NODE_DATA [mem 0x367ed000-0x367edfff]
  [    0.000000] Initmem setup node 1 [mem 0x840000000-0xfffffffff]
  [    0.000000] Cannot find 4096 bytes in node 1
  [    0.000000] 64664MB HIGHMEM available.
  [    0.000000] 871MB LOWMEM available.

To fix this issue, node data is allowed to be allocated from
other nodes if the memory of local node is still not mapped. The
expected result looks like this:

  [    0.000000] Initmem setup node 0 [mem 0x00000000-0x83fffffff]
  [    0.000000]   NODE_DATA [mem 0x367ed000-0x367edfff]
  [    0.000000] Initmem setup node 1 [mem 0x840000000-0xfffffffff]
  [    0.000000]   NODE_DATA [mem 0x367ec000-0x367ecfff]
  [    0.000000]     NODE_DATA(1) on node 0
  [    0.000000] 64664MB HIGHMEM available.
  [    0.000000] 871MB LOWMEM available.

Signed-off-by: Lans Zhang <jia.zhang@windriver.com>
Cc: <andi@firstfloor.org>
Cc: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/1386303510-18574-1-git-send-email-jia.zhang@windriver.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 24aec58..c85da7b 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -211,9 +211,13 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 	 */
 	nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
 	if (!nd_pa) {
-		pr_err("Cannot find %zu bytes in node %d\n",
-		       nd_size, nid);
-		return;
+		nd_pa = __memblock_alloc_base(nd_size, SMP_CACHE_BYTES,
+					      MEMBLOCK_ALLOC_ACCESSIBLE);
+		if (!nd_pa) {
+			pr_err("Cannot find %zu bytes in node %d\n",
+			       nd_size, nid);
+			return;
+		}
 	}
 	nd = __va(nd_pa);
 
-- 
cgit v0.10.2


From b66d8c0caa8f7925ae75fed243b0482a901f21e1 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 18 Dec 2013 15:37:41 -0300
Subject: perf annotate: Auto allocate symbol per addr hist buckets

Instead of open coding it in multiple places in 'report' and 'top'.

Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ay1ushp57qsva9aw59rha5ve@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 3a14dbe..b75fc36 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -140,22 +140,11 @@ static int perf_report__add_mem_hist_entry(struct perf_tool *tool,
 			goto out;
 	}
 
-	if (sort__has_sym && he->mem_info->daddr.sym && use_browser > 0) {
-		struct annotation *notes;
-
-		mx = he->mem_info;
-
-		notes = symbol__annotation(mx->daddr.sym);
-		if (notes->src == NULL && symbol__alloc_hist(mx->daddr.sym) < 0)
-			goto out;
-
-		err = symbol__inc_addr_samples(mx->daddr.sym,
-					       mx->daddr.map,
-					       evsel->idx,
-					       mx->daddr.al_addr);
-		if (err)
-			goto out;
-	}
+	mx = he->mem_info;
+	err = symbol__inc_addr_samples(mx->daddr.sym, mx->daddr.map,
+				       evsel->idx, mx->daddr.al_addr);
+	if (err)
+		goto out;
 
 	evsel->hists.stats.total_period += cost;
 	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
@@ -214,35 +203,19 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
 		he = __hists__add_entry(&evsel->hists, al, parent, &bi[i], NULL,
 					1, 1, 0);
 		if (he) {
-			struct annotation *notes;
 			bx = he->branch_info;
-			if (bx->from.sym && use_browser == 1 && sort__has_sym) {
-				notes = symbol__annotation(bx->from.sym);
-				if (!notes->src
-				    && symbol__alloc_hist(bx->from.sym) < 0)
-					goto out;
-
-				err = symbol__inc_addr_samples(bx->from.sym,
-							       bx->from.map,
-							       evsel->idx,
-							       bx->from.al_addr);
-				if (err)
-					goto out;
-			}
+			err = symbol__inc_addr_samples(bx->from.sym,
+						       bx->from.map, evsel->idx,
+						       bx->from.al_addr);
+			if (err)
+				goto out;
+
+			err = symbol__inc_addr_samples(bx->to.sym,
+						       bx->to.map, evsel->idx,
+						       bx->to.al_addr);
+			if (err)
+				goto out;
 
-			if (bx->to.sym && use_browser == 1 && sort__has_sym) {
-				notes = symbol__annotation(bx->to.sym);
-				if (!notes->src
-				    && symbol__alloc_hist(bx->to.sym) < 0)
-					goto out;
-
-				err = symbol__inc_addr_samples(bx->to.sym,
-							       bx->to.map,
-							       evsel->idx,
-							       bx->to.al_addr);
-				if (err)
-					goto out;
-			}
 			evsel->hists.stats.total_period += 1;
 			hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
 		} else
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 03d37a7..73df9c0 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -189,14 +189,6 @@ static void perf_top__record_precise_ip(struct perf_top *top,
 	if (pthread_mutex_trylock(&notes->lock))
 		return;
 
-	if (notes->src == NULL && symbol__alloc_hist(sym) < 0) {
-		pthread_mutex_unlock(&notes->lock);
-		pr_err("Not enough memory for annotating '%s' symbol!\n",
-		       sym->name);
-		sleep(1);
-		return;
-	}
-
 	ip = he->ms.map->map_ip(he->ms.map, ip);
 	err = symbol__inc_addr_samples(sym, he->ms.map, counter, ip);
 
@@ -204,6 +196,11 @@ static void perf_top__record_precise_ip(struct perf_top *top,
 
 	if (err == -ERANGE && !he->ms.map->erange_warned)
 		ui__warn_map_erange(he->ms.map, sym, ip);
+	else if (err == -ENOMEM) {
+		pr_err("Not enough memory for annotating '%s' symbol!\n",
+		       sym->name);
+		sleep(1);
+	}
 }
 
 static void perf_top__show_details(struct perf_top *top)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 0fcd81e..93614cd 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -464,17 +464,12 @@ void symbol__annotate_zero_histograms(struct symbol *sym)
 	pthread_mutex_unlock(&notes->lock);
 }
 
-int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
-			     int evidx, u64 addr)
+static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
+				      struct annotation *notes, int evidx, u64 addr)
 {
 	unsigned offset;
-	struct annotation *notes;
 	struct sym_hist *h;
 
-	notes = symbol__annotation(sym);
-	if (notes->src == NULL)
-		return -ENOMEM;
-
 	pr_debug3("%s: addr=%#" PRIx64 "\n", __func__, map->unmap_ip(map, addr));
 
 	if (addr < sym->start || addr > sym->end)
@@ -491,6 +486,23 @@ int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 	return 0;
 }
 
+int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
+			     int evidx, u64 addr)
+{
+	struct annotation *notes;
+
+	if (sym == NULL || use_browser != 1 || !sort__has_sym)
+		return 0;
+
+	notes = symbol__annotation(sym);
+	if (notes->src == NULL) {
+		if (symbol__alloc_hist(sym) < 0)
+			return -ENOMEM;
+	}
+
+	return __symbol__inc_addr_samples(sym, map, notes, evidx, addr);
+}
+
 static void disasm_line__init_ins(struct disasm_line *dl)
 {
 	dl->ins = ins__find(dl->name);
-- 
cgit v0.10.2


From 00e55218642b91c152917e170c8387c631467460 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 18 Dec 2013 15:46:32 -0300
Subject: perf hists: Leave symbol addr hist bucket auto alloc to symbol layer

Since now symbol__addr_inc_samples() does the auto alloc, no need to do
it prior to calling hist_entry__inc_addr_samples.

Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-6ife7xq2kef1nn017m04b3id@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 6fd52c8..4136f99 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -69,15 +69,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 	if (he == NULL)
 		return -ENOMEM;
 
-	ret = 0;
-	if (he->ms.sym != NULL) {
-		struct annotation *notes = symbol__annotation(he->ms.sym);
-		if (notes->src == NULL && symbol__alloc_hist(he->ms.sym) < 0)
-			return -ENOMEM;
-
-		ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-	}
-
+	ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
 	evsel->hists.stats.total_period += sample->period;
 	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
 	return ret;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index b75fc36..0615a63 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -122,23 +122,9 @@ static int perf_report__add_mem_hist_entry(struct perf_tool *tool,
 	if (!he)
 		return -ENOMEM;
 
-	/*
-	 * In the TUI browser, we are doing integrated annotation,
-	 * so we don't allocate the extra space needed because the stdio
-	 * code will not use it.
-	 */
-	if (sort__has_sym && he->ms.sym && use_browser > 0) {
-		struct annotation *notes = symbol__annotation(he->ms.sym);
-
-		assert(evsel != NULL);
-
-		if (notes->src == NULL && symbol__alloc_hist(he->ms.sym) < 0)
-			goto out;
-
-		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-		if (err)
-			goto out;
-	}
+	err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+	if (err)
+		goto out;
 
 	mx = he->mem_info;
 	err = symbol__inc_addr_samples(mx->daddr.sym, mx->daddr.map,
@@ -259,26 +245,10 @@ static int perf_evsel__add_hist_entry(struct perf_tool *tool,
 		if (err)
 			return err;
 	}
-	/*
-	 * Only in the TUI browser we are doing integrated annotation,
-	 * so we don't allocated the extra space needed because the stdio
-	 * code will not use it.
-	 */
-	if (he->ms.sym != NULL && use_browser == 1 && sort__has_sym) {
-		struct annotation *notes = symbol__annotation(he->ms.sym);
-
-		assert(evsel != NULL);
-
-		err = -ENOMEM;
-		if (notes->src == NULL && symbol__alloc_hist(he->ms.sym) < 0)
-			goto out;
-
-		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
-	}
 
+	err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
 	evsel->hists.stats.total_period += sample->period;
 	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
-out:
 	return err;
 }
 
-- 
cgit v0.10.2


From 0f4e7a24d0303eaf12847b4fdf4f2d31553fdc61 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 18 Dec 2013 16:48:29 -0300
Subject: perf annotate: Add inc_samples method to addr_map_symbol

Since there are three calls that could receive just the struct
addr_map_symbol pointer and call the symbol method.

Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-d728gz1orgkaknac9ppnzd9e@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 0615a63..9a20c9e 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -127,8 +127,7 @@ static int perf_report__add_mem_hist_entry(struct perf_tool *tool,
 		goto out;
 
 	mx = he->mem_info;
-	err = symbol__inc_addr_samples(mx->daddr.sym, mx->daddr.map,
-				       evsel->idx, mx->daddr.al_addr);
+	err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx);
 	if (err)
 		goto out;
 
@@ -190,15 +189,11 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
 					1, 1, 0);
 		if (he) {
 			bx = he->branch_info;
-			err = symbol__inc_addr_samples(bx->from.sym,
-						       bx->from.map, evsel->idx,
-						       bx->from.al_addr);
+			err = addr_map_symbol__inc_samples(&bx->from, evsel->idx);
 			if (err)
 				goto out;
 
-			err = symbol__inc_addr_samples(bx->to.sym,
-						       bx->to.map, evsel->idx,
-						       bx->to.al_addr);
+			err = addr_map_symbol__inc_samples(&bx->to, evsel->idx);
 			if (err)
 				goto out;
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 93614cd..2812e7b 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -503,6 +503,11 @@ int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 	return __symbol__inc_addr_samples(sym, map, notes, evidx, addr);
 }
 
+int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx)
+{
+	return symbol__inc_addr_samples(ams->sym, ams->map, evidx, ams->al_addr);
+}
+
 static void disasm_line__init_ins(struct disasm_line *dl)
 {
 	dl->ins = ins__find(dl->name);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 834b7b5..8de10b1 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -134,6 +134,9 @@ static inline struct annotation *symbol__annotation(struct symbol *sym)
 
 int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 			     int evidx, u64 addr);
+
+int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx);
+
 int symbol__alloc_hist(struct symbol *sym);
 void symbol__annotate_zero_histograms(struct symbol *sym);
 
-- 
cgit v0.10.2


From 618afb294e288db086fce59de4419644215265e5 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 18 Dec 2013 17:08:07 -0300
Subject: perf top: Use hist_entry__inc_addr_sample

Since it has a hist_entry, no need to skip the hist layer and use the
underlying symbol one.

Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-txsgu9umb0i86ijk888r1a0o@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 73df9c0..2c6cb66 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -190,7 +190,7 @@ static void perf_top__record_precise_ip(struct perf_top *top,
 		return;
 
 	ip = he->ms.map->map_ip(he->ms.map, ip);
-	err = symbol__inc_addr_samples(sym, he->ms.map, counter, ip);
+	err = hist_entry__inc_addr_samples(he, counter, ip);
 
 	pthread_mutex_unlock(&notes->lock);
 
-- 
cgit v0.10.2


From f626adffe17632aa7b0e2a7732b49e2c32d477d8 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 18 Dec 2013 17:10:15 -0300
Subject: perf annotate: Adopt methods from hists

Those are just wrappers to annotation methods, so move them to
annotate.c

Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-336h7z0bi2k51cbfi6mkpo5k@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 2812e7b..91e2526 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -508,6 +508,11 @@ int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx)
 	return symbol__inc_addr_samples(ams->sym, ams->map, evidx, ams->al_addr);
 }
 
+int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip)
+{
+	return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip);
+}
+
 static void disasm_line__init_ins(struct disasm_line *dl)
 {
 	dl->ins = ins__find(dl->name);
@@ -1393,3 +1398,8 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
 
 	return 0;
 }
+
+int hist_entry__annotate(struct hist_entry *he, size_t privsize)
+{
+	return symbol__annotate(he->ms.sym, he->ms.map, privsize);
+}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 8de10b1..43727a9 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -137,10 +137,15 @@ int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 
 int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx);
 
+int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr);
+
 int symbol__alloc_hist(struct symbol *sym);
 void symbol__annotate_zero_histograms(struct symbol *sym);
 
 int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize);
+
+int hist_entry__annotate(struct hist_entry *he, size_t privsize);
+
 int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym);
 int symbol__annotate_printf(struct symbol *sym, struct map *map,
 			    struct perf_evsel *evsel, bool full_paths,
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 63234e3..6cd4823 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1,4 +1,3 @@
-#include "annotate.h"
 #include "util.h"
 #include "build-id.h"
 #include "hist.h"
@@ -807,16 +806,6 @@ void hists__filter_by_symbol(struct hists *hists)
 	}
 }
 
-int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip)
-{
-	return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip);
-}
-
-int hist_entry__annotate(struct hist_entry *he, size_t privsize)
-{
-	return symbol__annotate(he->ms.sym, he->ms.map, privsize);
-}
-
 void events_stats__inc(struct events_stats *stats, u32 type)
 {
 	++stats->nr_events[0];
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index b621347a..a59743f 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -111,9 +111,6 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp);
 
-int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr);
-int hist_entry__annotate(struct hist_entry *he, size_t privsize);
-
 void hists__filter_by_dso(struct hists *hists);
 void hists__filter_by_thread(struct hists *hists);
 void hists__filter_by_symbol(struct hists *hists);
-- 
cgit v0.10.2


From 44e8303944cd45788abd48f14d4c683331ed6cf7 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 18 Dec 2013 17:12:24 -0300
Subject: perf annotate: Make symbol__inc_addr_samples private

Since it is now accessed just thru addr_map_symbol and hist_entry
wrappers.

Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-gjoam7wcfrb03sp753gk1nfk@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 91e2526..27ab7b5 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -486,8 +486,8 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 	return 0;
 }
 
-int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
-			     int evidx, u64 addr)
+static int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
+				    int evidx, u64 addr)
 {
 	struct annotation *notes;
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 43727a9..b2aef59 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -132,9 +132,6 @@ static inline struct annotation *symbol__annotation(struct symbol *sym)
 	return &a->annotation;
 }
 
-int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
-			     int evidx, u64 addr);
-
 int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx);
 
 int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr);
-- 
cgit v0.10.2


From 6dbc8ca97b7737fa9254083df29d06c556b0653c Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 18 Dec 2013 18:16:18 -0300
Subject: perf report: Introduce helpers for processing callchains

Continuing to try to remove the code duplication introduced with mem and
branch hist entry code, this time providing prologue and epilogues to
deal with callchains when processing samples.

Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-js3pour59yk2aibqzb1tpumh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 9a20c9e..8424053 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -75,6 +75,24 @@ static int perf_report_config(const char *var, const char *value, void *cb)
 	return perf_default_config(var, value, cb);
 }
 
+static int report__resolve_callchain(struct perf_report *rep, struct symbol **parent,
+				     struct perf_evsel *evsel, struct addr_location *al,
+				     struct perf_sample *sample, struct machine *machine)
+{
+	if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
+		return machine__resolve_callchain(machine, evsel, al->thread, sample,
+						  parent, al, rep->max_stack);
+	}
+	return 0;
+}
+
+static int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample)
+{
+	if (!symbol_conf.use_callchain)
+		return 0;
+	return callchain_append(he->callchain, &callchain_cursor, sample->period);
+}
+
 static int perf_report__add_mem_hist_entry(struct perf_tool *tool,
 					   struct addr_location *al,
 					   struct perf_sample *sample,
@@ -85,19 +103,13 @@ static int perf_report__add_mem_hist_entry(struct perf_tool *tool,
 	struct perf_report *rep = container_of(tool, struct perf_report, tool);
 	struct symbol *parent = NULL;
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-	int err = 0;
 	struct hist_entry *he;
 	struct mem_info *mi, *mx;
 	uint64_t cost;
+	int err = report__resolve_callchain(rep, &parent, evsel, al, sample, machine);
 
-	if ((sort__has_parent || symbol_conf.use_callchain) &&
-	    sample->callchain) {
-		err = machine__resolve_callchain(machine, evsel, al->thread,
-						 sample, &parent, al,
-						 rep->max_stack);
-		if (err)
-			return err;
-	}
+	if (err)
+		return err;
 
 	mi = machine__resolve_mem(machine, al->thread, sample, cpumode);
 	if (!mi)
@@ -133,13 +145,7 @@ static int perf_report__add_mem_hist_entry(struct perf_tool *tool,
 
 	evsel->hists.stats.total_period += cost;
 	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
-	err = 0;
-
-	if (symbol_conf.use_callchain) {
-		err = callchain_append(he->callchain,
-				       &callchain_cursor,
-				       sample->period);
-	}
+	err = hist_entry__append_callchain(he, sample);
 out:
 	return err;
 }
@@ -152,19 +158,13 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
 {
 	struct perf_report *rep = container_of(tool, struct perf_report, tool);
 	struct symbol *parent = NULL;
-	int err = 0;
 	unsigned i;
 	struct hist_entry *he;
 	struct branch_info *bi, *bx;
+	int err = report__resolve_callchain(rep, &parent, evsel, al, sample, machine);
 
-	if ((sort__has_parent || symbol_conf.use_callchain)
-	    && sample->callchain) {
-		err = machine__resolve_callchain(machine, evsel, al->thread,
-						 sample, &parent, al,
-						 rep->max_stack);
-		if (err)
-			return err;
-	}
+	if (err)
+		return err;
 
 	bi = machine__resolve_bstack(machine, al->thread,
 				     sample->branch_stack);
@@ -216,16 +216,11 @@ static int perf_evsel__add_hist_entry(struct perf_tool *tool,
 {
 	struct perf_report *rep = container_of(tool, struct perf_report, tool);
 	struct symbol *parent = NULL;
-	int err = 0;
 	struct hist_entry *he;
+	int err = report__resolve_callchain(rep, &parent, evsel, al, sample, machine);
 
-	if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
-		err = machine__resolve_callchain(machine, evsel, al->thread,
-						 sample, &parent, al,
-						 rep->max_stack);
-		if (err)
-			return err;
-	}
+	if (err)
+		return err;
 
 	he = __hists__add_entry(&evsel->hists, al, parent, NULL, NULL,
 				sample->period, sample->weight,
@@ -233,17 +228,14 @@ static int perf_evsel__add_hist_entry(struct perf_tool *tool,
 	if (he == NULL)
 		return -ENOMEM;
 
-	if (symbol_conf.use_callchain) {
-		err = callchain_append(he->callchain,
-				       &callchain_cursor,
-				       sample->period);
-		if (err)
-			return err;
-	}
+	err = hist_entry__append_callchain(he, sample);
+	if (err)
+		goto out;
 
 	err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
 	evsel->hists.stats.total_period += sample->period;
 	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+out:
 	return err;
 }
 
-- 
cgit v0.10.2


From 73db8f82619b7538d9b4badfe13f3ab2fef7d9b3 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung.kim@lge.com>
Date: Thu, 19 Dec 2013 16:00:08 +0900
Subject: perf tools: Get rid of a duplicate va_end() in error reporting
 routine

The va_end() in _eprintf() should be removed since the caller also
invokes va_end().

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1387436411-20160-4-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 8640a91..299b555 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -25,7 +25,6 @@ static int _eprintf(int level, const char *fmt, va_list args)
 			ui_helpline__vshow(fmt, args);
 		else
 			ret = vfprintf(stderr, fmt, args);
-		va_end(args);
 	}
 
 	return ret;
-- 
cgit v0.10.2


From 3406912cc1c631dea7ff050a9df92216e5a70e98 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 29 Oct 2013 19:04:57 +0100
Subject: perf inject: Handle output file via perf_data_file object

Using the perf_data_file object to handle output file processing.

No functional change intended.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-01j9ophd7tntmgrxa40uqjjm@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 6a25085..c9f6d74 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -22,14 +22,13 @@
 #include <linux/list.h>
 
 struct perf_inject {
-	struct perf_tool tool;
-	bool		 build_ids;
-	bool		 sched_stat;
-	const char	 *input_name;
-	int		 pipe_output,
-			 output;
-	u64		 bytes_written;
-	struct list_head samples;
+	struct perf_tool	tool;
+	bool			build_ids;
+	bool			sched_stat;
+	const char		*input_name;
+	struct perf_data_file	output;
+	u64			bytes_written;
+	struct list_head	samples;
 };
 
 struct event_entry {
@@ -42,21 +41,14 @@ static int perf_event__repipe_synth(struct perf_tool *tool,
 				    union perf_event *event)
 {
 	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
-	uint32_t size;
-	void *buf = event;
+	ssize_t size;
 
-	size = event->header.size;
-
-	while (size) {
-		int ret = write(inject->output, buf, size);
-		if (ret < 0)
-			return -errno;
-
-		size -= ret;
-		buf += ret;
-		inject->bytes_written += ret;
-	}
+	size = perf_data_file__write(&inject->output, event,
+				     event->header.size);
+	if (size < 0)
+		return -errno;
 
+	inject->bytes_written += size;
 	return 0;
 }
 
@@ -80,7 +72,7 @@ static int perf_event__repipe_attr(struct perf_tool *tool,
 	if (ret)
 		return ret;
 
-	if (!inject->pipe_output)
+	if (&inject->output.is_pipe)
 		return 0;
 
 	return perf_event__repipe_synth(tool, event);
@@ -355,6 +347,7 @@ static int __cmd_inject(struct perf_inject *inject)
 		.path = inject->input_name,
 		.mode = PERF_DATA_MODE_READ,
 	};
+	struct perf_data_file *file_out = &inject->output;
 
 	signal(SIGINT, sig_handler);
 
@@ -391,14 +384,14 @@ static int __cmd_inject(struct perf_inject *inject)
 		}
 	}
 
-	if (!inject->pipe_output)
-		lseek(inject->output, session->header.data_offset, SEEK_SET);
+	if (!file_out->is_pipe)
+		lseek(file_out->fd, session->header.data_offset, SEEK_SET);
 
 	ret = perf_session__process_events(session, &inject->tool);
 
-	if (!inject->pipe_output) {
+	if (!file_out->is_pipe) {
 		session->header.data_size = inject->bytes_written;
-		perf_session__write_header(session, session->evlist, inject->output, true);
+		perf_session__write_header(session, session->evlist, file_out->fd, true);
 	}
 
 	perf_session__delete(session);
@@ -427,14 +420,17 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 		},
 		.input_name  = "-",
 		.samples = LIST_HEAD_INIT(inject.samples),
+		.output = {
+			.path = "-",
+			.mode = PERF_DATA_MODE_WRITE,
+		},
 	};
-	const char *output_name = "-";
 	const struct option options[] = {
 		OPT_BOOLEAN('b', "build-ids", &inject.build_ids,
 			    "Inject build-ids into the output stream"),
 		OPT_STRING('i', "input", &inject.input_name, "file",
 			   "input file name"),
-		OPT_STRING('o', "output", &output_name, "file",
+		OPT_STRING('o', "output", &inject.output.path, "file",
 			   "output file name"),
 		OPT_BOOLEAN('s', "sched-stat", &inject.sched_stat,
 			    "Merge sched-stat and sched-switch for getting events "
@@ -456,16 +452,9 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (argc)
 		usage_with_options(inject_usage, options);
 
-	if (!strcmp(output_name, "-")) {
-		inject.pipe_output = 1;
-		inject.output = STDOUT_FILENO;
-	} else {
-		inject.output = open(output_name, O_CREAT | O_WRONLY | O_TRUNC,
-						  S_IRUSR | S_IWUSR);
-		if (inject.output < 0) {
-			perror("failed to create output file");
-			return -1;
-		}
+	if (perf_data_file__open(&inject.output)) {
+		perror("failed to create output file");
+		return -1;
 	}
 
 	if (symbol__init() < 0)
-- 
cgit v0.10.2


From 50a9b8680613a2708ca882d982dcfa4fd9a66673 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Fri, 22 Nov 2013 13:11:24 +0100
Subject: perf record: Use perf_data_file__write for output file

Changing the file output code to use the newly
added perf_data_file__write interface.

No functional change intended.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index c1c1200..8eed3d7 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -76,24 +76,19 @@ struct perf_record {
 	long			samples;
 };
 
-static int perf_record__write(struct perf_record *rec, void *buf, size_t size)
+static ssize_t perf_record__write(struct perf_record *rec,
+				  void *buf, size_t size)
 {
-	struct perf_data_file *file = &rec->file;
-
-	while (size) {
-		ssize_t ret = write(file->fd, buf, size);
-
-		if (ret < 0) {
-			pr_err("failed to write perf data, error: %m\n");
-			return -1;
-		}
-
-		size -= ret;
-		buf += ret;
+	struct perf_session *session = rec->session;
+	ssize_t ret;
 
-		rec->bytes_written += ret;
+	ret = perf_data_file__write(session->file, buf, size);
+	if (ret < 0) {
+		pr_err("failed to write perf data, error: %m\n");
+		return -1;
 	}
 
+	rec->bytes_written += ret;
 	return 0;
 }
 
-- 
cgit v0.10.2


From cf8b2e6941091d2034f19c1799f8d6407bd565a4 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 19 Dec 2013 14:26:26 -0300
Subject: perf record: Simplify perf_record__write

1. Since all callers either test if it is less than zero or assign its
   result to an int variable, convert it from ssize_t to int;

2. There is just one use for the 'session' variable, so use rec->session
   directly instead;

3. No need to store the result of perf_data_file__write, since that
   result is either 'size' or -1, the later making the error result to
   be stored in 'errno' and accessed thru printf's %m in the pr_err
   call.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-xwsk964dp681fica3xlqhjin@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 8eed3d7..e8d606c 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -76,19 +76,14 @@ struct perf_record {
 	long			samples;
 };
 
-static ssize_t perf_record__write(struct perf_record *rec,
-				  void *buf, size_t size)
+static int perf_record__write(struct perf_record *rec, void *bf, size_t size)
 {
-	struct perf_session *session = rec->session;
-	ssize_t ret;
-
-	ret = perf_data_file__write(session->file, buf, size);
-	if (ret < 0) {
+	if (perf_data_file__write(rec->session->file, bf, size) < 0) {
 		pr_err("failed to write perf data, error: %m\n");
 		return -1;
 	}
 
-	rec->bytes_written += ret;
+	rec->bytes_written += size;
 	return 0;
 }
 
-- 
cgit v0.10.2


From 8c6f45a7c263840c27dfe846d40577b49e43b85b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 19 Dec 2013 14:38:03 -0300
Subject: perf record: Rename 'perf_record' to plain 'record'

Its a local struct and the functions use the __ separator from the class
name to the method name, so its unlikely that this will clash with other
namespaces.

Save some typing then.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-r011tdv7ianars9jr9ur2n4q@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index e8d606c..f2624d4 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -62,7 +62,7 @@ static void __handle_on_exit_funcs(void)
 }
 #endif
 
-struct perf_record {
+struct record {
 	struct perf_tool	tool;
 	struct perf_record_opts	opts;
 	u64			bytes_written;
@@ -76,7 +76,7 @@ struct perf_record {
 	long			samples;
 };
 
-static int perf_record__write(struct perf_record *rec, void *bf, size_t size)
+static int record__write(struct record *rec, void *bf, size_t size)
 {
 	if (perf_data_file__write(rec->session->file, bf, size) < 0) {
 		pr_err("failed to write perf data, error: %m\n");
@@ -92,12 +92,11 @@ static int process_synthesized_event(struct perf_tool *tool,
 				     struct perf_sample *sample __maybe_unused,
 				     struct machine *machine __maybe_unused)
 {
-	struct perf_record *rec = container_of(tool, struct perf_record, tool);
-	return perf_record__write(rec, event, event->header.size);
+	struct record *rec = container_of(tool, struct record, tool);
+	return record__write(rec, event, event->header.size);
 }
 
-static int perf_record__mmap_read(struct perf_record *rec,
-				   struct perf_mmap *md)
+static int record__mmap_read(struct record *rec, struct perf_mmap *md)
 {
 	unsigned int head = perf_mmap__read_head(md);
 	unsigned int old = md->prev;
@@ -118,7 +117,7 @@ static int perf_record__mmap_read(struct perf_record *rec,
 		size = md->mask + 1 - (old & md->mask);
 		old += size;
 
-		if (perf_record__write(rec, buf, size) < 0) {
+		if (record__write(rec, buf, size) < 0) {
 			rc = -1;
 			goto out;
 		}
@@ -128,7 +127,7 @@ static int perf_record__mmap_read(struct perf_record *rec,
 	size = head - old;
 	old += size;
 
-	if (perf_record__write(rec, buf, size) < 0) {
+	if (record__write(rec, buf, size) < 0) {
 		rc = -1;
 		goto out;
 	}
@@ -153,9 +152,9 @@ static void sig_handler(int sig)
 	signr = sig;
 }
 
-static void perf_record__sig_exit(int exit_status __maybe_unused, void *arg)
+static void record__sig_exit(int exit_status __maybe_unused, void *arg)
 {
-	struct perf_record *rec = arg;
+	struct record *rec = arg;
 	int status;
 
 	if (rec->evlist->workload.pid > 0) {
@@ -173,7 +172,7 @@ static void perf_record__sig_exit(int exit_status __maybe_unused, void *arg)
 	signal(signr, SIG_DFL);
 }
 
-static int perf_record__open(struct perf_record *rec)
+static int record__open(struct record *rec)
 {
 	char msg[512];
 	struct perf_evsel *pos;
@@ -229,7 +228,7 @@ out:
 	return rc;
 }
 
-static int process_buildids(struct perf_record *rec)
+static int process_buildids(struct record *rec)
 {
 	struct perf_data_file *file  = &rec->file;
 	struct perf_session *session = rec->session;
@@ -244,9 +243,9 @@ static int process_buildids(struct perf_record *rec)
 					      size, &build_id__mark_dso_hit_ops);
 }
 
-static void perf_record__exit(int status, void *arg)
+static void record__exit(int status, void *arg)
 {
-	struct perf_record *rec = arg;
+	struct record *rec = arg;
 	struct perf_data_file *file = &rec->file;
 
 	if (status != 0)
@@ -302,14 +301,14 @@ static struct perf_event_header finished_round_event = {
 	.type = PERF_RECORD_FINISHED_ROUND,
 };
 
-static int perf_record__mmap_read_all(struct perf_record *rec)
+static int record__mmap_read_all(struct record *rec)
 {
 	int i;
 	int rc = 0;
 
 	for (i = 0; i < rec->evlist->nr_mmaps; i++) {
 		if (rec->evlist->mmap[i].base) {
-			if (perf_record__mmap_read(rec, &rec->evlist->mmap[i]) != 0) {
+			if (record__mmap_read(rec, &rec->evlist->mmap[i]) != 0) {
 				rc = -1;
 				goto out;
 			}
@@ -317,14 +316,13 @@ static int perf_record__mmap_read_all(struct perf_record *rec)
 	}
 
 	if (perf_header__has_feat(&rec->session->header, HEADER_TRACING_DATA))
-		rc = perf_record__write(rec, &finished_round_event,
-					sizeof(finished_round_event));
+		rc = record__write(rec, &finished_round_event, sizeof(finished_round_event));
 
 out:
 	return rc;
 }
 
-static void perf_record__init_features(struct perf_record *rec)
+static void record__init_features(struct record *rec)
 {
 	struct perf_evlist *evsel_list = rec->evlist;
 	struct perf_session *session = rec->session;
@@ -343,7 +341,7 @@ static void perf_record__init_features(struct perf_record *rec)
 		perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
 }
 
-static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
+static int __cmd_record(struct record *rec, int argc, const char **argv)
 {
 	int err;
 	unsigned long waking = 0;
@@ -358,7 +356,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 
 	rec->progname = argv[0];
 
-	on_exit(perf_record__sig_exit, rec);
+	on_exit(record__sig_exit, rec);
 	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);
 	signal(SIGUSR1, sig_handler);
@@ -372,7 +370,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 
 	rec->session = session;
 
-	perf_record__init_features(rec);
+	record__init_features(rec);
 
 	if (forks) {
 		err = perf_evlist__prepare_workload(evsel_list, &opts->target,
@@ -384,7 +382,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 		}
 	}
 
-	if (perf_record__open(rec) != 0) {
+	if (record__open(rec) != 0) {
 		err = -1;
 		goto out_delete_session;
 	}
@@ -393,9 +391,9 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 		perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);
 
 	/*
-	 * perf_session__delete(session) will be called at perf_record__exit()
+	 * perf_session__delete(session) will be called at record__exit()
 	 */
-	on_exit(perf_record__exit, rec);
+	on_exit(record__exit, rec);
 
 	if (file->is_pipe) {
 		err = perf_header__write_pipe(file->fd);
@@ -500,7 +498,7 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 	for (;;) {
 		int hits = rec->samples;
 
-		if (perf_record__mmap_read_all(rec) < 0) {
+		if (record__mmap_read_all(rec) < 0) {
 			err = -1;
 			goto out_delete_session;
 		}
@@ -765,8 +763,8 @@ static const char * const record_usage[] = {
 };
 
 /*
- * XXX Ideally would be local to cmd_record() and passed to a perf_record__new
- * because we need to have access to it in perf_record__exit, that is called
+ * XXX Ideally would be local to cmd_record() and passed to a record__new
+ * because we need to have access to it in record__exit, that is called
  * after cmd_record() exits, but since record_options need to be accessible to
  * builtin-script, leave it here.
  *
@@ -774,7 +772,7 @@ static const char * const record_usage[] = {
  *
  * Just say no to tons of global variables, sigh.
  */
-static struct perf_record record = {
+static struct record record = {
 	.opts = {
 		.mmap_pages	     = UINT_MAX,
 		.user_freq	     = UINT_MAX,
@@ -881,7 +879,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	int err = -ENOMEM;
 	struct perf_evlist *evsel_list;
-	struct perf_record *rec = &record;
+	struct record *rec = &record;
 	char errbuf[BUFSIZ];
 
 	evsel_list = perf_evlist__new();
-- 
cgit v0.10.2


From b40067964f09a5b4d9e133dec225007ee0a13050 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 19 Dec 2013 14:43:45 -0300
Subject: perf tools: Rename 'perf_record_opts' to 'record_opts

Reduce typing, functions use class__method convention, so unlikely to
clash with other libraries.

This actually was discussed in the "Link:" referenced message below.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/20131112113427.GA4053@ghostprotocols.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 154b397..5a80da6 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -89,7 +89,7 @@ struct exit_reasons_table {
 
 struct perf_kvm_stat {
 	struct perf_tool    tool;
-	struct perf_record_opts opts;
+	struct record_opts  opts;
 	struct perf_evlist  *evlist;
 	struct perf_session *session;
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f2624d4..6ec0cbc 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -64,7 +64,7 @@ static void __handle_on_exit_funcs(void)
 
 struct record {
 	struct perf_tool	tool;
-	struct perf_record_opts	opts;
+	struct record_opts	opts;
 	u64			bytes_written;
 	struct perf_data_file	file;
 	struct perf_evlist	*evlist;
@@ -178,7 +178,7 @@ static int record__open(struct record *rec)
 	struct perf_evsel *pos;
 	struct perf_evlist *evlist = rec->evlist;
 	struct perf_session *session = rec->session;
-	struct perf_record_opts *opts = &rec->opts;
+	struct record_opts *opts = &rec->opts;
 	int rc = 0;
 
 	perf_evlist__config(evlist, opts);
@@ -348,7 +348,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	const bool forks = argc > 0;
 	struct machine *machine;
 	struct perf_tool *tool = &rec->tool;
-	struct perf_record_opts *opts = &rec->opts;
+	struct record_opts *opts = &rec->opts;
 	struct perf_evlist *evsel_list = rec->evlist;
 	struct perf_data_file *file = &rec->file;
 	struct perf_session *session;
@@ -657,7 +657,7 @@ static int get_stack_size(char *str, unsigned long *_size)
 }
 #endif /* HAVE_LIBUNWIND_SUPPORT */
 
-int record_parse_callchain(const char *arg, struct perf_record_opts *opts)
+int record_parse_callchain(const char *arg, struct record_opts *opts)
 {
 	char *tok, *name, *saveptr = NULL;
 	char *buf;
@@ -713,7 +713,7 @@ int record_parse_callchain(const char *arg, struct perf_record_opts *opts)
 	return ret;
 }
 
-static void callchain_debug(struct perf_record_opts *opts)
+static void callchain_debug(struct record_opts *opts)
 {
 	pr_debug("callchain: type %d\n", opts->call_graph);
 
@@ -726,7 +726,7 @@ int record_parse_callchain_opt(const struct option *opt,
 			       const char *arg,
 			       int unset)
 {
-	struct perf_record_opts *opts = opt->value;
+	struct record_opts *opts = opt->value;
 	int ret;
 
 	/* --no-call-graph */
@@ -747,7 +747,7 @@ int record_callchain_opt(const struct option *opt,
 			 const char *arg __maybe_unused,
 			 int unset __maybe_unused)
 {
-	struct perf_record_opts *opts = opt->value;
+	struct record_opts *opts = opt->value;
 
 	if (opts->call_graph == CALLCHAIN_NONE)
 		opts->call_graph = CALLCHAIN_FP;
@@ -796,7 +796,7 @@ const char record_callchain_help[] = CALLCHAIN_HELP "fp";
 /*
  * XXX Will stay a global variable till we fix builtin-script.c to stop messing
  * with it and switch to use the library functions in perf_evlist that came
- * from builtin-record.c, i.e. use perf_record_opts,
+ * from builtin-record.c, i.e. use record_opts,
  * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
  * using pipes, etc.
  */
@@ -944,7 +944,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (perf_evlist__create_maps(evsel_list, &rec->opts.target) < 0)
 		usage_with_options(record_usage, record_options);
 
-	if (perf_record_opts__config(&rec->opts)) {
+	if (record_opts__config(&rec->opts)) {
 		err = -EINVAL;
 		goto out_free_fd;
 	}
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 2c6cb66..172e91a 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -854,7 +854,7 @@ static int perf_top__start_counters(struct perf_top *top)
 	char msg[512];
 	struct perf_evsel *counter;
 	struct perf_evlist *evlist = top->evlist;
-	struct perf_record_opts *opts = &top->record_opts;
+	struct record_opts *opts = &top->record_opts;
 
 	perf_evlist__config(evlist, opts);
 
@@ -906,7 +906,7 @@ static int perf_top__setup_sample_type(struct perf_top *top __maybe_unused)
 
 static int __cmd_top(struct perf_top *top)
 {
-	struct perf_record_opts *opts = &top->record_opts;
+	struct record_opts *opts = &top->record_opts;
 	pthread_t thread;
 	int ret;
 
@@ -1028,7 +1028,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		.max_stack	     = PERF_MAX_STACK_DEPTH,
 		.sym_pcnt_filter     = 5,
 	};
-	struct perf_record_opts *opts = &top.record_opts;
+	struct record_opts *opts = &top.record_opts;
 	struct target *target = &opts->target;
 	const struct option options[] = {
 	OPT_CALLBACK('e', "event", &top.evlist, "event",
@@ -1179,7 +1179,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (top.delay_secs < 1)
 		top.delay_secs = 1;
 
-	if (perf_record_opts__config(opts)) {
+	if (record_opts__config(opts)) {
 		status = -EINVAL;
 		goto out_delete_maps;
 	}
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 56bbca5..f64b5b0 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1159,7 +1159,7 @@ struct trace {
 		int		max;
 		struct syscall  *table;
 	} syscalls;
-	struct perf_record_opts opts;
+	struct record_opts	opts;
 	struct machine		*host;
 	u64			base_time;
 	bool			full_time;
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index b23fed5..b1cc84b 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -247,7 +247,7 @@ enum perf_call_graph_mode {
 	CALLCHAIN_DWARF
 };
 
-struct perf_record_opts {
+struct record_opts {
 	struct target target;
 	int	     call_graph;
 	bool	     group;
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 85d4919..4248d1e 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -391,7 +391,7 @@ static int do_test_code_reading(bool try_kcore)
 	struct machines machines;
 	struct machine *machine;
 	struct thread *thread;
-	struct perf_record_opts opts = {
+	struct record_opts opts = {
 		.mmap_pages	     = UINT_MAX,
 		.user_freq	     = UINT_MAX,
 		.user_interval	     = ULLONG_MAX,
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 376c356..27eb751 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -51,7 +51,7 @@ static int find_comm(struct perf_evlist *evlist, const char *comm)
  */
 int test__keep_tracking(void)
 {
-	struct perf_record_opts opts = {
+	struct record_opts opts = {
 		.mmap_pages	     = UINT_MAX,
 		.user_freq	     = UINT_MAX,
 		.user_interval	     = ULLONG_MAX,
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
index 41cc0ba..774620a 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -6,7 +6,7 @@
 
 int test__syscall_open_tp_fields(void)
 {
-	struct perf_record_opts opts = {
+	struct record_opts opts = {
 		.target = {
 			.uid = UINT_MAX,
 			.uses_mmap = true,
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 93a62b0..eeba562 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -34,7 +34,7 @@ realloc:
 
 int test__PERF_RECORD(void)
 {
-	struct perf_record_opts opts = {
+	struct record_opts opts = {
 		.target = {
 			.uid = UINT_MAX,
 			.uses_mmap = true,
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 4ca1b93..c6398b9 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -46,7 +46,7 @@ static u64 rdtsc(void)
  */
 int test__perf_time_to_tsc(void)
 {
-	struct perf_record_opts opts = {
+	struct record_opts opts = {
 		.mmap_pages	     = UINT_MAX,
 		.user_freq	     = UINT_MAX,
 		.user_interval	     = ULLONG_MAX,
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 4f7f989..08b25af 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -146,7 +146,7 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor)
 
 struct option;
 
-int record_parse_callchain(const char *arg, struct perf_record_opts *opts);
+int record_parse_callchain(const char *arg, struct record_opts *opts);
 int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset);
 int record_callchain_opt(const struct option *opt, const char *arg, int unset);
 
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 9f64ede..2fe5195 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -12,7 +12,7 @@
 struct pollfd;
 struct thread_map;
 struct cpu_map;
-struct perf_record_opts;
+struct record_opts;
 
 #define PERF_EVLIST__HLIST_BITS 8
 #define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
@@ -97,9 +97,8 @@ void perf_evlist__close(struct perf_evlist *evlist);
 
 void perf_evlist__set_id_pos(struct perf_evlist *evlist);
 bool perf_can_sample_identifier(void);
-void perf_evlist__config(struct perf_evlist *evlist,
-			 struct perf_record_opts *opts);
-int perf_record_opts__config(struct perf_record_opts *opts);
+void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts);
+int record_opts__config(struct record_opts *opts);
 
 int perf_evlist__prepare_workload(struct perf_evlist *evlist,
 				  struct target *target,
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 01ff4cf..6874e04 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -528,8 +528,7 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
  *     enable/disable events specifically, as there's no
  *     initial traced exec call.
  */
-void perf_evsel__config(struct perf_evsel *evsel,
-			struct perf_record_opts *opts)
+void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 {
 	struct perf_evsel *leader = evsel->leader;
 	struct perf_event_attr *attr = &evsel->attr;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 8120eeb..f1b3256 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -96,7 +96,7 @@ struct perf_evsel {
 struct cpu_map;
 struct thread_map;
 struct perf_evlist;
-struct perf_record_opts;
+struct record_opts;
 
 struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx);
 
@@ -120,7 +120,7 @@ void perf_evsel__exit(struct perf_evsel *evsel);
 void perf_evsel__delete(struct perf_evsel *evsel);
 
 void perf_evsel__config(struct perf_evsel *evsel,
-			struct perf_record_opts *opts);
+			struct record_opts *opts);
 
 int __perf_evsel__sample_size(u64 sample_type);
 void perf_evsel__calc_id_pos(struct perf_evsel *evsel);
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index e510453..104a475 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -74,8 +74,7 @@ bool perf_can_sample_identifier(void)
 	return perf_probe_api(perf_probe_sample_identifier);
 }
 
-void perf_evlist__config(struct perf_evlist *evlist,
-			struct perf_record_opts *opts)
+void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 {
 	struct perf_evsel *evsel;
 	bool use_sample_identifier = false;
@@ -123,7 +122,7 @@ static int get_max_rate(unsigned int *rate)
 	return filename__read_int(path, (int *) rate);
 }
 
-static int perf_record_opts__config_freq(struct perf_record_opts *opts)
+static int record_opts__config_freq(struct record_opts *opts)
 {
 	bool user_freq = opts->user_freq != UINT_MAX;
 	unsigned int max_rate;
@@ -173,9 +172,9 @@ static int perf_record_opts__config_freq(struct perf_record_opts *opts)
 	return 0;
 }
 
-int perf_record_opts__config(struct perf_record_opts *opts)
+int record_opts__config(struct record_opts *opts)
 {
-	return perf_record_opts__config_freq(opts);
+	return record_opts__config_freq(opts);
 }
 
 bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
diff --git a/tools/perf/util/top.c b/tools/perf/util/top.c
index ce793c7..8e517de 100644
--- a/tools/perf/util/top.c
+++ b/tools/perf/util/top.c
@@ -26,7 +26,7 @@ size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size)
 	float samples_per_sec;
 	float ksamples_per_sec;
 	float esamples_percent;
-	struct perf_record_opts *opts = &top->record_opts;
+	struct record_opts *opts = &top->record_opts;
 	struct target *target = &opts->target;
 	size_t ret = 0;
 
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index 88cfeaf..dab14d0 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -14,7 +14,7 @@ struct perf_session;
 struct perf_top {
 	struct perf_tool   tool;
 	struct perf_evlist *evlist;
-	struct perf_record_opts record_opts;
+	struct record_opts record_opts;
 	/*
 	 * Symbols will be added here in perf_event__process_sample and will
 	 * get out after decayed.
-- 
cgit v0.10.2


From ee4ad93e82b8fd260ae618f6b0413cd321bc09cb Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 19 Dec 2013 14:41:59 +0100
Subject: perf tests: Factor make install tests

Factoring make install tests to check for multiple files. Adding default
set of installed files for install and install_bin tests.

Putting the 'test' line into the log file instead to the screen as it
gets more complex now.

If the tests fails to find a file, following message is displayed:

$ make -f tests/make make_install_bin
- make_install_bin: cd . && make -f Makefile DESTDIR=/tmp/tmp.nCVuQoSHaJ install-bin
  failed to find: bin/perf

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1387460527-15030-2-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 2ca0abf..f641c35 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -106,10 +106,36 @@ test_make_python_perf_so := test -f $(PERF)/python/perf.so
 test_make_perf_o     := test -f $(PERF)/perf.o
 test_make_util_map_o := test -f $(PERF)/util/map.o
 
-test_make_install       := test -x $$TMP_DEST/bin/perf
-test_make_install_O     := $(test_make_install)
-test_make_install_bin   := $(test_make_install)
-test_make_install_bin_O := $(test_make_install)
+define test_dest_files
+  for file in $(1); do				\
+    if [ ! -x $$TMP_DEST/$$file ]; then		\
+      echo "  failed to find: $$file";		\
+    fi						\
+  done
+endef
+
+installed_files_bin := bin/perf
+installed_files_bin += etc/bash_completion.d/perf
+installed_files_bin += libexec/perf-core/perf-archive
+
+installed_files_plugins := lib64/traceevent/plugins/plugin_cfg80211.so
+installed_files_plugins += lib64/traceevent/plugins/plugin_scsi.so
+installed_files_plugins += lib64/traceevent/plugins/plugin_xen.so
+installed_files_plugins += lib64/traceevent/plugins/plugin_function.so
+installed_files_plugins += lib64/traceevent/plugins/plugin_sched_switch.so
+installed_files_plugins += lib64/traceevent/plugins/plugin_mac80211.so
+installed_files_plugins += lib64/traceevent/plugins/plugin_kvm.so
+installed_files_plugins += lib64/traceevent/plugins/plugin_kmem.so
+installed_files_plugins += lib64/traceevent/plugins/plugin_hrtimer.so
+installed_files_plugins += lib64/traceevent/plugins/plugin_jbd2.so
+
+installed_files_all := $(installed_files_bin)
+installed_files_all += $(installed_files_plugins)
+
+test_make_install       := $(call test_dest_files,$(installed_files_all))
+test_make_install_O     := $(call test_dest_files,$(installed_files_all))
+test_make_install_bin   := $(call test_dest_files,$(installed_files_bin))
+test_make_install_bin_O := $(call test_dest_files,$(installed_files_bin))
 
 # FIXME nothing gets installed
 test_make_install_man    := test -f $$TMP_DEST/share/man/man1/perf.1
@@ -162,7 +188,7 @@ $(run):
 	cmd="cd $(PERF) && make -f $(MK) DESTDIR=$$TMP_DEST $($@)"; \
 	echo "- $@: $$cmd" && echo $$cmd > $@ && \
 	( eval $$cmd ) >> $@ 2>&1; \
-	echo "  test: $(call test,$@)"; \
+	echo "  test: $(call test,$@)" >> $@ 2>&1; \
 	$(call test,$@) && \
 	rm -f $@ \
 	rm -rf $$TMP_DEST
@@ -174,7 +200,7 @@ $(run_O):
 	cmd="cd $(PERF) && make -f $(MK) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \
 	echo "- $@: $$cmd" && echo $$cmd > $@ && \
 	( eval $$cmd ) >> $@ 2>&1 && \
-	echo "  test: $(call test_O,$@)"; \
+	echo "  test: $(call test_O,$@)" >> $@ 2>&1; \
 	$(call test_O,$@) && \
 	rm -f $@ && \
 	rm -rf $$TMP_O \
-- 
cgit v0.10.2


From b7248defce917acce74b338d69c2b8f600370213 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 19 Dec 2013 14:42:00 +0100
Subject: perf tools: Making QUIET_(CLEAN|INSTAL) variables global

Moving QUIET_(CLEAN|INSTAL) variables into:

  tools/scripts/Makefile.include

to be usable by other tools. The change to use them in libtraceevent is
in following patches.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1387460527-15030-3-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak
index f168deb..4d985e0 100644
--- a/tools/perf/config/utilities.mak
+++ b/tools/perf/config/utilities.mak
@@ -178,10 +178,3 @@ endef
 _ge_attempt = $(if $(get-executable),$(get-executable),$(_gea_warn)$(call _gea_err,$(2)))
 _gea_warn = $(warning The path '$(1)' is not executable.)
 _gea_err  = $(if $(1),$(error Please set '$(1)' appropriately))
-
-ifneq ($(findstring $(MAKEFLAGS),s),s)
-  ifneq ($(V),1)
-    QUIET_CLEAN		= @printf '  CLEAN    %s\n' $1;
-    QUIET_INSTALL	= @printf '  INSTALL  %s\n' $1;
-  endif
-endif
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index ee76544..e4cfbed 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -76,5 +76,8 @@ ifneq ($(findstring $(MAKEFLAGS),s),s)
 		+@echo	       '  DESCEND  '$(1); \
 		mkdir -p $(OUTPUT)$(1) && \
 		$(MAKE) $(COMMAND_O) subdir=$(if $(subdir),$(subdir)/$(1),$(1)) $(PRINT_DIR) -C $(1) $(2)
+
+	QUIET_CLEAN    = @printf '  CLEAN    %s\n' $1;
+	QUIET_INSTALL  = @printf '  INSTALL  %s\n' $1;
   endif
 endif
-- 
cgit v0.10.2


From db72a330587e10d6b8009e0dcf3d97aa9b1e2659 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 19 Dec 2013 14:42:01 +0100
Subject: tools lib traceevent: Remove print_app_build variable

Removing print_app_build variable, because it's not needed.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1387460527-15030-4-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 0d9cbb4..022c987 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -151,7 +151,6 @@ override CFLAGS += $(udis86-flags) -D_GNU_SOURCE
 ifeq ($(VERBOSE),1)
   Q =
   print_compile =
-  print_app_build =
   print_fpic_compile =
   print_shared_lib_compile =
   print_plugin_obj_compile =
@@ -160,7 +159,6 @@ ifeq ($(VERBOSE),1)
 else
   Q = @
   print_compile =		echo '  CC       '$(OBJ);
-  print_app_build =		echo '  BUILD    '$(OBJ);
   print_fpic_compile =		echo '  CC FPIC  '$(OBJ);
   print_shared_lib_compile =	echo '  BUILD    SHARED LIB '$(OBJ);
   print_plugin_obj_compile =	echo '  CC FPIC  '$(OBJ);
@@ -173,10 +171,6 @@ do_fpic_compile =					\
 	($(print_fpic_compile)				\
 	$(CC) -c $(CFLAGS) $(EXT) -fPIC $< -o $@)
 
-do_app_build =						\
-	($(print_app_build)				\
-	$(CC) $^ -rdynamic -o $@ $(CONFIG_LIBS) $(LIBS))
-
 do_compile_shared_library =			\
 	($(print_shared_lib_compile)		\
 	$(CC) --shared $^ -o $@)
-- 
cgit v0.10.2


From c3d090f498a4d7a8905c92dbf83ae2aa4810fbef Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 19 Dec 2013 14:42:02 +0100
Subject: tools lib traceevent: Use global QUIET_CC build output

Using global QUIET_CC build output variable and getting rid of local
print_compile.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1387460527-15030-5-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 022c987..e852a8d 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -67,6 +67,8 @@ PLUGIN_DIR = -DPLUGIN_DIR="$(DESTDIR)/$(plugin_dir)"
 PLUGIN_DIR_SQ = '$(subst ','\'',$(PLUGIN_DIR))'
 endif
 
+include $(if $(BUILD_SRC),$(BUILD_SRC)/)../../scripts/Makefile.include
+
 # copy a bit from Linux kbuild
 
 ifeq ("$(origin V)", "command line")
@@ -150,7 +152,6 @@ override CFLAGS += $(udis86-flags) -D_GNU_SOURCE
 
 ifeq ($(VERBOSE),1)
   Q =
-  print_compile =
   print_fpic_compile =
   print_shared_lib_compile =
   print_plugin_obj_compile =
@@ -158,7 +159,6 @@ ifeq ($(VERBOSE),1)
   print_install =
 else
   Q = @
-  print_compile =		echo '  CC       '$(OBJ);
   print_fpic_compile =		echo '  CC FPIC  '$(OBJ);
   print_shared_lib_compile =	echo '  BUILD    SHARED LIB '$(OBJ);
   print_plugin_obj_compile =	echo '  CC FPIC  '$(OBJ);
@@ -188,16 +188,13 @@ do_build_static_lib =				\
 	$(RM) $@;  $(AR) rcs $@ $^)
 
 
-define do_compile
-	$(print_compile)						\
-	$(CC) -c $(CFLAGS) $(EXT) $< -o $(obj)/$@;
-endef
+do_compile = $(QUIET_CC)$(CC) -c $(CFLAGS) $(EXT) $< -o $(obj)/$@;
 
 $(obj)/%.o: $(src)/%.c
-	$(Q)$(call do_compile)
+	$(call do_compile)
 
 %.o: $(src)/%.c
-	$(Q)$(call do_compile)
+	$(call do_compile)
 
 PEVENT_LIB_OBJS  = event-parse.o
 PEVENT_LIB_OBJS += event-plugin.o
-- 
cgit v0.10.2


From bdebbacd421184234b5551c468e53956a9b6edf5 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 19 Dec 2013 14:42:03 +0100
Subject: tools lib traceevent: Add global QUIET_CC_FPIC build output

Adding global QUIET_CC_FPIC build output variable and getting rid of
local print_fpic_compile and print_plugin_obj_compile.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1387460527-15030-6-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index e852a8d..24203cc 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -152,33 +152,21 @@ override CFLAGS += $(udis86-flags) -D_GNU_SOURCE
 
 ifeq ($(VERBOSE),1)
   Q =
-  print_fpic_compile =
   print_shared_lib_compile =
-  print_plugin_obj_compile =
   print_plugin_build =
   print_install =
 else
   Q = @
-  print_fpic_compile =		echo '  CC FPIC  '$(OBJ);
   print_shared_lib_compile =	echo '  BUILD    SHARED LIB '$(OBJ);
-  print_plugin_obj_compile =	echo '  CC FPIC  '$(OBJ);
   print_plugin_build =		echo '  BUILD    PLUGIN '$(OBJ);
   print_static_lib_build =	echo '  BUILD    STATIC LIB '$(OBJ);
   print_install =		echo '  INSTALL  '$1;
 endif
 
-do_fpic_compile =					\
-	($(print_fpic_compile)				\
-	$(CC) -c $(CFLAGS) $(EXT) -fPIC $< -o $@)
-
 do_compile_shared_library =			\
 	($(print_shared_lib_compile)		\
 	$(CC) --shared $^ -o $@)
 
-do_compile_plugin_obj =				\
-	($(print_plugin_obj_compile)		\
-	$(CC) -c $(CFLAGS) -fPIC -o $@ $<)
-
 do_plugin_build =				\
 	($(print_plugin_build)			\
 	$(CC) $(CFLAGS) -shared -nostartfiles -o $@ $<)
@@ -236,10 +224,10 @@ libtraceevent.a: $(PEVENT_LIB_OBJS)
 plugins: $(PLUGINS)
 
 $(PEVENT_LIB_OBJS): %.o: $(src)/%.c TRACEEVENT-CFLAGS
-	$(Q)$(do_fpic_compile)
+	$(QUIET_CC_FPIC)$(CC) -c $(CFLAGS) $(EXT) -fPIC $< -o $@
 
 $(PLUGIN_OBJS): %.o : $(src)/%.c
-	$(Q)$(do_compile_plugin_obj)
+	$(QUIET_CC_FPIC)$(CC) -c $(CFLAGS) -fPIC -o $@ $<
 
 $(PLUGINS): %.so: %.o
 	$(Q)$(do_plugin_build)
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index e4cfbed..8abbef1 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -61,6 +61,7 @@ QUIET_SUBDIR1  =
 ifneq ($(findstring $(MAKEFLAGS),s),s)
   ifneq ($(V),1)
 	QUIET_CC       = @echo '  CC       '$@;
+	QUIET_CC_FPIC  = @echo '  CC FPIC  '$@;
 	QUIET_AR       = @echo '  AR       '$@;
 	QUIET_LINK     = @echo '  LINK     '$@;
 	QUIET_MKDIR    = @echo '  MKDIR    '$@;
-- 
cgit v0.10.2


From e6262e23134f575ae07ecc25bb69ddb63caebc95 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 19 Dec 2013 14:42:04 +0100
Subject: tools lib traceevent: Use global QUIET_LINK build output

Using global QUIET_LINK build output variable and getting rid of local
print_static_lib_build, print_plugin_build and print_shared_lib_compile.

We no longer distinguish between shared and static library in the build
message. It's differenced by the built file suffix, like:

  $ make
    ...
    LINK     libtraceevent.a
    LINK     libtraceevent.so

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1387460527-15030-7-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 24203cc..51be8ab 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -152,14 +152,9 @@ override CFLAGS += $(udis86-flags) -D_GNU_SOURCE
 
 ifeq ($(VERBOSE),1)
   Q =
-  print_shared_lib_compile =
-  print_plugin_build =
   print_install =
 else
   Q = @
-  print_shared_lib_compile =	echo '  BUILD    SHARED LIB '$(OBJ);
-  print_plugin_build =		echo '  BUILD    PLUGIN '$(OBJ);
-  print_static_lib_build =	echo '  BUILD    STATIC LIB '$(OBJ);
   print_install =		echo '  INSTALL  '$1;
 endif
 
@@ -216,10 +211,10 @@ all: all_cmd
 all_cmd: $(CMD_TARGETS)
 
 libtraceevent.so: $(PEVENT_LIB_OBJS)
-	$(Q)$(do_compile_shared_library)
+	$(QUIET_LINK)$(CC) --shared $^ -o $@
 
 libtraceevent.a: $(PEVENT_LIB_OBJS)
-	$(Q)$(do_build_static_lib)
+	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
 
 plugins: $(PLUGINS)
 
@@ -230,7 +225,7 @@ $(PLUGIN_OBJS): %.o : $(src)/%.c
 	$(QUIET_CC_FPIC)$(CC) -c $(CFLAGS) -fPIC -o $@ $<
 
 $(PLUGINS): %.so: %.o
-	$(Q)$(do_plugin_build)
+	$(QUIET_LINK)$(CC) $(CFLAGS) -shared -nostartfiles -o $@ $<
 
 define make_version.h
 	(echo '/* This file is automatically generated. Do not modify. */';		\
-- 
cgit v0.10.2


From 02a82c7bcd353b8cc4d4f8b3c872b527fbac7c31 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 19 Dec 2013 14:42:05 +0100
Subject: tools lib traceevent: Use global QUIET_INSTALL build output

Using global QUIET_INSTALL build output variable and factoring plugins
installation so we could have only single install message for plugins:

  INSTALL trace_plugins

Getting rid of local print_install.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1387460527-15030-8-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 51be8ab..8ea4368 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -152,10 +152,8 @@ override CFLAGS += $(udis86-flags) -D_GNU_SOURCE
 
 ifeq ($(VERBOSE),1)
   Q =
-  print_install =
 else
   Q = @
-  print_install =		echo '  INSTALL  '$1;
 endif
 
 do_compile_shared_library =			\
@@ -307,22 +305,25 @@ TAGS:	force
 	--regex='/_PE(\([^,)]*\).*/PEVENT_ERRNO__\1/'
 
 define do_install
-	$(print_install)				\
 	if [ ! -d '$(DESTDIR_SQ)$2' ]; then		\
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2';	\
 	fi;						\
 	$(INSTALL) $1 '$(DESTDIR_SQ)$2'
 endef
 
-install_lib: all_cmd install_plugins
-	$(Q)$(call do_install,$(LIB_FILE),$(bindir_SQ))
-
-PLUGINS_INSTALL = $(subst .so,.install,$(PLUGINS))
+define do_install_plugins
+	for plugin in $1; do				\
+	  $(call do_install,$$plugin,$(plugin_dir_SQ));	\
+	done
+endef
 
-$(PLUGINS_INSTALL): %.install : %.so force
-	$(Q)$(call do_install,$<,$(plugin_dir_SQ))
+install_lib: all_cmd install_plugins
+	$(call QUIET_INSTALL, $(LIB_FILE)) \
+		$(call do_install,$(LIB_FILE),$(bindir_SQ))
 
-install_plugins: $(PLUGINS_INSTALL)
+install_plugins: $(PLUGINS)
+	$(call QUIET_INSTALL, trace_plugins) \
+		$(call do_install_plugins, $(PLUGINS))
 
 install: install_lib
 
-- 
cgit v0.10.2


From 4a953c716af285c94432e2d303ca5ee8f66129c0 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 19 Dec 2013 14:42:06 +0100
Subject: tools lib traceevent: Use global QUIET_CLEAN build output

Using global QUIET_CLEAN build output variable and so we could have only
single clean message:

  CLEAN libtraceevent

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1387460527-15030-9-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 8ea4368..3496c9c 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -328,8 +328,9 @@ install_plugins: $(PLUGINS)
 install: install_lib
 
 clean:
-	$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d
-	$(RM) TRACEEVENT-CFLAGS tags TAGS
+	$(call QUIET_CLEAN, libtraceevent) \
+		$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d \
+		$(RM) TRACEEVENT-CFLAGS tags TAGS
 
 endif # skip-makefile
 
-- 
cgit v0.10.2


From 4c7aafc950178cd78f8cbda916ee8208afe039b5 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 19 Dec 2013 14:42:07 +0100
Subject: tools lib traceevent: Use global 'O' processing code

Using global 'O' processing code because it's already setup due to the
scripts/Makefile.include include.

Using global variable OUTPUT instead of the local BUILD_OUTPUT.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1387460527-15030-10-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 3496c9c..ca4ab78 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -83,18 +83,13 @@ ifeq ("$(origin O)", "command line")
 endif
 
 ifeq ($(BUILD_SRC),)
-ifneq ($(BUILD_OUTPUT),)
+ifneq ($(OUTPUT),)
 
 define build_output
-	$(if $(VERBOSE:1=),@)+$(MAKE) -C $(BUILD_OUTPUT) 	\
-	BUILD_SRC=$(CURDIR) -f $(CURDIR)/Makefile $1
+	$(if $(VERBOSE:1=),@)+$(MAKE) -C $(OUTPUT) \
+	BUILD_SRC=$(CURDIR)/ -f $(CURDIR)/Makefile $1
 endef
 
-saved-output := $(BUILD_OUTPUT)
-BUILD_OUTPUT := $(shell cd $(BUILD_OUTPUT) && /bin/pwd)
-$(if $(BUILD_OUTPUT),, \
-     $(error output directory "$(saved-output)" does not exist))
-
 all: sub-make
 
 $(MAKECMDGOALS): sub-make
@@ -106,7 +101,7 @@ sub-make: force
 # Leave processing to above invocation of make
 skip-makefile := 1
 
-endif # BUILD_OUTPUT
+endif # OUTPUT
 endif # BUILD_SRC
 
 # We process the rest of the Makefile if this is the final invocation of make
-- 
cgit v0.10.2


From 28b21393fa0472501b5a2a85a0b008b4e3dc154c Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 19 Dec 2013 14:53:53 -0300
Subject: perf report: Rename 'perf_report' to 'report'

Reduce typing, functions use class__method convention, so unlikely to
clash with other libraries.

This actually was discussed in the "Link:" referenced message below.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/20131112113427.GA4053@ghostprotocols.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8424053..da156a4 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -39,7 +39,7 @@
 #include <dlfcn.h>
 #include <linux/bitmap.h>
 
-struct perf_report {
+struct report {
 	struct perf_tool	tool;
 	struct perf_session	*session;
 	bool			force, use_tui, use_gtk, use_stdio;
@@ -60,14 +60,14 @@ struct perf_report {
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
-static int perf_report_config(const char *var, const char *value, void *cb)
+static int report__config(const char *var, const char *value, void *cb)
 {
 	if (!strcmp(var, "report.group")) {
 		symbol_conf.event_group = perf_config_bool(var, value);
 		return 0;
 	}
 	if (!strcmp(var, "report.percent-limit")) {
-		struct perf_report *rep = cb;
+		struct report *rep = cb;
 		rep->min_percent = strtof(value, NULL);
 		return 0;
 	}
@@ -75,7 +75,7 @@ static int perf_report_config(const char *var, const char *value, void *cb)
 	return perf_default_config(var, value, cb);
 }
 
-static int report__resolve_callchain(struct perf_report *rep, struct symbol **parent,
+static int report__resolve_callchain(struct report *rep, struct symbol **parent,
 				     struct perf_evsel *evsel, struct addr_location *al,
 				     struct perf_sample *sample, struct machine *machine)
 {
@@ -93,14 +93,11 @@ static int hist_entry__append_callchain(struct hist_entry *he, struct perf_sampl
 	return callchain_append(he->callchain, &callchain_cursor, sample->period);
 }
 
-static int perf_report__add_mem_hist_entry(struct perf_tool *tool,
-					   struct addr_location *al,
-					   struct perf_sample *sample,
-					   struct perf_evsel *evsel,
-					   struct machine *machine,
-					   union perf_event *event)
+static int report__add_mem_hist_entry(struct perf_tool *tool, struct addr_location *al,
+				      struct perf_sample *sample, struct perf_evsel *evsel,
+				      struct machine *machine, union perf_event *event)
 {
-	struct perf_report *rep = container_of(tool, struct perf_report, tool);
+	struct report *rep = container_of(tool, struct report, tool);
 	struct symbol *parent = NULL;
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	struct hist_entry *he;
@@ -150,13 +147,11 @@ out:
 	return err;
 }
 
-static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
-					struct addr_location *al,
-					struct perf_sample *sample,
-					struct perf_evsel *evsel,
-				      struct machine *machine)
+static int report__add_branch_hist_entry(struct perf_tool *tool, struct addr_location *al,
+					 struct perf_sample *sample, struct perf_evsel *evsel,
+					 struct machine *machine)
 {
-	struct perf_report *rep = container_of(tool, struct perf_report, tool);
+	struct report *rep = container_of(tool, struct report, tool);
 	struct symbol *parent = NULL;
 	unsigned i;
 	struct hist_entry *he;
@@ -208,13 +203,11 @@ out:
 	return err;
 }
 
-static int perf_evsel__add_hist_entry(struct perf_tool *tool,
-				      struct perf_evsel *evsel,
-				      struct addr_location *al,
-				      struct perf_sample *sample,
-				      struct machine *machine)
+static int report__add_hist_entry(struct perf_tool *tool, struct perf_evsel *evsel,
+				  struct addr_location *al, struct perf_sample *sample,
+				  struct machine *machine)
 {
-	struct perf_report *rep = container_of(tool, struct perf_report, tool);
+	struct report *rep = container_of(tool, struct report, tool);
 	struct symbol *parent = NULL;
 	struct hist_entry *he;
 	int err = report__resolve_callchain(rep, &parent, evsel, al, sample, machine);
@@ -246,7 +239,7 @@ static int process_sample_event(struct perf_tool *tool,
 				struct perf_evsel *evsel,
 				struct machine *machine)
 {
-	struct perf_report *rep = container_of(tool, struct perf_report, tool);
+	struct report *rep = container_of(tool, struct report, tool);
 	struct addr_location al;
 	int ret;
 
@@ -263,21 +256,18 @@ static int process_sample_event(struct perf_tool *tool,
 		return 0;
 
 	if (sort__mode == SORT_MODE__BRANCH) {
-		ret = perf_report__add_branch_hist_entry(tool, &al, sample,
-							 evsel, machine);
+		ret = report__add_branch_hist_entry(tool, &al, sample, evsel, machine);
 		if (ret < 0)
 			pr_debug("problem adding lbr entry, skipping event\n");
 	} else if (rep->mem_mode == 1) {
-		ret = perf_report__add_mem_hist_entry(tool, &al, sample,
-						      evsel, machine, event);
+		ret = report__add_mem_hist_entry(tool, &al, sample, evsel, machine, event);
 		if (ret < 0)
 			pr_debug("problem adding mem entry, skipping event\n");
 	} else {
 		if (al.map != NULL)
 			al.map->dso->hit = 1;
 
-		ret = perf_evsel__add_hist_entry(tool, evsel, &al, sample,
-						 machine);
+		ret = report__add_hist_entry(tool, evsel, &al, sample, machine);
 		if (ret < 0)
 			pr_debug("problem incrementing symbol period, skipping event\n");
 	}
@@ -290,7 +280,7 @@ static int process_read_event(struct perf_tool *tool,
 			      struct perf_evsel *evsel,
 			      struct machine *machine __maybe_unused)
 {
-	struct perf_report *rep = container_of(tool, struct perf_report, tool);
+	struct report *rep = container_of(tool, struct report, tool);
 
 	if (rep->show_threads) {
 		const char *name = evsel ? perf_evsel__name(evsel) : "unknown";
@@ -309,7 +299,7 @@ static int process_read_event(struct perf_tool *tool,
 }
 
 /* For pipe mode, sample_type is not currently set */
-static int perf_report__setup_sample_type(struct perf_report *rep)
+static int report__setup_sample_type(struct report *rep)
 {
 	struct perf_session *session = rep->session;
 	u64 sample_type = perf_evlist__combined_sample_type(session->evlist);
@@ -354,8 +344,7 @@ static void sig_handler(int sig __maybe_unused)
 	session_done = 1;
 }
 
-static size_t hists__fprintf_nr_sample_events(struct perf_report *rep,
-					      struct hists *hists,
+static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report *rep,
 					      const char *evname, FILE *fp)
 {
 	size_t ret;
@@ -392,7 +381,7 @@ static size_t hists__fprintf_nr_sample_events(struct perf_report *rep,
 }
 
 static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
-					 struct perf_report *rep,
+					 struct report *rep,
 					 const char *help)
 {
 	struct perf_evsel *pos;
@@ -405,7 +394,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 		    !perf_evsel__is_group_leader(pos))
 			continue;
 
-		hists__fprintf_nr_sample_events(rep, hists, evname, stdout);
+		hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
 		hists__fprintf(hists, true, 0, 0, rep->min_percent, stdout);
 		fprintf(stdout, "\n\n");
 	}
@@ -425,7 +414,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 	return 0;
 }
 
-static int __cmd_report(struct perf_report *rep)
+static int __cmd_report(struct report *rep)
 {
 	int ret = -EINVAL;
 	u64 nr_samples;
@@ -449,7 +438,7 @@ static int __cmd_report(struct perf_report *rep)
 	if (rep->show_threads)
 		perf_read_values_init(&rep->show_threads_values);
 
-	ret = perf_report__setup_sample_type(rep);
+	ret = report__setup_sample_type(rep);
 	if (ret)
 		return ret;
 
@@ -568,7 +557,7 @@ static int __cmd_report(struct perf_report *rep)
 static int
 parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 {
-	struct perf_report *rep = (struct perf_report *)opt->value;
+	struct report *rep = (struct report *)opt->value;
 	char *tok, *tok2;
 	char *endptr;
 
@@ -688,7 +677,7 @@ static int
 parse_percent_limit(const struct option *opt, const char *str,
 		    int unset __maybe_unused)
 {
-	struct perf_report *rep = opt->value;
+	struct report *rep = opt->value;
 
 	rep->min_percent = strtof(str, NULL);
 	return 0;
@@ -706,7 +695,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		"perf report [<options>]",
 		NULL
 	};
-	struct perf_report report = {
+	struct report report = {
 		.tool = {
 			.sample		 = process_sample_event,
 			.mmap		 = perf_event__process_mmap,
@@ -822,7 +811,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		.mode  = PERF_DATA_MODE_READ,
 	};
 
-	perf_config(perf_report_config, &report);
+	perf_config(report__config, &report);
 
 	argc = parse_options(argc, argv, options, report_usage, 0);
 
-- 
cgit v0.10.2


From 3184c47cb8b04b8bb5c1005168049519b066bcd1 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 19 Dec 2013 16:25:17 -0300
Subject: perf ui browser: Remove misplaced __maybe_unused

The 'browser' arg _is_ used, so ditch the misplaced attribute.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-bo4dabkip5iikhk3x384ac46@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index cbaa7af..94223d40 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -268,7 +268,7 @@ int ui_browser__show(struct ui_browser *browser, const char *title,
 	return err ? 0 : -1;
 }
 
-void ui_browser__hide(struct ui_browser *browser __maybe_unused)
+void ui_browser__hide(struct ui_browser *browser)
 {
 	pthread_mutex_lock(&ui__lock);
 	ui_helpline__pop();
-- 
cgit v0.10.2


From b7fff6b5f977115be1757f18b1aca928803b1e17 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 19 Dec 2013 16:34:52 -0300
Subject: perf scripting python: Shorten function signatures

Removing unused parameters.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-fspmnjadohrik8uvhytyu8lp@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 53c20e7..fc00792 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -231,13 +231,10 @@ static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
 	return event;
 }
 
-static void python_process_tracepoint(union perf_event *perf_event
-				      __maybe_unused,
-				 struct perf_sample *sample,
-				 struct perf_evsel *evsel,
-				 struct machine *machine __maybe_unused,
-				 struct thread *thread,
-				 struct addr_location *al)
+static void python_process_tracepoint(struct perf_sample *sample,
+				      struct perf_evsel *evsel,
+				      struct thread *thread,
+				      struct addr_location *al)
 {
 	PyObject *handler, *retval, *context, *t, *obj, *dict = NULL;
 	static char handler_name[256];
@@ -351,11 +348,8 @@ static void python_process_tracepoint(union perf_event *perf_event
 	Py_DECREF(t);
 }
 
-static void python_process_general_event(union perf_event *perf_event
-					 __maybe_unused,
-					 struct perf_sample *sample,
+static void python_process_general_event(struct perf_sample *sample,
 					 struct perf_evsel *evsel,
-					 struct machine *machine __maybe_unused,
 					 struct thread *thread,
 					 struct addr_location *al)
 {
@@ -411,22 +405,20 @@ exit:
 	Py_DECREF(t);
 }
 
-static void python_process_event(union perf_event *perf_event,
+static void python_process_event(union perf_event *event __maybe_unused,
 				 struct perf_sample *sample,
 				 struct perf_evsel *evsel,
-				 struct machine *machine,
+				 struct machine *machine __maybe_unused,
 				 struct thread *thread,
 				 struct addr_location *al)
 {
 	switch (evsel->attr.type) {
 	case PERF_TYPE_TRACEPOINT:
-		python_process_tracepoint(perf_event, sample, evsel,
-					  machine, thread, al);
+		python_process_tracepoint(sample, evsel, thread, al);
 		break;
 	/* Reserve for future process_hw/sw/raw APIs */
 	default:
-		python_process_general_event(perf_event, sample, evsel,
-					     machine, thread, al);
+		python_process_general_event(sample, evsel, thread, al);
 	}
 }
 
-- 
cgit v0.10.2


From 8853a1b76288d79aa1a6c5b8fe623d892aa9958b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 19 Dec 2013 16:39:31 -0300
Subject: perf scripting perl: Shorten function signatures

Removing unused parameters.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-b7r7o80o2xwwtlzgqxv50foe@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index d5e5969..b672ef0 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -257,12 +257,9 @@ static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
 	return event;
 }
 
-static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused,
-				    struct perf_sample *sample,
+static void perl_process_tracepoint(struct perf_sample *sample,
 				    struct perf_evsel *evsel,
-				    struct machine *machine __maybe_unused,
-				    struct thread *thread,
-					struct addr_location *al)
+				    struct thread *thread)
 {
 	struct format_field *field;
 	static char handler[256];
@@ -349,10 +346,7 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused,
 
 static void perl_process_event_generic(union perf_event *event,
 				       struct perf_sample *sample,
-				       struct perf_evsel *evsel,
-				       struct machine *machine __maybe_unused,
-				       struct thread *thread __maybe_unused,
-					   struct addr_location *al __maybe_unused)
+				       struct perf_evsel *evsel)
 {
 	dSP;
 
@@ -377,12 +371,12 @@ static void perl_process_event_generic(union perf_event *event,
 static void perl_process_event(union perf_event *event,
 			       struct perf_sample *sample,
 			       struct perf_evsel *evsel,
-			       struct machine *machine,
+			       struct machine *machine __maybe_unused,
 			       struct thread *thread,
-				   struct addr_location *al)
+			       struct addr_location *al __maybe_unused)
 {
-	perl_process_tracepoint(event, sample, evsel, machine, thread, al);
-	perl_process_event_generic(event, sample, evsel, machine, thread, al);
+	perl_process_tracepoint(sample, evsel, thread);
+	perl_process_event_generic(event, sample, evsel);
 }
 
 static void run_start_sub(void)
-- 
cgit v0.10.2


From 16824255394f55adf31b9a96a9965d8c15bdac4c Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 12 Dec 2013 15:08:36 +0100
Subject: x86, acpi, idle: Restructure the mwait idle routines

People seem to delight in writing wrong and broken mwait idle routines;
collapse the lot.

This leaves mwait_play_dead() the sole remaining user of __mwait() and
new __mwait() users are probably doing it wrong.

Also remove __sti_mwait() as its unused.

Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Jacob Jun Pan <jacob.jun.pan@linux.intel.com>
Cc: Mike Galbraith <bitbucket@online.de>
Cc: Len Brown <lenb@kernel.org>
Cc: Rui Zhang <rui.zhang@intel.com>
Acked-by: Rafael Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131212141654.616820819@infradead.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 2f366d0..361b02e 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_MWAIT_H
 #define _ASM_X86_MWAIT_H
 
+#include <linux/sched.h>
+
 #define MWAIT_SUBSTATE_MASK		0xf
 #define MWAIT_CSTATE_MASK		0xf
 #define MWAIT_SUBSTATE_SIZE		4
@@ -13,4 +15,42 @@
 
 #define MWAIT_ECX_INTERRUPT_BREAK	0x1
 
+static inline void __monitor(const void *eax, unsigned long ecx,
+			     unsigned long edx)
+{
+	/* "monitor %eax, %ecx, %edx;" */
+	asm volatile(".byte 0x0f, 0x01, 0xc8;"
+		     :: "a" (eax), "c" (ecx), "d"(edx));
+}
+
+static inline void __mwait(unsigned long eax, unsigned long ecx)
+{
+	/* "mwait %eax, %ecx;" */
+	asm volatile(".byte 0x0f, 0x01, 0xc9;"
+		     :: "a" (eax), "c" (ecx));
+}
+
+/*
+ * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
+ * which can obviate IPI to trigger checking of need_resched.
+ * We execute MONITOR against need_resched and enter optimized wait state
+ * through MWAIT. Whenever someone changes need_resched, we would be woken
+ * up from MWAIT (without an IPI).
+ *
+ * New with Core Duo processors, MWAIT can take some hints based on CPU
+ * capability.
+ */
+static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
+{
+	if (!current_set_polling_and_test()) {
+		if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
+			clflush((void *)&current_thread_info()->flags);
+
+		__monitor((void *)&current_thread_info()->flags, 0, 0);
+		if (!need_resched())
+			__mwait(eax, ecx);
+	}
+	__current_clr_polling();
+}
+
 #endif /* _ASM_X86_MWAIT_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 7b034a4..24821f5 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -700,29 +700,6 @@ static inline void sync_core(void)
 #endif
 }
 
-static inline void __monitor(const void *eax, unsigned long ecx,
-			     unsigned long edx)
-{
-	/* "monitor %eax, %ecx, %edx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xc8;"
-		     :: "a" (eax), "c" (ecx), "d"(edx));
-}
-
-static inline void __mwait(unsigned long eax, unsigned long ecx)
-{
-	/* "mwait %eax, %ecx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xc9;"
-		     :: "a" (eax), "c" (ecx));
-}
-
-static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
-{
-	trace_hardirqs_on();
-	/* "mwait %eax, %ecx;" */
-	asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
-		     :: "a" (eax), "c" (ecx));
-}
-
 extern void select_idle_routine(const struct cpuinfo_x86 *c);
 extern void init_amd_e400_c1e_mask(void);
 
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index d2b7f27..e69182f 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -150,29 +150,6 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 }
 EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe);
 
-/*
- * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
- * which can obviate IPI to trigger checking of need_resched.
- * We execute MONITOR against need_resched and enter optimized wait state
- * through MWAIT. Whenever someone changes need_resched, we would be woken
- * up from MWAIT (without an IPI).
- *
- * New with Core Duo processors, MWAIT can take some hints based on CPU
- * capability.
- */
-void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
-{
-	if (!need_resched()) {
-		if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
-			clflush((void *)&current_thread_info()->flags);
-
-		__monitor((void *)&current_thread_info()->flags, 0, 0);
-		smp_mb();
-		if (!need_resched())
-			__mwait(ax, cx);
-	}
-}
-
 void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx)
 {
 	unsigned int cpu = smp_processor_id();
diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index fc6008f..509452a 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -193,10 +193,7 @@ static int power_saving_thread(void *data)
 					CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
 			stop_critical_timings();
 
-			__monitor((void *)&current_thread_info()->flags, 0, 0);
-			smp_mb();
-			if (!need_resched())
-				__mwait(power_saving_mwait_eax, 1);
+			mwait_idle_with_hints(power_saving_mwait_eax, 1);
 
 			start_critical_timings();
 			if (lapic_marked_unstable)
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 644516d..f90c56c 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -727,11 +727,6 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev,
 	if (unlikely(!pr))
 		return -EINVAL;
 
-	if (cx->entry_method == ACPI_CSTATE_FFH) {
-		if (current_set_polling_and_test())
-			return -EINVAL;
-	}
-
 	lapic_timer_state_broadcast(pr, cx, 1);
 	acpi_idle_do_entry(cx);
 
@@ -785,11 +780,6 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev,
 	if (unlikely(!pr))
 		return -EINVAL;
 
-	if (cx->entry_method == ACPI_CSTATE_FFH) {
-		if (current_set_polling_and_test())
-			return -EINVAL;
-	}
-
 	/*
 	 * Must be done before busmaster disable as we might need to
 	 * access HPET !
@@ -841,11 +831,6 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev,
 		}
 	}
 
-	if (cx->entry_method == ACPI_CSTATE_FFH) {
-		if (current_set_polling_and_test())
-			return -EINVAL;
-	}
-
 	acpi_unlazy_tlb(smp_processor_id());
 
 	/* Tell the scheduler that we are going deep-idle: */
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index f80b700..efec405 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -375,16 +375,7 @@ static int intel_idle(struct cpuidle_device *dev,
 	if (!(lapic_timer_reliable_states & (1 << (cstate))))
 		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
 
-	if (!current_set_polling_and_test()) {
-
-		if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
-			clflush((void *)&current_thread_info()->flags);
-
-		__monitor((void *)&current_thread_info()->flags, 0, 0);
-		smp_mb();
-		if (!need_resched())
-			__mwait(eax, ecx);
-	}
+	mwait_idle_with_hints(eax, ecx);
 
 	if (!(lapic_timer_reliable_states & (1 << (cstate))))
 		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c
index 8f181b3..e8275f2 100644
--- a/drivers/thermal/intel_powerclamp.c
+++ b/drivers/thermal/intel_powerclamp.c
@@ -438,9 +438,7 @@ static int clamp_thread(void *arg)
 			 */
 			local_touch_nmi();
 			stop_critical_timings();
-			__monitor((void *)&current_thread_info()->flags, 0, 0);
-			cpu_relax(); /* allow HT sibling to run */
-			__mwait(eax, ecx);
+			mwait_idle_with_hints(eax, ecx);
 			start_critical_timings();
 			atomic_inc(&idle_wakeup_counter);
 		}
-- 
cgit v0.10.2


From b1aac815c0891fe4a55a6b0b715910142227700f Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Tue, 17 Dec 2013 00:38:39 +0100
Subject: net: inet_diag: zero out uninitialized idiag_{src,dst} fields

Jakub reported while working with nlmon netlink sniffer that parts of
the inet_diag_sockid are not initialized when r->idiag_family != AF_INET6.
That is, fields of r->id.idiag_src[1 ... 3], r->id.idiag_dst[1 ... 3].

In fact, it seems that we can leak 6 * sizeof(u32) byte of kernel [slab]
memory through this. At least, in udp_dump_one(), we allocate a skb in ...

  rep = nlmsg_new(sizeof(struct inet_diag_msg) + ..., GFP_KERNEL);

... and then pass that to inet_sk_diag_fill() that puts the whole struct
inet_diag_msg into the skb, where we only fill out r->id.idiag_src[0],
r->id.idiag_dst[0] and leave the rest untouched:

  r->id.idiag_src[0] = inet->inet_rcv_saddr;
  r->id.idiag_dst[0] = inet->inet_daddr;

struct inet_diag_msg embeds struct inet_diag_sockid that is correctly /
fully filled out in IPv6 case, but for IPv4 not.

So just zero them out by using plain memset (for this little amount of
bytes it's probably not worth the extra check for idiag_family == AF_INET).

Similarly, fix also other places where we fill that out.

Reported-by: Jakub Zawadzki <darkjames-ws@darkjames.pl>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 56a964a..a0f52da 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -106,6 +106,10 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 
 	r->id.idiag_sport = inet->inet_sport;
 	r->id.idiag_dport = inet->inet_dport;
+
+	memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+	memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
 	r->id.idiag_src[0] = inet->inet_rcv_saddr;
 	r->id.idiag_dst[0] = inet->inet_daddr;
 
@@ -240,12 +244,19 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
 
 	r->idiag_family	      = tw->tw_family;
 	r->idiag_retrans      = 0;
+
 	r->id.idiag_if	      = tw->tw_bound_dev_if;
 	sock_diag_save_cookie(tw, r->id.idiag_cookie);
+
 	r->id.idiag_sport     = tw->tw_sport;
 	r->id.idiag_dport     = tw->tw_dport;
+
+	memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+	memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
 	r->id.idiag_src[0]    = tw->tw_rcv_saddr;
 	r->id.idiag_dst[0]    = tw->tw_daddr;
+
 	r->idiag_state	      = tw->tw_substate;
 	r->idiag_timer	      = 3;
 	r->idiag_expires      = jiffies_to_msecs(tmo);
@@ -726,8 +737,13 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
 
 	r->id.idiag_sport = inet->inet_sport;
 	r->id.idiag_dport = ireq->ir_rmt_port;
+
+	memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
+	memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst));
+
 	r->id.idiag_src[0] = ireq->ir_loc_addr;
 	r->id.idiag_dst[0] = ireq->ir_rmt_addr;
+
 	r->idiag_expires = jiffies_to_msecs(tmo);
 	r->idiag_rqueue = 0;
 	r->idiag_wqueue = 0;
-- 
cgit v0.10.2


From 7e98b71920464b8d15fa95c74366416cd3c88861 Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@linux.intel.com>
Date: Thu, 19 Dec 2013 11:58:16 -0800
Subject: x86, idle: Use static_cpu_has() for CLFLUSH workaround, add barriers

Use static_cpu_has() to conditionalize the CLFLUSH workaround, and add
memory barriers around it since the documentation is explicit that
CLFLUSH is only ordered with respect to MFENCE.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Len Brown <len.brown@intel.com>
Link: http://lkml.kernel.org/r/CA%2B55aFzGxcML7j8CEvQPYzh0W81uVoAAVmGctMOUZ7CZ1yYd2A@mail.gmail.com

diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 361b02e..19b71c4 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -43,8 +43,11 @@ static inline void __mwait(unsigned long eax, unsigned long ecx)
 static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
 {
 	if (!current_set_polling_and_test()) {
-		if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR))
+		if (static_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) {
+			mb();
 			clflush((void *)&current_thread_info()->flags);
+			mb();
+		}
 
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
 		if (!need_resched())
-- 
cgit v0.10.2


From 0c8d087c04cdcef501064552149289866e53aa6c Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyj.lk@gmail.com>
Date: Tue, 17 Dec 2013 10:42:09 +0800
Subject: xen-netback: fix some error return code

'err' is overwrited to 0 after maybe_pull_tail() call, so the error
code was not set if skb_partial_csum_set() call failed. Fix to return
error -EPROTO from those error handling case instead of 0.

Fixes: d52eb0d46f36 ('xen-netback: make sure skb linear area covers checksum field')
Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 27bbe58..7b4fd93 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -1209,8 +1209,10 @@ static int checksum_setup_ip(struct xenvif *vif, struct sk_buff *skb,
 			goto out;
 
 		if (!skb_partial_csum_set(skb, off,
-					  offsetof(struct tcphdr, check)))
+					  offsetof(struct tcphdr, check))) {
+			err = -EPROTO;
 			goto out;
+		}
 
 		if (recalculate_partial_csum)
 			tcp_hdr(skb)->check =
@@ -1227,8 +1229,10 @@ static int checksum_setup_ip(struct xenvif *vif, struct sk_buff *skb,
 			goto out;
 
 		if (!skb_partial_csum_set(skb, off,
-					  offsetof(struct udphdr, check)))
+					  offsetof(struct udphdr, check))) {
+			err = -EPROTO;
 			goto out;
+		}
 
 		if (recalculate_partial_csum)
 			udp_hdr(skb)->check =
@@ -1350,8 +1354,10 @@ static int checksum_setup_ipv6(struct xenvif *vif, struct sk_buff *skb,
 			goto out;
 
 		if (!skb_partial_csum_set(skb, off,
-					  offsetof(struct tcphdr, check)))
+					  offsetof(struct tcphdr, check))) {
+			err = -EPROTO;
 			goto out;
+		}
 
 		if (recalculate_partial_csum)
 			tcp_hdr(skb)->check =
@@ -1368,8 +1374,10 @@ static int checksum_setup_ipv6(struct xenvif *vif, struct sk_buff *skb,
 			goto out;
 
 		if (!skb_partial_csum_set(skb, off,
-					  offsetof(struct udphdr, check)))
+					  offsetof(struct udphdr, check))) {
+			err = -EPROTO;
 			goto out;
+		}
 
 		if (recalculate_partial_csum)
 			udp_hdr(skb)->check =
-- 
cgit v0.10.2


From e9db5c21d3646a6454fcd04938dd215ac3ab620a Mon Sep 17 00:00:00 2001
From: Wenliang Fan <fanwlexca@gmail.com>
Date: Tue, 17 Dec 2013 11:25:28 +0800
Subject: drivers/net/hamradio: Integer overflow in hdlcdrv_ioctl()

The local variable 'bi' comes from userspace. If userspace passed a
large number to 'bi.data.calibrate', there would be an integer overflow
in the following line:
	s->hdlctx.calibrate = bi.data.calibrate * s->par.bitrate / 16;

Signed-off-by: Wenliang Fan <fanwlexca@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/hamradio/hdlcdrv.c b/drivers/net/hamradio/hdlcdrv.c
index 3169252..5d78c1d 100644
--- a/drivers/net/hamradio/hdlcdrv.c
+++ b/drivers/net/hamradio/hdlcdrv.c
@@ -571,6 +571,8 @@ static int hdlcdrv_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	case HDLCDRVCTL_CALIBRATE:
 		if(!capable(CAP_SYS_RAWIO))
 			return -EPERM;
+		if (bi.data.calibrate > INT_MAX / s->par.bitrate)
+			return -EINVAL;
 		s->hdlctx.calibrate = bi.data.calibrate * s->par.bitrate / 16;
 		return 0;
 
-- 
cgit v0.10.2


From 8b640cc4c56cee14bfe5cfb4dbb372ac66d5ec6b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 19 Dec 2013 17:00:45 -0300
Subject: perf mem: Remove unused parameter from dump_raw_samples()

The 'evsel' parameter is not used, ditch it, reducing the function
signature.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-kx9temzdcy7mk2edya9c1tdu@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 31c00f1..2e3ade69 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -62,7 +62,6 @@ static int
 dump_raw_samples(struct perf_tool *tool,
 		 union perf_event *event,
 		 struct perf_sample *sample,
-		 struct perf_evsel *evsel __maybe_unused,
 		 struct machine *machine)
 {
 	struct perf_mem *mem = container_of(tool, struct perf_mem, tool);
@@ -112,10 +111,10 @@ dump_raw_samples(struct perf_tool *tool,
 static int process_sample_event(struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
-				struct perf_evsel *evsel,
+				struct perf_evsel *evsel __maybe_unused,
 				struct machine *machine)
 {
-	return dump_raw_samples(tool, event, sample, evsel, machine);
+	return dump_raw_samples(tool, event, sample, machine);
 }
 
 static int report_raw_events(struct perf_mem *mem)
-- 
cgit v0.10.2


From 8e3fbf870481eb53b2d3a322d1fc395ad8b367ed Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Salva=20Peir=C3=B3?= <speiro@ai2.upv.es>
Date: Tue, 17 Dec 2013 10:06:30 +0100
Subject: hamradio/yam: fix info leak in ioctl
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The yam_ioctl() code fails to initialise the cmd field
of the struct yamdrv_ioctl_cfg. Add an explicit memset(0)
before filling the structure to avoid the 4-byte info leak.

Signed-off-by: Salva Peiró <speiro@ai2.upv.es>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c
index 1971411..61dd244 100644
--- a/drivers/net/hamradio/yam.c
+++ b/drivers/net/hamradio/yam.c
@@ -1057,6 +1057,7 @@ static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		break;
 
 	case SIOCYAMGCFG:
+		memset(&yi, 0, sizeof(yi));
 		yi.cfg.mask = 0xffffffff;
 		yi.cfg.iobase = yp->iobase;
 		yi.cfg.irq = yp->irq;
-- 
cgit v0.10.2


From c047e0707307717818542c939223fc8ca454e2c9 Mon Sep 17 00:00:00 2001
From: Michal Schmidt <mschmidt@redhat.com>
Date: Tue, 17 Dec 2013 18:51:25 +0100
Subject: bnx2x: downgrade "valid ME register value" message level

"valid ME register value" is not an error. It should be logged for
debugging only.

Signed-off-by: Michal Schmidt <mschmidt@redhat.com>
Acked-by: Yuval Mintz <yuvalmin@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index efa8a15..3dc2537 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -208,7 +208,7 @@ static int bnx2x_get_vf_id(struct bnx2x *bp, u32 *vf_id)
 		return -EINVAL;
 	}
 
-	BNX2X_ERR("valid ME register value: 0x%08x\n", me_reg);
+	DP(BNX2X_MSG_IOV, "valid ME register value: 0x%08x\n", me_reg);
 
 	*vf_id = (me_reg & ME_REG_VF_NUM_MASK) >> ME_REG_VF_NUM_SHIFT;
 
-- 
cgit v0.10.2


From 7d590cca7cd2cce4ed7c47d221d6f90566653ba8 Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@linux.intel.com>
Date: Thu, 19 Dec 2013 12:30:03 -0800
Subject: x86, idle: Add memory barriers around clflush in mwait_play_dead()

For consistency with mwait_idle_with_hints().  Not sure they help, but
they really won't hurt...

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Len Brown <len.brown@intel.com>
Link: http://lkml.kernel.org/r/CA%2B55aFzGxcML7j8CEvQPYzh0W81uVoAAVmGctMOUZ7CZ1yYd2A@mail.gmail.com

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 85dc05a..f5252c4 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1417,7 +1417,9 @@ static inline void mwait_play_dead(void)
 		 * The WBINVD is insufficient due to the spurious-wakeup
 		 * case where we return around the loop.
 		 */
+		mb();
 		clflush(mwait_ptr);
+		mb();
 		__monitor(mwait_ptr, 0, 0);
 		mb();
 		__mwait(eax, 0);
-- 
cgit v0.10.2


From cc22e575a6fddbe3183ac14c28e2f792704995c5 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 19 Dec 2013 17:20:06 -0300
Subject: perf symbols: Add 'machine' member to struct addr_location

The addr_location struct should fully qualify an address, and to do that
it should have in it the machine where the thread was found.

Thus all functions that receive an addr_location now don't need to also
receive a 'machine', those functions just need to access al->machine
instead, just like it does with the other parts of an address location:
al->thread, al->map, etc.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-o51iiee7vyq4r3k362uvuylg@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index da156a4..ec7399a 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -77,10 +77,10 @@ static int report__config(const char *var, const char *value, void *cb)
 
 static int report__resolve_callchain(struct report *rep, struct symbol **parent,
 				     struct perf_evsel *evsel, struct addr_location *al,
-				     struct perf_sample *sample, struct machine *machine)
+				     struct perf_sample *sample)
 {
 	if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
-		return machine__resolve_callchain(machine, evsel, al->thread, sample,
+		return machine__resolve_callchain(al->machine, evsel, al->thread, sample,
 						  parent, al, rep->max_stack);
 	}
 	return 0;
@@ -95,7 +95,7 @@ static int hist_entry__append_callchain(struct hist_entry *he, struct perf_sampl
 
 static int report__add_mem_hist_entry(struct perf_tool *tool, struct addr_location *al,
 				      struct perf_sample *sample, struct perf_evsel *evsel,
-				      struct machine *machine, union perf_event *event)
+				      union perf_event *event)
 {
 	struct report *rep = container_of(tool, struct report, tool);
 	struct symbol *parent = NULL;
@@ -103,12 +103,12 @@ static int report__add_mem_hist_entry(struct perf_tool *tool, struct addr_locati
 	struct hist_entry *he;
 	struct mem_info *mi, *mx;
 	uint64_t cost;
-	int err = report__resolve_callchain(rep, &parent, evsel, al, sample, machine);
+	int err = report__resolve_callchain(rep, &parent, evsel, al, sample);
 
 	if (err)
 		return err;
 
-	mi = machine__resolve_mem(machine, al->thread, sample, cpumode);
+	mi = machine__resolve_mem(al->machine, al->thread, sample, cpumode);
 	if (!mi)
 		return -ENOMEM;
 
@@ -148,20 +148,19 @@ out:
 }
 
 static int report__add_branch_hist_entry(struct perf_tool *tool, struct addr_location *al,
-					 struct perf_sample *sample, struct perf_evsel *evsel,
-					 struct machine *machine)
+					 struct perf_sample *sample, struct perf_evsel *evsel)
 {
 	struct report *rep = container_of(tool, struct report, tool);
 	struct symbol *parent = NULL;
 	unsigned i;
 	struct hist_entry *he;
 	struct branch_info *bi, *bx;
-	int err = report__resolve_callchain(rep, &parent, evsel, al, sample, machine);
+	int err = report__resolve_callchain(rep, &parent, evsel, al, sample);
 
 	if (err)
 		return err;
 
-	bi = machine__resolve_bstack(machine, al->thread,
+	bi = machine__resolve_bstack(al->machine, al->thread,
 				     sample->branch_stack);
 	if (!bi)
 		return -ENOMEM;
@@ -204,13 +203,12 @@ out:
 }
 
 static int report__add_hist_entry(struct perf_tool *tool, struct perf_evsel *evsel,
-				  struct addr_location *al, struct perf_sample *sample,
-				  struct machine *machine)
+				  struct addr_location *al, struct perf_sample *sample)
 {
 	struct report *rep = container_of(tool, struct report, tool);
 	struct symbol *parent = NULL;
 	struct hist_entry *he;
-	int err = report__resolve_callchain(rep, &parent, evsel, al, sample, machine);
+	int err = report__resolve_callchain(rep, &parent, evsel, al, sample);
 
 	if (err)
 		return err;
@@ -256,18 +254,18 @@ static int process_sample_event(struct perf_tool *tool,
 		return 0;
 
 	if (sort__mode == SORT_MODE__BRANCH) {
-		ret = report__add_branch_hist_entry(tool, &al, sample, evsel, machine);
+		ret = report__add_branch_hist_entry(tool, &al, sample, evsel);
 		if (ret < 0)
 			pr_debug("problem adding lbr entry, skipping event\n");
 	} else if (rep->mem_mode == 1) {
-		ret = report__add_mem_hist_entry(tool, &al, sample, evsel, machine, event);
+		ret = report__add_mem_hist_entry(tool, &al, sample, evsel, event);
 		if (ret < 0)
 			pr_debug("problem adding mem entry, skipping event\n");
 	} else {
 		if (al.map != NULL)
 			al.map->dso->hit = 1;
 
-		ret = report__add_hist_entry(tool, evsel, &al, sample, machine);
+		ret = report__add_hist_entry(tool, evsel, &al, sample);
 		if (ret < 0)
 			pr_debug("problem incrementing symbol period, skipping event\n");
 	}
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index f8ab125..62ef190 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -423,7 +423,6 @@ static void print_sample_addr(union perf_event *event,
 static void print_sample_bts(union perf_event *event,
 			     struct perf_sample *sample,
 			     struct perf_evsel *evsel,
-			     struct machine *machine,
 			     struct thread *thread,
 			     struct addr_location *al)
 {
@@ -435,7 +434,7 @@ static void print_sample_bts(union perf_event *event,
 			printf(" ");
 		else
 			printf("\n");
-		perf_evsel__print_ip(evsel, sample, machine, al,
+		perf_evsel__print_ip(evsel, sample, al,
 				     output[attr->type].print_ip_opts,
 				     PERF_MAX_STACK_DEPTH);
 	}
@@ -446,14 +445,13 @@ static void print_sample_bts(union perf_event *event,
 	if (PRINT_FIELD(ADDR) ||
 	    ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
 	     !output[attr->type].user_set))
-		print_sample_addr(event, sample, machine, thread, attr);
+		print_sample_addr(event, sample, al->machine, thread, attr);
 
 	printf("\n");
 }
 
 static void process_event(union perf_event *event, struct perf_sample *sample,
-			  struct perf_evsel *evsel, struct machine *machine,
-			  struct thread *thread,
+			  struct perf_evsel *evsel, struct thread *thread,
 			  struct addr_location *al)
 {
 	struct perf_event_attr *attr = &evsel->attr;
@@ -469,7 +467,7 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 	}
 
 	if (is_bts_event(attr)) {
-		print_sample_bts(event, sample, evsel, machine, thread, al);
+		print_sample_bts(event, sample, evsel, thread, al);
 		return;
 	}
 
@@ -477,7 +475,7 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 		event_format__print(evsel->tp_format, sample->cpu,
 				    sample->raw_data, sample->raw_size);
 	if (PRINT_FIELD(ADDR))
-		print_sample_addr(event, sample, machine, thread, attr);
+		print_sample_addr(event, sample, al->machine, thread, attr);
 
 	if (PRINT_FIELD(IP)) {
 		if (!symbol_conf.use_callchain)
@@ -485,7 +483,7 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 		else
 			printf("\n");
 
-		perf_evsel__print_ip(evsel, sample, machine, al,
+		perf_evsel__print_ip(evsel, sample, al,
 				     output[attr->type].print_ip_opts,
 				     PERF_MAX_STACK_DEPTH);
 	}
@@ -574,7 +572,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
 		return 0;
 
-	scripting_ops->process_event(event, sample, evsel, machine, thread, &al);
+	scripting_ops->process_event(event, sample, evsel, thread, &al);
 
 	evsel->hists.stats.total_period += sample->period;
 	return 0;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 6948768..fe20227 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -638,6 +638,7 @@ void thread__find_addr_map(struct thread *thread,
 	struct map_groups *mg = &thread->mg;
 	bool load_map = false;
 
+	al->machine = machine;
 	al->thread = thread;
 	al->addr = addr;
 	al->cpumode = cpumode;
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index b672ef0..3773c48 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -371,7 +371,6 @@ static void perl_process_event_generic(union perf_event *event,
 static void perl_process_event(union perf_event *event,
 			       struct perf_sample *sample,
 			       struct perf_evsel *evsel,
-			       struct machine *machine __maybe_unused,
 			       struct thread *thread,
 			       struct addr_location *al __maybe_unused)
 {
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index fc00792..b258de6 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -408,7 +408,6 @@ exit:
 static void python_process_event(union perf_event *event __maybe_unused,
 				 struct perf_sample *sample,
 				 struct perf_evsel *evsel,
-				 struct machine *machine __maybe_unused,
 				 struct thread *thread,
 				 struct addr_location *al)
 {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 989b2e3..cbacaab 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1467,7 +1467,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 }
 
 void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
-			  struct machine *machine, struct addr_location *al,
+			  struct addr_location *al,
 			  unsigned int print_opts, unsigned int stack_depth)
 {
 	struct callchain_cursor_node *node;
@@ -1482,7 +1482,7 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
 	if (symbol_conf.use_callchain && sample->callchain) {
 		struct addr_location node_al;
 
-		if (machine__resolve_callchain(machine, evsel, al->thread,
+		if (machine__resolve_callchain(al->machine, evsel, al->thread,
 					       sample, NULL, NULL,
 					       PERF_MAX_STACK_DEPTH) != 0) {
 			if (verbose)
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 9c25d49..3140f8a 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -106,7 +106,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 					    unsigned int type);
 
 void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
-			  struct machine *machine, struct addr_location *al,
+			  struct addr_location *al,
 			  unsigned int print_opts, unsigned int stack_depth);
 
 int perf_session__cpu_bitmap(struct perf_session *session,
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 8a9d910..cbd6803 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -164,6 +164,7 @@ struct mem_info {
 };
 
 struct addr_location {
+	struct machine *machine;
 	struct thread *thread;
 	struct map    *map;
 	struct symbol *sym;
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 95199e4..57aaccc 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -38,9 +38,8 @@ static int stop_script_unsupported(void)
 static void process_event_unsupported(union perf_event *event __maybe_unused,
 				      struct perf_sample *sample __maybe_unused,
 				      struct perf_evsel *evsel __maybe_unused,
-				      struct machine *machine __maybe_unused,
 				      struct thread *thread __maybe_unused,
-					  struct addr_location *al __maybe_unused)
+				      struct addr_location *al __maybe_unused)
 {
 }
 
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 3a01618..7b6d686 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -68,7 +68,6 @@ struct scripting_ops {
 	void (*process_event) (union perf_event *event,
 			       struct perf_sample *sample,
 			       struct perf_evsel *evsel,
-			       struct machine *machine,
 			       struct thread *thread,
 				   struct addr_location *al);
 	int (*generate_script) (struct pevent *pevent, const char *outfile);
-- 
cgit v0.10.2


From 7a2a84518cfb263d2c4171b3d63671f88316adb2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 19 Dec 2013 10:53:02 -0800
Subject: net: fec: fix potential use after free

skb_tx_timestamp(skb) should be called _before_ TX completion
has a chance to trigger, otherwise it is too late and we access
freed memory.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: de5fb0a05348 ("net: fec: put tx to napi poll function to fix dead lock")
Cc: Frank Li <Frank.Li@freescale.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Acked-by: Frank Li <Frank.Li@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index e7c8b74..50bb71c 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -428,6 +428,8 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	/* If this was the last BD in the ring, start at the beginning again. */
 	bdp = fec_enet_get_nextdesc(bdp, fep);
 
+	skb_tx_timestamp(skb);
+
 	fep->cur_tx = bdp;
 
 	if (fep->cur_tx == fep->dirty_tx)
@@ -436,8 +438,6 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	/* Trigger transmission start */
 	writel(0, fep->hwp + FEC_X_DES_ACTIVE);
 
-	skb_tx_timestamp(skb);
-
 	return NETDEV_TX_OK;
 }
 
-- 
cgit v0.10.2


From 24f5b855e17df7e355eacd6c4a12cc4d6a6c9ff0 Mon Sep 17 00:00:00 2001
From: Li RongQing <roy.qing.li@gmail.com>
Date: Thu, 19 Dec 2013 12:40:26 +0800
Subject: ipv6: always set the new created dst's from in ip6_rt_copy

ip6_rt_copy only sets dst.from if ort has flag RTF_ADDRCONF and RTF_DEFAULT.
but the prefix routes which did get installed by hand locally can have an
expiration, and no any flag combination which can ensure a potential from
does never expire, so we should always set the new created dst's from.

This also fixes the new created dst is always expired since the ort, which
is created by RA, maybe has RTF_EXPIRES and RTF_ADDRCONF, but no RTF_DEFAULT.

Suggested-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
CC: Gao feng <gaofeng@cn.fujitsu.com>
Signed-off-by: Li RongQing <roy.qing.li@gmail.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a0a48ac..4b4944c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1905,9 +1905,7 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
 		else
 			rt->rt6i_gateway = *dest;
 		rt->rt6i_flags = ort->rt6i_flags;
-		if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) ==
-		    (RTF_DEFAULT | RTF_ADDRCONF))
-			rt6_set_from(rt, ort);
+		rt6_set_from(rt, ort);
 		rt->rt6i_metric = 0;
 
 #ifdef CONFIG_IPV6_SUBTREES
-- 
cgit v0.10.2


From a4f63634760acfcc349a5582c77ca4a004c813f6 Mon Sep 17 00:00:00 2001
From: Betty Dall <betty.dall@hp.com>
Date: Thu, 19 Dec 2013 10:59:09 -0700
Subject: atl1c: Check return from pci_find_ext_capability() in
 atl1c_reset_pcie()

The function atl1c_reset_pcie() does not check the return from
pci_find_ext_cabability() where it is getting the postion of the
PCI_EXT_CAP_ID_ERR. It is possible for the return to be 0.

Signed-off-by: Betty Dall <betty.dall@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index a36a760..2980175 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -145,9 +145,11 @@ static void atl1c_reset_pcie(struct atl1c_hw *hw, u32 flag)
 	 * Mask some pcie error bits
 	 */
 	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR);
-	pci_read_config_dword(pdev, pos + PCI_ERR_UNCOR_SEVER, &data);
-	data &= ~(PCI_ERR_UNC_DLP | PCI_ERR_UNC_FCP);
-	pci_write_config_dword(pdev, pos + PCI_ERR_UNCOR_SEVER, data);
+	if (pos) {
+		pci_read_config_dword(pdev, pos + PCI_ERR_UNCOR_SEVER, &data);
+		data &= ~(PCI_ERR_UNC_DLP | PCI_ERR_UNC_FCP);
+		pci_write_config_dword(pdev, pos + PCI_ERR_UNCOR_SEVER, data);
+	}
 	/* clear error status */
 	pcie_capability_write_word(pdev, PCI_EXP_DEVSTA,
 			PCI_EXP_DEVSTA_NFED |
-- 
cgit v0.10.2


From 1a1f20bc9debd133549d5b289bd5494a4264a73d Mon Sep 17 00:00:00 2001
From: Leigh Brown <leigh@solinno.co.uk>
Date: Thu, 19 Dec 2013 13:09:48 +0000
Subject: net: mvmdio: fix interrupt timeout handling

This version corrects the whitespace issue.

orion_mdio_wait_ready uses wait_event_timeout to wait for the
SMI interrupt to fire.  wait_event_timeout waits for between
"timeout - 1" and "timeout" jiffies.  In this case a 1ms timeout
when HZ is 1000 results in a wait of 0 to 1 jiffies, causing
premature timeouts.

This fix ensures a minimum timeout of 2 jiffies, ensuring
wait_event_timeout will always wait at least 1 jiffie.

Issue reported by Nicolas Schichan.

Tested-by: Nicolas Schichan <nschichan@freebox.fr>
Signed-off-by: Leigh Brown <leigh@solinno.co.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index 7354960..c4eeb69 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -92,6 +92,12 @@ static int orion_mdio_wait_ready(struct mii_bus *bus)
 			if (time_is_before_jiffies(end))
 				++timedout;
 	        } else {
+			/* wait_event_timeout does not guarantee a delay of at
+			 * least one whole jiffie, so timeout must be no less
+			 * than two.
+			 */
+			if (timeout < 2)
+				timeout = 2;
 			wait_event_timeout(dev->smi_busy_wait,
 				           orion_mdio_smi_is_done(dev),
 				           timeout);
-- 
cgit v0.10.2


From 965cdea825693c821d200e38fac9402cde6dce6a Mon Sep 17 00:00:00 2001
From: Wang Weidong <wangweidong1@huawei.com>
Date: Tue, 17 Dec 2013 19:24:33 -0700
Subject: dccp: catch failed request_module call in dccp_probe init

Check the return value of request_module during dccp_probe initialisation,
bail out if that call fails.

Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: Wang Weidong <wangweidong1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/dccp/probe.c b/net/dccp/probe.c
index 4c6bdf9..595ddf0 100644
--- a/net/dccp/probe.c
+++ b/net/dccp/probe.c
@@ -152,17 +152,6 @@ static const struct file_operations dccpprobe_fops = {
 	.llseek  = noop_llseek,
 };
 
-static __init int setup_jprobe(void)
-{
-	int ret = register_jprobe(&dccp_send_probe);
-
-	if (ret) {
-		request_module("dccp");
-		ret = register_jprobe(&dccp_send_probe);
-	}
-	return ret;
-}
-
 static __init int dccpprobe_init(void)
 {
 	int ret = -ENOMEM;
@@ -174,7 +163,13 @@ static __init int dccpprobe_init(void)
 	if (!proc_create(procname, S_IRUSR, init_net.proc_net, &dccpprobe_fops))
 		goto err0;
 
-	ret = setup_jprobe();
+	ret = register_jprobe(&dccp_send_probe);
+	if (ret) {
+		ret = request_module("dccp");
+		if (!ret)
+			ret = register_jprobe(&dccp_send_probe);
+	}
+
 	if (ret)
 		goto err1;
 
-- 
cgit v0.10.2


From 19952a92037e752f9d3bbbad552d596f9a56e146 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 19 Dec 2013 11:35:58 -0800
Subject: stackprotector: Unify the HAVE_CC_STACKPROTECTOR logic between
 architectures

Instead of duplicating the CC_STACKPROTECTOR Kconfig and
Makefile logic in each architecture, switch to using
HAVE_CC_STACKPROTECTOR and keep everything in one place. This
retains the x86-specific bug verification scripts.

Signed-off-by: Kees Cook <keescook@chromium.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Michal Marek <mmarek@suse.cz>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Shawn Guo <shawn.guo@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-mips@linux-mips.org
Cc: linux-arch@vger.kernel.org
Link: http://lkml.kernel.org/r/1387481759-14535-2-git-send-email-keescook@chromium.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/Makefile b/Makefile
index 858a147..84fb5cd 100644
--- a/Makefile
+++ b/Makefile
@@ -595,10 +595,18 @@ ifneq ($(CONFIG_FRAME_WARN),0)
 KBUILD_CFLAGS += $(call cc-option,-Wframe-larger-than=${CONFIG_FRAME_WARN})
 endif
 
-# Force gcc to behave correct even for buggy distributions
-ifndef CONFIG_CC_STACKPROTECTOR
-KBUILD_CFLAGS += $(call cc-option, -fno-stack-protector)
+# Handle stack protector mode.
+ifdef CONFIG_CC_STACKPROTECTOR
+  stackp-flag := -fstack-protector
+  ifeq ($(call cc-option, $(stackp-flag)),)
+    $(warning Cannot use CONFIG_CC_STACKPROTECTOR: \
+	      -fstack-protector not supported by compiler))
+  endif
+else
+  # Force off for distro compilers that enable stack protector by default.
+  stackp-flag := $(call cc-option, -fno-stack-protector)
 endif
+KBUILD_CFLAGS += $(stackp-flag)
 
 # This warning generated too much noise in a regular build.
 # Use make W=1 to enable this warning (see scripts/Makefile.build)
diff --git a/arch/Kconfig b/arch/Kconfig
index f1cf895..24e026d 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -336,6 +336,28 @@ config SECCOMP_FILTER
 
 	  See Documentation/prctl/seccomp_filter.txt for details.
 
+config HAVE_CC_STACKPROTECTOR
+	bool
+	help
+	  An arch should select this symbol if:
+	  - its compiler supports the -fstack-protector option
+	  - it has implemented a stack canary (e.g. __stack_chk_guard)
+
+config CC_STACKPROTECTOR
+	bool "Enable -fstack-protector buffer overflow detection"
+	depends on HAVE_CC_STACKPROTECTOR
+	help
+	  This option turns on the -fstack-protector GCC feature. This
+	  feature puts, at the beginning of functions, a canary value on
+	  the stack just before the return address, and validates
+	  the value just before actually returning.  Stack based buffer
+	  overflows (that need to overwrite this return address) now also
+	  overwrite the canary, which gets detected and the attack is then
+	  neutralized via a kernel panic.
+
+	  This feature requires gcc version 4.2 or above, or a distribution
+	  gcc with the feature backported.
+
 config HAVE_CONTEXT_TRACKING
 	bool
 	help
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index c1f1a7e..9c909fc 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -30,6 +30,7 @@ config ARM
 	select HAVE_BPF_JIT
 	select HAVE_CONTEXT_TRACKING
 	select HAVE_C_RECORDMCOUNT
+	select HAVE_CC_STACKPROTECTOR
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_ATTRS
@@ -1856,18 +1857,6 @@ config SECCOMP
 	  and the task is only allowed to execute a few safe syscalls
 	  defined by each seccomp mode.
 
-config CC_STACKPROTECTOR
-	bool "Enable -fstack-protector buffer overflow detection (EXPERIMENTAL)"
-	help
-	  This option turns on the -fstack-protector GCC feature. This
-	  feature puts, at the beginning of functions, a canary value on
-	  the stack just before the return address, and validates
-	  the value just before actually returning.  Stack based buffer
-	  overflows (that need to overwrite this return address) now also
-	  overwrite the canary, which gets detected and the attack is then
-	  neutralized via a kernel panic.
-	  This feature requires gcc version 4.2 or above.
-
 config SWIOTLB
 	def_bool y
 
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index c99b108..55b4255 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -40,10 +40,6 @@ ifeq ($(CONFIG_FRAME_POINTER),y)
 KBUILD_CFLAGS	+=-fno-omit-frame-pointer -mapcs -mno-sched-prolog
 endif
 
-ifeq ($(CONFIG_CC_STACKPROTECTOR),y)
-KBUILD_CFLAGS	+=-fstack-protector
-endif
-
 ifeq ($(CONFIG_CPU_BIG_ENDIAN),y)
 KBUILD_CPPFLAGS	+= -mbig-endian
 AS		+= -EB
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 650de39..c93d92b 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -47,6 +47,7 @@ config MIPS
 	select MODULES_USE_ELF_RELA if MODULES && 64BIT
 	select CLONE_BACKWARDS
 	select HAVE_DEBUG_STACKOVERFLOW
+	select HAVE_CC_STACKPROTECTOR
 
 menu "Machine selection"
 
@@ -2322,19 +2323,6 @@ config SECCOMP
 
 	  If unsure, say Y. Only embedded should say N here.
 
-config CC_STACKPROTECTOR
-	bool "Enable -fstack-protector buffer overflow detection (EXPERIMENTAL)"
-	help
-	  This option turns on the -fstack-protector GCC feature. This
-	  feature puts, at the beginning of functions, a canary value on
-	  the stack just before the return address, and validates
-	  the value just before actually returning.  Stack based buffer
-	  overflows (that need to overwrite this return address) now also
-	  overwrite the canary, which gets detected and the attack is then
-	  neutralized via a kernel panic.
-
-	  This feature requires gcc version 4.2 or above.
-
 config USE_OF
 	bool
 	select OF
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index de300b9..efe50787 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -232,10 +232,6 @@ bootvars-y	= VMLINUX_LOAD_ADDRESS=$(load-y) \
 
 LDFLAGS			+= -m $(ld-emul)
 
-ifdef CONFIG_CC_STACKPROTECTOR
-  KBUILD_CFLAGS += -fstack-protector
-endif
-
 ifdef CONFIG_MIPS
 CHECKFLAGS += $(shell $(CC) $(KBUILD_CFLAGS) -dM -E -x c /dev/null | \
 	egrep -vw '__GNUC_(|MINOR_|PATCHLEVEL_)_' | \
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 9b0979f..ce29831 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -66,6 +66,7 @@ config SUPERH32
 	select PERF_EVENTS
 	select ARCH_HIBERNATION_POSSIBLE if MMU
 	select SPARSE_IRQ
+	select HAVE_CC_STACKPROTECTOR
 
 config SUPERH64
 	def_bool ARCH = "sh64"
@@ -695,20 +696,6 @@ config SECCOMP
 
 	  If unsure, say N.
 
-config CC_STACKPROTECTOR
-	bool "Enable -fstack-protector buffer overflow detection (EXPERIMENTAL)"
-	depends on SUPERH32
-	help
-	  This option turns on the -fstack-protector GCC feature. This
-	  feature puts, at the beginning of functions, a canary value on
-	  the stack just before the return address, and validates
-	  the value just before actually returning.  Stack based buffer
-	  overflows (that need to overwrite this return address) now also
-	  overwrite the canary, which gets detected and the attack is then
-	  neutralized via a kernel panic.
-
-	  This feature requires gcc version 4.2 or above.
-
 config SMP
 	bool "Symmetric multi-processing support"
 	depends on SYS_SUPPORTS_SMP
diff --git a/arch/sh/Makefile b/arch/sh/Makefile
index aed701c..d4d16e4 100644
--- a/arch/sh/Makefile
+++ b/arch/sh/Makefile
@@ -199,10 +199,6 @@ ifeq ($(CONFIG_DWARF_UNWINDER),y)
   KBUILD_CFLAGS += -fasynchronous-unwind-tables
 endif
 
-ifeq ($(CONFIG_CC_STACKPROTECTOR),y)
-  KBUILD_CFLAGS += -fstack-protector
-endif
-
 libs-$(CONFIG_SUPERH32)		:= arch/sh/lib/	$(libs-y)
 libs-$(CONFIG_SUPERH64)		:= arch/sh/lib64/ $(libs-y)
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0952ecd..838e7c3 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -125,6 +125,7 @@ config X86
 	select RTC_LIB
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64
+	select HAVE_CC_STACKPROTECTOR
 
 config INSTRUCTION_DECODER
 	def_bool y
@@ -1617,22 +1618,6 @@ config SECCOMP
 
 	  If unsure, say Y. Only embedded should say N here.
 
-config CC_STACKPROTECTOR
-	bool "Enable -fstack-protector buffer overflow detection"
-	---help---
-	  This option turns on the -fstack-protector GCC feature. This
-	  feature puts, at the beginning of functions, a canary value on
-	  the stack just before the return address, and validates
-	  the value just before actually returning.  Stack based buffer
-	  overflows (that need to overwrite this return address) now also
-	  overwrite the canary, which gets detected and the attack is then
-	  neutralized via a kernel panic.
-
-	  This feature requires gcc version 4.2 or above, or a distribution
-	  gcc with the feature backported. Older versions are automatically
-	  detected and for those versions, this configuration option is
-	  ignored. (and a warning is printed during bootup)
-
 source kernel/Kconfig.hz
 
 config KEXEC
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 57d0215..13b22e0 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -89,13 +89,11 @@ else
         KBUILD_CFLAGS += -maccumulate-outgoing-args
 endif
 
+# Make sure compiler does not have buggy stack-protector support.
 ifdef CONFIG_CC_STACKPROTECTOR
 	cc_has_sp := $(srctree)/scripts/gcc-x86_$(BITS)-has-stack-protector.sh
-        ifeq ($(shell $(CONFIG_SHELL) $(cc_has_sp) $(CC) $(KBUILD_CPPFLAGS) $(biarch)),y)
-                stackp-y := -fstack-protector
-                KBUILD_CFLAGS += $(stackp-y)
-        else
-                $(warning stack protector enabled but no compiler support)
+        ifneq ($(shell $(CONFIG_SHELL) $(cc_has_sp) $(CC) $(KBUILD_CPPFLAGS) $(biarch)),y)
+                $(warning stack-protector enabled but compiler support broken)
         endif
 endif
 
-- 
cgit v0.10.2


From 8779657d29c0ebcc0c94ede4df2f497baf1b563f Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 19 Dec 2013 11:35:59 -0800
Subject: stackprotector: Introduce CONFIG_CC_STACKPROTECTOR_STRONG

This changes the stack protector config option into a choice of
"None", "Regular", and "Strong":

   CONFIG_CC_STACKPROTECTOR_NONE
   CONFIG_CC_STACKPROTECTOR_REGULAR
   CONFIG_CC_STACKPROTECTOR_STRONG

"Regular" means the old CONFIG_CC_STACKPROTECTOR=y option.

"Strong" is a new mode introduced by this patch. With "Strong" the
kernel is built with -fstack-protector-strong (available in
gcc 4.9 and later). This option increases the coverage of the stack
protector without the heavy performance hit of -fstack-protector-all.

For reference, the stack protector options available in gcc are:

-fstack-protector-all:
  Adds the stack-canary saving prefix and stack-canary checking
  suffix to _all_ function entry and exit. Results in substantial
  use of stack space for saving the canary for deep stack users
  (e.g. historically xfs), and measurable (though shockingly still
  low) performance hit due to all the saving/checking. Really not
  suitable for sane systems, and was entirely removed as an option
  from the kernel many years ago.

-fstack-protector:
  Adds the canary save/check to functions that define an 8
  (--param=ssp-buffer-size=N, N=8 by default) or more byte local
  char array. Traditionally, stack overflows happened with
  string-based manipulations, so this was a way to find those
  functions. Very few total functions actually get the canary; no
  measurable performance or size overhead.

-fstack-protector-strong
  Adds the canary for a wider set of functions, since it's not
  just those with strings that have ultimately been vulnerable to
  stack-busting. With this superset, more functions end up with a
  canary, but it still remains small compared to all functions
  with only a small change in performance. Based on the original
  design document, a function gets the canary when it contains any
  of:

    - local variable's address used as part of the right hand side
      of an assignment or function argument
    - local variable is an array (or union containing an array),
      regardless of array type or length
    - uses register local variables

  https://docs.google.com/a/google.com/document/d/1xXBH6rRZue4f296vGt9YQcuLVQHeE516stHwt8M9xyU

Find below a comparison of "size" and "objdump" output when built with
gcc-4.9 in three configurations:

  - defconfig
	11430641 kernel text size
	36110 function bodies

  - defconfig + CONFIG_CC_STACKPROTECTOR_REGULAR
	11468490 kernel text size (+0.33%)
	1015 of 36110 functions are stack-protected (2.81%)

  - defconfig + CONFIG_CC_STACKPROTECTOR_STRONG via this patch
	11692790 kernel text size (+2.24%)
	7401 of 36110 functions are stack-protected (20.5%)

With -strong, ARM's compressed boot code now triggers stack
protection, so a static guard was added. Since this is only used
during decompression and was never used before, the exposure
here is very small. Once it switches to the full kernel, the
stack guard is back to normal.

Chrome OS has been using -fstack-protector-strong for its kernel
builds for the last 8 months with no problems.

Signed-off-by: Kees Cook <keescook@chromium.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Michal Marek <mmarek@suse.cz>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Shawn Guo <shawn.guo@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-mips@linux-mips.org
Cc: linux-arch@vger.kernel.org
Link: http://lkml.kernel.org/r/1387481759-14535-3-git-send-email-keescook@chromium.org
[ Improved the changelog and descriptions some more. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/Makefile b/Makefile
index 84fb5cd..5271b96 100644
--- a/Makefile
+++ b/Makefile
@@ -596,12 +596,18 @@ KBUILD_CFLAGS += $(call cc-option,-Wframe-larger-than=${CONFIG_FRAME_WARN})
 endif
 
 # Handle stack protector mode.
-ifdef CONFIG_CC_STACKPROTECTOR
+ifdef CONFIG_CC_STACKPROTECTOR_REGULAR
   stackp-flag := -fstack-protector
   ifeq ($(call cc-option, $(stackp-flag)),)
     $(warning Cannot use CONFIG_CC_STACKPROTECTOR: \
 	      -fstack-protector not supported by compiler))
   endif
+else ifdef CONFIG_CC_STACKPROTECTOR_STRONG
+  stackp-flag := -fstack-protector-strong
+  ifeq ($(call cc-option, $(stackp-flag)),)
+    $(warning Cannot use CONFIG_CC_STACKPROTECTOR_STRONG: \
+	      -fstack-protector-strong not supported by compiler)
+  endif
 else
   # Force off for distro compilers that enable stack protector by default.
   stackp-flag := $(call cc-option, -fno-stack-protector)
diff --git a/arch/Kconfig b/arch/Kconfig
index 24e026d..80bbb8c 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -344,10 +344,17 @@ config HAVE_CC_STACKPROTECTOR
 	  - it has implemented a stack canary (e.g. __stack_chk_guard)
 
 config CC_STACKPROTECTOR
-	bool "Enable -fstack-protector buffer overflow detection"
+	def_bool n
+	help
+	  Set when a stack-protector mode is enabled, so that the build
+	  can enable kernel-side support for the GCC feature.
+
+choice
+	prompt "Stack Protector buffer overflow detection"
 	depends on HAVE_CC_STACKPROTECTOR
+	default CC_STACKPROTECTOR_NONE
 	help
-	  This option turns on the -fstack-protector GCC feature. This
+	  This option turns on the "stack-protector" GCC feature. This
 	  feature puts, at the beginning of functions, a canary value on
 	  the stack just before the return address, and validates
 	  the value just before actually returning.  Stack based buffer
@@ -355,8 +362,46 @@ config CC_STACKPROTECTOR
 	  overwrite the canary, which gets detected and the attack is then
 	  neutralized via a kernel panic.
 
+config CC_STACKPROTECTOR_NONE
+	bool "None"
+	help
+	  Disable "stack-protector" GCC feature.
+
+config CC_STACKPROTECTOR_REGULAR
+	bool "Regular"
+	select CC_STACKPROTECTOR
+	help
+	  Functions will have the stack-protector canary logic added if they
+	  have an 8-byte or larger character array on the stack.
+
 	  This feature requires gcc version 4.2 or above, or a distribution
-	  gcc with the feature backported.
+	  gcc with the feature backported ("-fstack-protector").
+
+	  On an x86 "defconfig" build, this feature adds canary checks to
+	  about 3% of all kernel functions, which increases kernel code size
+	  by about 0.3%.
+
+config CC_STACKPROTECTOR_STRONG
+	bool "Strong"
+	select CC_STACKPROTECTOR
+	help
+	  Functions will have the stack-protector canary logic added in any
+	  of the following conditions:
+
+	  - local variable's address used as part of the right hand side of an
+	    assignment or function argument
+	  - local variable is an array (or union containing an array),
+	    regardless of array type or length
+	  - uses register local variables
+
+	  This feature requires gcc version 4.9 or above, or a distribution
+	  gcc with the feature backported ("-fstack-protector-strong").
+
+	  On an x86 "defconfig" build, this feature adds canary checks to
+	  about 20% of all kernel functions, which increases the kernel code
+	  size by about 2%.
+
+endchoice
 
 config HAVE_CONTEXT_TRACKING
 	bool
diff --git a/arch/arm/boot/compressed/misc.c b/arch/arm/boot/compressed/misc.c
index 31bd43b..d4f891f 100644
--- a/arch/arm/boot/compressed/misc.c
+++ b/arch/arm/boot/compressed/misc.c
@@ -127,6 +127,18 @@ asmlinkage void __div0(void)
 	error("Attempting division by 0!");
 }
 
+unsigned long __stack_chk_guard;
+
+void __stack_chk_guard_setup(void)
+{
+	__stack_chk_guard = 0x000a0dff;
+}
+
+void __stack_chk_fail(void)
+{
+	error("stack-protector: Kernel stack is corrupted\n");
+}
+
 extern int do_decompress(u8 *input, int len, u8 *output, void (*error)(char *x));
 
 
@@ -137,6 +149,8 @@ decompress_kernel(unsigned long output_start, unsigned long free_mem_ptr_p,
 {
 	int ret;
 
+	__stack_chk_guard_setup();
+
 	output_data		= (unsigned char *)output_start;
 	free_mem_ptr		= free_mem_ptr_p;
 	free_mem_end_ptr	= free_mem_ptr_end_p;
-- 
cgit v0.10.2


From 540436c80e5918dd5ed838449e108b1726fc4d68 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Fri, 20 Dec 2013 11:23:15 +0100
Subject: netfilter: nft_exthdr: call ipv6_find_hdr() with explicitly
 initialized offset

In nft's nft_exthdr_eval() routine we process IPv6 extension header
through invoking ipv6_find_hdr(), but we call it with an uninitialized
offset variable that contains some stack value. In ipv6_find_hdr()
we then test if the value of offset != 0 and call skb_header_pointer()
on that offset in order to map struct ipv6hdr into it. Fix it up by
initializing offset to 0 as it was probably intended to be.

Fixes: 96518518cc41 ("netfilter: add nftables")
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index 8e0bb75..55c939f 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -31,7 +31,7 @@ static void nft_exthdr_eval(const struct nft_expr *expr,
 {
 	struct nft_exthdr *priv = nft_expr_priv(expr);
 	struct nft_data *dest = &data[priv->dreg];
-	unsigned int offset;
+	unsigned int offset = 0;
 	int err;
 
 	err = ipv6_find_hdr(pkt->skb, &offset, priv->type, NULL, NULL);
-- 
cgit v0.10.2


From dfd11184d894cd0a92397b25cac18831a1a6a5bc Mon Sep 17 00:00:00 2001
From: Steven Whitehouse <swhiteho@redhat.com>
Date: Wed, 18 Dec 2013 14:14:52 +0000
Subject: GFS2: Fix incorrect invalidation for DIO/buffered I/O

In patch 209806aba9d540dde3db0a5ce72307f85f33468f we allowed
local deferred locks to be granted against a cached exclusive
lock. That opened up a corner case which this patch now
fixes.

The solution to the problem is to check whether we have cached
pages each time we do direct I/O and if so to unmap, flush
and invalidate those pages. Since the glock state machine
normally does that for us, mostly the code will be a no-op.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index b7fc035..73f3e4e 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -986,6 +986,7 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
+	struct address_space *mapping = inode->i_mapping;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
 	int rv;
@@ -1006,6 +1007,35 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
 	if (rv != 1)
 		goto out; /* dio not valid, fall back to buffered i/o */
 
+	/*
+	 * Now since we are holding a deferred (CW) lock at this point, you
+	 * might be wondering why this is ever needed. There is a case however
+	 * where we've granted a deferred local lock against a cached exclusive
+	 * glock. That is ok provided all granted local locks are deferred, but
+	 * it also means that it is possible to encounter pages which are
+	 * cached and possibly also mapped. So here we check for that and sort
+	 * them out ahead of the dio. The glock state machine will take care of
+	 * everything else.
+	 *
+	 * If in fact the cached glock state (gl->gl_state) is deferred (CW) in
+	 * the first place, mapping->nr_pages will always be zero.
+	 */
+	if (mapping->nrpages) {
+		loff_t lstart = offset & (PAGE_CACHE_SIZE - 1);
+		loff_t len = iov_length(iov, nr_segs);
+		loff_t end = PAGE_ALIGN(offset + len) - 1;
+
+		rv = 0;
+		if (len == 0)
+			goto out;
+		if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
+			unmap_shared_mapping_range(ip->i_inode.i_mapping, offset, len);
+		rv = filemap_write_and_wait_range(mapping, lstart, end);
+		if (rv)
+			return rv;
+		truncate_inode_pages_range(mapping, lstart, end);
+	}
+
 	rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
 				  offset, nr_segs, gfs2_get_block_direct,
 				  NULL, NULL, 0);
-- 
cgit v0.10.2


From 582d2f7aedfde9e1a01170deb003df510aa778d3 Mon Sep 17 00:00:00 2001
From: Steven Whitehouse <swhiteho@redhat.com>
Date: Thu, 19 Dec 2013 11:04:14 +0000
Subject: GFS2: Wait for async DIO in glock state changes

We need to wait for any outstanding DIO to complete in a couple
of situations. Firstly, in case we are changing out of deferred
mode (in inode_go_sync) where GLF_DIRTY will not be set. That
call could be prefixed with a test for gl_state == LM_ST_DEFERRED
but it doesn't seem worth it bearing in mind that the test for
outstanding DIO is very quick anyway, in the usual case that there
is none.

The second case is in inode_go_lock which will catch the cases
where we have a cached EX lock, but where we grant deferred locks
against it so that there is no glock state transistion. We only
need to wait if the state is not deferred, since DIO is valid
anyway in that state.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index db908f6..f88dcd9 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -192,8 +192,11 @@ static void inode_go_sync(struct gfs2_glock *gl)
 
 	if (ip && !S_ISREG(ip->i_inode.i_mode))
 		ip = NULL;
-	if (ip && test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
-		unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0);
+	if (ip) {
+		if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
+			unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0);
+		inode_dio_wait(&ip->i_inode);
+	}
 	if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
 		return;
 
@@ -410,6 +413,9 @@ static int inode_go_lock(struct gfs2_holder *gh)
 			return error;
 	}
 
+	if (gh->gh_state != LM_ST_DEFERRED)
+		inode_dio_wait(&ip->i_inode);
+
 	if ((ip->i_diskflags & GFS2_DIF_TRUNC_IN_PROG) &&
 	    (gl->gl_state == LM_ST_EXCLUSIVE) &&
 	    (gh->gh_state == LM_ST_EXCLUSIVE)) {
-- 
cgit v0.10.2


From 443d20fd188208aa4df2118ad49f9168e411016d Mon Sep 17 00:00:00 2001
From: Helmut Schaa <helmut.schaa@googlemail.com>
Date: Fri, 20 Dec 2013 14:41:54 +0100
Subject: netfilter: nf_ct_timestamp: Fix BUG_ON after netns deletion

When having nf_conntrack_timestamp enabled deleting a netns
can lead to the following BUG being triggered:

[63836.660000] Kernel bug detected[#1]:
[63836.660000] CPU: 0 PID: 0 Comm: swapper Not tainted 3.10.18 #14
[63836.660000] task: 802d9420 ti: 802d2000 task.ti: 802d2000
[63836.660000] $ 0   : 00000000 00000000 00000000 00000000
[63836.660000] $ 4   : 00000001 00000004 00000020 00000020
[63836.660000] $ 8   : 00000000 80064910 00000000 00000000
[63836.660000] $12   : 0bff0002 00000001 00000000 0a0a0abe
[63836.660000] $16   : 802e70a0 85f29d80 00000000 00000004
[63836.660000] $20   : 85fb62a0 00000002 802d3bc0 85fb62a0
[63836.660000] $24   : 00000000 87138110
[63836.660000] $28   : 802d2000 802d3b40 00000014 871327cc
[63836.660000] Hi    : 000005ff
[63836.660000] Lo    : f2edd000
[63836.660000] epc   : 87138794 __nf_ct_ext_add_length+0xe8/0x1ec [nf_conntrack]
[63836.660000]     Not tainted
[63836.660000] ra    : 871327cc nf_conntrack_in+0x31c/0x7b8 [nf_conntrack]
[63836.660000] Status: 1100d403 KERNEL EXL IE
[63836.660000] Cause : 00800034
[63836.660000] PrId  : 0001974c (MIPS 74Kc)
[63836.660000] Modules linked in: ath9k ath9k_common pppoe ppp_async iptable_nat ath9k_hw ath pppox ppp_generic nf_nat_ipv4 nf_conntrack_ipv4 mac80211 ipt_MASQUERADE cfg80211 xt_time xt_tcpudp xt_state xt_quota xt_policy xt_pkttype xt_owner xt_nat xt_multiport xt_mark xh
[63836.660000] Process swapper (pid: 0, threadinfo=802d2000, task=802d9420, tls=00000000)
[63836.660000] Stack : 802e70a0 871323d4 00000005 87080234 802e70a0 86d2a840 00000000 00000000
[63836.660000] Call Trace:
[63836.660000] [<87138794>] __nf_ct_ext_add_length+0xe8/0x1ec [nf_conntrack]
[63836.660000] [<871327cc>] nf_conntrack_in+0x31c/0x7b8 [nf_conntrack]
[63836.660000] [<801ff63c>] nf_iterate+0x90/0xec
[63836.660000] [<801ff730>] nf_hook_slow+0x98/0x164
[63836.660000] [<80205968>] ip_rcv+0x3e8/0x40c
[63836.660000] [<801d9754>] __netif_receive_skb_core+0x624/0x6a4
[63836.660000] [<801da124>] process_backlog+0xa4/0x16c
[63836.660000] [<801d9bb4>] net_rx_action+0x10c/0x1e0
[63836.660000] [<8007c5a4>] __do_softirq+0xd0/0x1bc
[63836.660000] [<8007c730>] do_softirq+0x48/0x68
[63836.660000] [<8007c964>] irq_exit+0x54/0x70
[63836.660000] [<80060830>] ret_from_irq+0x0/0x4
[63836.660000] [<8006a9f8>] r4k_wait_irqoff+0x18/0x1c
[63836.660000] [<8009cfb8>] cpu_startup_entry+0xa4/0x104
[63836.660000] [<802eb918>] start_kernel+0x394/0x3ac
[63836.660000]
[63836.660000]
Code: 00821021  8c420000  2c440001 <00040336> 90440011  92350010  90560010  2485ffff  02a5a821
[63837.040000] ---[ end trace ebf660c3ce3b55e7 ]---
[63837.050000] Kernel panic - not syncing: Fatal exception in interrupt
[63837.050000] Rebooting in 3 seconds..

Fix this by not unregistering the conntrack extension in the per-netns
cleanup code.

This bug was introduced in (73f4001 netfilter: nf_ct_tstamp: move
initialization out of pernet_operations).

Signed-off-by: Helmut Schaa <helmut.schaa@googlemail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

diff --git a/net/netfilter/nf_conntrack_timestamp.c b/net/netfilter/nf_conntrack_timestamp.c
index 902fb0a..7a394df 100644
--- a/net/netfilter/nf_conntrack_timestamp.c
+++ b/net/netfilter/nf_conntrack_timestamp.c
@@ -97,7 +97,6 @@ int nf_conntrack_tstamp_pernet_init(struct net *net)
 void nf_conntrack_tstamp_pernet_fini(struct net *net)
 {
 	nf_conntrack_tstamp_fini_sysctl(net);
-	nf_ct_extend_unregister(&tstamp_extend);
 }
 
 int nf_conntrack_tstamp_init(void)
-- 
cgit v0.10.2


From a42101418072d3be357b534521be2849518611e6 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung.kim@lge.com>
Date: Fri, 20 Dec 2013 14:11:12 +0900
Subject: perf report: Use pr_*() functions where applicable

There're some places printing messages to stdout/err directly.

It should be converted to use proper error printing functions instead.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1387516278-17024-2-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index ec7399a..0c9ec3e 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -242,8 +242,8 @@ static int process_sample_event(struct perf_tool *tool,
 	int ret;
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
-		fprintf(stderr, "problem processing %d event, skipping it.\n",
-			event->header.type);
+		pr_debug("problem processing %d event, skipping it.\n",
+			 event->header.type);
 		return -1;
 	}
 
@@ -637,7 +637,7 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 		return -1;
 setup:
 	if (callchain_register_param(&callchain_param) < 0) {
-		fprintf(stderr, "Can't register callchain params\n");
+		pr_err("Can't register callchain params\n");
 		return -1;
 	}
 	return 0;
@@ -859,7 +859,7 @@ repeat:
 	}
 	if (report.mem_mode) {
 		if (sort__mode == SORT_MODE__BRANCH) {
-			fprintf(stderr, "branch and mem mode incompatible\n");
+			pr_err("branch and mem mode incompatible\n");
 			goto error;
 		}
 		sort__mode = SORT_MODE__MEMORY;
-- 
cgit v0.10.2


From 150e465ac99ed18fb9555c16e0def7ce01913a2a Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung.kim@lge.com>
Date: Fri, 20 Dec 2013 14:11:13 +0900
Subject: perf report: Print session information only if --stdio is given

Move those print functions under "if (use_browser == 0)" so that they
don't interfere with TUI output.

Maybe they can handle other UIs later.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1387516278-17024-3-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 0c9ec3e..bf8dd2e 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -469,15 +469,17 @@ static int __cmd_report(struct report *rep)
 		desc);
 	}
 
-	if (verbose > 3)
-		perf_session__fprintf(session, stdout);
+	if (use_browser == 0) {
+		if (verbose > 3)
+			perf_session__fprintf(session, stdout);
 
-	if (verbose > 2)
-		perf_session__fprintf_dsos(session, stdout);
+		if (verbose > 2)
+			perf_session__fprintf_dsos(session, stdout);
 
-	if (dump_trace) {
-		perf_session__fprintf_nr_events(session, stdout);
-		return 0;
+		if (dump_trace) {
+			perf_session__fprintf_nr_events(session, stdout);
+			return 0;
+		}
 	}
 
 	nr_samples = 0;
-- 
cgit v0.10.2


From 11daf32be9a6041a2406c2cbf76b75a9c4a6eaaa Mon Sep 17 00:00:00 2001
From: Matteo Facchinetti <matteo.facchinetti@sirius-es.it>
Date: Fri, 20 Dec 2013 10:16:22 +0100
Subject: powerpc/512x: dts: disable MPC5125 usb module

At the moment the USB controller's pin muxing is not setup
correctly and causes a kernel panic upon system startup, so
disable the USB1 device tree node in the MPC5125 tower board
dts file.

The USB controller is connected to an USB3320 ULPI transceiver
and the device tree should receive an update to reflect correct
dependencies and required initialization data before the USB1
node can get re-enabled.

Signed-off-by: Matteo Facchinetti <matteo.facchinetti@sirius-es.it>
Signed-off-by: Anatolij Gustschin <agust@denx.de>

diff --git a/arch/powerpc/boot/dts/mpc5125twr.dts b/arch/powerpc/boot/dts/mpc5125twr.dts
index 0a0fe92..a618dfc 100644
--- a/arch/powerpc/boot/dts/mpc5125twr.dts
+++ b/arch/powerpc/boot/dts/mpc5125twr.dts
@@ -188,6 +188,10 @@
 			reg = <0xA000 0x1000>;
 		};
 
+		// disable USB1 port
+		// TODO:
+		// correct pinmux config and fix USB3320 ulpi dependency
+		// before re-enabling it
 		usb@3000 {
 			compatible = "fsl,mpc5121-usb2-dr";
 			reg = <0x3000 0x400>;
@@ -196,6 +200,7 @@
 			interrupts = <43 0x8>;
 			dr_mode = "host";
 			phy_type = "ulpi";
+			status = "disabled";
 		};
 
 		// 5125 PSCs are not 52xx or 5121 PSC compatible
-- 
cgit v0.10.2


From 95edca5c523c4b404dd60baa0a1bea0e4c38fd72 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Wed, 18 Dec 2013 12:35:20 -0500
Subject: localmodconfig: Add config depends by default settings

Currently localmodconfig will miss dependencies from the default option.
For example:

config FOO
	default y if BAR || ZOO

If FOO is needed for a module and is set to '=m', and so are BAR or ZOO,
localmodconfig will not see that BOO or ZOO are also needed for the foo
module, and will incorrectly disable them.

Link: http://lkml.kernel.org/r/20131218175137.162937350@goodmis.org

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

diff --git a/scripts/kconfig/streamline_config.pl b/scripts/kconfig/streamline_config.pl
index 4606cdf..3133172 100644
--- a/scripts/kconfig/streamline_config.pl
+++ b/scripts/kconfig/streamline_config.pl
@@ -219,6 +219,13 @@ sub read_kconfig {
 	    $depends{$config} = $1;
 	} elsif ($state eq "DEP" && /^\s*depends\s+on\s+(.*)$/) {
 	    $depends{$config} .= " " . $1;
+	} elsif ($state eq "DEP" && /^\s*def(_(bool|tristate)|ault)\s+(\S.*)$/) {
+	    my $dep = $3;
+	    if ($dep !~ /^\s*(y|m|n)\s*$/) {
+		$dep =~ s/.*\sif\s+//;
+		$depends{$config} .= " " . $dep;
+		dprint "Added default depends $dep to $config\n";
+	    }
 
 	# Get the configs that select this config
 	} elsif ($state ne "NONE" && /^\s*select\s+(\S+)/) {
-- 
cgit v0.10.2


From 90ed4988b8c030d65b41b7d13140e9376dc6ec5a Mon Sep 17 00:00:00 2001
From: Aristeu Rozanski <aris@redhat.com>
Date: Thu, 5 Dec 2013 10:37:56 -0500
Subject: e752x_edac: Fix pci_dev usage count

In case the device 0, function 1 is not found using pci_get_device(),
pci_scan_single_device() will be used but, differently than
pci_get_device(), it allocates a pci_dev but doesn't does bump the usage
count on the pci_dev and after few module removals and loads the pci_dev
will be freed.

Signed-off-by: Aristeu Rozanski <aris@redhat.com>
Reviewed-by: mark gross <mark.gross@intel.com>
Link: http://lkml.kernel.org/r/20131205153755.GL4545@redhat.com
Signed-off-by: Borislav Petkov <bp@suse.de>

diff --git a/drivers/edac/e752x_edac.c b/drivers/edac/e752x_edac.c
index 5fb01b0..92d54fa 100644
--- a/drivers/edac/e752x_edac.c
+++ b/drivers/edac/e752x_edac.c
@@ -1182,9 +1182,11 @@ static int e752x_get_devs(struct pci_dev *pdev, int dev_idx,
 	pvt->bridge_ck = pci_get_device(PCI_VENDOR_ID_INTEL,
 				pvt->dev_info->err_dev, pvt->bridge_ck);
 
-	if (pvt->bridge_ck == NULL)
+	if (pvt->bridge_ck == NULL) {
 		pvt->bridge_ck = pci_scan_single_device(pdev->bus,
 							PCI_DEVFN(0, 1));
+		pci_dev_get(pvt->bridge_ck);
+	}
 
 	if (pvt->bridge_ck == NULL) {
 		e752x_printk(KERN_ERR, "error reporting device not found:"
-- 
cgit v0.10.2


From addccbb264e5e0e5762f4893f6df24afad327c8c Mon Sep 17 00:00:00 2001
From: "Chen, Gong" <gong.chen@linux.intel.com>
Date: Mon, 25 Nov 2013 02:15:00 -0500
Subject: ACPI, APEI, GHES: Do not report only correctable errors with SCI

Currently SCI is employed to handle corrected errors - memory corrected
errors, more specifically but in fact SCI still can be used to handle
any errors, e.g. uncorrected or even fatal ones if enabled by the BIOS.
Enable logging for those kinds of errors too.

Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Tony Luck <tony.luck@intel.com>
Link: http://lkml.kernel.org/r/1385363701-12387-1-git-send-email-gong.chen@linux.intel.com
[ Boris: massage commit message, rename function arg. ]
Signed-off-by: Borislav Petkov <bp@suse.de>

diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
index de8b60a..a1aef95 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
@@ -33,22 +33,28 @@
 #include <linux/acpi.h>
 #include <linux/cper.h>
 #include <acpi/apei.h>
+#include <acpi/ghes.h>
 #include <asm/mce.h>
 
 #include "mce-internal.h"
 
-void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err)
+void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err)
 {
 	struct mce m;
 
-	/* Only corrected MC is reported */
-	if (!corrected || !(mem_err->validation_bits & CPER_MEM_VALID_PA))
+	if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
 		return;
 
 	mce_setup(&m);
 	m.bank = 1;
-	/* Fake a memory read corrected error with unknown channel */
+	/* Fake a memory read error with unknown channel */
 	m.status = MCI_STATUS_VAL | MCI_STATUS_EN | MCI_STATUS_ADDRV | 0x9f;
+
+	if (severity >= GHES_SEV_RECOVERABLE)
+		m.status |= MCI_STATUS_UC;
+	if (severity >= GHES_SEV_PANIC)
+		m.status |= MCI_STATUS_PCC;
+
 	m.addr = mem_err->physical_addr;
 	mce_log(&m);
 	mce_notify_irq();
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index a30bc31..ce3683d 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -453,8 +453,7 @@ static void ghes_do_proc(struct ghes *ghes,
 			ghes_edac_report_mem_error(ghes, sev, mem_err);
 
 #ifdef CONFIG_X86_MCE
-			apei_mce_report_mem_error(sev == GHES_SEV_CORRECTED,
-						  mem_err);
+			apei_mce_report_mem_error(sev, mem_err);
 #endif
 			ghes_handle_memory_failure(gdata, sev);
 		}
-- 
cgit v0.10.2


From d3ab3edc029bf79b09f91d6a22881c24ecaeb000 Mon Sep 17 00:00:00 2001
From: "Chen, Gong" <gong.chen@linux.intel.com>
Date: Wed, 18 Dec 2013 01:30:49 -0500
Subject: ACPI, APEI: Cleanup alignment-aware accesses

We do use memcpy to avoid access alignment issues between firmware and
OS. Now we can use a better and standard way to avoid this issue. While
at it, simplify some variable names to avoid the 80 cols limit and
use structure assignment instead of unnecessary memcpy. No functional
changes.

Because ERST record id cache is implemented in memory to increase the
access speed via caching ERST content we can refrain from using memcpy
there too and use regular assignment instead.

Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
Cc: Cc: Tony Luck <tony.luck@intel.com>
Link: http://lkml.kernel.org/r/1387348249-20014-1-git-send-email-gong.chen@linux.intel.com
[ Boris: massage commit message a bit. ]
Signed-off-by: Borislav Petkov <bp@suse.de>

diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c
index 6d2c49b..e55584a 100644
--- a/drivers/acpi/apei/apei-base.c
+++ b/drivers/acpi/apei/apei-base.c
@@ -41,6 +41,7 @@
 #include <linux/rculist.h>
 #include <linux/interrupt.h>
 #include <linux/debugfs.h>
+#include <asm/unaligned.h>
 
 #include "apei-internal.h"
 
@@ -567,8 +568,7 @@ static int apei_check_gar(struct acpi_generic_address *reg, u64 *paddr,
 	bit_offset = reg->bit_offset;
 	access_size_code = reg->access_width;
 	space_id = reg->space_id;
-	/* Handle possible alignment issues */
-	memcpy(paddr, &reg->address, sizeof(*paddr));
+	*paddr = get_unaligned(&reg->address);
 	if (!*paddr) {
 		pr_warning(FW_BUG APEI_PFX
 			   "Invalid physical address in GAR [0x%llx/%u/%u/%u/%u]\n",
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
index fb57d03..361177a 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj.c
@@ -34,6 +34,7 @@
 #include <linux/delay.h>
 #include <linux/mm.h>
 #include <acpi/acpi.h>
+#include <asm/unaligned.h>
 
 #include "apei-internal.h"
 
@@ -216,7 +217,7 @@ static void check_vendor_extension(u64 paddr,
 static void *einj_get_parameter_address(void)
 {
 	int i;
-	u64 paddrv4 = 0, paddrv5 = 0;
+	u64 pa_v4 = 0, pa_v5 = 0;
 	struct acpi_whea_header *entry;
 
 	entry = EINJ_TAB_ENTRY(einj_tab);
@@ -225,30 +226,28 @@ static void *einj_get_parameter_address(void)
 		    entry->instruction == ACPI_EINJ_WRITE_REGISTER &&
 		    entry->register_region.space_id ==
 		    ACPI_ADR_SPACE_SYSTEM_MEMORY)
-			memcpy(&paddrv4, &entry->register_region.address,
-			       sizeof(paddrv4));
+			pa_v4 = get_unaligned(&entry->register_region.address);
 		if (entry->action == ACPI_EINJ_SET_ERROR_TYPE_WITH_ADDRESS &&
 		    entry->instruction == ACPI_EINJ_WRITE_REGISTER &&
 		    entry->register_region.space_id ==
 		    ACPI_ADR_SPACE_SYSTEM_MEMORY)
-			memcpy(&paddrv5, &entry->register_region.address,
-			       sizeof(paddrv5));
+			pa_v5 = get_unaligned(&entry->register_region.address);
 		entry++;
 	}
-	if (paddrv5) {
+	if (pa_v5) {
 		struct set_error_type_with_address *v5param;
 
-		v5param = acpi_os_map_memory(paddrv5, sizeof(*v5param));
+		v5param = acpi_os_map_memory(pa_v5, sizeof(*v5param));
 		if (v5param) {
 			acpi5 = 1;
-			check_vendor_extension(paddrv5, v5param);
+			check_vendor_extension(pa_v5, v5param);
 			return v5param;
 		}
 	}
-	if (param_extension && paddrv4) {
+	if (param_extension && pa_v4) {
 		struct einj_parameter *v4param;
 
-		v4param = acpi_os_map_memory(paddrv4, sizeof(*v4param));
+		v4param = acpi_os_map_memory(pa_v4, sizeof(*v4param));
 		if (!v4param)
 			return NULL;
 		if (v4param->reserved1 || v4param->reserved2) {
diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index 26311f2..bf30a12 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -611,7 +611,7 @@ static void __erst_record_id_cache_compact(void)
 		if (entries[i] == APEI_ERST_INVALID_RECORD_ID)
 			continue;
 		if (wpos != i)
-			memcpy(&entries[wpos], &entries[i], sizeof(entries[i]));
+			entries[wpos] = entries[i];
 		wpos++;
 	}
 	erst_record_id_cache.len = wpos;
-- 
cgit v0.10.2


From ca104edc17841da87850b20ab77e57fe0a99ead6 Mon Sep 17 00:00:00 2001
From: "Chen, Gong" <gong.chen@linux.intel.com>
Date: Mon, 25 Nov 2013 02:15:01 -0500
Subject: ACPI, APEI, GHES: Cleanup ghes memory error handling

Cleanup the logic in ghes_handle_memory_failure(). While at it, add
proper PFN validity check for UC error and cleanup the code logic to
make it simpler and cleaner.

Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1385363701-12387-2-git-send-email-gong.chen@linux.intel.com
[ Boris: massage commit message. ]
Signed-off-by: Borislav Petkov <bp@suse.de>

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index ce3683d..46766ef 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -413,27 +413,31 @@ static void ghes_handle_memory_failure(struct acpi_generic_data *gdata, int sev)
 {
 #ifdef CONFIG_ACPI_APEI_MEMORY_FAILURE
 	unsigned long pfn;
+	int flags = -1;
 	int sec_sev = ghes_severity(gdata->error_severity);
 	struct cper_sec_mem_err *mem_err;
 	mem_err = (struct cper_sec_mem_err *)(gdata + 1);
 
-	if (sec_sev == GHES_SEV_CORRECTED &&
-	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED) &&
-	    (mem_err->validation_bits & CPER_MEM_VALID_PA)) {
-		pfn = mem_err->physical_addr >> PAGE_SHIFT;
-		if (pfn_valid(pfn))
-			memory_failure_queue(pfn, 0, MF_SOFT_OFFLINE);
-		else if (printk_ratelimit())
-			pr_warn(FW_WARN GHES_PFX
-			"Invalid address in generic error data: %#llx\n",
-			mem_err->physical_addr);
-	}
-	if (sev == GHES_SEV_RECOVERABLE &&
-	    sec_sev == GHES_SEV_RECOVERABLE &&
-	    mem_err->validation_bits & CPER_MEM_VALID_PA) {
-		pfn = mem_err->physical_addr >> PAGE_SHIFT;
-		memory_failure_queue(pfn, 0, 0);
+	if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
+		return;
+
+	pfn = mem_err->physical_addr >> PAGE_SHIFT;
+	if (!pfn_valid(pfn)) {
+		pr_warn_ratelimited(FW_WARN GHES_PFX
+		"Invalid address in generic error data: %#llx\n",
+		mem_err->physical_addr);
+		return;
 	}
+
+	/* iff following two events can be handled properly by now */
+	if (sec_sev == GHES_SEV_CORRECTED &&
+	    (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED))
+		flags = MF_SOFT_OFFLINE;
+	if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE)
+		flags = 0;
+
+	if (flags != -1)
+		memory_failure_queue(pfn, 0, flags);
 #endif
 }
 
-- 
cgit v0.10.2


From 2da6e57cce14a1c3b0692d6f877b72e185110e2e Mon Sep 17 00:00:00 2001
From: Dave Young <dyoung@redhat.com>
Date: Fri, 20 Dec 2013 18:02:13 +0800
Subject: x86/efi: Remove unused variables in __map_region()

variables size and end is useless in this function, thus remove them.

Reported-by: Toshi Kani <toshi.kani@hp.com>
Tested-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Dave Young <dyoung@redhat.com>
Acked-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index bf286c3..c5a6491 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -148,15 +148,11 @@ void efi_setup_page_tables(void)
 static void __init __map_region(efi_memory_desc_t *md, u64 va)
 {
 	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
-	unsigned long pf = 0, size;
-	u64 end;
+	unsigned long pf = 0;
 
 	if (!(md->attribute & EFI_MEMORY_WB))
 		pf |= _PAGE_PCD;
 
-	size = md->num_pages << PAGE_SHIFT;
-	end  = va + size;
-
 	if (kernel_map_pages_in_pgd(pgd, md->phys_addr, va, md->num_pages, pf))
 		pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n",
 			   md->phys_addr, va);
-- 
cgit v0.10.2


From 3b2664964bc886ae9d5127c8d3708b1acc0626d2 Mon Sep 17 00:00:00 2001
From: Dave Young <dyoung@redhat.com>
Date: Fri, 20 Dec 2013 18:02:14 +0800
Subject: x86/efi: Add a wrapper function efi_map_region_fixed()

Kexec kernel will use saved runtime virtual mapping, so add a new
function efi_map_region_fixed() for directly mapping a md to md->virt.

The md is passed in from 1st kernel, the virtual addr is saved in
md->virt_addr.

Signed-off-by: Dave Young <dyoung@redhat.com>
Acked-by: Borislav Petkov <bp@suse.de>
Tested-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 89a05b0..9fbaeb2 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -128,6 +128,7 @@ extern void efi_call_phys_epilog(void);
 extern void efi_unmap_memmap(void);
 extern void efi_memory_uc(u64 addr, unsigned long size);
 extern void __init efi_map_region(efi_memory_desc_t *md);
+extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
 extern void efi_sync_low_kernel_mappings(void);
 extern void efi_setup_page_tables(void);
 extern void __init old_map_region(efi_memory_desc_t *md);
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index e94557c..7b3ec6e 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -47,6 +47,8 @@ void __init efi_map_region(efi_memory_desc_t *md)
 	old_map_region(md);
 }
 
+void __init efi_map_region_fixed(efi_memory_desc_t *md) {}
+
 void efi_call_phys_prelog(void)
 {
 	struct desc_ptr gdt_descr;
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index c5a6491..ff08cb1 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -199,6 +199,16 @@ void __init efi_map_region(efi_memory_desc_t *md)
 	md->virt_addr = efi_va;
 }
 
+/*
+ * kexec kernel will use efi_map_region_fixed to map efi runtime memory ranges.
+ * md->virt_addr is the original virtual address which had been mapped in kexec
+ * 1st kernel.
+ */
+void __init efi_map_region_fixed(efi_memory_desc_t *md)
+{
+	__map_region(md, md->virt_addr);
+}
+
 void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
 				 u32 type, u64 attribute)
 {
-- 
cgit v0.10.2


From a7f84f03f660d93574ac88835d056c0d6468aebe Mon Sep 17 00:00:00 2001
From: Dave Young <dyoung@redhat.com>
Date: Fri, 20 Dec 2013 18:02:15 +0800
Subject: x86/efi: Fix off-by-one bug in EFI Boot Services reservation

Current code check boot service region with kernel text region by:
start+size >= __pa_symbol(_text)
The end of the above region should be start + size - 1 instead.

I see this problem in ovmf + Fedora 19 grub boot:
text start: 1000000 md start: 800000 md size: 800000

Signed-off-by: Dave Young <dyoung@redhat.com>
Acked-by: Borislav Petkov <bp@suse.de>
Acked-by: Toshi Kani <toshi.kani@hp.com>
Tested-by: Toshi Kani <toshi.kani@hp.com>
Cc: stable@vger.kernel.org
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index f8ec4da..15e3b5e 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -438,7 +438,7 @@ void __init efi_reserve_boot_services(void)
 		 * - Not within any part of the kernel
 		 * - Not the bios reserved area
 		*/
-		if ((start+size >= __pa_symbol(_text)
+		if ((start + size > __pa_symbol(_text)
 				&& start <= __pa_symbol(_end)) ||
 			!e820_all_mapped(start, start+size, E820_RAM) ||
 			memblock_is_region_reserved(start, size)) {
-- 
cgit v0.10.2


From 481f75c043cf44ec11c7fbdbbf37d43463f1e719 Mon Sep 17 00:00:00 2001
From: Dave Young <dyoung@redhat.com>
Date: Fri, 20 Dec 2013 18:02:16 +0800
Subject: x86/efi: Cleanup efi_enter_virtual_mode() function

Add two small functions:
efi_merge_regions() and efi_map_regions(), efi_enter_virtual_mode()
calls them instead of embedding two long for loop.

Signed-off-by: Dave Young <dyoung@redhat.com>
Acked-by: Borislav Petkov <bp@suse.de>
Tested-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 15e3b5e..4694632 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -773,44 +773,12 @@ void __init old_map_region(efi_memory_desc_t *md)
 		       (unsigned long long)md->phys_addr);
 }
 
-/*
- * This function will switch the EFI runtime services to virtual mode.
- * Essentially, we look through the EFI memmap and map every region that
- * has the runtime attribute bit set in its memory descriptor into the
- * ->trampoline_pgd page table using a top-down VA allocation scheme.
- *
- * The old method which used to update that memory descriptor with the
- * virtual address obtained from ioremap() is still supported when the
- * kernel is booted with efi=old_map on its command line. Same old
- * method enabled the runtime services to be called without having to
- * thunk back into physical mode for every invocation.
- *
- * The new method does a pagetable switch in a preemption-safe manner
- * so that we're in a different address space when calling a runtime
- * function. For function arguments passing we do copy the PGDs of the
- * kernel page table into ->trampoline_pgd prior to each call.
- */
-void __init efi_enter_virtual_mode(void)
+/* Merge contiguous regions of the same type and attribute */
+static void __init efi_merge_regions(void)
 {
+	void *p;
 	efi_memory_desc_t *md, *prev_md = NULL;
-	void *p, *new_memmap = NULL;
-	unsigned long size;
-	efi_status_t status;
-	u64 end, systab;
-	int count = 0;
-
-	efi.systab = NULL;
 
-	/*
-	 * We don't do virtual mode, since we don't do runtime services, on
-	 * non-native EFI
-	 */
-	if (!efi_is_native()) {
-		efi_unmap_memmap();
-		return;
-	}
-
-	/* Merge contiguous regions of the same type and attribute */
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		u64 prev_size;
 		md = p;
@@ -835,8 +803,31 @@ void __init efi_enter_virtual_mode(void)
 			continue;
 		}
 		prev_md = md;
+	}
+}
+
+static void __init get_systab_virt_addr(efi_memory_desc_t *md)
+{
+	unsigned long size;
+	u64 end, systab;
 
+	size = md->num_pages << EFI_PAGE_SHIFT;
+	end = md->phys_addr + size;
+	systab = (u64)(unsigned long)efi_phys.systab;
+	if (md->phys_addr <= systab && systab < end) {
+		systab += md->virt_addr - md->phys_addr;
+		efi.systab = (efi_system_table_t *)(unsigned long)systab;
 	}
+}
+
+/*
+ * Map efi memory ranges for runtime serivce and update new_memmap with virtual
+ * addresses.
+ */
+static void * __init efi_map_regions(int *count)
+{
+	efi_memory_desc_t *md;
+	void *p, *tmp, *new_memmap = NULL;
 
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
@@ -849,26 +840,64 @@ void __init efi_enter_virtual_mode(void)
 		}
 
 		efi_map_region(md);
+		get_systab_virt_addr(md);
+
+		tmp = krealloc(new_memmap, (*count + 1) * memmap.desc_size,
+			       GFP_KERNEL);
+		if (!tmp)
+			goto out_krealloc;
+		new_memmap = tmp;
+		memcpy(new_memmap + (*count * memmap.desc_size), md,
+		       memmap.desc_size);
+		(*count)++;
+	}
 
-		size = md->num_pages << EFI_PAGE_SHIFT;
-		end = md->phys_addr + size;
+	return new_memmap;
+out_krealloc:
+	kfree(new_memmap);
+	return NULL;
+}
+
+/*
+ * This function will switch the EFI runtime services to virtual mode.
+ * Essentially, we look through the EFI memmap and map every region that
+ * has the runtime attribute bit set in its memory descriptor into the
+ * ->trampoline_pgd page table using a top-down VA allocation scheme.
+ *
+ * The old method which used to update that memory descriptor with the
+ * virtual address obtained from ioremap() is still supported when the
+ * kernel is booted with efi=old_map on its command line. Same old
+ * method enabled the runtime services to be called without having to
+ * thunk back into physical mode for every invocation.
+ *
+ * The new method does a pagetable switch in a preemption-safe manner
+ * so that we're in a different address space when calling a runtime
+ * function. For function arguments passing we do copy the PGDs of the
+ * kernel page table into ->trampoline_pgd prior to each call.
+ */
+void __init efi_enter_virtual_mode(void)
+{
+	efi_status_t status;
+	void *new_memmap = NULL;
+	int count = 0;
 
-		systab = (u64) (unsigned long) efi_phys.systab;
-		if (md->phys_addr <= systab && systab < end) {
-			systab += md->virt_addr - md->phys_addr;
+	efi.systab = NULL;
 
-			efi.systab = (efi_system_table_t *) (unsigned long) systab;
-		}
+	/*
+	 * We don't do virtual mode, since we don't do runtime services, on
+	 * non-native EFI
+	 */
+	if (!efi_is_native()) {
+		efi_unmap_memmap();
+		return;
+	}
 
-		new_memmap = krealloc(new_memmap,
-				      (count + 1) * memmap.desc_size,
-				      GFP_KERNEL);
-		if (!new_memmap)
-			goto err_out;
+	efi_merge_regions();
 
-		memcpy(new_memmap + (count * memmap.desc_size), md,
-		       memmap.desc_size);
-		count++;
+	new_memmap = efi_map_regions(&count);
+	if (!new_memmap) {
+		pr_err("Error reallocating memory, EFI runtime non-functional!\n");
+		return;
 	}
 
 	BUG_ON(!efi.systab);
@@ -922,9 +951,6 @@ void __init efi_enter_virtual_mode(void)
 			 0, NULL);
 
 	return;
-
- err_out:
-	pr_err("Error reallocating memory, EFI runtime non-functional!\n");
 }
 
 /*
-- 
cgit v0.10.2


From a0998eb15afeffbf52a2c2829318f67df9ac57b8 Mon Sep 17 00:00:00 2001
From: Dave Young <dyoung@redhat.com>
Date: Fri, 20 Dec 2013 18:02:17 +0800
Subject: efi: Export more EFI table variables to sysfs

Export fw_vendor, runtime and config table physical addresses to
/sys/firmware/efi/{fw_vendor,runtime,config_table} because kexec kernels
need them.

From EFI spec these 3 variables will be updated to virtual address after
entering virtual mode. But kernel startup code will need the physical
address.

Signed-off-by: Dave Young <dyoung@redhat.com>
Tested-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/Documentation/ABI/testing/sysfs-firmware-efi b/Documentation/ABI/testing/sysfs-firmware-efi
new file mode 100644
index 0000000..05874da
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-firmware-efi
@@ -0,0 +1,20 @@
+What:		/sys/firmware/efi/fw_vendor
+Date:		December 2013
+Contact:	Dave Young <dyoung@redhat.com>
+Description:	It shows the physical address of firmware vendor field in the
+		EFI system table.
+Users:		Kexec
+
+What:		/sys/firmware/efi/runtime
+Date:		December 2013
+Contact:	Dave Young <dyoung@redhat.com>
+Description:	It shows the physical address of runtime service table entry in
+		the EFI system table.
+Users:		Kexec
+
+What:		/sys/firmware/efi/config_table
+Date:		December 2013
+Contact:	Dave Young <dyoung@redhat.com>
+Description:	It shows the physical address of config table entry in the EFI
+		system table.
+Users:		Kexec
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 4694632..2859107 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -653,6 +653,10 @@ void __init efi_init(void)
 
 	set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility);
 
+	efi.config_table = (unsigned long)efi.systab->tables;
+	efi.fw_vendor	 = (unsigned long)efi.systab->fw_vendor;
+	efi.runtime	 = (unsigned long)efi.systab->runtime;
+
 	/*
 	 * Show what we know for posterity
 	 */
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 2e2fbde..72533af 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -32,6 +32,9 @@ struct efi __read_mostly efi = {
 	.hcdp       = EFI_INVALID_TABLE_ADDR,
 	.uga        = EFI_INVALID_TABLE_ADDR,
 	.uv_systab  = EFI_INVALID_TABLE_ADDR,
+	.fw_vendor  = EFI_INVALID_TABLE_ADDR,
+	.runtime    = EFI_INVALID_TABLE_ADDR,
+	.config_table  = EFI_INVALID_TABLE_ADDR,
 };
 EXPORT_SYMBOL(efi);
 
@@ -71,13 +74,49 @@ static ssize_t systab_show(struct kobject *kobj,
 static struct kobj_attribute efi_attr_systab =
 			__ATTR(systab, 0400, systab_show, NULL);
 
+#define EFI_FIELD(var) efi.var
+
+#define EFI_ATTR_SHOW(name) \
+static ssize_t name##_show(struct kobject *kobj, \
+				struct kobj_attribute *attr, char *buf) \
+{ \
+	return sprintf(buf, "0x%lx\n", EFI_FIELD(name)); \
+}
+
+EFI_ATTR_SHOW(fw_vendor);
+EFI_ATTR_SHOW(runtime);
+EFI_ATTR_SHOW(config_table);
+
+static struct kobj_attribute efi_attr_fw_vendor = __ATTR_RO(fw_vendor);
+static struct kobj_attribute efi_attr_runtime = __ATTR_RO(runtime);
+static struct kobj_attribute efi_attr_config_table = __ATTR_RO(config_table);
+
 static struct attribute *efi_subsys_attrs[] = {
 	&efi_attr_systab.attr,
-	NULL,	/* maybe more in the future? */
+	&efi_attr_fw_vendor.attr,
+	&efi_attr_runtime.attr,
+	&efi_attr_config_table.attr,
+	NULL,
 };
 
+static umode_t efi_attr_is_visible(struct kobject *kobj,
+				   struct attribute *attr, int n)
+{
+	umode_t mode = attr->mode;
+
+	if (attr == &efi_attr_fw_vendor.attr)
+		return (efi.fw_vendor == EFI_INVALID_TABLE_ADDR) ? 0 : mode;
+	else if (attr == &efi_attr_runtime.attr)
+		return (efi.runtime == EFI_INVALID_TABLE_ADDR) ? 0 : mode;
+	else if (attr == &efi_attr_config_table.attr)
+		return (efi.config_table == EFI_INVALID_TABLE_ADDR) ? 0 : mode;
+
+	return mode;
+}
+
 static struct attribute_group efi_subsys_attr_group = {
 	.attrs = efi_subsys_attrs,
+	.is_visible = efi_attr_is_visible,
 };
 
 static struct efivars generic_efivars;
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 6c0ca52..fb60b10 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -556,6 +556,9 @@ extern struct efi {
 	unsigned long hcdp;		/* HCDP table */
 	unsigned long uga;		/* UGA table */
 	unsigned long uv_systab;	/* UV system table */
+	unsigned long fw_vendor;	/* fw_vendor */
+	unsigned long runtime;		/* runtime table */
+	unsigned long config_table;	/* config tables */
 	efi_get_time_t *get_time;
 	efi_set_time_t *set_time;
 	efi_get_wakeup_time_t *get_wakeup_time;
-- 
cgit v0.10.2


From 926172d46038d7610b6b8d84e40db727cefb482d Mon Sep 17 00:00:00 2001
From: Dave Young <dyoung@redhat.com>
Date: Fri, 20 Dec 2013 18:02:18 +0800
Subject: efi: Export EFI runtime memory mapping to sysfs

kexec kernel will need exactly same mapping for EFI runtime memory
ranges. Thus here export the runtime ranges mapping to sysfs,
kexec-tools will assemble them and pass to 2nd kernel via setup_data.

Introducing a new directory /sys/firmware/efi/runtime-map just like
/sys/firmware/memmap. Containing below attribute in each file of that
directory:

attribute  num_pages  phys_addr  type  virt_addr

Signed-off-by: Dave Young <dyoung@redhat.com>
Tested-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/Documentation/ABI/testing/sysfs-firmware-efi-runtime-map b/Documentation/ABI/testing/sysfs-firmware-efi-runtime-map
new file mode 100644
index 0000000..c61b9b3
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-firmware-efi-runtime-map
@@ -0,0 +1,34 @@
+What:		/sys/firmware/efi/runtime-map/
+Date:		December 2013
+Contact:	Dave Young <dyoung@redhat.com>
+Description:	Switching efi runtime services to virtual mode requires
+		that all efi memory ranges which have the runtime attribute
+		bit set to be mapped to virtual addresses.
+
+		The efi runtime services can only be switched to virtual
+		mode once without rebooting. The kexec kernel must maintain
+		the same physical to virtual address mappings as the first
+		kernel. The mappings are exported to sysfs so userspace tools
+		can reassemble them and pass them into the kexec kernel.
+
+		/sys/firmware/efi/runtime-map/ is the directory the kernel
+		exports that information in.
+
+		subdirectories are named with the number of the memory range:
+
+			/sys/firmware/efi/runtime-map/0
+			/sys/firmware/efi/runtime-map/1
+			/sys/firmware/efi/runtime-map/2
+			/sys/firmware/efi/runtime-map/3
+			...
+
+		Each subdirectory contains five files:
+
+		attribute : The attributes of the memory range.
+		num_pages : The size of the memory range in pages.
+		phys_addr : The physical address of the memory range.
+		type      : The type of the memory range.
+		virt_addr : The virtual address of the memory range.
+
+		Above values are all hexadecimal numbers with the '0x' prefix.
+Users:		Kexec
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 2859107..74fe7a7 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -76,6 +76,9 @@ static __initdata efi_config_table_type_t arch_tables[] = {
 	{NULL_GUID, NULL, NULL},
 };
 
+static void *efi_runtime_map;
+static int nr_efi_runtime_map;
+
 /*
  * Returns 1 if 'facility' is enabled, 0 otherwise.
  */
@@ -824,6 +827,39 @@ static void __init get_systab_virt_addr(efi_memory_desc_t *md)
 	}
 }
 
+static int __init save_runtime_map(void)
+{
+	efi_memory_desc_t *md;
+	void *tmp, *p, *q = NULL;
+	int count = 0;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		md = p;
+
+		if (!(md->attribute & EFI_MEMORY_RUNTIME) ||
+		    (md->type == EFI_BOOT_SERVICES_CODE) ||
+		    (md->type == EFI_BOOT_SERVICES_DATA))
+			continue;
+		tmp = krealloc(q, (count + 1) * memmap.desc_size, GFP_KERNEL);
+		if (!tmp)
+			goto out;
+		q = tmp;
+
+		memcpy(q + count * memmap.desc_size, md, memmap.desc_size);
+		count++;
+	}
+
+	efi_runtime_map = q;
+	nr_efi_runtime_map = count;
+	efi_runtime_map_setup(efi_runtime_map, nr_efi_runtime_map,
+			      boot_params.efi_info.efi_memdesc_size);
+
+	return 0;
+out:
+	kfree(q);
+	return -ENOMEM;
+}
+
 /*
  * Map efi memory ranges for runtime serivce and update new_memmap with virtual
  * addresses.
@@ -849,7 +885,7 @@ static void * __init efi_map_regions(int *count)
 		tmp = krealloc(new_memmap, (*count + 1) * memmap.desc_size,
 			       GFP_KERNEL);
 		if (!tmp)
-			goto out_krealloc;
+			goto out;
 		new_memmap = tmp;
 		memcpy(new_memmap + (*count * memmap.desc_size), md,
 		       memmap.desc_size);
@@ -857,7 +893,7 @@ static void * __init efi_map_regions(int *count)
 	}
 
 	return new_memmap;
-out_krealloc:
+out:
 	kfree(new_memmap);
 	return NULL;
 }
@@ -883,7 +919,7 @@ void __init efi_enter_virtual_mode(void)
 {
 	efi_status_t status;
 	void *new_memmap = NULL;
-	int count = 0;
+	int err, count = 0;
 
 	efi.systab = NULL;
 
@@ -904,6 +940,10 @@ void __init efi_enter_virtual_mode(void)
 		return;
 	}
 
+	err = save_runtime_map();
+	if (err)
+		pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n");
+
 	BUG_ON(!efi.systab);
 
 	efi_setup_page_tables();
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 3150aa4..730f5f2 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -39,4 +39,15 @@ config EFI_VARS_PSTORE_DEFAULT_DISABLE
 config UEFI_CPER
 	def_bool n
 
+config EFI_RUNTIME_MAP
+	bool "Export efi runtime maps to sysfs"
+	depends on X86 && EFI && KEXEC
+	default y
+	help
+	  Export efi runtime memory maps to /sys/firmware/efi/runtime-map.
+	  That memory map is used for example by kexec to set up efi virtual
+	  mapping the 2nd kernel, but can also be used for debugging purposes.
+
+	  See also Documentation/ABI/testing/sysfs-firmware-efi-runtime-map.
+
 endmenu
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index 9ba156d..a58e0f1 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -5,3 +5,4 @@ obj-y					+= efi.o vars.o
 obj-$(CONFIG_EFI_VARS)			+= efivars.o
 obj-$(CONFIG_EFI_VARS_PSTORE)		+= efi-pstore.o
 obj-$(CONFIG_UEFI_CPER)			+= cper.o
+obj-$(CONFIG_EFI_RUNTIME_MAP)		+= runtime-map.o
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 72533af..4753bac 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -167,6 +167,10 @@ static int __init efisubsys_init(void)
 		goto err_unregister;
 	}
 
+	error = efi_runtime_map_init(efi_kobj);
+	if (error)
+		goto err_remove_group;
+
 	/* and the standard mountpoint for efivarfs */
 	efivars_kobj = kobject_create_and_add("efivars", efi_kobj);
 	if (!efivars_kobj) {
diff --git a/drivers/firmware/efi/runtime-map.c b/drivers/firmware/efi/runtime-map.c
new file mode 100644
index 0000000..97cdd16
--- /dev/null
+++ b/drivers/firmware/efi/runtime-map.c
@@ -0,0 +1,181 @@
+/*
+ * linux/drivers/efi/runtime-map.c
+ * Copyright (C) 2013 Red Hat, Inc., Dave Young <dyoung@redhat.com>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/efi.h>
+#include <linux/slab.h>
+
+#include <asm/setup.h>
+
+static void *efi_runtime_map;
+static int nr_efi_runtime_map;
+static u32 efi_memdesc_size;
+
+struct efi_runtime_map_entry {
+	efi_memory_desc_t md;
+	struct kobject kobj;   /* kobject for each entry */
+};
+
+static struct efi_runtime_map_entry **map_entries;
+
+struct map_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct efi_runtime_map_entry *entry, char *buf);
+};
+
+static inline struct map_attribute *to_map_attr(struct attribute *attr)
+{
+	return container_of(attr, struct map_attribute, attr);
+}
+
+static ssize_t type_show(struct efi_runtime_map_entry *entry, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "0x%x\n", entry->md.type);
+}
+
+#define EFI_RUNTIME_FIELD(var) entry->md.var
+
+#define EFI_RUNTIME_U64_ATTR_SHOW(name) \
+static ssize_t name##_show(struct efi_runtime_map_entry *entry, char *buf) \
+{ \
+	return snprintf(buf, PAGE_SIZE, "0x%llx\n", EFI_RUNTIME_FIELD(name)); \
+}
+
+EFI_RUNTIME_U64_ATTR_SHOW(phys_addr);
+EFI_RUNTIME_U64_ATTR_SHOW(virt_addr);
+EFI_RUNTIME_U64_ATTR_SHOW(num_pages);
+EFI_RUNTIME_U64_ATTR_SHOW(attribute);
+
+static inline struct efi_runtime_map_entry *to_map_entry(struct kobject *kobj)
+{
+	return container_of(kobj, struct efi_runtime_map_entry, kobj);
+}
+
+static ssize_t map_attr_show(struct kobject *kobj, struct attribute *attr,
+			      char *buf)
+{
+	struct efi_runtime_map_entry *entry = to_map_entry(kobj);
+	struct map_attribute *map_attr = to_map_attr(attr);
+
+	return map_attr->show(entry, buf);
+}
+
+static struct map_attribute map_type_attr = __ATTR_RO(type);
+static struct map_attribute map_phys_addr_attr   = __ATTR_RO(phys_addr);
+static struct map_attribute map_virt_addr_attr  = __ATTR_RO(virt_addr);
+static struct map_attribute map_num_pages_attr  = __ATTR_RO(num_pages);
+static struct map_attribute map_attribute_attr  = __ATTR_RO(attribute);
+
+/*
+ * These are default attributes that are added for every memmap entry.
+ */
+static struct attribute *def_attrs[] = {
+	&map_type_attr.attr,
+	&map_phys_addr_attr.attr,
+	&map_virt_addr_attr.attr,
+	&map_num_pages_attr.attr,
+	&map_attribute_attr.attr,
+	NULL
+};
+
+static const struct sysfs_ops map_attr_ops = {
+	.show = map_attr_show,
+};
+
+static void map_release(struct kobject *kobj)
+{
+	struct efi_runtime_map_entry *entry;
+
+	entry = to_map_entry(kobj);
+	kfree(entry);
+}
+
+static struct kobj_type __refdata map_ktype = {
+	.sysfs_ops	= &map_attr_ops,
+	.default_attrs	= def_attrs,
+	.release	= map_release,
+};
+
+static struct kset *map_kset;
+
+static struct efi_runtime_map_entry *
+add_sysfs_runtime_map_entry(struct kobject *kobj, int nr)
+{
+	int ret;
+	struct efi_runtime_map_entry *entry;
+
+	if (!map_kset) {
+		map_kset = kset_create_and_add("runtime-map", NULL, kobj);
+		if (!map_kset)
+			return ERR_PTR(-ENOMEM);
+	}
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry) {
+		kset_unregister(map_kset);
+		return entry;
+	}
+
+	memcpy(&entry->md, efi_runtime_map + nr * efi_memdesc_size,
+	       sizeof(efi_memory_desc_t));
+
+	kobject_init(&entry->kobj, &map_ktype);
+	entry->kobj.kset = map_kset;
+	ret = kobject_add(&entry->kobj, NULL, "%d", nr);
+	if (ret) {
+		kobject_put(&entry->kobj);
+		kset_unregister(map_kset);
+		return ERR_PTR(ret);
+	}
+
+	return entry;
+}
+
+void efi_runtime_map_setup(void *map, int nr_entries, u32 desc_size)
+{
+	efi_runtime_map = map;
+	nr_efi_runtime_map = nr_entries;
+	efi_memdesc_size = desc_size;
+}
+
+int __init efi_runtime_map_init(struct kobject *efi_kobj)
+{
+	int i, j, ret = 0;
+	struct efi_runtime_map_entry *entry;
+
+	if (!efi_runtime_map)
+		return 0;
+
+	map_entries = kzalloc(nr_efi_runtime_map * sizeof(entry), GFP_KERNEL);
+	if (!map_entries) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < nr_efi_runtime_map; i++) {
+		entry = add_sysfs_runtime_map_entry(efi_kobj, i);
+		if (IS_ERR(entry)) {
+			ret = PTR_ERR(entry);
+			goto out_add_entry;
+		}
+		*(map_entries + i) = entry;
+	}
+
+	return 0;
+out_add_entry:
+	for (j = i - 1; j > 0; j--) {
+		entry = *(map_entries + j);
+		kobject_put(&entry->kobj);
+	}
+	if (map_kset)
+		kset_unregister(map_kset);
+out:
+	return ret;
+}
diff --git a/include/linux/efi.h b/include/linux/efi.h
index fb60b10..e645407 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -872,4 +872,17 @@ int efivars_sysfs_init(void);
 
 #endif /* CONFIG_EFI_VARS */
 
+#ifdef CONFIG_EFI_RUNTIME_MAP
+int efi_runtime_map_init(struct kobject *);
+void efi_runtime_map_setup(void *, int, u32);
+#else
+static inline int efi_runtime_map_init(struct kobject *kobj)
+{
+	return 0;
+}
+
+static inline void
+efi_runtime_map_setup(void *map, int nr_entries, u32 desc_size) {}
+#endif
+
 #endif /* _LINUX_EFI_H */
-- 
cgit v0.10.2


From a68f9614614749727286f675d15f1e09d13cb54a Mon Sep 17 00:00:00 2001
From: Haiyang Zhang <haiyangz@microsoft.com>
Date: Fri, 20 Dec 2013 16:52:31 -0800
Subject: hyperv: Fix race between probe and open calls

Moving the register_netdev to the end of probe to prevent
possible open call happens before NetVSP is connected.

Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index f813572..71baeb3 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -261,9 +261,7 @@ int netvsc_recv_callback(struct hv_device *device_obj,
 	struct sk_buff *skb;
 
 	net = ((struct netvsc_device *)hv_get_drvdata(device_obj))->ndev;
-	if (!net) {
-		netdev_err(net, "got receive callback but net device"
-			" not initialized yet\n");
+	if (!net || net->reg_state != NETREG_REGISTERED) {
 		packet->status = NVSP_STAT_FAIL;
 		return 0;
 	}
@@ -435,19 +433,11 @@ static int netvsc_probe(struct hv_device *dev,
 	SET_ETHTOOL_OPS(net, &ethtool_ops);
 	SET_NETDEV_DEV(net, &dev->device);
 
-	ret = register_netdev(net);
-	if (ret != 0) {
-		pr_err("Unable to register netdev.\n");
-		free_netdev(net);
-		goto out;
-	}
-
 	/* Notify the netvsc driver of the new device */
 	device_info.ring_size = ring_size;
 	ret = rndis_filter_device_add(dev, &device_info);
 	if (ret != 0) {
 		netdev_err(net, "unable to add netvsc device (ret %d)\n", ret);
-		unregister_netdev(net);
 		free_netdev(net);
 		hv_set_drvdata(dev, NULL);
 		return ret;
@@ -456,7 +446,13 @@ static int netvsc_probe(struct hv_device *dev,
 
 	netif_carrier_on(net);
 
-out:
+	ret = register_netdev(net);
+	if (ret != 0) {
+		pr_err("Unable to register netdev.\n");
+		rndis_filter_device_remove(dev);
+		free_netdev(net);
+	}
+
 	return ret;
 }
 
-- 
cgit v0.10.2


From b6f8eaece6d5f0247931b6dac140e6cf876f48de Mon Sep 17 00:00:00 2001
From: Kumar Sanghvi <kumaras@chelsio.com>
Date: Wed, 18 Dec 2013 16:38:19 +0530
Subject: cxgb4: Reserve stid 0 for T4/T5 adapters

When creating offload server entries, an IPv6 passive connection request
can trigger a reply with a null STID, whereas the driver would expect
the reply 'STID to match the value used for the request.
This happens due to h/w limitation on T4 and T5.

This patch ensures that STID 0 is never used if the stid range starts
from zero.

Based on original work by Santosh Rastapur <santosh@chelsio.com>

Signed-off-by: Kumar Sanghvi <kumaras@chelsio.com>
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index d6b12e0..f36f8e1 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -3134,6 +3134,7 @@ static int tid_init(struct tid_info *t)
 	size_t size;
 	unsigned int stid_bmap_size;
 	unsigned int natids = t->natids;
+	struct adapter *adap = container_of(t, struct adapter, tids);
 
 	stid_bmap_size = BITS_TO_LONGS(t->nstids + t->nsftids);
 	size = t->ntids * sizeof(*t->tid_tab) +
@@ -3167,6 +3168,11 @@ static int tid_init(struct tid_info *t)
 		t->afree = t->atid_tab;
 	}
 	bitmap_zero(t->stid_bmap, t->nstids + t->nsftids);
+	/* Reserve stid 0 for T4/T5 adapters */
+	if (!t->stid_base &&
+	    (is_t4(adap->params.chip) || is_t5(adap->params.chip)))
+		__set_bit(0, t->stid_bmap);
+
 	return 0;
 }
 
-- 
cgit v0.10.2


From 7c89e5550ccb2a3118854639d9525847e896c686 Mon Sep 17 00:00:00 2001
From: Kumar Sanghvi <kumaras@chelsio.com>
Date: Wed, 18 Dec 2013 16:38:20 +0530
Subject: cxgb4: Include TCP as protocol when creating server filters

We were creating LE Workaround Server Filters without specifying
IPPROTO_TCP (6) in the filters (when F_PROTOCOL is set in TP_VLAN_PRI_MAP).
This meant that UDP packets with matching IP Addresses/Ports would get
caught up in the filter and be delivered to ULDs like iw_cxgb4.
So, include the protocol information in the server filter properly.

Based on original work by Casey Leedom <leedom@chelsio.com>

Signed-off-by: Kumar Sanghvi <kumaras@chelsio.com>
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index f36f8e1..df1d6b8 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -4217,6 +4217,11 @@ int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
 		}
 	}
 
+	if (adap->filter_mode & F_PROTOCOL) {
+		f->fs.val.proto = IPPROTO_TCP;
+		f->fs.mask.proto = ~0;
+	}
+
 	f->fs.dirsteer = 1;
 	f->fs.iq = queue;
 	/* Mark filter as locked */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index 0a8205d..d3dd218 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -1171,6 +1171,10 @@
 
 #define A_TP_TX_SCHED_PCMD 0x25
 
+#define S_PROTOCOL    5
+#define V_PROTOCOL(x) ((x) << S_PROTOCOL)
+#define F_PROTOCOL    V_PROTOCOL(1U)
+
 #define S_PORT    1
 #define V_PORT(x) ((x) << S_PORT)
 #define F_PORT    V_PORT(1U)
-- 
cgit v0.10.2


From 470c60c47a03f74f0ec1a83576eb6000025634a9 Mon Sep 17 00:00:00 2001
From: Kumar Sanghvi <kumaras@chelsio.com>
Date: Wed, 18 Dec 2013 16:38:21 +0530
Subject: cxgb4: Assign filter server TIDs properly

The LE workaround code is incorrectly reusing the TCAM TIDs
(meant for allocation by firmware in case of hash collisions) for filter
servers. This patch assigns the filter server TIDs properly starting from
sftid_base index.

Based on original work by Santosh Rastapur <santosh@chelsio.com>

Signed-off-by: Kumar Sanghvi <kumaras@chelsio.com>
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index df1d6b8..f4f46fc 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -3012,7 +3012,8 @@ int cxgb4_alloc_sftid(struct tid_info *t, int family, void *data)
 	}
 	if (stid >= 0) {
 		t->stid_tab[stid].data = data;
-		stid += t->stid_base;
+		stid -= t->nstids;
+		stid += t->sftid_base;
 		t->stids_in_use++;
 	}
 	spin_unlock_bh(&t->stid_lock);
@@ -3024,7 +3025,14 @@ EXPORT_SYMBOL(cxgb4_alloc_sftid);
  */
 void cxgb4_free_stid(struct tid_info *t, unsigned int stid, int family)
 {
-	stid -= t->stid_base;
+	/* Is it a server filter TID? */
+	if (t->nsftids && (stid >= t->sftid_base)) {
+		stid -= t->sftid_base;
+		stid += t->nstids;
+	} else {
+		stid -= t->stid_base;
+	}
+
 	spin_lock_bh(&t->stid_lock);
 	if (family == PF_INET)
 		__clear_bit(stid, t->stid_bmap);
@@ -4185,7 +4193,7 @@ int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
 	adap = netdev2adap(dev);
 
 	/* Adjust stid to correct filter index */
-	stid -= adap->tids.nstids;
+	stid -= adap->tids.sftid_base;
 	stid += adap->tids.nftids;
 
 	/* Check to make sure the filter requested is writable ...
@@ -4248,7 +4256,7 @@ int cxgb4_remove_server_filter(const struct net_device *dev, unsigned int stid,
 	adap = netdev2adap(dev);
 
 	/* Adjust stid to correct filter index */
-	stid -= adap->tids.nstids;
+	stid -= adap->tids.sftid_base;
 	stid += adap->tids.nftids;
 
 	f = &adap->tids.ftid_tab[stid];
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index 6f21f24..4dd0a82 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -131,7 +131,14 @@ static inline void *lookup_atid(const struct tid_info *t, unsigned int atid)
 
 static inline void *lookup_stid(const struct tid_info *t, unsigned int stid)
 {
-	stid -= t->stid_base;
+	/* Is it a server filter TID? */
+	if (t->nsftids && (stid >= t->sftid_base)) {
+		stid -= t->sftid_base;
+		stid += t->nstids;
+	} else {
+		stid -= t->stid_base;
+	}
+
 	return stid < (t->nstids + t->nsftids) ? t->stid_tab[stid].data : NULL;
 }
 
-- 
cgit v0.10.2


From 15f63b74c25797f9246b1738f0cfabd5febe226e Mon Sep 17 00:00:00 2001
From: Kumar Sanghvi <kumaras@chelsio.com>
Date: Wed, 18 Dec 2013 16:38:22 +0530
Subject: cxgb4: Account for stid entries properly in case of IPv6

IPv6 uses 2 TIDs with CLIP enabled and 4 TIDs without CLIP.
Currently we are incrementing STIDs in use by 1 for both IPv4 and IPv6 which
is wrong.

Further, driver currently does not have interface to query if CLIP is programmed
for particular IPv6 address. So, in this patch we increment/decrement TIDs in use
by 4 for IPv6 assuming absence of CLIP. Such assumption keeps us on safe side and
we don't end up allocating more stids for IPv6 than actually supported.

Based on original work by Santosh Rastapur <santosh@chelsio.com>

Signed-off-by: Kumar Sanghvi <kumaras@chelsio.com>
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index f4f46fc..f9ca36c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -2986,7 +2986,14 @@ int cxgb4_alloc_stid(struct tid_info *t, int family, void *data)
 	if (stid >= 0) {
 		t->stid_tab[stid].data = data;
 		stid += t->stid_base;
-		t->stids_in_use++;
+		/* IPv6 requires max of 520 bits or 16 cells in TCAM
+		 * This is equivalent to 4 TIDs. With CLIP enabled it
+		 * needs 2 TIDs.
+		 */
+		if (family == PF_INET)
+			t->stids_in_use++;
+		else
+			t->stids_in_use += 4;
 	}
 	spin_unlock_bh(&t->stid_lock);
 	return stid;
@@ -3039,7 +3046,10 @@ void cxgb4_free_stid(struct tid_info *t, unsigned int stid, int family)
 	else
 		bitmap_release_region(t->stid_bmap, stid, 2);
 	t->stid_tab[stid].data = NULL;
-	t->stids_in_use--;
+	if (family == PF_INET)
+		t->stids_in_use--;
+	else
+		t->stids_in_use -= 4;
 	spin_unlock_bh(&t->stid_lock);
 }
 EXPORT_SYMBOL(cxgb4_free_stid);
-- 
cgit v0.10.2


From dcf7b6f5bdeaa13d5e465d8795d2e7d6d1e27b65 Mon Sep 17 00:00:00 2001
From: Kumar Sanghvi <kumaras@chelsio.com>
Date: Wed, 18 Dec 2013 16:38:23 +0530
Subject: cxgb4: Add API to correctly calculate tuple fields

Adds API cxgb4_select_ntuple so as to enable Upper Level Drivers to correctly
calculate the tuple fields.

Adds constant definitions for TP_VLAN_PRI_MAP for the Compressed
Filter Tuple field widths and structures and uses them.

Also, the CPL Parameters field for T5 is 40 bits so we need to prototype
cxgb4_select_ntuple() to calculate and return u64 values.

Based on original work by Casey Leedom <leedom@chelsio.com>

Signed-off-by: Kumar Sanghvi <kumaras@chelsio.com>
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 6c93088..56e0415 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -228,6 +228,25 @@ struct tp_params {
 
 	uint32_t dack_re;            /* DACK timer resolution */
 	unsigned short tx_modq[NCHAN];	/* channel to modulation queue map */
+
+	u32 vlan_pri_map;               /* cached TP_VLAN_PRI_MAP */
+	u32 ingress_config;             /* cached TP_INGRESS_CONFIG */
+
+	/* TP_VLAN_PRI_MAP Compressed Filter Tuple field offsets.  This is a
+	 * subset of the set of fields which may be present in the Compressed
+	 * Filter Tuple portion of filters and TCP TCB connections.  The
+	 * fields which are present are controlled by the TP_VLAN_PRI_MAP.
+	 * Since a variable number of fields may or may not be present, their
+	 * shifted field positions within the Compressed Filter Tuple may
+	 * vary, or not even be present if the field isn't selected in
+	 * TP_VLAN_PRI_MAP.  Since some of these fields are needed in various
+	 * places we store their offsets here, or a -1 if the field isn't
+	 * present.
+	 */
+	int vlan_shift;
+	int vnic_shift;
+	int port_shift;
+	int protocol_shift;
 };
 
 struct vpd_params {
@@ -926,6 +945,8 @@ int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info,
 	       const u8 *fw_data, unsigned int fw_size,
 	       struct fw_hdr *card_fw, enum dev_state state, int *reset);
 int t4_prep_adapter(struct adapter *adapter);
+int t4_init_tp_params(struct adapter *adap);
+int t4_filter_field_shift(const struct adapter *adap, int filter_sel);
 int t4_port_init(struct adapter *adap, int mbox, int pf, int vf);
 void t4_fatal_err(struct adapter *adapter);
 int t4_config_rss_range(struct adapter *adapter, int mbox, unsigned int viid,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index f9ca36c..fff02ed 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -3755,7 +3755,7 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
 	lli.ucq_density = 1 << QUEUESPERPAGEPF0_GET(
 			t4_read_reg(adap, SGE_INGRESS_QUEUES_PER_PAGE_PF) >>
 			(adap->fn * 4));
-	lli.filt_mode = adap->filter_mode;
+	lli.filt_mode = adap->params.tp.vlan_pri_map;
 	/* MODQ_REQ_MAP sets queues 0-3 to chan 0-3 */
 	for (i = 0; i < NCHAN; i++)
 		lli.tx_modq[i] = i;
@@ -4229,13 +4229,13 @@ int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
 			f->fs.val.lip[i] = val[i];
 			f->fs.mask.lip[i] = ~0;
 		}
-		if (adap->filter_mode & F_PORT) {
+		if (adap->params.tp.vlan_pri_map & F_PORT) {
 			f->fs.val.iport = port;
 			f->fs.mask.iport = mask;
 		}
 	}
 
-	if (adap->filter_mode & F_PROTOCOL) {
+	if (adap->params.tp.vlan_pri_map & F_PROTOCOL) {
 		f->fs.val.proto = IPPROTO_TCP;
 		f->fs.mask.proto = ~0;
 	}
@@ -5121,7 +5121,7 @@ static int adap_init0(struct adapter *adap)
 	enum dev_state state;
 	u32 params[7], val[7];
 	struct fw_caps_config_cmd caps_cmd;
-	int reset = 1, j;
+	int reset = 1;
 
 	/*
 	 * Contact FW, advertising Master capability (and potentially forcing
@@ -5463,21 +5463,11 @@ static int adap_init0(struct adapter *adap)
 	/*
 	 * These are finalized by FW initialization, load their values now.
 	 */
-	v = t4_read_reg(adap, TP_TIMER_RESOLUTION);
-	adap->params.tp.tre = TIMERRESOLUTION_GET(v);
-	adap->params.tp.dack_re = DELAYEDACKRESOLUTION_GET(v);
 	t4_read_mtu_tbl(adap, adap->params.mtus, NULL);
 	t4_load_mtus(adap, adap->params.mtus, adap->params.a_wnd,
 		     adap->params.b_wnd);
 
-	/* MODQ_REQ_MAP defaults to setting queues 0-3 to chan 0-3 */
-	for (j = 0; j < NCHAN; j++)
-		adap->params.tp.tx_modq[j] = j;
-
-	t4_read_indirect(adap, TP_PIO_ADDR, TP_PIO_DATA,
-			 &adap->filter_mode, 1,
-			 TP_VLAN_PRI_MAP);
-
+	t4_init_tp_params(adap);
 	adap->flags |= FW_OK;
 	return 0;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
index 2987809..cb05be9 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
@@ -45,6 +45,7 @@
 #include "l2t.h"
 #include "t4_msg.h"
 #include "t4fw_api.h"
+#include "t4_regs.h"
 
 #define VLAN_NONE 0xfff
 
@@ -411,6 +412,40 @@ done:
 }
 EXPORT_SYMBOL(cxgb4_l2t_get);
 
+u64 cxgb4_select_ntuple(struct net_device *dev,
+			const struct l2t_entry *l2t)
+{
+	struct adapter *adap = netdev2adap(dev);
+	struct tp_params *tp = &adap->params.tp;
+	u64 ntuple = 0;
+
+	/* Initialize each of the fields which we care about which are present
+	 * in the Compressed Filter Tuple.
+	 */
+	if (tp->vlan_shift >= 0 && l2t->vlan != VLAN_NONE)
+		ntuple |= (F_FT_VLAN_VLD | l2t->vlan) << tp->vlan_shift;
+
+	if (tp->port_shift >= 0)
+		ntuple |= (u64)l2t->lport << tp->port_shift;
+
+	if (tp->protocol_shift >= 0)
+		ntuple |= (u64)IPPROTO_TCP << tp->protocol_shift;
+
+	if (tp->vnic_shift >= 0) {
+		u32 viid = cxgb4_port_viid(dev);
+		u32 vf = FW_VIID_VIN_GET(viid);
+		u32 pf = FW_VIID_PFN_GET(viid);
+		u32 vld = FW_VIID_VIVLD_GET(viid);
+
+		ntuple |= (u64)(V_FT_VNID_ID_VF(vf) |
+				V_FT_VNID_ID_PF(pf) |
+				V_FT_VNID_ID_VLD(vld)) << tp->vnic_shift;
+	}
+
+	return ntuple;
+}
+EXPORT_SYMBOL(cxgb4_select_ntuple);
+
 /*
  * Called when address resolution fails for an L2T entry to handle packets
  * on the arpq head.  If a packet specifies a failure handler it is invoked,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.h b/drivers/net/ethernet/chelsio/cxgb4/l2t.h
index 108c0f1..85eb5c7 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.h
@@ -98,7 +98,8 @@ int cxgb4_l2t_send(struct net_device *dev, struct sk_buff *skb,
 struct l2t_entry *cxgb4_l2t_get(struct l2t_data *d, struct neighbour *neigh,
 				const struct net_device *physdev,
 				unsigned int priority);
-
+u64 cxgb4_select_ntuple(struct net_device *dev,
+			const struct l2t_entry *l2t);
 void t4_l2t_update(struct adapter *adap, struct neighbour *neigh);
 struct l2t_entry *t4_l2t_alloc_switching(struct l2t_data *d);
 int t4_l2t_set_switching(struct adapter *adap, struct l2t_entry *e, u16 vlan,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 74a6fce..e1413ea 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -3808,6 +3808,109 @@ int t4_prep_adapter(struct adapter *adapter)
 	return 0;
 }
 
+/**
+ *      t4_init_tp_params - initialize adap->params.tp
+ *      @adap: the adapter
+ *
+ *      Initialize various fields of the adapter's TP Parameters structure.
+ */
+int t4_init_tp_params(struct adapter *adap)
+{
+	int chan;
+	u32 v;
+
+	v = t4_read_reg(adap, TP_TIMER_RESOLUTION);
+	adap->params.tp.tre = TIMERRESOLUTION_GET(v);
+	adap->params.tp.dack_re = DELAYEDACKRESOLUTION_GET(v);
+
+	/* MODQ_REQ_MAP defaults to setting queues 0-3 to chan 0-3 */
+	for (chan = 0; chan < NCHAN; chan++)
+		adap->params.tp.tx_modq[chan] = chan;
+
+	/* Cache the adapter's Compressed Filter Mode and global Incress
+	 * Configuration.
+	 */
+	t4_read_indirect(adap, TP_PIO_ADDR, TP_PIO_DATA,
+			 &adap->params.tp.vlan_pri_map, 1,
+			 TP_VLAN_PRI_MAP);
+	t4_read_indirect(adap, TP_PIO_ADDR, TP_PIO_DATA,
+			 &adap->params.tp.ingress_config, 1,
+			 TP_INGRESS_CONFIG);
+
+	/* Now that we have TP_VLAN_PRI_MAP cached, we can calculate the field
+	 * shift positions of several elements of the Compressed Filter Tuple
+	 * for this adapter which we need frequently ...
+	 */
+	adap->params.tp.vlan_shift = t4_filter_field_shift(adap, F_VLAN);
+	adap->params.tp.vnic_shift = t4_filter_field_shift(adap, F_VNIC_ID);
+	adap->params.tp.port_shift = t4_filter_field_shift(adap, F_PORT);
+	adap->params.tp.protocol_shift = t4_filter_field_shift(adap,
+							       F_PROTOCOL);
+
+	/* If TP_INGRESS_CONFIG.VNID == 0, then TP_VLAN_PRI_MAP.VNIC_ID
+	 * represents the presense of an Outer VLAN instead of a VNIC ID.
+	 */
+	if ((adap->params.tp.ingress_config & F_VNIC) == 0)
+		adap->params.tp.vnic_shift = -1;
+
+	return 0;
+}
+
+/**
+ *      t4_filter_field_shift - calculate filter field shift
+ *      @adap: the adapter
+ *      @filter_sel: the desired field (from TP_VLAN_PRI_MAP bits)
+ *
+ *      Return the shift position of a filter field within the Compressed
+ *      Filter Tuple.  The filter field is specified via its selection bit
+ *      within TP_VLAN_PRI_MAL (filter mode).  E.g. F_VLAN.
+ */
+int t4_filter_field_shift(const struct adapter *adap, int filter_sel)
+{
+	unsigned int filter_mode = adap->params.tp.vlan_pri_map;
+	unsigned int sel;
+	int field_shift;
+
+	if ((filter_mode & filter_sel) == 0)
+		return -1;
+
+	for (sel = 1, field_shift = 0; sel < filter_sel; sel <<= 1) {
+		switch (filter_mode & sel) {
+		case F_FCOE:
+			field_shift += W_FT_FCOE;
+			break;
+		case F_PORT:
+			field_shift += W_FT_PORT;
+			break;
+		case F_VNIC_ID:
+			field_shift += W_FT_VNIC_ID;
+			break;
+		case F_VLAN:
+			field_shift += W_FT_VLAN;
+			break;
+		case F_TOS:
+			field_shift += W_FT_TOS;
+			break;
+		case F_PROTOCOL:
+			field_shift += W_FT_PROTOCOL;
+			break;
+		case F_ETHERTYPE:
+			field_shift += W_FT_ETHERTYPE;
+			break;
+		case F_MACMATCH:
+			field_shift += W_FT_MACMATCH;
+			break;
+		case F_MPSHITTYPE:
+			field_shift += W_FT_MPSHITTYPE;
+			break;
+		case F_FRAGMENTATION:
+			field_shift += W_FT_FRAGMENTATION;
+			break;
+		}
+	}
+	return field_shift;
+}
+
 int t4_port_init(struct adapter *adap, int mbox, int pf, int vf)
 {
 	u8 addr[6];
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index d3dd218..4082522 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -1171,14 +1171,50 @@
 
 #define A_TP_TX_SCHED_PCMD 0x25
 
+#define S_VNIC    11
+#define V_VNIC(x) ((x) << S_VNIC)
+#define F_VNIC    V_VNIC(1U)
+
+#define S_FRAGMENTATION    9
+#define V_FRAGMENTATION(x) ((x) << S_FRAGMENTATION)
+#define F_FRAGMENTATION    V_FRAGMENTATION(1U)
+
+#define S_MPSHITTYPE    8
+#define V_MPSHITTYPE(x) ((x) << S_MPSHITTYPE)
+#define F_MPSHITTYPE    V_MPSHITTYPE(1U)
+
+#define S_MACMATCH    7
+#define V_MACMATCH(x) ((x) << S_MACMATCH)
+#define F_MACMATCH    V_MACMATCH(1U)
+
+#define S_ETHERTYPE    6
+#define V_ETHERTYPE(x) ((x) << S_ETHERTYPE)
+#define F_ETHERTYPE    V_ETHERTYPE(1U)
+
 #define S_PROTOCOL    5
 #define V_PROTOCOL(x) ((x) << S_PROTOCOL)
 #define F_PROTOCOL    V_PROTOCOL(1U)
 
+#define S_TOS    4
+#define V_TOS(x) ((x) << S_TOS)
+#define F_TOS    V_TOS(1U)
+
+#define S_VLAN    3
+#define V_VLAN(x) ((x) << S_VLAN)
+#define F_VLAN    V_VLAN(1U)
+
+#define S_VNIC_ID    2
+#define V_VNIC_ID(x) ((x) << S_VNIC_ID)
+#define F_VNIC_ID    V_VNIC_ID(1U)
+
 #define S_PORT    1
 #define V_PORT(x) ((x) << S_PORT)
 #define F_PORT    V_PORT(1U)
 
+#define S_FCOE    0
+#define V_FCOE(x) ((x) << S_FCOE)
+#define F_FCOE    V_FCOE(1U)
+
 #define NUM_MPS_CLS_SRAM_L_INSTANCES 336
 #define NUM_MPS_T5_CLS_SRAM_L_INSTANCES 512
 
@@ -1217,4 +1253,37 @@
 #define V_CHIPID(x) ((x) << S_CHIPID)
 #define G_CHIPID(x) (((x) >> S_CHIPID) & M_CHIPID)
 
+/* TP_VLAN_PRI_MAP controls which subset of fields will be present in the
+ * Compressed Filter Tuple for LE filters.  Each bit set in TP_VLAN_PRI_MAP
+ * selects for a particular field being present.  These fields, when present
+ * in the Compressed Filter Tuple, have the following widths in bits.
+ */
+#define W_FT_FCOE                       1
+#define W_FT_PORT                       3
+#define W_FT_VNIC_ID                    17
+#define W_FT_VLAN                       17
+#define W_FT_TOS                        8
+#define W_FT_PROTOCOL                   8
+#define W_FT_ETHERTYPE                  16
+#define W_FT_MACMATCH                   9
+#define W_FT_MPSHITTYPE                 3
+#define W_FT_FRAGMENTATION              1
+
+/* Some of the Compressed Filter Tuple fields have internal structure.  These
+ * bit shifts/masks describe those structures.  All shifts are relative to the
+ * base position of the fields within the Compressed Filter Tuple
+ */
+#define S_FT_VLAN_VLD                   16
+#define V_FT_VLAN_VLD(x)                ((x) << S_FT_VLAN_VLD)
+#define F_FT_VLAN_VLD                   V_FT_VLAN_VLD(1U)
+
+#define S_FT_VNID_ID_VF                 0
+#define V_FT_VNID_ID_VF(x)              ((x) << S_FT_VNID_ID_VF)
+
+#define S_FT_VNID_ID_PF                 7
+#define V_FT_VNID_ID_PF(x)              ((x) << S_FT_VNID_ID_PF)
+
+#define S_FT_VNID_ID_VLD                16
+#define V_FT_VNID_ID_VLD(x)             ((x) << S_FT_VNID_ID_VLD)
+
 #endif /* __T4_REGS_H */
-- 
cgit v0.10.2


From a4ea025fc24532bae8a038d038f8e0f15b8a7d98 Mon Sep 17 00:00:00 2001
From: Kumar Sanghvi <kumaras@chelsio.com>
Date: Wed, 18 Dec 2013 16:38:24 +0530
Subject: RDMA/cxgb4: Calculate the filter server TID properly

Based on original work by Santosh Rastapur <santosh@chelsio.com>

Signed-off-by: Kumar Sanghvi <kumaras@chelsio.com>
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 12fef76..02c7515 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -3323,9 +3323,7 @@ static int rx_pkt(struct c4iw_dev *dev, struct sk_buff *skb)
 	/*
 	 * Calculate the server tid from filter hit index from cpl_rx_pkt.
 	 */
-	stid = (__force int) cpu_to_be32((__force u32) rss->hash_val)
-					  - dev->rdev.lldi.tids->sftid_base
-					  + dev->rdev.lldi.tids->nstids;
+	stid = (__force int) cpu_to_be32((__force u32) rss->hash_val);
 
 	lep = (struct c4iw_ep *)lookup_stid(dev->rdev.lldi.tids, stid);
 	if (!lep) {
-- 
cgit v0.10.2


From 8c04469057c3307d92d2c7076edcf9eb8f752bca Mon Sep 17 00:00:00 2001
From: Kumar Sanghvi <kumaras@chelsio.com>
Date: Wed, 18 Dec 2013 16:38:25 +0530
Subject: RDMA/cxgb4: Server filters are supported only for IPv4

Signed-off-by: Kumar Sanghvi <kumaras@chelsio.com>
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 02c7515..bfd4ed7 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -2938,7 +2938,8 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog)
 	/*
 	 * Allocate a server TID.
 	 */
-	if (dev->rdev.lldi.enable_fw_ofld_conn)
+	if (dev->rdev.lldi.enable_fw_ofld_conn &&
+	    ep->com.local_addr.ss_family == AF_INET)
 		ep->stid = cxgb4_alloc_sftid(dev->rdev.lldi.tids,
 					     cm_id->local_addr.ss_family, ep);
 	else
-- 
cgit v0.10.2


From 41b4f86c1368758a02129e0629a9cc7c2811fa32 Mon Sep 17 00:00:00 2001
From: Kumar Sanghvi <kumaras@chelsio.com>
Date: Wed, 18 Dec 2013 16:38:26 +0530
Subject: RDMA/cxgb4: Use cxgb4_select_ntuple to correctly calculate ntuple
 fields

Signed-off-by: Kumar Sanghvi <kumaras@chelsio.com>
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index bfd4ed7..4512687 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -524,50 +524,6 @@ static int send_abort(struct c4iw_ep *ep, struct sk_buff *skb, gfp_t gfp)
 	return c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
 }
 
-#define VLAN_NONE 0xfff
-#define FILTER_SEL_VLAN_NONE 0xffff
-#define FILTER_SEL_WIDTH_P_FC (3+1) /* port uses 3 bits, FCoE one bit */
-#define FILTER_SEL_WIDTH_VIN_P_FC \
-	(6 + 7 + FILTER_SEL_WIDTH_P_FC) /* 6 bits are unused, VF uses 7 bits*/
-#define FILTER_SEL_WIDTH_TAG_P_FC \
-	(3 + FILTER_SEL_WIDTH_VIN_P_FC) /* PF uses 3 bits */
-#define FILTER_SEL_WIDTH_VLD_TAG_P_FC (1 + FILTER_SEL_WIDTH_TAG_P_FC)
-
-static unsigned int select_ntuple(struct c4iw_dev *dev, struct dst_entry *dst,
-				  struct l2t_entry *l2t)
-{
-	unsigned int ntuple = 0;
-	u32 viid;
-
-	switch (dev->rdev.lldi.filt_mode) {
-
-	/* default filter mode */
-	case HW_TPL_FR_MT_PR_IV_P_FC:
-		if (l2t->vlan == VLAN_NONE)
-			ntuple |= FILTER_SEL_VLAN_NONE << FILTER_SEL_WIDTH_P_FC;
-		else {
-			ntuple |= l2t->vlan << FILTER_SEL_WIDTH_P_FC;
-			ntuple |= 1 << FILTER_SEL_WIDTH_TAG_P_FC;
-		}
-		ntuple |= l2t->lport << S_PORT | IPPROTO_TCP <<
-			  FILTER_SEL_WIDTH_VLD_TAG_P_FC;
-		break;
-	case HW_TPL_FR_MT_PR_OV_P_FC: {
-		viid = cxgb4_port_viid(l2t->neigh->dev);
-
-		ntuple |= FW_VIID_VIN_GET(viid) << FILTER_SEL_WIDTH_P_FC;
-		ntuple |= FW_VIID_PFN_GET(viid) << FILTER_SEL_WIDTH_VIN_P_FC;
-		ntuple |= FW_VIID_VIVLD_GET(viid) << FILTER_SEL_WIDTH_TAG_P_FC;
-		ntuple |= l2t->lport << S_PORT | IPPROTO_TCP <<
-			  FILTER_SEL_WIDTH_VLD_TAG_P_FC;
-		break;
-	}
-	default:
-		break;
-	}
-	return ntuple;
-}
-
 static int send_connect(struct c4iw_ep *ep)
 {
 	struct cpl_act_open_req *req;
@@ -641,8 +597,9 @@ static int send_connect(struct c4iw_ep *ep)
 			req->local_ip = la->sin_addr.s_addr;
 			req->peer_ip = ra->sin_addr.s_addr;
 			req->opt0 = cpu_to_be64(opt0);
-			req->params = cpu_to_be32(select_ntuple(ep->com.dev,
-						ep->dst, ep->l2t));
+			req->params = cpu_to_be32(cxgb4_select_ntuple(
+						ep->com.dev->rdev.lldi.ports[0],
+						ep->l2t));
 			req->opt2 = cpu_to_be32(opt2);
 		} else {
 			req6 = (struct cpl_act_open_req6 *)skb_put(skb, wrlen);
@@ -662,9 +619,9 @@ static int send_connect(struct c4iw_ep *ep)
 			req6->peer_ip_lo = *((__be64 *)
 						(ra6->sin6_addr.s6_addr + 8));
 			req6->opt0 = cpu_to_be64(opt0);
-			req6->params = cpu_to_be32(
-					select_ntuple(ep->com.dev, ep->dst,
-						      ep->l2t));
+			req6->params = cpu_to_be32(cxgb4_select_ntuple(
+						ep->com.dev->rdev.lldi.ports[0],
+						ep->l2t));
 			req6->opt2 = cpu_to_be32(opt2);
 		}
 	} else {
@@ -681,8 +638,9 @@ static int send_connect(struct c4iw_ep *ep)
 			t5_req->peer_ip = ra->sin_addr.s_addr;
 			t5_req->opt0 = cpu_to_be64(opt0);
 			t5_req->params = cpu_to_be64(V_FILTER_TUPLE(
-						select_ntuple(ep->com.dev,
-						ep->dst, ep->l2t)));
+						     cxgb4_select_ntuple(
+					     ep->com.dev->rdev.lldi.ports[0],
+					     ep->l2t)));
 			t5_req->opt2 = cpu_to_be32(opt2);
 		} else {
 			t5_req6 = (struct cpl_t5_act_open_req6 *)
@@ -703,7 +661,9 @@ static int send_connect(struct c4iw_ep *ep)
 						(ra6->sin6_addr.s6_addr + 8));
 			t5_req6->opt0 = cpu_to_be64(opt0);
 			t5_req6->params = (__force __be64)cpu_to_be32(
-				select_ntuple(ep->com.dev, ep->dst, ep->l2t));
+							cxgb4_select_ntuple(
+						ep->com.dev->rdev.lldi.ports[0],
+						ep->l2t));
 			t5_req6->opt2 = cpu_to_be32(opt2);
 		}
 	}
@@ -1630,7 +1590,8 @@ static void send_fw_act_open_req(struct c4iw_ep *ep, unsigned int atid)
 	memset(req, 0, sizeof(*req));
 	req->op_compl = htonl(V_WR_OP(FW_OFLD_CONNECTION_WR));
 	req->len16_pkd = htonl(FW_WR_LEN16(DIV_ROUND_UP(sizeof(*req), 16)));
-	req->le.filter = cpu_to_be32(select_ntuple(ep->com.dev, ep->dst,
+	req->le.filter = cpu_to_be32(cxgb4_select_ntuple(
+				     ep->com.dev->rdev.lldi.ports[0],
 				     ep->l2t));
 	sin = (struct sockaddr_in *)&ep->com.local_addr;
 	req->le.lport = sin->sin_port;
@@ -3396,7 +3357,9 @@ static int rx_pkt(struct c4iw_dev *dev, struct sk_buff *skb)
 	window = (__force u16) htons((__force u16)tcph->window);
 
 	/* Calcuate filter portion for LE region. */
-	filter = (__force unsigned int) cpu_to_be32(select_ntuple(dev, dst, e));
+	filter = (__force unsigned int) cpu_to_be32(cxgb4_select_ntuple(
+						    dev->rdev.lldi.ports[0],
+						    e));
 
 	/*
 	 * Synthesize the cpl_pass_accept_req. We have everything except the
-- 
cgit v0.10.2


From db850559a303dc9459d7dd7339bd19a66907a15a Mon Sep 17 00:00:00 2001
From: Mugunthan V N <mugunthanvnm@ti.com>
Date: Wed, 18 Dec 2013 21:33:50 +0530
Subject: drivers: net : cpsw: pass proper device name while requesting irq

During checking the interrupts with "cat /proc/interrupts", it is showing
device name as (null), this change was done with commit id aa1a15e2d where
request_irq is changed to devm_request_irq also changing the irq name from
platform device name to net device name, but the net device is not
registered at this point with the network frame work, so devm_request_irq
is called with device name as NULL, by which it is showed as "(null)" in
"cat /proc/interrupts". So this patch changes back irq name to platform
device name itself in devm_request_irq so that the device name shows as
below.

Previous to this patch
root@am335x-evm:~# cat /proc/interrupts
           CPU0
 28:       2265      INTC  12  edma
 30:         80      INTC  14  edma_error
 56:          0      INTC  40  (null)
 57:       1794      INTC  41  (null)
 58:          7      INTC  42  (null)
 59:          0      INTC  43  (null)

With this patch
root@am335x-evm:~# cat /proc/interrupts
           CPU0
 28:        213      INTC  12  edma
 30:          9      INTC  14  edma_error
 56:          0      INTC  40  4a100000.ethernet
 57:      16097      INTC  41  4a100000.ethernet
 58:      11964      INTC  42  4a100000.ethernet
 59:          0      INTC  43  4a100000.ethernet

Signed-off-by: Mugunthan V N <mugunthanvnm@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 614f284..5330fd2 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -2108,7 +2108,7 @@ static int cpsw_probe(struct platform_device *pdev)
 	while ((res = platform_get_resource(priv->pdev, IORESOURCE_IRQ, k))) {
 		for (i = res->start; i <= res->end; i++) {
 			if (devm_request_irq(&pdev->dev, i, cpsw_interrupt, 0,
-					     dev_name(priv->dev), priv)) {
+					     dev_name(&pdev->dev), priv)) {
 				dev_err(priv->dev, "error attaching irq\n");
 				goto clean_ale_ret;
 			}
-- 
cgit v0.10.2


From 61e7f09d0f437c9614029445754099383ec2eec4 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Thu, 19 Dec 2013 02:13:36 +0100
Subject: ipv4: consistent reporting of pmtu data in case of corking

We report different pmtu values back on the first write and on further
writes on an corked socket.

Also don't include the dst.header_len (respectively exthdrlen) as this
should already be dealt with by the interface mtu of the outgoing
(virtual) interface and policy of that interface should dictate if
fragmentation should happen.

Instead reduce the pmtu data by IP options as we do for IPv6. Make the
same changes for ip_append_data, where we did not care about options or
dst.header_len at all.

Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 9124027..df18461 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -828,7 +828,7 @@ static int __ip_append_data(struct sock *sk,
 
 	if (cork->length + length > maxnonfragsize - fragheaderlen) {
 		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
-			       mtu-exthdrlen);
+			       mtu - (opt ? opt->optlen : 0));
 		return -EMSGSIZE;
 	}
 
@@ -1151,7 +1151,8 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 			 mtu : 0xFFFF;
 
 	if (cork->length + size > maxnonfragsize - fragheaderlen) {
-		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu);
+		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
+			       mtu - (opt ? opt->optlen : 0));
 		return -EMSGSIZE;
 	}
 
-- 
cgit v0.10.2


From bae651dbd7ade3c5d6518f89599ae680a2fe2b85 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Fri, 20 Dec 2013 17:48:54 +0100
Subject: drm/radeon: fix UVD 256MB check
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Otherwise the kernel might reject our decoding requests.

Signed-off-by: Christian König <christian.koenig@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 373d088..b9c0529 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -473,7 +473,7 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p,
 		return -EINVAL;
 	}
 
-	if ((start >> 28) != (end >> 28)) {
+	if ((start >> 28) != ((end - 1) >> 28)) {
 		DRM_ERROR("reloc %LX-%LX crossing 256MB boundary!\n",
 			  start, end);
 		return -EINVAL;
-- 
cgit v0.10.2


From d00adcc8ae9e22eca9d8af5f66c59ad9a74c90ec Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 23 Dec 2013 09:31:58 -0500
Subject: drm/radeon: 0x9649 is SUMO2 not SUMO

Fixes rendering corruption due to incorrect
gfx configuration.

bug:
https://bugs.freedesktop.org/show_bug.cgi?id=63599

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 87578c1..49376ae 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -600,7 +600,7 @@
 	{0x1002, 0x9645, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9647, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
 	{0x1002, 0x9648, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
-	{0x1002, 0x9649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
+	{0x1002, 0x9649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
 	{0x1002, 0x964a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x964b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x964c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
-- 
cgit v0.10.2


From 9fadb352ed73edd7801a280b552d33a6040c8721 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Ol=C5=A1=C3=A1k?= <marek.olsak@amd.com>
Date: Sun, 22 Dec 2013 02:18:00 +0100
Subject: drm/radeon: fix render backend setup for SI and CIK
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Only the render backends of the first shader engine were enabled. The others
were erroneously disabled. Enabling the other render backends improves
performance a lot.

Unigine Sanctuary on Bonaire:
  Before: 15 fps
  After:  90 fps

Judging from the fan noise, the GPU was also underclocked when the other
render backends were disabled, resulting in horrible performance. The fan is
a lot noisy under load now.

Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index b43a3a3..138a776 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -3057,7 +3057,7 @@ static u32 cik_create_bitmask(u32 bit_width)
  * Returns the disabled RB bitmask.
  */
 static u32 cik_get_rb_disabled(struct radeon_device *rdev,
-			      u32 max_rb_num, u32 se_num,
+			      u32 max_rb_num_per_se,
 			      u32 sh_per_se)
 {
 	u32 data, mask;
@@ -3071,7 +3071,7 @@ static u32 cik_get_rb_disabled(struct radeon_device *rdev,
 
 	data >>= BACKEND_DISABLE_SHIFT;
 
-	mask = cik_create_bitmask(max_rb_num / se_num / sh_per_se);
+	mask = cik_create_bitmask(max_rb_num_per_se / sh_per_se);
 
 	return data & mask;
 }
@@ -3088,7 +3088,7 @@ static u32 cik_get_rb_disabled(struct radeon_device *rdev,
  */
 static void cik_setup_rb(struct radeon_device *rdev,
 			 u32 se_num, u32 sh_per_se,
-			 u32 max_rb_num)
+			 u32 max_rb_num_per_se)
 {
 	int i, j;
 	u32 data, mask;
@@ -3098,7 +3098,7 @@ static void cik_setup_rb(struct radeon_device *rdev,
 	for (i = 0; i < se_num; i++) {
 		for (j = 0; j < sh_per_se; j++) {
 			cik_select_se_sh(rdev, i, j);
-			data = cik_get_rb_disabled(rdev, max_rb_num, se_num, sh_per_se);
+			data = cik_get_rb_disabled(rdev, max_rb_num_per_se, sh_per_se);
 			if (rdev->family == CHIP_HAWAII)
 				disabled_rbs |= data << ((i * sh_per_se + j) * HAWAII_RB_BITMAP_WIDTH_PER_SH);
 			else
@@ -3108,7 +3108,7 @@ static void cik_setup_rb(struct radeon_device *rdev,
 	cik_select_se_sh(rdev, 0xffffffff, 0xffffffff);
 
 	mask = 1;
-	for (i = 0; i < max_rb_num; i++) {
+	for (i = 0; i < max_rb_num_per_se * se_num; i++) {
 		if (!(disabled_rbs & mask))
 			enabled_rbs |= mask;
 		mask <<= 1;
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index a36736d..3eed9a1 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2811,7 +2811,7 @@ static void si_setup_spi(struct radeon_device *rdev,
 }
 
 static u32 si_get_rb_disabled(struct radeon_device *rdev,
-			      u32 max_rb_num, u32 se_num,
+			      u32 max_rb_num_per_se,
 			      u32 sh_per_se)
 {
 	u32 data, mask;
@@ -2825,14 +2825,14 @@ static u32 si_get_rb_disabled(struct radeon_device *rdev,
 
 	data >>= BACKEND_DISABLE_SHIFT;
 
-	mask = si_create_bitmask(max_rb_num / se_num / sh_per_se);
+	mask = si_create_bitmask(max_rb_num_per_se / sh_per_se);
 
 	return data & mask;
 }
 
 static void si_setup_rb(struct radeon_device *rdev,
 			u32 se_num, u32 sh_per_se,
-			u32 max_rb_num)
+			u32 max_rb_num_per_se)
 {
 	int i, j;
 	u32 data, mask;
@@ -2842,14 +2842,14 @@ static void si_setup_rb(struct radeon_device *rdev,
 	for (i = 0; i < se_num; i++) {
 		for (j = 0; j < sh_per_se; j++) {
 			si_select_se_sh(rdev, i, j);
-			data = si_get_rb_disabled(rdev, max_rb_num, se_num, sh_per_se);
+			data = si_get_rb_disabled(rdev, max_rb_num_per_se, sh_per_se);
 			disabled_rbs |= data << ((i * sh_per_se + j) * TAHITI_RB_BITMAP_WIDTH_PER_SH);
 		}
 	}
 	si_select_se_sh(rdev, 0xffffffff, 0xffffffff);
 
 	mask = 1;
-	for (i = 0; i < max_rb_num; i++) {
+	for (i = 0; i < max_rb_num_per_se * se_num; i++) {
 		if (!(disabled_rbs & mask))
 			enabled_rbs |= mask;
 		mask <<= 1;
-- 
cgit v0.10.2


From 439a1cfffe2c1a06e5a6394ccd5d18a8e89b15d3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Ol=C5=A1=C3=A1k?= <marek.olsak@amd.com>
Date: Sun, 22 Dec 2013 02:18:01 +0100
Subject: drm/radeon: expose render backend mask to the userspace
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This will allow userspace to correctly program the PA_SC_RASTER_CONFIG
register, so it can be considered a fix.

Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 138a776..e950fab 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -3114,6 +3114,8 @@ static void cik_setup_rb(struct radeon_device *rdev,
 		mask <<= 1;
 	}
 
+	rdev->config.cik.backend_enable_mask = enabled_rbs;
+
 	for (i = 0; i < se_num; i++) {
 		cik_select_se_sh(rdev, i, 0xffffffff);
 		data = 0;
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index b1f990d..45e1f44 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1940,7 +1940,7 @@ struct si_asic {
 	unsigned sc_earlyz_tile_fifo_size;
 
 	unsigned num_tile_pipes;
-	unsigned num_backends_per_se;
+	unsigned backend_enable_mask;
 	unsigned backend_disable_mask_per_asic;
 	unsigned backend_map;
 	unsigned num_texture_channel_caches;
@@ -1970,7 +1970,7 @@ struct cik_asic {
 	unsigned sc_earlyz_tile_fifo_size;
 
 	unsigned num_tile_pipes;
-	unsigned num_backends_per_se;
+	unsigned backend_enable_mask;
 	unsigned backend_disable_mask_per_asic;
 	unsigned backend_map;
 	unsigned num_texture_channel_caches;
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 55d0b47..21d593c 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -461,6 +461,15 @@ int radeon_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	case RADEON_INFO_SI_CP_DMA_COMPUTE:
 		*value = 1;
 		break;
+	case RADEON_INFO_SI_BACKEND_ENABLED_MASK:
+		if (rdev->family >= CHIP_BONAIRE) {
+			*value = rdev->config.cik.backend_enable_mask;
+		} else if (rdev->family >= CHIP_TAHITI) {
+			*value = rdev->config.si.backend_enable_mask;
+		} else {
+			DRM_DEBUG_KMS("BACKEND_ENABLED_MASK is si+ only!\n");
+		}
+		break;
 	default:
 		DRM_DEBUG_KMS("Invalid request %d\n", info->request);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 3eed9a1..85e1edf 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2855,6 +2855,8 @@ static void si_setup_rb(struct radeon_device *rdev,
 		mask <<= 1;
 	}
 
+	rdev->config.si.backend_enable_mask = enabled_rbs;
+
 	for (i = 0; i < se_num; i++) {
 		si_select_se_sh(rdev, i, 0xffffffff);
 		data = 0;
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 2f3f7ea..fe421e8 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -983,6 +983,8 @@ struct drm_radeon_cs {
 #define RADEON_INFO_SI_CP_DMA_COMPUTE	0x17
 /* CIK macrotile mode array */
 #define RADEON_INFO_CIK_MACROTILE_MODE_ARRAY	0x18
+/* query the number of render backends */
+#define RADEON_INFO_SI_BACKEND_ENABLED_MASK	0x19
 
 
 struct drm_radeon_info {
-- 
cgit v0.10.2


From 35a905282b20e556cd09f348f9c2bc8a22ea26d5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Ol=C5=A1=C3=A1k?= <marek.olsak@amd.com>
Date: Mon, 23 Dec 2013 17:11:35 +0100
Subject: drm/radeon: set correct pipe config for Hawaii in DCE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index b197059..ec97bad 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1180,19 +1180,12 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 		fb_format |= EVERGREEN_GRPH_ARRAY_MODE(EVERGREEN_GRPH_ARRAY_1D_TILED_THIN1);
 
 	if (rdev->family >= CHIP_BONAIRE) {
-		u32 num_pipe_configs = rdev->config.cik.max_tile_pipes;
-		u32 num_rb = rdev->config.cik.max_backends_per_se;
-		if (num_pipe_configs > 8)
-			num_pipe_configs = 8;
-		if (num_pipe_configs == 8)
-			fb_format |= CIK_GRPH_PIPE_CONFIG(CIK_ADDR_SURF_P8_32x32_16x16);
-		else if (num_pipe_configs == 4) {
-			if (num_rb == 4)
-				fb_format |= CIK_GRPH_PIPE_CONFIG(CIK_ADDR_SURF_P4_16x16);
-			else if (num_rb < 4)
-				fb_format |= CIK_GRPH_PIPE_CONFIG(CIK_ADDR_SURF_P4_8x16);
-		} else if (num_pipe_configs == 2)
-			fb_format |= CIK_GRPH_PIPE_CONFIG(CIK_ADDR_SURF_P2);
+		/* Read the pipe config from the 2D TILED SCANOUT mode.
+		 * It should be the same for the other modes too, but not all
+		 * modes set the pipe config field. */
+		u32 pipe_config = (rdev->config.cik.tile_mode_array[10] >> 6) & 0x1f;
+
+		fb_format |= CIK_GRPH_PIPE_CONFIG(pipe_config);
 	} else if ((rdev->family == CHIP_TAHITI) ||
 		   (rdev->family == CHIP_PITCAIRN))
 		fb_format |= SI_GRPH_PIPE_CONFIG(SI_ADDR_SURF_P8_32x32_8x16);
-- 
cgit v0.10.2


From e3ea94a60f12025a3a547964c31245e71ac8fa77 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Ol=C5=A1=C3=A1k?= <marek.olsak@amd.com>
Date: Mon, 23 Dec 2013 17:11:36 +0100
Subject: drm/radeon: set correct number of banks for CIK chips in DCE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We don't have the NUM_BANKS parameter, so we have to calculate it
from the other parameters. NUM_BANKS is not constant on CIK.

This fixes 2D tiling for the display engine on CIK.

Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index ec97bad..0b9621c 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1143,31 +1143,53 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 	}
 
 	if (tiling_flags & RADEON_TILING_MACRO) {
-		if (rdev->family >= CHIP_BONAIRE)
-			tmp = rdev->config.cik.tile_config;
-		else if (rdev->family >= CHIP_TAHITI)
-			tmp = rdev->config.si.tile_config;
-		else if (rdev->family >= CHIP_CAYMAN)
-			tmp = rdev->config.cayman.tile_config;
-		else
-			tmp = rdev->config.evergreen.tile_config;
+		evergreen_tiling_fields(tiling_flags, &bankw, &bankh, &mtaspect, &tile_split);
 
-		switch ((tmp & 0xf0) >> 4) {
-		case 0: /* 4 banks */
-			fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_4_BANK);
-			break;
-		case 1: /* 8 banks */
-		default:
-			fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_8_BANK);
-			break;
-		case 2: /* 16 banks */
-			fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_16_BANK);
-			break;
+		/* Set NUM_BANKS. */
+		if (rdev->family >= CHIP_BONAIRE) {
+			unsigned tileb, index, num_banks, tile_split_bytes;
+
+			/* Calculate the macrotile mode index. */
+			tile_split_bytes = 64 << tile_split;
+			tileb = 8 * 8 * target_fb->bits_per_pixel / 8;
+			tileb = min(tile_split_bytes, tileb);
+
+			for (index = 0; tileb > 64; index++) {
+				tileb >>= 1;
+			}
+
+			if (index >= 16) {
+				DRM_ERROR("Wrong screen bpp (%u) or tile split (%u)\n",
+					  target_fb->bits_per_pixel, tile_split);
+				return -EINVAL;
+			}
+
+			num_banks = (rdev->config.cik.macrotile_mode_array[index] >> 6) & 0x3;
+			fb_format |= EVERGREEN_GRPH_NUM_BANKS(num_banks);
+		} else {
+			/* SI and older. */
+			if (rdev->family >= CHIP_TAHITI)
+				tmp = rdev->config.si.tile_config;
+			else if (rdev->family >= CHIP_CAYMAN)
+				tmp = rdev->config.cayman.tile_config;
+			else
+				tmp = rdev->config.evergreen.tile_config;
+
+			switch ((tmp & 0xf0) >> 4) {
+			case 0: /* 4 banks */
+				fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_4_BANK);
+				break;
+			case 1: /* 8 banks */
+			default:
+				fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_8_BANK);
+				break;
+			case 2: /* 16 banks */
+				fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_16_BANK);
+				break;
+			}
 		}
 
 		fb_format |= EVERGREEN_GRPH_ARRAY_MODE(EVERGREEN_GRPH_ARRAY_2D_TILED_THIN1);
-
-		evergreen_tiling_fields(tiling_flags, &bankw, &bankh, &mtaspect, &tile_split);
 		fb_format |= EVERGREEN_GRPH_TILE_SPLIT(tile_split);
 		fb_format |= EVERGREEN_GRPH_BANK_WIDTH(bankw);
 		fb_format |= EVERGREEN_GRPH_BANK_HEIGHT(bankh);
-- 
cgit v0.10.2


From 9482d0d37b46d2bd968d357bbd912cae49caf163 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 23 Dec 2013 11:31:44 -0500
Subject: drm/radeon: Bump version for CIK DCE tiling fix

Note when CIK DCE tiling was fixed.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 1958b36a..db39ea3 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -77,9 +77,10 @@
  *   2.33.0 - Add SI tiling mode array query
  *   2.34.0 - Add CIK tiling mode array query
  *   2.35.0 - Add CIK macrotile mode array query
+ *   2.36.0 - Fix CIK DCE tiling setup
  */
 #define KMS_DRIVER_MAJOR	2
-#define KMS_DRIVER_MINOR	35
+#define KMS_DRIVER_MINOR	36
 #define KMS_DRIVER_PATCHLEVEL	0
 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
 int radeon_driver_unload_kms(struct drm_device *dev);
-- 
cgit v0.10.2


From f55c07607a38f84b5c7e6066ee1cfe433fa5643c Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Wed, 11 Dec 2013 18:50:25 -0800
Subject: timekeeping: Fix lost updates to tai adjustment

Since 48cdc135d4840 (Implement a shadow timekeeper), we have to
call timekeeping_update() after any adjustment to the timekeeping
structure in order to make sure that any adjustments to the structure
persist.

Unfortunately, the updates to the tai offset via adjtimex do not
trigger this update, causing adjustments to the tai offset to be
made and then over-written by the previous value at the next
update_wall_time() call.

This patch resovles the issue by calling timekeeping_update()
right after setting the tai offset.

Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: stable <stable@vger.kernel.org> #3.10+
Signed-off-by: John Stultz <john.stultz@linaro.org>

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 3abf534..7488f0b 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -610,6 +610,7 @@ void timekeeping_set_tai_offset(s32 tai_offset)
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&timekeeper_seq);
 	__timekeeping_set_tai_offset(tk, tai_offset);
+	timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 	clock_was_set();
@@ -1698,7 +1699,7 @@ int do_adjtimex(struct timex *txc)
 
 	if (tai != orig_tai) {
 		__timekeeping_set_tai_offset(tk, tai);
-		update_pvclock_gtod(tk, true);
+		timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
 		clock_was_set_delayed();
 	}
 	write_seqcount_end(&timekeeper_seq);
-- 
cgit v0.10.2


From ad85ace07a05062ef6b59c35a5e80b6eaee1eee6 Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Fri, 20 Dec 2013 13:41:47 -0500
Subject: perf kvm: Fix kvm report without guestmount.

Currently, if we use perf kvm --guestkallsyms --guestmodules report, we
can not get the perf information from perf data file. All sample are
shown as unknown.

Reproducing steps:
	# perf kvm --guestkallsyms /tmp/kallsyms --guestmodules /tmp/modules record -a sleep 1
	[ perf record: Woken up 1 times to write data ]
	[ perf record: Captured and wrote 0.624 MB perf.data.guest (~27260 samples) ]
	# perf kvm --guestkallsyms /tmp/kallsyms --guestmodules /tmp/modules report |grep %
	   100.00%  [guest/6471]  [unknown]         [g] 0xffffffff8164f330

This bug was introduced by 207b57926 (perf kvm: Fix regression with guest machine creation).
In original code, it uses perf_session__find_machine(), it means we deliver symbol to machine
which has the same pid, if no machine found, deliver it to *default* guest. But if we use
perf_session__findnew_machine() here, if no machine was found, new machine with pid will be built
and added. Then the default guest which with pid == 0 will never get a symbol.

And because the new machine initialized here has no kernel map created, the symbol delivered to
it will be marked as "unknown".

This patch here is to revert commit 207b57926 and fix the SEGFAULT bug in another way.

Verification steps:
	# ./perf kvm --guestkallsyms /home/kallsyms --guestmodules /home/modules record -a sleep 1
	[ perf record: Woken up 1 times to write data ]
	[ perf record: Captured and wrote 0.651 MB perf.data.guest (~28437 samples) ]
	# ./perf kvm --guestkallsyms /home/kallsyms --guestmodules /home/modules report |grep %
	    22.64%    :6471  [guest.kernel.kallsyms]  [g] update_rq_clock.part.70
	    19.99%    :6471  [guest.kernel.kallsyms]  [g] d_free
	    18.46%    :6471  [guest.kernel.kallsyms]  [g] bio_phys_segments
	    16.25%    :6471  [guest.kernel.kallsyms]  [g] dequeue_task
	    12.78%    :6471  [guest.kernel.kallsyms]  [g] __switch_to
	     7.91%    :6471  [guest.kernel.kallsyms]  [g] scheduler_tick
	     1.75%    :6471  [guest.kernel.kallsyms]  [g] native_apic_mem_write
	     0.21%    :6471  [guest.kernel.kallsyms]  [g] apic_timer_interrupt

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Acked-by: David Ahern <dsahern@gmail.com>
Cc: stable@vger.kernel.org # 3.3+
Cc: David Ahern <dsahern@gmail.com>
Link: http://lkml.kernel.org/r/1387564907-3045-1-git-send-email-yangds.fnst@cn.fujitsu.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index cbacaab..d3a857be 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -830,6 +830,7 @@ static struct machine *
 					       struct perf_sample *sample)
 {
 	const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	struct machine *machine;
 
 	if (perf_guest &&
 	    ((cpumode == PERF_RECORD_MISC_GUEST_KERNEL) ||
@@ -842,7 +843,11 @@ static struct machine *
 		else
 			pid = sample->pid;
 
-		return perf_session__findnew_machine(session, pid);
+		machine = perf_session__find_machine(session, pid);
+		if (!machine)
+			machine = perf_session__findnew_machine(session,
+						DEFAULT_GUEST_KERNEL_ID);
+		return machine;
 	}
 
 	return &session->machines.host;
-- 
cgit v0.10.2


From fb50bb43d051d12aad9e2337d0d5d14d0d3dd281 Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Fri, 20 Dec 2013 15:52:56 -0500
Subject: perf tools: Add support for PERF_RECORD_MISC_GUEST_USER in
 thread__find_addr_map().

This patch remove a TODO in thread__find_addr_map() and add support of
PERF_RECORD_MISC_GUEST_USER.

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Link: http://lkml.kernel.org/r/3dd652201171a19c910b500984c7c3590e77603b.1387572416.git.yangds.fnst@cn.fujitsu.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index fe20227..484e994 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -659,15 +659,10 @@ void thread__find_addr_map(struct thread *thread,
 		al->level = 'g';
 		mg = &machine->kmaps;
 		load_map = true;
+	} else if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest) {
+		al->level = 'u';
 	} else {
-		/*
-		 * 'u' means guest os user space.
-		 * TODO: We don't support guest user space. Might support late.
-		 */
-		if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest)
-			al->level = 'u';
-		else
-			al->level = 'H';
+		al->level = 'H';
 		al->map = NULL;
 
 		if ((cpumode == PERF_RECORD_MISC_GUEST_USER ||
-- 
cgit v0.10.2


From 995634650ef1f907196bd7e9ae45354124a80e47 Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Fri, 20 Dec 2013 15:52:57 -0500
Subject: perf tools: Find the proc info under machine->root_dir.

When we synthesize the threads, we are looking for the infomation under
/proc. But it is only for host.

This patch look for the path of proc under machine->root_dir, then
XXX__synthesize_threads() functions can support guest machines.

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Link: http://lkml.kernel.org/r/927b937da9177a079abafe4532fa9c9b60b5c4b7.1387572416.git.yangds.fnst@cn.fujitsu.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 484e994..a61726e 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -129,7 +129,8 @@ static pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 		goto out;
 	}
 
-	snprintf(filename, sizeof(filename), "/proc/%d/task", pid);
+	snprintf(filename, sizeof(filename), "%s/proc/%d/task",
+		 machine->root_dir, pid);
 
 	tasks = opendir(filename);
 	if (tasks == NULL) {
@@ -178,7 +179,8 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 	FILE *fp;
 	int rc = 0;
 
-	snprintf(filename, sizeof(filename), "/proc/%d/maps", pid);
+	snprintf(filename, sizeof(filename), "%s/proc/%d/maps",
+		 machine->root_dir, pid);
 
 	fp = fopen(filename, "r");
 	if (fp == NULL) {
@@ -387,6 +389,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 				   struct machine *machine, bool mmap_data)
 {
 	DIR *proc;
+	char proc_path[PATH_MAX];
 	struct dirent dirent, *next;
 	union perf_event *comm_event, *mmap_event;
 	int err = -1;
@@ -399,7 +402,9 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	if (mmap_event == NULL)
 		goto out_free_comm;
 
-	proc = opendir("/proc");
+	snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
+	proc = opendir(proc_path);
+
 	if (proc == NULL)
 		goto out_free_mmap;
 
-- 
cgit v0.10.2


From 73547aacdcd45cdf8b53245ded9593d7c587501a Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Fri, 20 Dec 2013 15:52:58 -0500
Subject: perf tools: Set event->header.misc to PERF_RECORD_MISC_GUEST_USER if
 machine is guest.

When we synthesize the mmap events of user space, if machine is guest,
we should set the event->header.misc to PERF_RECORD_MISC_GUEST_USER,
rather than PERF_RECORD_MISC_USER.

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Link: http://lkml.kernel.org/r/e6f8ff6505d2db8a4b21bff8e448bb9be0bcff35.1387572416.git.yangds.fnst@cn.fujitsu.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index a61726e..07c0783 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -220,7 +220,10 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		/*
 		 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
 		 */
-		event->header.misc = PERF_RECORD_MISC_USER;
+		if (machine__is_host(machine))
+			event->header.misc = PERF_RECORD_MISC_USER;
+		else
+			event->header.misc = PERF_RECORD_MISC_GUEST_USER;
 
 		if (prot[2] != 'x') {
 			if (!mmap_data || prot[0] != 'r')
-- 
cgit v0.10.2


From f5db57c4c47f3985dfc677152e25636a3401fa13 Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Fri, 20 Dec 2013 15:52:59 -0500
Subject: perf tools: Use machine->pid for tgid if machine is guest.

When we synthesize an comm event, if machine is guest, we should
use the pid of machine as the event->comm.pid, rather than tgid
of thread.

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Link: http://lkml.kernel.org/r/22455abe107c618a361e7b667ad0f098f7c9b4a3.1387572416.git.yangds.fnst@cn.fujitsu.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 07c0783..2905771 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -106,8 +106,12 @@ static pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 
 	memset(&event->comm, 0, sizeof(event->comm));
 
-	tgid = perf_event__get_comm_tgid(pid, event->comm.comm,
-					 sizeof(event->comm.comm));
+	if (machine__is_host(machine))
+		tgid = perf_event__get_comm_tgid(pid, event->comm.comm,
+						 sizeof(event->comm.comm));
+	else
+		tgid = machine->pid;
+
 	if (tgid < 0)
 		goto out;
 
-- 
cgit v0.10.2


From c239c25a82808ad2cbc795b69e621c4c24f154d6 Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Date: Fri, 20 Dec 2013 15:53:00 -0500
Subject: perf tools: Do not synthesize the treads of default guest.

As the default guest is designed to handle orphan kernel symboles with
--guestkallsysms and --guestmodules, it has no user space.

So we should skip synthesizing threads if machine is default guest.

Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Link: http://lkml.kernel.org/r/e9ddb5dac6f963169657218b12ceb3c2030f54e8.1387572416.git.yangds.fnst@cn.fujitsu.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 2905771..45a76c6 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -133,6 +133,9 @@ static pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 		goto out;
 	}
 
+	if (machine__is_default_guest(machine))
+		return 0;
+
 	snprintf(filename, sizeof(filename), "%s/proc/%d/task",
 		 machine->root_dir, pid);
 
@@ -183,6 +186,9 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 	FILE *fp;
 	int rc = 0;
 
+	if (machine__is_default_guest(machine))
+		return 0;
+
 	snprintf(filename, sizeof(filename), "%s/proc/%d/maps",
 		 machine->root_dir, pid);
 
@@ -409,6 +415,9 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	if (mmap_event == NULL)
 		goto out_free_comm;
 
+	if (machine__is_default_guest(machine))
+		return 0;
+
 	snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
 	proc = opendir(proc_path);
 
-- 
cgit v0.10.2


From 56560ec692c142bb9ee404764e3b67999031ad19 Mon Sep 17 00:00:00 2001
From: Chunwei Chen <tuxoko@gmail.com>
Date: Sat, 21 Dec 2013 13:48:11 +0800
Subject: perf config: Ignore generated files in feature-checks

1. Rename the test-* binary files to test-*.bin for easier pattern matching as
   suggested by Ingo.
2. Ignore *.bin and *.d files.

Signed-off-by: Chunwei Chen <tuxoko@gmail.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/52B52B9B.50708@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 5a1f4df..14faeeb 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -126,7 +126,7 @@ endif
 
 feature_check = $(eval $(feature_check_code))
 define feature_check_code
-  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C config/feature-checks test-$1 >/dev/null 2>/dev/null && echo 1 || echo 0)
+  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C config/feature-checks test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0)
 endef
 
 feature_set = $(eval $(feature_set_code))
@@ -173,7 +173,7 @@ CORE_FEATURE_TESTS =			\
 # to skip the print-out of the long features list if the file
 # existed before and after it was built:
 #
-ifeq ($(wildcard $(OUTPUT)config/feature-checks/test-all),)
+ifeq ($(wildcard $(OUTPUT)config/feature-checks/test-all.bin),)
   test-all-failed := 1
 else
   test-all-failed := 0
@@ -203,7 +203,7 @@ ifeq ($(feature-all), 1)
   #
   $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_set,$(feat)))
 else
-  $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS)" LDFLAGS=$(LDFLAGS) -i -j -C config/feature-checks $(CORE_FEATURE_TESTS) >/dev/null 2>&1)
+  $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CFLAGS="$(EXTRA_CFLAGS)" LDFLAGS=$(LDFLAGS) -i -j -C config/feature-checks $(addsuffix .bin,$(CORE_FEATURE_TESTS)) >/dev/null 2>&1)
   $(foreach feat,$(CORE_FEATURE_TESTS),$(call feature_check,$(feat)))
 endif
 
diff --git a/tools/perf/config/feature-checks/.gitignore b/tools/perf/config/feature-checks/.gitignore
new file mode 100644
index 0000000..80f3da0
--- /dev/null
+++ b/tools/perf/config/feature-checks/.gitignore
@@ -0,0 +1,2 @@
+*.d
+*.bin
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index bc86462..7cf6fcd 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -1,90 +1,90 @@
 
 FILES=					\
-	test-all			\
-	test-backtrace			\
-	test-bionic			\
-	test-dwarf			\
-	test-fortify-source		\
-	test-glibc			\
-	test-gtk2			\
-	test-gtk2-infobar		\
-	test-hello			\
-	test-libaudit			\
-	test-libbfd			\
-	test-liberty			\
-	test-liberty-z			\
-	test-cplus-demangle		\
-	test-libelf			\
-	test-libelf-getphdrnum		\
-	test-libelf-mmap		\
-	test-libnuma			\
-	test-libperl			\
-	test-libpython			\
-	test-libpython-version		\
-	test-libslang			\
-	test-libunwind			\
-	test-libunwind-debug-frame	\
-	test-on-exit			\
-	test-stackprotector-all		\
-	test-timerfd
+	test-all.bin			\
+	test-backtrace.bin		\
+	test-bionic.bin			\
+	test-dwarf.bin			\
+	test-fortify-source.bin		\
+	test-glibc.bin			\
+	test-gtk2.bin			\
+	test-gtk2-infobar.bin		\
+	test-hello.bin			\
+	test-libaudit.bin		\
+	test-libbfd.bin			\
+	test-liberty.bin		\
+	test-liberty-z.bin		\
+	test-cplus-demangle.bin		\
+	test-libelf.bin			\
+	test-libelf-getphdrnum.bin	\
+	test-libelf-mmap.bin		\
+	test-libnuma.bin		\
+	test-libperl.bin		\
+	test-libpython.bin		\
+	test-libpython-version.bin	\
+	test-libslang.bin		\
+	test-libunwind.bin		\
+	test-libunwind-debug-frame.bin	\
+	test-on-exit.bin		\
+	test-stackprotector-all.bin	\
+	test-timerfd.bin
 
 CC := $(CC) -MD
 
 all: $(FILES)
 
-BUILD = $(CC) $(CFLAGS) -o $(OUTPUT)$@ $@.c $(LDFLAGS)
+BUILD = $(CC) $(CFLAGS) -o $(OUTPUT)$@ $(patsubst %.bin,%.c,$@) $(LDFLAGS)
 
 ###############################
 
-test-all:
+test-all.bin:
 	$(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl
 
-test-hello:
+test-hello.bin:
 	$(BUILD)
 
-test-stackprotector-all:
+test-stackprotector-all.bin:
 	$(BUILD) -Werror -fstack-protector-all
 
-test-fortify-source:
+test-fortify-source.bin:
 	$(BUILD) -O2 -Werror -D_FORTIFY_SOURCE=2
 
-test-bionic:
+test-bionic.bin:
 	$(BUILD)
 
-test-libelf:
+test-libelf.bin:
 	$(BUILD) -lelf
 
-test-glibc:
+test-glibc.bin:
 	$(BUILD)
 
-test-dwarf:
+test-dwarf.bin:
 	$(BUILD) -ldw
 
-test-libelf-mmap:
+test-libelf-mmap.bin:
 	$(BUILD) -lelf
 
-test-libelf-getphdrnum:
+test-libelf-getphdrnum.bin:
 	$(BUILD) -lelf
 
-test-libnuma:
+test-libnuma.bin:
 	$(BUILD) -lnuma
 
-test-libunwind:
+test-libunwind.bin:
 	$(BUILD) -lelf
 
-test-libunwind-debug-frame:
+test-libunwind-debug-frame.bin:
 	$(BUILD) -lelf
 
-test-libaudit:
+test-libaudit.bin:
 	$(BUILD) -laudit
 
-test-libslang:
+test-libslang.bin:
 	$(BUILD) -I/usr/include/slang -lslang
 
-test-gtk2:
+test-gtk2.bin:
 	$(BUILD) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null)
 
-test-gtk2-infobar:
+test-gtk2-infobar.bin:
 	$(BUILD) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null)
 
 grep-libs  = $(filter -l%,$(1))
@@ -96,7 +96,7 @@ PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
 PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
 FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 
-test-libperl:
+test-libperl.bin:
 	$(BUILD) $(FLAGS_PERL_EMBED)
 
 override PYTHON := python
@@ -113,31 +113,31 @@ PYTHON_EMBED_LIBADD = $(call grep-libs,$(PYTHON_EMBED_LDOPTS))
 PYTHON_EMBED_CCOPTS = $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
 FLAGS_PYTHON_EMBED = $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 
-test-libpython:
+test-libpython.bin:
 	$(BUILD) $(FLAGS_PYTHON_EMBED)
 
-test-libpython-version:
+test-libpython-version.bin:
 	$(BUILD) $(FLAGS_PYTHON_EMBED)
 
-test-libbfd:
+test-libbfd.bin:
 	$(BUILD) -DPACKAGE='"perf"' -lbfd -ldl
 
-test-liberty:
+test-liberty.bin:
 	$(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty
 
-test-liberty-z:
+test-liberty-z.bin:
 	$(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty -lz
 
-test-cplus-demangle:
+test-cplus-demangle.bin:
 	$(BUILD) -liberty
 
-test-on-exit:
+test-on-exit.bin:
 	$(BUILD)
 
-test-backtrace:
+test-backtrace.bin:
 	$(BUILD)
 
-test-timerfd:
+test-timerfd.bin:
 	$(BUILD)
 
 -include *.d
-- 
cgit v0.10.2


From 5258d3f25c76f6ab86e9333abf97a55a877d3870 Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Wed, 11 Dec 2013 20:07:49 -0800
Subject: timekeeping: Fix potential lost pv notification of time change

In 780427f0e11 (Indicate that clock was set in the pvclock
gtod notifier), logic was added to pass a CLOCK_WAS_SET
notification to the pvclock notifier chain.

While that patch added a action flag returned from
accumulate_nsecs_to_secs(), it only uses the returned value
in one location, and not in the logarithmic accumulation.

This means if a leap second triggered during the logarithmic
accumulation (which is most likely where it would happen),
the notification that the clock was set would not make it to
the pv notifiers.

This patch extends the logarithmic_accumulation pass down
that action flag so proper notification will occur.

This patch also changes the varialbe action -> clock_set
per Ingo's suggestion.

Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: <xen-devel@lists.xen.org>
Cc: stable <stable@vger.kernel.org> #3.11+
Signed-off-by: John Stultz <john.stultz@linaro.org>

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 7488f0b..051855f 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1256,7 +1256,7 @@ out_adjust:
 static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
 {
 	u64 nsecps = (u64)NSEC_PER_SEC << tk->shift;
-	unsigned int action = 0;
+	unsigned int clock_set = 0;
 
 	while (tk->xtime_nsec >= nsecps) {
 		int leap;
@@ -1279,10 +1279,10 @@ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
 			__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
 
 			clock_was_set_delayed();
-			action = TK_CLOCK_WAS_SET;
+			clock_set = TK_CLOCK_WAS_SET;
 		}
 	}
-	return action;
+	return clock_set;
 }
 
 /**
@@ -1295,7 +1295,8 @@ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
  * Returns the unconsumed cycles.
  */
 static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
-						u32 shift)
+						u32 shift,
+						unsigned int *clock_set)
 {
 	cycle_t interval = tk->cycle_interval << shift;
 	u64 raw_nsecs;
@@ -1309,7 +1310,7 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
 	tk->cycle_last += interval;
 
 	tk->xtime_nsec += tk->xtime_interval << shift;
-	accumulate_nsecs_to_secs(tk);
+	*clock_set |= accumulate_nsecs_to_secs(tk);
 
 	/* Accumulate raw time */
 	raw_nsecs = (u64)tk->raw_interval << shift;
@@ -1367,7 +1368,7 @@ static void update_wall_time(void)
 	struct timekeeper *tk = &shadow_timekeeper;
 	cycle_t offset;
 	int shift = 0, maxshift;
-	unsigned int action;
+	unsigned int clock_set = 0;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
@@ -1402,7 +1403,8 @@ static void update_wall_time(void)
 	maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1;
 	shift = min(shift, maxshift);
 	while (offset >= tk->cycle_interval) {
-		offset = logarithmic_accumulation(tk, offset, shift);
+		offset = logarithmic_accumulation(tk, offset, shift,
+							&clock_set);
 		if (offset < tk->cycle_interval<<shift)
 			shift--;
 	}
@@ -1420,7 +1422,7 @@ static void update_wall_time(void)
 	 * Finally, make sure that after the rounding
 	 * xtime_nsec isn't larger than NSEC_PER_SEC
 	 */
-	action = accumulate_nsecs_to_secs(tk);
+	clock_set |= accumulate_nsecs_to_secs(tk);
 
 	write_seqcount_begin(&timekeeper_seq);
 	/* Update clock->cycle_last with the new value */
@@ -1436,7 +1438,7 @@ static void update_wall_time(void)
 	 * updating.
 	 */
 	memcpy(real_tk, tk, sizeof(*tk));
-	timekeeping_update(real_tk, action);
+	timekeeping_update(real_tk, clock_set);
 	write_seqcount_end(&timekeeper_seq);
 out:
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
-- 
cgit v0.10.2


From 6fdda9a9c5db367130cf32df5d6618d08b89f46a Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Tue, 10 Dec 2013 17:18:18 -0800
Subject: timekeeping: Avoid possible deadlock from clock_was_set_delayed

As part of normal operaions, the hrtimer subsystem frequently calls
into the timekeeping code, creating a locking order of
  hrtimer locks -> timekeeping locks

clock_was_set_delayed() was suppoed to allow us to avoid deadlocks
between the timekeeping the hrtimer subsystem, so that we could
notify the hrtimer subsytem the time had changed while holding
the timekeeping locks. This was done by scheduling delayed work
that would run later once we were out of the timekeeing code.

But unfortunately the lock chains are complex enoguh that in
scheduling delayed work, we end up eventually trying to grab
an hrtimer lock.

Sasha Levin noticed this in testing when the new seqlock lockdep
enablement triggered the following (somewhat abrieviated) message:

[  251.100221] ======================================================
[  251.100221] [ INFO: possible circular locking dependency detected ]
[  251.100221] 3.13.0-rc2-next-20131206-sasha-00005-g8be2375-dirty #4053 Not tainted
[  251.101967] -------------------------------------------------------
[  251.101967] kworker/10:1/4506 is trying to acquire lock:
[  251.101967]  (timekeeper_seq){----..}, at: [<ffffffff81160e96>] retrigger_next_event+0x56/0x70
[  251.101967]
[  251.101967] but task is already holding lock:
[  251.101967]  (hrtimer_bases.lock#11){-.-...}, at: [<ffffffff81160e7c>] retrigger_next_event+0x3c/0x70
[  251.101967]
[  251.101967] which lock already depends on the new lock.
[  251.101967]
[  251.101967]
[  251.101967] the existing dependency chain (in reverse order) is:
[  251.101967]
-> #5 (hrtimer_bases.lock#11){-.-...}:
[snipped]
-> #4 (&rt_b->rt_runtime_lock){-.-...}:
[snipped]
-> #3 (&rq->lock){-.-.-.}:
[snipped]
-> #2 (&p->pi_lock){-.-.-.}:
[snipped]
-> #1 (&(&pool->lock)->rlock){-.-...}:
[  251.101967]        [<ffffffff81194803>] validate_chain+0x6c3/0x7b0
[  251.101967]        [<ffffffff81194d9d>] __lock_acquire+0x4ad/0x580
[  251.101967]        [<ffffffff81194ff2>] lock_acquire+0x182/0x1d0
[  251.101967]        [<ffffffff84398500>] _raw_spin_lock+0x40/0x80
[  251.101967]        [<ffffffff81153e69>] __queue_work+0x1a9/0x3f0
[  251.101967]        [<ffffffff81154168>] queue_work_on+0x98/0x120
[  251.101967]        [<ffffffff81161351>] clock_was_set_delayed+0x21/0x30
[  251.101967]        [<ffffffff811c4bd1>] do_adjtimex+0x111/0x160
[  251.101967]        [<ffffffff811e2711>] compat_sys_adjtimex+0x41/0x70
[  251.101967]        [<ffffffff843a4b49>] ia32_sysret+0x0/0x5
[  251.101967]
-> #0 (timekeeper_seq){----..}:
[snipped]
[  251.101967] other info that might help us debug this:
[  251.101967]
[  251.101967] Chain exists of:
  timekeeper_seq --> &rt_b->rt_runtime_lock --> hrtimer_bases.lock#11

[  251.101967]  Possible unsafe locking scenario:
[  251.101967]
[  251.101967]        CPU0                    CPU1
[  251.101967]        ----                    ----
[  251.101967]   lock(hrtimer_bases.lock#11);
[  251.101967]                                lock(&rt_b->rt_runtime_lock);
[  251.101967]                                lock(hrtimer_bases.lock#11);
[  251.101967]   lock(timekeeper_seq);
[  251.101967]
[  251.101967]  *** DEADLOCK ***
[  251.101967]
[  251.101967] 3 locks held by kworker/10:1/4506:
[  251.101967]  #0:  (events){.+.+.+}, at: [<ffffffff81154960>] process_one_work+0x200/0x530
[  251.101967]  #1:  (hrtimer_work){+.+...}, at: [<ffffffff81154960>] process_one_work+0x200/0x530
[  251.101967]  #2:  (hrtimer_bases.lock#11){-.-...}, at: [<ffffffff81160e7c>] retrigger_next_event+0x3c/0x70
[  251.101967]
[  251.101967] stack backtrace:
[  251.101967] CPU: 10 PID: 4506 Comm: kworker/10:1 Not tainted 3.13.0-rc2-next-20131206-sasha-00005-g8be2375-dirty #4053
[  251.101967] Workqueue: events clock_was_set_work

So the best solution is to avoid calling clock_was_set_delayed() while
holding the timekeeping lock, and instead using a flag variable to
decide if we should call clock_was_set() once we've released the locks.

This works for the case here, where the do_adjtimex() was the deadlock
trigger point. Unfortuantely, in update_wall_time() we still hold
the jiffies lock, which would deadlock with the ipi triggered by
clock_was_set(), preventing us from calling it even after we drop the
timekeeping lock. So instead call clock_was_set_delayed() at that point.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: stable <stable@vger.kernel.org> #3.10+
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 051855f..d62682b 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1278,7 +1278,6 @@ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
 
 			__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
 
-			clock_was_set_delayed();
 			clock_set = TK_CLOCK_WAS_SET;
 		}
 	}
@@ -1442,6 +1441,19 @@ static void update_wall_time(void)
 	write_seqcount_end(&timekeeper_seq);
 out:
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+	if (clock_was_set) {
+		/*
+		 * XXX -  I'd rather we just call clock_was_set(), but
+		 * since we're currently holding the jiffies lock, calling
+		 * clock_was_set would trigger an ipi which would then grab
+		 * the jiffies lock and we'd deadlock. :(
+		 * The right solution should probably be droping
+		 * the jiffies lock before calling update_wall_time
+		 * but that requires some rework of the tick sched
+		 * code.
+		 */
+		clock_was_set_delayed();
+	}
 }
 
 /**
@@ -1702,11 +1714,13 @@ int do_adjtimex(struct timex *txc)
 	if (tai != orig_tai) {
 		__timekeeping_set_tai_offset(tk, tai);
 		timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
-		clock_was_set_delayed();
 	}
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
+	if (tai != orig_tai)
+		clock_was_set();
+
 	ntp_notify_cmos_timer();
 
 	return ret;
-- 
cgit v0.10.2


From 47a1b796306356f358e515149d86baf0cc6bf007 Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Thu, 12 Dec 2013 13:10:55 -0800
Subject: tick/timekeeping: Call update_wall_time outside the jiffies lock

Since the xtime lock was split into the timekeeping lock and
the jiffies lock, we no longer need to call update_wall_time()
while holding the jiffies lock.

Thus, this patch splits update_wall_time() out from do_timer().

This allows us to get away from calling clock_was_set_delayed()
in update_wall_time() and instead use the standard clock_was_set()
call that previously would deadlock, as it causes the jiffies lock
to be acquired.

Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>

diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 64522ec..91c5f27 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -70,6 +70,7 @@ static void tick_periodic(int cpu)
 
 		do_timer(1);
 		write_sequnlock(&jiffies_lock);
+		update_wall_time();
 	}
 
 	update_process_times(user_mode(get_irq_regs()));
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index e2bced5..8329669 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -155,3 +155,4 @@ static inline int tick_device_is_functional(struct clock_event_device *dev)
 #endif
 
 extern void do_timer(unsigned long ticks);
+extern void update_wall_time(void);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 2afd43f..c58b03d 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -86,6 +86,7 @@ static void tick_do_update_jiffies64(ktime_t now)
 		tick_next_period = ktime_add(last_jiffies_update, tick_period);
 	}
 	write_sequnlock(&jiffies_lock);
+	update_wall_time();
 }
 
 /*
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index d62682b..44b7e6b 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1360,7 +1360,7 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk)
  * update_wall_time - Uses the current clocksource to increment the wall time
  *
  */
-static void update_wall_time(void)
+void update_wall_time(void)
 {
 	struct clocksource *clock;
 	struct timekeeper *real_tk = &timekeeper;
@@ -1441,19 +1441,8 @@ static void update_wall_time(void)
 	write_seqcount_end(&timekeeper_seq);
 out:
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
-	if (clock_was_set) {
-		/*
-		 * XXX -  I'd rather we just call clock_was_set(), but
-		 * since we're currently holding the jiffies lock, calling
-		 * clock_was_set would trigger an ipi which would then grab
-		 * the jiffies lock and we'd deadlock. :(
-		 * The right solution should probably be droping
-		 * the jiffies lock before calling update_wall_time
-		 * but that requires some rework of the tick sched
-		 * code.
-		 */
-		clock_was_set_delayed();
-	}
+	if (clock_set)
+		clock_was_set();
 }
 
 /**
@@ -1598,7 +1587,6 @@ struct timespec get_monotonic_coarse(void)
 void do_timer(unsigned long ticks)
 {
 	jiffies_64 += ticks;
-	update_wall_time();
 	calc_global_load(ticks);
 }
 
@@ -1756,4 +1744,5 @@ void xtime_update(unsigned long ticks)
 	write_seqlock(&jiffies_lock);
 	do_timer(ticks);
 	write_sequnlock(&jiffies_lock);
+	update_wall_time();
 }
-- 
cgit v0.10.2


From 04005f6011e3b504cd4d791d9769f7cb9a3b2eae Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Tue, 10 Dec 2013 17:13:35 -0800
Subject: timekeeping: Fix CLOCK_TAI timer/nanosleep delays

A think-o in the calculation of the monotonic -> tai time offset
results in CLOCK_TAI timers and nanosleeps to expire late (the
latency is ~2x the tai offset).

Fix this by adding the tai offset from the realtime offset instead
of subtracting.

Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: stable <stable@vger.kernel.org> #3.10+
Signed-off-by: John Stultz <john.stultz@linaro.org>

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 44b7e6b..3f6a827 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -77,7 +77,7 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec wtm)
 	tk->wall_to_monotonic = wtm;
 	set_normalized_timespec(&tmp, -wtm.tv_sec, -wtm.tv_nsec);
 	tk->offs_real = timespec_to_ktime(tmp);
-	tk->offs_tai = ktime_sub(tk->offs_real, ktime_set(tk->tai_offset, 0));
+	tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0));
 }
 
 static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t)
@@ -595,7 +595,7 @@ s32 timekeeping_get_tai_offset(void)
 static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset)
 {
 	tk->tai_offset = tai_offset;
-	tk->offs_tai = ktime_sub(tk->offs_real, ktime_set(tai_offset, 0));
+	tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0));
 }
 
 /**
-- 
cgit v0.10.2


From 330a1617b0a6268d427aa5922c94d082b1d3e96d Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Wed, 11 Dec 2013 19:10:36 -0800
Subject: timekeeping: Fix missing timekeeping_update in suspend path

Since 48cdc135d4840 (Implement a shadow timekeeper), we have to
call timekeeping_update() after any adjustment to the timekeeping
structure in order to make sure that any adjustments to the structure
persist.

In the timekeeping suspend path, we udpate the timekeeper
structure, so we should be sure to update the shadow-timekeeper
before releasing the timekeeping locks. Currently this isn't done.

In most cases, the next time related code to run would be
timekeeping_resume, which does update the shadow-timekeeper, but
in an abundence of caution, this patch adds the call to
timekeeping_update() in the suspend path.

Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: stable <stable@vger.kernel.org> #3.10+
Signed-off-by: John Stultz <john.stultz@linaro.org>

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 3f6a827..2793c43 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1024,6 +1024,8 @@ static int timekeeping_suspend(void)
 		timekeeping_suspend_time =
 			timespec_add(timekeeping_suspend_time, delta_delta);
 	}
+
+	timekeeping_update(tk, TK_MIRROR);
 	write_seqcount_end(&timekeeper_seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
-- 
cgit v0.10.2


From d26e4fe0dbe95778b9dbe80b6aa884d71fb6f459 Mon Sep 17 00:00:00 2001
From: Yijing Wang <wangyijing@huawei.com>
Date: Thu, 28 Nov 2013 16:28:55 +0800
Subject: timekeeper: fix comment typo for tk_setup_internals()

Fix trivial comment typo for tk_setup_internals().

Signed-off-by: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 2793c43..3ff3064 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -90,8 +90,9 @@ static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t)
 }
 
 /**
- * timekeeper_setup_internals - Set up internals to use clocksource clock.
+ * tk_setup_internals - Set up internals to use clocksource clock.
  *
+ * @tk:		The target timekeeper to setup.
  * @clock:		Pointer to clocksource.
  *
  * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment
-- 
cgit v0.10.2


From d5a1c7e3fc38d9c7d629e1e47f32f863acbdec3d Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@alien8.de>
Date: Sat, 20 Jul 2013 19:00:23 +0200
Subject: rtc-cmos: Add an alarm disable quirk

41c7f7424259f ("rtc: Disable the alarm in the hardware (v2)") added the
functionality to disable the RTC wake alarm when shutting down the box.

However, there are at least two b0rked BIOSes we know about:

https://bugzilla.novell.com/show_bug.cgi?id=812592
https://bugzilla.novell.com/show_bug.cgi?id=805740

where, when wakeup alarm is enabled in the BIOS, the machine reboots
automatically right after shutdown, regardless of what wakeup time is
programmed.

Bisecting the issue lead to this patch so disable its functionality with
a DMI quirk only for those boxes.

Cc: Brecht Machiels <brecht@mos6581.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Rabin Vincent <rabin.vincent@stericsson.com>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
[jstultz: Changed variable name for clarity, added extra dmi entry]
Tested-by: Brecht Machiels <brecht@mos6581.org>
Tested-by: Borislav Petkov <bp@suse.de>
Signed-off-by: John Stultz <john.stultz@linaro.org>

diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index f148762..a2325bc 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -34,11 +34,11 @@
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
 #include <linux/platform_device.h>
-#include <linux/mod_devicetable.h>
 #include <linux/log2.h>
 #include <linux/pm.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/dmi.h>
 
 /* this is for "generic access to PC-style RTC" using CMOS_READ/CMOS_WRITE */
 #include <asm-generic/rtc.h>
@@ -377,6 +377,51 @@ static int cmos_set_alarm(struct device *dev, struct rtc_wkalrm *t)
 	return 0;
 }
 
+/*
+ * Do not disable RTC alarm on shutdown - workaround for b0rked BIOSes.
+ */
+static bool alarm_disable_quirk;
+
+static int __init set_alarm_disable_quirk(const struct dmi_system_id *id)
+{
+	alarm_disable_quirk = true;
+	pr_info("rtc-cmos: BIOS has alarm-disable quirk. ");
+	pr_info("RTC alarms disabled\n");
+	return 0;
+}
+
+static const struct dmi_system_id rtc_quirks[] __initconst = {
+	/* https://bugzilla.novell.com/show_bug.cgi?id=805740 */
+	{
+		.callback = set_alarm_disable_quirk,
+		.ident    = "IBM Truman",
+		.matches  = {
+			DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "4852570"),
+		},
+	},
+	/* https://bugzilla.novell.com/show_bug.cgi?id=812592 */
+	{
+		.callback = set_alarm_disable_quirk,
+		.ident    = "Gigabyte GA-990XA-UD3",
+		.matches  = {
+			DMI_MATCH(DMI_SYS_VENDOR,
+					"Gigabyte Technology Co., Ltd."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "GA-990XA-UD3"),
+		},
+	},
+	/* http://permalink.gmane.org/gmane.linux.kernel/1604474 */
+	{
+		.callback = set_alarm_disable_quirk,
+		.ident    = "Toshiba Satellite L300",
+		.matches  = {
+			DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Satellite L300"),
+		},
+	},
+	{}
+};
+
 static int cmos_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
 	struct cmos_rtc	*cmos = dev_get_drvdata(dev);
@@ -385,6 +430,9 @@ static int cmos_alarm_irq_enable(struct device *dev, unsigned int enabled)
 	if (!is_valid_irq(cmos->irq))
 		return -EINVAL;
 
+	if (alarm_disable_quirk)
+		return 0;
+
 	spin_lock_irqsave(&rtc_lock, flags);
 
 	if (enabled)
@@ -1157,6 +1205,8 @@ static int __init cmos_init(void)
 			platform_driver_registered = true;
 	}
 
+	dmi_check_system(rtc_quirks);
+
 	if (retval == 0)
 		return 0;
 
-- 
cgit v0.10.2


From 38aef31ce7773624c8f09ff58c4c27b3b955faaf Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Mon, 23 Dec 2013 12:53:22 -0800
Subject: timekeeping: Remove comment that's mostly out of date

Prior to 92bb1fcf57a0c2e45f7e67fbf0a8ed475a749236 (Only
do nanosecond rounding on GENERIC_TIME_VSYSCALL_OLD
systems), the comment here was accuate, but now we can
mostly avoid the extra rounding which causes the unlikey
to be actually likely here.

So remove the out of date comment.

Signed-off-by: John Stultz <john.stultz@linaro.org>

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 3ff3064..abfa4e8 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1134,16 +1134,6 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
 		 * we can adjust by 1.
 		 */
 		error >>= 2;
-		/*
-		 * XXX - In update_wall_time, we round up to the next
-		 * nanosecond, and store the amount rounded up into
-		 * the error. This causes the likely below to be unlikely.
-		 *
-		 * The proper fix is to avoid rounding up by using
-		 * the high precision tk->xtime_nsec instead of
-		 * xtime.tv_nsec everywhere. Fixing this will take some
-		 * time.
-		 */
 		if (likely(error <= interval))
 			adj = 1;
 		else
-- 
cgit v0.10.2


From dcd740b645003b866d7eb30d13d34d0729cce9db Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Date: Mon, 16 Dec 2013 19:16:07 +0100
Subject: ARM: shmobile: armadillo: Fix coherent DMA mask

Commit 4dcfa60071b3d23f0181f27d8519f12e37cefbb9 ("ARM: DMA-API: better
handing of DMA masks for coherent allocations") added an additional
check to the coherent DMA mask that results in an error when the mask is
larger than what dma_addr_t can address.

Set the LCDC coherent DMA mask to DMA_BIT_MASK(32) instead of ~0 to fix
the problem.

Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>

diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c
index c186891..8ea87bd 100644
--- a/arch/arm/mach-shmobile/board-armadillo800eva.c
+++ b/arch/arm/mach-shmobile/board-armadillo800eva.c
@@ -483,7 +483,7 @@ static struct platform_device lcdc0_device = {
 	.id		= 0,
 	.dev	= {
 		.platform_data	= &lcdc0_info,
-		.coherent_dma_mask = ~0,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 	},
 };
 
@@ -580,7 +580,7 @@ static struct platform_device hdmi_lcdc_device = {
 	.id		= 1,
 	.dev	= {
 		.platform_data	= &hdmi_lcdc_info,
-		.coherent_dma_mask = ~0,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 	},
 };
 
-- 
cgit v0.10.2


From 4f387323853c495ac589210832fad4503f75a0e7 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Date: Mon, 16 Dec 2013 19:16:08 +0100
Subject: ARM: shmobile: kzm9g: Fix coherent DMA mask

Commit 4dcfa60071b3d23f0181f27d8519f12e37cefbb9 ("ARM: DMA-API: better
handing of DMA masks for coherent allocations") added an additional
check to the coherent DMA mask that results in an error when the mask is
larger than what dma_addr_t can address.

Set the LCDC coherent DMA mask to DMA_BIT_MASK(32) instead of ~0 to fix
the problem.

Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>

diff --git a/arch/arm/mach-shmobile/board-kzm9g.c b/arch/arm/mach-shmobile/board-kzm9g.c
index fe689b7..bc40b85 100644
--- a/arch/arm/mach-shmobile/board-kzm9g.c
+++ b/arch/arm/mach-shmobile/board-kzm9g.c
@@ -334,7 +334,7 @@ static struct platform_device lcdc_device = {
 	.resource	= lcdc_resources,
 	.dev	= {
 		.platform_data	= &lcdc_info,
-		.coherent_dma_mask = ~0,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 	},
 };
 
-- 
cgit v0.10.2


From b6328a6b7ba57fc84c38248f6f0e387e1170f1a8 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Date: Mon, 16 Dec 2013 19:16:09 +0100
Subject: ARM: shmobile: mackerel: Fix coherent DMA mask

Commit 4dcfa60071b3d23f0181f27d8519f12e37cefbb9 ("ARM: DMA-API: better
handing of DMA masks for coherent allocations") added an additional
check to the coherent DMA mask that results in an error when the mask is
larger than what dma_addr_t can address.

Set the LCDC coherent DMA mask to DMA_BIT_MASK(32) instead of ~0 to fix
the problem.

Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>

diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index af06753..e721d2c 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -409,7 +409,7 @@ static struct platform_device lcdc_device = {
 	.resource	= lcdc_resources,
 	.dev	= {
 		.platform_data	= &lcdc_info,
-		.coherent_dma_mask = ~0,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 	},
 };
 
@@ -499,7 +499,7 @@ static struct platform_device hdmi_lcdc_device = {
 	.id		= 1,
 	.dev	= {
 		.platform_data	= &hdmi_lcdc_info,
-		.coherent_dma_mask = ~0,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 	},
 };
 
-- 
cgit v0.10.2


From 8a613d40e389b723fd5889ac8d4033ed4030be31 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Date: Thu, 26 Dec 2013 05:41:50 +0000
Subject: perf probe: Expand given path to absolute path

Expand given path to absolute path in the option parser, except for a
module name.

Since realpath at later stage in processing several probe point, can be
called several times (even if currently doesn't, it can happen when we
expands the feature), it is waste of the performance.

Processing it once at the early stage can avoid that.

Changes from previous one:
 - Fix not to print null string.
 - Allocate memory for given path/module name everytime.

Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: "David A. Long" <dave.long@linaro.org>
Cc: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: systemtap@sourceware.org
Cc: yrl.pp-manager.tt@hitachi.com
Link: http://lkml.kernel.org/r/20131226054150.22364.12187.stgit@kbuild-fedora.novalocal
[ Clarified the pr_warning message as per David Ahern's suggestion ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index c98ccb5..1792a3f 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -169,6 +169,7 @@ static int opt_set_target(const struct option *opt, const char *str,
 			int unset __maybe_unused)
 {
 	int ret = -ENOENT;
+	char *tmp;
 
 	if  (str && !params.target) {
 		if (!strcmp(opt->long_name, "exec"))
@@ -180,7 +181,19 @@ static int opt_set_target(const struct option *opt, const char *str,
 		else
 			return ret;
 
-		params.target = str;
+		/* Expand given path to absolute path, except for modulename */
+		if (params.uprobes || strchr(str, '/')) {
+			tmp = realpath(str, NULL);
+			if (!tmp) {
+				pr_warning("Failed to get the absolute path of %s: %m\n", str);
+				return ret;
+			}
+		} else {
+			tmp = strdup(str);
+			if (!tmp)
+				return -ENOMEM;
+		}
+		params.target = tmp;
 		ret = 0;
 	}
 
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 544ac18..68013b9 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2281,7 +2281,7 @@ static int convert_name_to_addr(struct perf_probe_event *pev, const char *exec)
 	struct perf_probe_point *pp = &pev->point;
 	struct symbol *sym;
 	struct map *map = NULL;
-	char *function = NULL, *name = NULL;
+	char *function = NULL;
 	int ret = -EINVAL;
 	unsigned long long vaddr = 0;
 
@@ -2297,12 +2297,7 @@ static int convert_name_to_addr(struct perf_probe_event *pev, const char *exec)
 		goto out;
 	}
 
-	name = realpath(exec, NULL);
-	if (!name) {
-		pr_warning("Cannot find realpath for %s.\n", exec);
-		goto out;
-	}
-	map = dso__new_map(name);
+	map = dso__new_map(exec);
 	if (!map) {
 		pr_warning("Cannot find appropriate DSO for %s.\n", exec);
 		goto out;
@@ -2367,7 +2362,5 @@ out:
 	}
 	if (function)
 		free(function);
-	if (name)
-		free(name);
 	return ret;
 }
-- 
cgit v0.10.2


From fb7345bbf7fad9bf72ef63a19c707970b9685812 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Date: Thu, 26 Dec 2013 05:41:53 +0000
Subject: perf probe: Support basic dwarf-based operations on uprobe events

Support basic dwarf(debuginfo) based operations for uprobe events.  With
this change, perf probe can analyze debuginfo of user application binary
to set up new uprobe event.

This allows perf-probe --add(with local variables, line numbers) and
--line works with -x option.  (Actually, --vars has already accepted -x
option)

For example, the following command shows the probe-able lines of a given
user space function. Something that so far was only available in the
'perf probe' tool for kernel space functions:

  # ./perf probe -x perf --line map__load
  <map__load@/home/fedora/ksrc/linux-2.6/tools/perf/util/map.c:0>
        0  int map__load(struct map *map, symbol_filter_t filter)
        1  {
        2         const char *name = map->dso->long_name;
                  int nr;

        5         if (dso__loaded(map->dso, map->type))
        6                 return 0;

        8         nr = dso__load(map->dso, map, filter);
        9         if (nr < 0) {
       10                 if (map->dso->has_build_id) {

And this shows the available variables at the given line of the
function.

  # ./perf probe -x perf --vars map__load:8
  Available variables at map__load:8
          @<map__load+96>
                  char*   name
                  struct map*     map
                  symbol_filter_t filter
          @<map__find_symbol+112>
                  char*   name
                  symbol_filter_t filter
          @<map__find_symbol_by_name+136>
                  char*   name
                  symbol_filter_t filter
          @<map_groups__find_symbol_by_name+176>
                  char*   name
                  struct map*     map
                  symbol_filter_t filter

And lastly, we can now define probe(s) with all available
variables on the given line:

  # ./perf probe -x perf --add 'map__load:8 $vars'

  Added new events:
    probe_perf:map__load (on map__load:8 with $vars)
    probe_perf:map__load_1 (on map__load:8 with $vars)
    probe_perf:map__load_2 (on map__load:8 with $vars)
    probe_perf:map__load_3 (on map__load:8 with $vars)

  You can now use it in all perf tools, such as:

          perf record -e probe_perf:map__load_3 -aR sleep 1

  Changes from previous version:
   - Add examples in the patch description.
   - Use .text section start address and dwarf symbol address
     for calculating the offset of given symbol, instead of
     searching the symbol in symtab again.
     With this change, we can safely handle multiple local
     function instances (e.g. scnprintf in perf).

Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: David A. Long <dave.long@linaro.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: systemtap@sourceware.org
Cc: yrl.pp-manager.tt@hitachi.com
Link: http://lkml.kernel.org/r/20131226054152.22364.47021.stgit@kbuild-fedora.novalocal
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 1792a3f..43ff33d 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -424,7 +424,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	}
 
 #ifdef HAVE_DWARF_SUPPORT
-	if (params.show_lines && !params.uprobes) {
+	if (params.show_lines) {
 		if (params.mod_events) {
 			pr_err("  Error: Don't use --line with"
 			       " --add/--del.\n");
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 68013b9..72b56ae 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -172,6 +172,52 @@ const char *kernel_get_module_path(const char *module)
 	return (dso) ? dso->long_name : NULL;
 }
 
+/* Copied from unwind.c */
+static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
+				    GElf_Shdr *shp, const char *name)
+{
+	Elf_Scn *sec = NULL;
+
+	while ((sec = elf_nextscn(elf, sec)) != NULL) {
+		char *str;
+
+		gelf_getshdr(sec, shp);
+		str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name);
+		if (!strcmp(name, str))
+			break;
+	}
+
+	return sec;
+}
+
+static int get_text_start_address(const char *exec, unsigned long *address)
+{
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	GElf_Shdr shdr;
+	int fd, ret = -ENOENT;
+
+	fd = open(exec, O_RDONLY);
+	if (fd < 0)
+		return -errno;
+
+	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+	if (elf == NULL)
+		return -EINVAL;
+
+	if (gelf_getehdr(elf, &ehdr) == NULL)
+		goto out;
+
+	if (!elf_section_by_name(elf, &ehdr, &shdr, ".text"))
+		goto out;
+
+	*address = shdr.sh_addr - shdr.sh_offset;
+	ret = 0;
+out:
+	elf_end(elf);
+	return ret;
+}
+
 static int init_user_exec(void)
 {
 	int ret = 0;
@@ -186,6 +232,37 @@ static int init_user_exec(void)
 	return ret;
 }
 
+static int convert_exec_to_group(const char *exec, char **result)
+{
+	char *ptr1, *ptr2, *exec_copy;
+	char buf[64];
+	int ret;
+
+	exec_copy = strdup(exec);
+	if (!exec_copy)
+		return -ENOMEM;
+
+	ptr1 = basename(exec_copy);
+	if (!ptr1) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ptr2 = strpbrk(ptr1, "-._");
+	if (ptr2)
+		*ptr2 = '\0';
+	ret = e_snprintf(buf, 64, "%s_%s", PERFPROBE_GROUP, ptr1);
+	if (ret < 0)
+		goto out;
+
+	*result = strdup(buf);
+	ret = *result ? 0 : -ENOMEM;
+
+out:
+	free(exec_copy);
+	return ret;
+}
+
 static int convert_to_perf_probe_point(struct probe_trace_point *tp,
 					struct perf_probe_point *pp)
 {
@@ -261,6 +338,40 @@ static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
 	return 0;
 }
 
+static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
+					  int ntevs, const char *exec)
+{
+	int i, ret = 0;
+	unsigned long offset, stext = 0;
+	char buf[32];
+
+	if (!exec)
+		return 0;
+
+	ret = get_text_start_address(exec, &stext);
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; i < ntevs && ret >= 0; i++) {
+		offset = tevs[i].point.address - stext;
+		offset += tevs[i].point.offset;
+		tevs[i].point.offset = 0;
+		free(tevs[i].point.symbol);
+		ret = e_snprintf(buf, 32, "0x%lx", offset);
+		if (ret < 0)
+			break;
+		tevs[i].point.module = strdup(exec);
+		tevs[i].point.symbol = strdup(buf);
+		if (!tevs[i].point.symbol || !tevs[i].point.module) {
+			ret = -ENOMEM;
+			break;
+		}
+		tevs[i].uprobes = true;
+	}
+
+	return ret;
+}
+
 static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
 					    int ntevs, const char *module)
 {
@@ -305,15 +416,6 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 	struct debuginfo *dinfo;
 	int ntevs, ret = 0;
 
-	if (pev->uprobes) {
-		if (need_dwarf) {
-			pr_warning("Debuginfo-analysis is not yet supported"
-					" with -x/--exec option.\n");
-			return -ENOSYS;
-		}
-		return convert_name_to_addr(pev, target);
-	}
-
 	dinfo = open_debuginfo(target);
 
 	if (!dinfo) {
@@ -332,9 +434,14 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 
 	if (ntevs > 0) {	/* Succeeded to find trace events */
 		pr_debug("find %d probe_trace_events.\n", ntevs);
-		if (target)
-			ret = add_module_to_probe_trace_events(*tevs, ntevs,
-							       target);
+		if (target) {
+			if (pev->uprobes)
+				ret = add_exec_to_probe_trace_events(*tevs,
+						 ntevs, target);
+			else
+				ret = add_module_to_probe_trace_events(*tevs,
+						 ntevs, target);
+		}
 		return ret < 0 ? ret : ntevs;
 	}
 
@@ -654,9 +761,6 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 		return -ENOSYS;
 	}
 
-	if (pev->uprobes)
-		return convert_name_to_addr(pev, target);
-
 	return 0;
 }
 
@@ -1913,14 +2017,29 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev,
 					  int max_tevs, const char *target)
 {
 	struct symbol *sym;
-	int ret = 0, i;
+	int ret, i;
 	struct probe_trace_event *tev;
 
+	if (pev->uprobes && !pev->group) {
+		/* Replace group name if not given */
+		ret = convert_exec_to_group(target, &pev->group);
+		if (ret != 0) {
+			pr_warning("Failed to make a group name.\n");
+			return ret;
+		}
+	}
+
 	/* Convert perf_probe_event with debuginfo */
 	ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target);
 	if (ret != 0)
 		return ret;	/* Found in debuginfo or got an error */
 
+	if (pev->uprobes) {
+		ret = convert_name_to_addr(pev, target);
+		if (ret < 0)
+			return ret;
+	}
+
 	/* Allocate trace event buffer */
 	tev = *tevs = zalloc(sizeof(struct probe_trace_event));
 	if (tev == NULL)
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index f9f3de8..d481c46 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -12,6 +12,7 @@ struct probe_trace_point {
 	char		*symbol;	/* Base symbol */
 	char		*module;	/* Module name */
 	unsigned long	offset;		/* Offset from symbol */
+	unsigned long	address;	/* Actual address of the trace point */
 	bool		retprobe;	/* Return probe flag */
 };
 
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index ffb657f..7db7e05 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -729,6 +729,7 @@ static int convert_to_trace_point(Dwarf_Die *sp_die, Dwfl_Module *mod,
 		return -ENOENT;
 	}
 	tp->offset = (unsigned long)(paddr - sym.st_value);
+	tp->address = (unsigned long)paddr;
 	tp->symbol = strdup(symbol);
 	if (!tp->symbol)
 		return -ENOMEM;
-- 
cgit v0.10.2


From 5c743cf573e6974befe917ed4a36d42b39ef1ce0 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung.kim@lge.com>
Date: Thu, 26 Dec 2013 14:37:57 +0900
Subject: perf ui/tui: Protect windows by ui__lock

Sometimes perf top TUI breaks display with concurrent help/input window
and pr_* messages since they're not protected by ui__lock.

You can check it by pressing (and not releasing) 'h' key on a "perf top
-vvv" TUI session.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1388036284-32342-2-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/ui/tui/util.c b/tools/perf/ui/tui/util.c
index 092902e..bf890f7 100644
--- a/tools/perf/ui/tui/util.c
+++ b/tools/perf/ui/tui/util.c
@@ -92,6 +92,8 @@ int ui_browser__input_window(const char *title, const char *text, char *input,
 		t = sep + 1;
 	}
 
+	pthread_mutex_lock(&ui__lock);
+
 	max_len += 2;
 	nr_lines += 8;
 	y = SLtt_Screen_Rows / 2 - nr_lines / 2;
@@ -120,13 +122,19 @@ int ui_browser__input_window(const char *title, const char *text, char *input,
 	SLsmg_write_nstring((char *)exit_msg, max_len);
 	SLsmg_refresh();
 
+	pthread_mutex_unlock(&ui__lock);
+
 	x += 2;
 	len = 0;
 	key = ui__getch(delay_secs);
 	while (key != K_TIMER && key != K_ENTER && key != K_ESC) {
+		pthread_mutex_lock(&ui__lock);
+
 		if (key == K_BKSPC) {
-			if (len == 0)
+			if (len == 0) {
+				pthread_mutex_unlock(&ui__lock);
 				goto next_key;
+			}
 			SLsmg_gotorc(y, x + --len);
 			SLsmg_write_char(' ');
 		} else {
@@ -136,6 +144,8 @@ int ui_browser__input_window(const char *title, const char *text, char *input,
 		}
 		SLsmg_refresh();
 
+		pthread_mutex_unlock(&ui__lock);
+
 		/* XXX more graceful overflow handling needed */
 		if (len == sizeof(buf) - 1) {
 			ui_helpline__push("maximum size of symbol name reached!");
@@ -174,6 +184,8 @@ int ui__question_window(const char *title, const char *text,
 		t = sep + 1;
 	}
 
+	pthread_mutex_lock(&ui__lock);
+
 	max_len += 2;
 	nr_lines += 4;
 	y = SLtt_Screen_Rows / 2 - nr_lines / 2,
@@ -195,6 +207,9 @@ int ui__question_window(const char *title, const char *text,
 	SLsmg_gotorc(y + nr_lines - 1, x);
 	SLsmg_write_nstring((char *)exit_msg, max_len);
 	SLsmg_refresh();
+
+	pthread_mutex_unlock(&ui__lock);
+
 	return ui__getch(delay_secs);
 }
 
@@ -215,9 +230,7 @@ static int __ui__warning(const char *title, const char *format, va_list args)
 	if (vasprintf(&s, format, args) > 0) {
 		int key;
 
-		pthread_mutex_lock(&ui__lock);
 		key = ui__question_window(title, s, "Press any key...", 0);
-		pthread_mutex_unlock(&ui__lock);
 		free(s);
 		return key;
 	}
-- 
cgit v0.10.2


From e8e684a58b9bddde3fdb1a65cd26eb7a3e1e746e Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung.kim@lge.com>
Date: Thu, 26 Dec 2013 14:37:58 +0900
Subject: perf ui/tui: Split help message for perf top and report

Some hotkeys don't work for perf top so split help messages for them.

It'll be helpful to a future modification.  Also sort the message by
alphabetical order of the hotkey.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1388036284-32342-3-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index a440e03..d43ec79 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1400,6 +1400,35 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	char script_opt[64];
 	int delay_secs = hbt ? hbt->refresh : 0;
 
+#define HIST_BROWSER_HELP_COMMON					\
+	"h/?/F1        Show this window\n"				\
+	"UP/DOWN/PGUP\n"						\
+	"PGDN/SPACE    Navigate\n"					\
+	"q/ESC/CTRL+C  Exit browser\n\n"				\
+	"For multiple event sessions:\n\n"				\
+	"TAB/UNTAB     Switch events\n\n"				\
+	"For symbolic views (--sort has sym):\n\n"			\
+	"->            Zoom into DSO/Threads & Annotate current symbol\n" \
+	"<-            Zoom out\n"					\
+	"a             Annotate current symbol\n"			\
+	"C             Collapse all callchains\n"			\
+	"d             Zoom into current DSO\n"				\
+	"E             Expand all callchains\n"				\
+
+	/* help messages are sorted by lexical order of the hotkey */
+	const char report_help[] = HIST_BROWSER_HELP_COMMON
+	"P             Print histograms to perf.hist.N\n"
+	"r             Run available scripts\n"
+	"s             Switch to another data file in PWD\n"
+	"t             Zoom into current Thread\n"
+	"V             Verbose (DSO names in callchains, etc)\n"
+	"/             Filter symbol by name";
+	const char top_help[] = HIST_BROWSER_HELP_COMMON
+	"P             Print histograms to perf.hist.N\n"
+	"t             Zoom into current Thread\n"
+	"V             Verbose (DSO names in callchains, etc)\n"
+	"/             Filter symbol by name";
+
 	if (browser == NULL)
 		return -1;
 
@@ -1488,25 +1517,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 		case 'h':
 		case '?':
 			ui_browser__help_window(&browser->b,
-					"h/?/F1        Show this window\n"
-					"UP/DOWN/PGUP\n"
-					"PGDN/SPACE    Navigate\n"
-					"q/ESC/CTRL+C  Exit browser\n\n"
-					"For multiple event sessions:\n\n"
-					"TAB/UNTAB Switch events\n\n"
-					"For symbolic views (--sort has sym):\n\n"
-					"->            Zoom into DSO/Threads & Annotate current symbol\n"
-					"<-            Zoom out\n"
-					"a             Annotate current symbol\n"
-					"C             Collapse all callchains\n"
-					"E             Expand all callchains\n"
-					"d             Zoom into current DSO\n"
-					"t             Zoom into current Thread\n"
-					"r             Run available scripts('perf report' only)\n"
-					"s             Switch to another data file in PWD ('perf report' only)\n"
-					"P             Print histograms to perf.hist.N\n"
-					"V             Verbose (DSO names in callchains, etc)\n"
-					"/             Filter symbol by name");
+				is_report_browser(hbt) ? report_help : top_help);
 			continue;
 		case K_ENTER:
 		case K_RIGHT:
-- 
cgit v0.10.2


From 6dd601354f14b5cd7a0a4103811e52ccec22ac53 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung.kim@lge.com>
Date: Thu, 26 Dec 2013 14:37:59 +0900
Subject: perf ui/tui: Implement header window

Implement a simple, full-screen header window which shows session header
(metadata) information.  Press 'i' key to display the header window.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1388036284-32342-4-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 97a2145..3638b0b 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -489,6 +489,7 @@ ifndef NO_SLANG
   LIB_OBJS += $(OUTPUT)ui/browsers/hists.o
   LIB_OBJS += $(OUTPUT)ui/browsers/map.o
   LIB_OBJS += $(OUTPUT)ui/browsers/scripts.o
+  LIB_OBJS += $(OUTPUT)ui/browsers/header.o
   LIB_OBJS += $(OUTPUT)ui/tui/setup.o
   LIB_OBJS += $(OUTPUT)ui/tui/util.o
   LIB_OBJS += $(OUTPUT)ui/tui/helpline.o
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index 7d45d2f..118cca2 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -59,6 +59,8 @@ int ui_browser__help_window(struct ui_browser *browser, const char *text);
 bool ui_browser__dialog_yesno(struct ui_browser *browser, const char *text);
 int ui_browser__input_window(const char *title, const char *text, char *input,
 			     const char *exit_msg, int delay_sec);
+struct perf_session_env;
+int tui__header_window(struct perf_session_env *env);
 
 void ui_browser__argv_seek(struct ui_browser *browser, off_t offset, int whence);
 unsigned int ui_browser__argv_refresh(struct ui_browser *browser);
diff --git a/tools/perf/ui/browsers/header.c b/tools/perf/ui/browsers/header.c
new file mode 100644
index 0000000..89c16b9
--- /dev/null
+++ b/tools/perf/ui/browsers/header.c
@@ -0,0 +1,127 @@
+#include "util/cache.h"
+#include "util/debug.h"
+#include "ui/browser.h"
+#include "ui/ui.h"
+#include "ui/util.h"
+#include "ui/libslang.h"
+#include "util/header.h"
+#include "util/session.h"
+
+static void ui_browser__argv_write(struct ui_browser *browser,
+				   void *entry, int row)
+{
+	char **arg = entry;
+	char *str = *arg;
+	char empty[] = " ";
+	bool current_entry = ui_browser__is_current_entry(browser, row);
+	unsigned long offset = (unsigned long)browser->priv;
+
+	if (offset >= strlen(str))
+		str = empty;
+	else
+		str = str + offset;
+
+	ui_browser__set_color(browser, current_entry ? HE_COLORSET_SELECTED :
+						       HE_COLORSET_NORMAL);
+
+	slsmg_write_nstring(str, browser->width);
+}
+
+static int list_menu__run(struct ui_browser *menu)
+{
+	int key;
+	unsigned long offset;
+	const char help[] =
+	"h/?/F1        Show this window\n"
+	"UP/DOWN/PGUP\n"
+	"PGDN/SPACE\n"
+	"LEFT/RIGHT    Navigate\n"
+	"q/ESC/CTRL+C  Exit browser";
+
+	if (ui_browser__show(menu, "Header information", "Press 'q' to exit") < 0)
+		return -1;
+
+	while (1) {
+		key = ui_browser__run(menu, 0);
+
+		switch (key) {
+		case K_RIGHT:
+			offset = (unsigned long)menu->priv;
+			offset += 10;
+			menu->priv = (void *)offset;
+			continue;
+		case K_LEFT:
+			offset = (unsigned long)menu->priv;
+			if (offset >= 10)
+				offset -= 10;
+			menu->priv = (void *)offset;
+			continue;
+		case K_F1:
+		case 'h':
+		case '?':
+			ui_browser__help_window(menu, help);
+			continue;
+		case K_ESC:
+		case 'q':
+		case CTRL('c'):
+			key = -1;
+			break;
+		default:
+			continue;
+		}
+
+		break;
+	}
+
+	ui_browser__hide(menu);
+	return key;
+}
+
+static int ui__list_menu(int argc, char * const argv[])
+{
+	struct ui_browser menu = {
+		.entries    = (void *)argv,
+		.refresh    = ui_browser__argv_refresh,
+		.seek	    = ui_browser__argv_seek,
+		.write	    = ui_browser__argv_write,
+		.nr_entries = argc,
+	};
+
+	return list_menu__run(&menu);
+}
+
+int tui__header_window(struct perf_session_env *env)
+{
+	int i, argc = 0;
+	char **argv;
+	struct perf_session *session;
+	char *ptr, *pos;
+	size_t size;
+	FILE *fp = open_memstream(&ptr, &size);
+
+	session = container_of(env, struct perf_session, header.env);
+	perf_header__fprintf_info(session, fp, true);
+	fclose(fp);
+
+	for (pos = ptr, argc = 0; (pos = strchr(pos, '\n')) != NULL; pos++)
+		argc++;
+
+	argv = calloc(argc + 1, sizeof(*argv));
+	if (argv == NULL)
+		goto out;
+
+	argv[0] = pos = ptr;
+	for (i = 1; (pos = strchr(pos, '\n')) != NULL; i++) {
+		*pos++ = '\0';
+		argv[i] = pos;
+	}
+
+	BUG_ON(i != argc + 1);
+
+	ui__list_menu(argc, argv);
+
+out:
+	free(argv);
+	free(ptr);
+	return 0;
+}
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index d43ec79..0d9dd99 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1417,6 +1417,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
 	/* help messages are sorted by lexical order of the hotkey */
 	const char report_help[] = HIST_BROWSER_HELP_COMMON
+	"i             Show header information\n"
 	"P             Print histograms to perf.hist.N\n"
 	"r             Run available scripts\n"
 	"s             Switch to another data file in PWD\n"
@@ -1513,6 +1514,11 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			if (is_report_browser(hbt))
 				goto do_data_switch;
 			continue;
+		case 'i':
+			/* env->arch is NULL for live-mode (i.e. perf top) */
+			if (env->arch)
+				tui__header_window(env);
+			continue;
 		case K_F1:
 		case 'h':
 		case '?':
-- 
cgit v0.10.2


From 797f87f83b60685ff8a13fa0572d2f10393c50d3 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 26 Dec 2013 12:17:00 +0100
Subject: macvlan: fix netdev feature propagation from lower device

There are inconsistencies wrt. feature propagation/inheritance between
macvlan and the underlying interface.

When a feature is turned off on the real device before a macvlan is
created on top, these will remain enabled on the macvlan device, whereas
turning off the feature on the lower device after macvlan creation the
kernel will propagate the changes to the macvlan.

The second issue is that, when propagating changes from underlying device
to the macvlan interface, macvlan can erronously lose its NETIF_F_LLTX flag,
as features are anded with the underlying device.

However, LLTX should be kept since it has no dependencies on physical
hardware (LLTX is set on macvlan creation regardless of the lower
device properties, see 8ffab51b3dfc54876f145f15b351c41f3f703195
(macvlan: lockless tx path).

The LLTX flag is now forced regardless of user settings in absence of
layer2 hw acceleration (a6cc0cfa72e0b6d9f2c8fd858aa,
net: Add layer 2 hardware acceleration operations for macvlan devices).

Use netdev_increment_features to rebuild the feature set on capability
changes on either the lower device or on the macvlan interface.

As pointed out by Ben Hutchings, use netdev_update_features on
NETDEV_FEAT_CHANGE event (it calls macvlan_fix_features/netdev_features_change
if needed).

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index acf9379..60406b0 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -690,8 +690,19 @@ static netdev_features_t macvlan_fix_features(struct net_device *dev,
 					      netdev_features_t features)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
+	netdev_features_t mask;
 
-	return features & (vlan->set_features | ~MACVLAN_FEATURES);
+	features |= NETIF_F_ALL_FOR_ALL;
+	features &= (vlan->set_features | ~MACVLAN_FEATURES);
+	mask = features;
+
+	features = netdev_increment_features(vlan->lowerdev->features,
+					     features,
+					     mask);
+	if (!vlan->fwd_priv)
+		features |= NETIF_F_LLTX;
+
+	return features;
 }
 
 static const struct ethtool_ops macvlan_ethtool_ops = {
@@ -1019,9 +1030,8 @@ static int macvlan_device_event(struct notifier_block *unused,
 		break;
 	case NETDEV_FEAT_CHANGE:
 		list_for_each_entry(vlan, &port->vlans, list) {
-			vlan->dev->features = dev->features & MACVLAN_FEATURES;
 			vlan->dev->gso_max_size = dev->gso_max_size;
-			netdev_features_change(vlan->dev);
+			netdev_update_features(vlan->dev);
 		}
 		break;
 	case NETDEV_UNREGISTER:
-- 
cgit v0.10.2


From f5385650c02cd4373c4124c8a8fac3b5f9851e7f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 26 Dec 2013 15:54:57 -0300
Subject: perf tools: No need to test against NULL before calling free()

Its perfectly fine to call free(NULL), so no need to clutter the source
code with all those superfluous testing.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-uux5wpvevlerd42gqer13e7n@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 5a80da6..a6ec105 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1158,9 +1158,7 @@ out:
 	if (kvm->timerfd >= 0)
 		close(kvm->timerfd);
 
-	if (pollfds)
-		free(pollfds);
-
+	free(pollfds);
 	return err;
 }
 
diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c
index d63c68e..402d2bd 100644
--- a/tools/perf/ui/browsers/scripts.c
+++ b/tools/perf/ui/browsers/scripts.c
@@ -173,8 +173,7 @@ int script_browse(const char *script_opt)
 	if (script.b.width > AVERAGE_LINE_LEN)
 		script.b.width = AVERAGE_LINE_LEN;
 
-	if (line)
-		free(line);
+	free(line);
 	pclose(fp);
 
 	script.nr_lines = nr_entries;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 61c5421..10730b0 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1232,10 +1232,8 @@ static void free_event_desc(struct perf_evsel *events)
 		return;
 
 	for (evsel = events; evsel->attr.size; evsel++) {
-		if (evsel->name)
-			free(evsel->name);
-		if (evsel->id)
-			free(evsel->id);
+		free(evsel->name);
+		free(evsel->id);
 	}
 
 	free(events);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 72b56ae..095a98e 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -401,9 +401,7 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
 		}
 	}
 
-	if (tmp)
-		free(tmp);
-
+	free(tmp);
 	return ret;
 }
 
@@ -1382,8 +1380,7 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
 error:
 	pr_debug("Failed to synthesize perf probe point: %s\n",
 		 strerror(-ret));
-	if (buf)
-		free(buf);
+	free(buf);
 	return NULL;
 }
 
@@ -1584,34 +1581,25 @@ void clear_perf_probe_event(struct perf_probe_event *pev)
 	struct perf_probe_arg_field *field, *next;
 	int i;
 
-	if (pev->event)
-		free(pev->event);
-	if (pev->group)
-		free(pev->group);
-	if (pp->file)
-		free(pp->file);
-	if (pp->function)
-		free(pp->function);
-	if (pp->lazy_line)
-		free(pp->lazy_line);
+	free(pev->event);
+	free(pev->group);
+	free(pp->file);
+	free(pp->function);
+	free(pp->lazy_line);
+
 	for (i = 0; i < pev->nargs; i++) {
-		if (pev->args[i].name)
-			free(pev->args[i].name);
-		if (pev->args[i].var)
-			free(pev->args[i].var);
-		if (pev->args[i].type)
-			free(pev->args[i].type);
+		free(pev->args[i].name);
+		free(pev->args[i].var);
+		free(pev->args[i].type);
 		field = pev->args[i].field;
 		while (field) {
 			next = field->next;
-			if (field->name)
-				free(field->name);
+			free(field->name);
 			free(field);
 			field = next;
 		}
 	}
-	if (pev->args)
-		free(pev->args);
+	free(pev->args);
 	memset(pev, 0, sizeof(*pev));
 }
 
@@ -1620,21 +1608,14 @@ static void clear_probe_trace_event(struct probe_trace_event *tev)
 	struct probe_trace_arg_ref *ref, *next;
 	int i;
 
-	if (tev->event)
-		free(tev->event);
-	if (tev->group)
-		free(tev->group);
-	if (tev->point.symbol)
-		free(tev->point.symbol);
-	if (tev->point.module)
-		free(tev->point.module);
+	free(tev->event);
+	free(tev->group);
+	free(tev->point.symbol);
+	free(tev->point.module);
 	for (i = 0; i < tev->nargs; i++) {
-		if (tev->args[i].name)
-			free(tev->args[i].name);
-		if (tev->args[i].value)
-			free(tev->args[i].value);
-		if (tev->args[i].type)
-			free(tev->args[i].type);
+		free(tev->args[i].name);
+		free(tev->args[i].value);
+		free(tev->args[i].type);
 		ref = tev->args[i].ref;
 		while (ref) {
 			next = ref->next;
@@ -1642,8 +1623,7 @@ static void clear_probe_trace_event(struct probe_trace_event *tev)
 			ref = next;
 		}
 	}
-	if (tev->args)
-		free(tev->args);
+	free(tev->args);
 	memset(tev, 0, sizeof(*tev));
 }
 
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 7db7e05..8c08735 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1414,10 +1414,8 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 	if (ret < 0) {
 		/* Free vlist for error */
 		while (af.nvls--) {
-			if (af.vls[af.nvls].point.symbol)
-				free(af.vls[af.nvls].point.symbol);
-			if (af.vls[af.nvls].vars)
-				strlist__delete(af.vls[af.nvls].vars);
+			free(af.vls[af.nvls].point.symbol);
+			strlist__delete(af.vls[af.nvls].vars);
 		}
 		free(af.vls);
 		*vls = NULL;
@@ -1524,10 +1522,8 @@ post:
 	if (fname) {
 		ppt->file = strdup(fname);
 		if (ppt->file == NULL) {
-			if (ppt->function) {
-				free(ppt->function);
-				ppt->function = NULL;
-			}
+			free(ppt->function);
+			ppt->function = NULL;
 			ret = -ENOMEM;
 			goto end;
 		}
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 3773c48..e108207 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -194,8 +194,7 @@ static void define_event_symbols(struct event_format *event,
 		zero_flag_atom = 0;
 		break;
 	case PRINT_FIELD:
-		if (cur_field_name)
-			free(cur_field_name);
+		free(cur_field_name);
 		cur_field_name = strdup(args->field.name);
 		break;
 	case PRINT_FLAGS:
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index b258de6..cd9774d 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -161,8 +161,7 @@ static void define_event_symbols(struct event_format *event,
 		zero_flag_atom = 0;
 		break;
 	case PRINT_FIELD:
-		if (cur_field_name)
-			free(cur_field_name);
+		free(cur_field_name);
 		cur_field_name = strdup(args->field.name);
 		break;
 	case PRINT_FLAGS:
-- 
cgit v0.10.2


From db12cf27435356017e7ab375ef5e82a1cc749384 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Mon, 16 Dec 2013 17:09:41 +0100
Subject: netfilter: WARN about wrong usage of sequence number adjustments

Since commit 41d73ec053d2 (netfilter: nf_conntrack: make sequence
number adjustments usuable without NAT), the sequence number extension
is dynamically allocated.

Instead of dying, give a WARN splash, in case of wrong usage of the
seqadj code, e.g. when forgetting to allocate via nfct_seqadj_ext_add().

Wrong usage have been seen in the IPVS code path.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>

diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c
index 17c1bcb..b2d38da 100644
--- a/net/netfilter/nf_conntrack_seqadj.c
+++ b/net/netfilter/nf_conntrack_seqadj.c
@@ -36,6 +36,11 @@ int nf_ct_seqadj_set(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
 	if (off == 0)
 		return 0;
 
+	if (unlikely(!seqadj)) {
+		WARN(1, "Wrong seqadj usage, missing nfct_seqadj_ext_add()\n");
+		return 0;
+	}
+
 	set_bit(IPS_SEQ_ADJUST_BIT, &ct->status);
 
 	spin_lock_bh(&ct->lock);
-- 
cgit v0.10.2


From b25adce1606427fd88da08f5203714cada7f6a98 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Mon, 16 Dec 2013 17:09:47 +0100
Subject: ipvs: correct usage/allocation of seqadj ext in ipvs

The IPVS FTP helper ip_vs_ftp could trigger an OOPS in nf_ct_seqadj_set,
after commit 41d73ec053d2 (netfilter: nf_conntrack: make sequence number
adjustments usuable without NAT).

This is because, the seqadj ext is now allocated dynamically, and the
IPVS code didn't handle this situation.  Fix this in the IPVS nfct
code by invoking the alloc function nfct_seqadj_ext_add().

Fixes: 41d73ec053d2 (netfilter: nf_conntrack: make sequence number adjustments usuable without NAT)
Suggested-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>

diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c
index c8beafd..5a355a4 100644
--- a/net/netfilter/ipvs/ip_vs_nfct.c
+++ b/net/netfilter/ipvs/ip_vs_nfct.c
@@ -63,6 +63,7 @@
 #include <net/ip_vs.h>
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_conntrack_expect.h>
+#include <net/netfilter/nf_conntrack_seqadj.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_zones.h>
 
@@ -97,6 +98,11 @@ ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, int outin)
 	if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
 		return;
 
+	/* Applications may adjust TCP seqs */
+	if (cp->app && nf_ct_protonum(ct) == IPPROTO_TCP &&
+	    !nfct_seqadj(ct) && !nfct_seqadj_ext_add(ct))
+		return;
+
 	/*
 	 * The connection is not yet in the hashtable, so we update it.
 	 * CIP->VIP will remain the same, so leave the tuple in
-- 
cgit v0.10.2


From c2349758acf1874e4c2b93fe41d072336f1a31d0 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Wed, 18 Dec 2013 23:49:42 -0500
Subject: rds: prevent dereference of a NULL device

Binding might result in a NULL device, which is dereferenced
causing this BUG:

[ 1317.260548] BUG: unable to handle kernel NULL pointer dereference at 000000000000097
4
[ 1317.261847] IP: [<ffffffff84225f52>] rds_ib_laddr_check+0x82/0x110
[ 1317.263315] PGD 418bcb067 PUD 3ceb21067 PMD 0
[ 1317.263502] Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[ 1317.264179] Dumping ftrace buffer:
[ 1317.264774]    (ftrace buffer empty)
[ 1317.265220] Modules linked in:
[ 1317.265824] CPU: 4 PID: 836 Comm: trinity-child46 Tainted: G        W    3.13.0-rc4-
next-20131218-sasha-00013-g2cebb9b-dirty #4159
[ 1317.267415] task: ffff8803ddf33000 ti: ffff8803cd31a000 task.ti: ffff8803cd31a000
[ 1317.268399] RIP: 0010:[<ffffffff84225f52>]  [<ffffffff84225f52>] rds_ib_laddr_check+
0x82/0x110
[ 1317.269670] RSP: 0000:ffff8803cd31bdf8  EFLAGS: 00010246
[ 1317.270230] RAX: 0000000000000000 RBX: ffff88020b0dd388 RCX: 0000000000000000
[ 1317.270230] RDX: ffffffff8439822e RSI: 00000000000c000a RDI: 0000000000000286
[ 1317.270230] RBP: ffff8803cd31be38 R08: 0000000000000000 R09: 0000000000000000
[ 1317.270230] R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000000
[ 1317.270230] R13: 0000000054086700 R14: 0000000000a25de0 R15: 0000000000000031
[ 1317.270230] FS:  00007ff40251d700(0000) GS:ffff88022e200000(0000) knlGS:000000000000
0000
[ 1317.270230] CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
[ 1317.270230] CR2: 0000000000000974 CR3: 00000003cd478000 CR4: 00000000000006e0
[ 1317.270230] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 1317.270230] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000090602
[ 1317.270230] Stack:
[ 1317.270230]  0000000054086700 5408670000a25de0 5408670000000002 0000000000000000
[ 1317.270230]  ffffffff84223542 00000000ea54c767 0000000000000000 ffffffff86d26160
[ 1317.270230]  ffff8803cd31be68 ffffffff84223556 ffff8803cd31beb8 ffff8800c6765280
[ 1317.270230] Call Trace:
[ 1317.270230]  [<ffffffff84223542>] ? rds_trans_get_preferred+0x42/0xa0
[ 1317.270230]  [<ffffffff84223556>] rds_trans_get_preferred+0x56/0xa0
[ 1317.270230]  [<ffffffff8421c9c3>] rds_bind+0x73/0xf0
[ 1317.270230]  [<ffffffff83e4ce62>] SYSC_bind+0x92/0xf0
[ 1317.270230]  [<ffffffff812493f8>] ? context_tracking_user_exit+0xb8/0x1d0
[ 1317.270230]  [<ffffffff8119313d>] ? trace_hardirqs_on+0xd/0x10
[ 1317.270230]  [<ffffffff8107a852>] ? syscall_trace_enter+0x32/0x290
[ 1317.270230]  [<ffffffff83e4cece>] SyS_bind+0xe/0x10
[ 1317.270230]  [<ffffffff843a6ad0>] tracesys+0xdd/0xe2
[ 1317.270230] Code: 00 8b 45 cc 48 8d 75 d0 48 c7 45 d8 00 00 00 00 66 c7 45 d0 02 00
89 45 d4 48 89 df e8 78 49 76 ff 41 89 c4 85 c0 75 0c 48 8b 03 <80> b8 74 09 00 00 01 7
4 06 41 bc 9d ff ff ff f6 05 2a b6 c2 02
[ 1317.270230] RIP  [<ffffffff84225f52>] rds_ib_laddr_check+0x82/0x110
[ 1317.270230]  RSP <ffff8803cd31bdf8>
[ 1317.270230] CR2: 0000000000000974

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/rds/ib.c b/net/rds/ib.c
index b4c8b00..ba2dffe 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -338,7 +338,8 @@ static int rds_ib_laddr_check(__be32 addr)
 	ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);
 	/* due to this, we will claim to support iWARP devices unless we
 	   check node_type. */
-	if (ret || cm_id->device->node_type != RDMA_NODE_IB_CA)
+	if (ret || !cm_id->device ||
+	    cm_id->device->node_type != RDMA_NODE_IB_CA)
 		ret = -EADDRNOTAVAIL;
 
 	rdsdebug("addr %pI4 ret %d node type %d\n",
-- 
cgit v0.10.2


From 1a29321ed045e3aad23c5f7b63036e465ee3093a Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Mon, 23 Dec 2013 08:02:11 -0500
Subject: net_sched: act: Dont increment refcnt on replace

 This is a bug fix. The existing code tries to kill many
 birds with one stone: Handling binding of actions to
 filters, new actions and replacing of action
 attributes. A simple test case to illustrate:

XXXX
 moja@fe1:~$ sudo tc actions add action drop index 12
 moja@fe1:~$ actions get action gact index 12
 action order 1: gact action drop
  random type none pass val 0
  index 12 ref 1 bind 0
 moja@fe1:~$ sudo tc actions replace action ok index 12
 moja@fe1:~$ actions get action gact index 12
 action order 1: gact action drop
  random type none pass val 0
  index 12 ref 2 bind 0
XXXX

The above shows the refcounf being wrongly incremented on replace.
There are more complex scenarios with binding of actions to filters
that i am leaving out that didnt work as well...

Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 5c5edf5..11fe1a4 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -77,16 +77,16 @@ static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est,
 				     &csum_idx_gen, &csum_hash_info);
 		if (IS_ERR(pc))
 			return PTR_ERR(pc);
-		p = to_tcf_csum(pc);
 		ret = ACT_P_CREATED;
 	} else {
-		p = to_tcf_csum(pc);
-		if (!ovr) {
-			tcf_hash_release(pc, bind, &csum_hash_info);
+		if (bind)/* dont override defaults */
+			return 0;
+		tcf_hash_release(pc, bind, &csum_hash_info);
+		if (!ovr)
 			return -EEXIST;
-		}
 	}
 
+	p = to_tcf_csum(pc);
 	spin_lock_bh(&p->tcf_lock);
 	p->tcf_action = parm->action;
 	p->update_flags = parm->update_flags;
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 5645a4d..eb9ba60 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -102,10 +102,11 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 			return PTR_ERR(pc);
 		ret = ACT_P_CREATED;
 	} else {
-		if (!ovr) {
-			tcf_hash_release(pc, bind, &gact_hash_info);
+		if (bind)/* dont override defaults */
+			return 0;
+		tcf_hash_release(pc, bind, &gact_hash_info);
+		if (!ovr)
 			return -EEXIST;
-		}
 	}
 
 	gact = to_gact(pc);
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 882a897..dcbfe8c 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -141,10 +141,12 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 			return PTR_ERR(pc);
 		ret = ACT_P_CREATED;
 	} else {
-		if (!ovr) {
-			tcf_ipt_release(to_ipt(pc), bind);
+		if (bind)/* dont override defaults */
+			return 0;
+		tcf_ipt_release(to_ipt(pc), bind);
+
+		if (!ovr)
 			return -EEXIST;
-		}
 	}
 	ipt = to_ipt(pc);
 
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 6a15ace..7686953 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -70,15 +70,15 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 				     &nat_idx_gen, &nat_hash_info);
 		if (IS_ERR(pc))
 			return PTR_ERR(pc);
-		p = to_tcf_nat(pc);
 		ret = ACT_P_CREATED;
 	} else {
-		p = to_tcf_nat(pc);
-		if (!ovr) {
-			tcf_hash_release(pc, bind, &nat_hash_info);
+		if (bind)
+			return 0;
+		tcf_hash_release(pc, bind, &nat_hash_info);
+		if (!ovr)
 			return -EEXIST;
-		}
 	}
+	p = to_tcf_nat(pc);
 
 	spin_lock_bh(&p->tcf_lock);
 	p->old_addr = parm->old_addr;
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 03b6767..7aa2dcd 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -84,10 +84,12 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 		ret = ACT_P_CREATED;
 	} else {
 		p = to_pedit(pc);
-		if (!ovr) {
-			tcf_hash_release(pc, bind, &pedit_hash_info);
+		tcf_hash_release(pc, bind, &pedit_hash_info);
+		if (bind)
+			return 0;
+		if (!ovr)
 			return -EEXIST;
-		}
+
 		if (p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys) {
 			keys = kmalloc(ksize, GFP_KERNEL);
 			if (keys == NULL)
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 16a62c3..ef246d8 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -177,10 +177,12 @@ static int tcf_act_police_locate(struct net *net, struct nlattr *nla,
 			if (bind) {
 				police->tcf_bindcnt += 1;
 				police->tcf_refcnt += 1;
+				return 0;
 			}
 			if (ovr)
 				goto override;
-			return ret;
+			/* not replacing */
+			return -EEXIST;
 		}
 	}
 
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 31157d3..f7b45ab 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -142,10 +142,13 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 		ret = ACT_P_CREATED;
 	} else {
 		d = to_defact(pc);
-		if (!ovr) {
-			tcf_simp_release(d, bind);
+
+		if (bind)
+			return 0;
+		tcf_simp_release(d, bind);
+		if (!ovr)
 			return -EEXIST;
-		}
+
 		reset_policy(d, defdata, parm);
 	}
 
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 35ea643..8fe9d25 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -120,10 +120,11 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 		ret = ACT_P_CREATED;
 	} else {
 		d = to_skbedit(pc);
-		if (!ovr) {
-			tcf_hash_release(pc, bind, &skbedit_hash_info);
+		if (bind)
+			return 0;
+		tcf_hash_release(pc, bind, &skbedit_hash_info);
+		if (!ovr)
 			return -EEXIST;
-		}
 	}
 
 	spin_lock_bh(&d->tcf_lock);
-- 
cgit v0.10.2


From 375679104ab3ccfd18dcbd7ba503734fb9a2c63a Mon Sep 17 00:00:00 2001
From: Nithin Sujir <nsujir@broadcom.com>
Date: Thu, 19 Dec 2013 17:44:11 -0800
Subject: tg3: Expand 4g_overflow_test workaround to skb fragments of any size.

The current driver assumes that an skb fragment can only be upto jumbo
size. Presumably this was a fast-path optimization. This assumption is
no longer true as fragments can be upto 32k.

v2: Remove unnecessary parantheses per Eric Dumazet.

Cc: stable@vger.kernel.org
Signed-off-by: Nithin Nayak Sujir <nsujir@broadcom.com>
Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index f3dd93b..15a66e4 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -7622,7 +7622,7 @@ static inline int tg3_4g_overflow_test(dma_addr_t mapping, int len)
 {
 	u32 base = (u32) mapping & 0xffffffff;
 
-	return (base > 0xffffdcc0) && (base + len + 8 < base);
+	return base + len + 8 < base;
 }
 
 /* Test for TSO DMA buffers that cross into regions which are within MSS bytes
-- 
cgit v0.10.2


From 37ec274e9713eafc2ba6c4471420f06cb8f68ecf Mon Sep 17 00:00:00 2001
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Thu, 19 Dec 2013 18:10:40 -0800
Subject: arc_emac: fix potential use after free

Signed-off-by: Eric Dumazet <edumazet@google.com>

skb_tx_timestamp(skb) should be called _before_ TX completion
has a chance to trigger, otherwise it is too late and we access
freed memory.

Fixes: e4f2379db6c6 ("ethernet/arc/arc_emac - Add new driver")
From: Eric Dumazet <edumazet@google.com>
Cc: Alexey Brodkin <Alexey.Brodkin@synopsys.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index b2ffad1..248baf6 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -565,6 +565,8 @@ static int arc_emac_tx(struct sk_buff *skb, struct net_device *ndev)
 	/* Make sure pointer to data buffer is set */
 	wmb();
 
+	skb_tx_timestamp(skb);
+
 	*info = cpu_to_le32(FOR_EMAC | FIRST_OR_LAST_MASK | len);
 
 	/* Increment index to point to the next BD */
@@ -579,8 +581,6 @@ static int arc_emac_tx(struct sk_buff *skb, struct net_device *ndev)
 
 	arc_reg_set(priv, R_STATUS, TXPL_MASK);
 
-	skb_tx_timestamp(skb);
-
 	return NETDEV_TX_OK;
 }
 
-- 
cgit v0.10.2


From 73409f3b0ff0ae7bc1f647936b23e6d5d5dcbe28 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 27 Dec 2013 13:04:33 -0500
Subject: net: Add some clarification to skb_tx_timestamp() comment.

We've seen so many instances of people invoking skb_tx_timestamp()
after the device already has been given the packet, that it's worth
being a little bit more verbose and explicit in this comment.

Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6aae838..6f69b3f 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2531,6 +2531,10 @@ static inline void sw_tx_timestamp(struct sk_buff *skb)
  * Ethernet MAC Drivers should call this function in their hard_xmit()
  * function immediately before giving the sk_buff to the MAC hardware.
  *
+ * Specifically, one should make absolutely sure that this function is
+ * called before TX completion of this packet can trigger.  Otherwise
+ * the packet could potentially already be freed.
+ *
  * @skb: A socket buffer.
  */
 static inline void skb_tx_timestamp(struct sk_buff *skb)
-- 
cgit v0.10.2


From 4710b2ba873692194c636811ceda398f95e02db2 Mon Sep 17 00:00:00 2001
From: David Gibson <david@gibson.dropbear.id.au>
Date: Fri, 20 Dec 2013 15:10:44 +1100
Subject: netxen: Correct off-by-one errors in bounds checks

netxen_process_lro() contains two bounds checks.  One for the ring number
against the number of rings, and one for the Rx buffer ID against the
array of receive buffers.

Both of these have off-by-one errors, using > instead of >=. The correct
versions are used in netxen_process_rcv(), they're just wrong in
netxen_process_lro().

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
index 7692dfd..cc68657 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_init.c
@@ -1604,13 +1604,13 @@ netxen_process_lro(struct netxen_adapter *adapter,
 	u32 seq_number;
 	u8 vhdr_len = 0;
 
-	if (unlikely(ring > adapter->max_rds_rings))
+	if (unlikely(ring >= adapter->max_rds_rings))
 		return NULL;
 
 	rds_ring = &recv_ctx->rds_rings[ring];
 
 	index = netxen_get_lro_sts_refhandle(sts_data0);
-	if (unlikely(index > rds_ring->num_desc))
+	if (unlikely(index >= rds_ring->num_desc))
 		return NULL;
 
 	buffer = &rds_ring->rx_buf_arr[index];
-- 
cgit v0.10.2


From 6a9eadccff2926e392173a989042f14c867cffbf Mon Sep 17 00:00:00 2001
From: Li RongQing <roy.qing.li@gmail.com>
Date: Fri, 20 Dec 2013 17:20:12 +0800
Subject: ipv6: release dst properly in ipip6_tunnel_xmit

if a dst is not attached to anywhere, it should be released before
exit ipip6_tunnel_xmit, otherwise cause dst memory leakage.

Fixes: 61c1db7fae21 ("ipv6: sit: add GSO/TSO support")
Signed-off-by: Li RongQing <roy.qing.li@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index a710fde..c874822 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -966,8 +966,10 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
 
 	skb = iptunnel_handle_offloads(skb, false, SKB_GSO_SIT);
-	if (IS_ERR(skb))
+	if (IS_ERR(skb)) {
+		ip_rt_put(rt);
 		goto out;
+	}
 
 	err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, IPPROTO_IPV6, tos,
 			    ttl, df, !net_eq(tunnel->net, dev_net(dev)));
-- 
cgit v0.10.2


From 046625231a0397f1776eb353a4ec9ff142cd2f6b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 26 Dec 2013 17:41:15 -0300
Subject: perf tools: Introduce zfree

For the frequent idiom of:

   free(ptr);
   ptr = NULL;

Make it expect a pointer to the pointer being freed, so that it becomes
clear at first sight that the variable being freed is being modified.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-pfw02ezuab37kha18wlut7ir@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index aacef07..42faf36 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -154,8 +154,7 @@ static int perf_session_env__lookup_binutils_path(struct perf_session_env *env,
 		}
 		if (lookup_path(buf))
 			goto out;
-		free(buf);
-		buf = NULL;
+		zfree(&buf);
 	}
 
 	if (!strcmp(arch, "arm"))
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 4136f99..ab65057 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -180,8 +180,7 @@ find_next:
 			 * symbol, free he->ms.sym->src to signal we already
 			 * processed this symbol.
 			 */
-			free(notes->src);
-			notes->src = NULL;
+			zfree(&notes->src);
 		}
 	}
 }
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index dab98b5..106a5e5 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -185,8 +185,7 @@ static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 
 static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
 {
-	free(evsel->priv);
-	evsel->priv = NULL;
+	zfree(&evsel->priv);
 }
 
 static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel)
@@ -208,8 +207,7 @@ static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel)
 
 static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
 {
-	free(evsel->prev_raw_counts);
-	evsel->prev_raw_counts = NULL;
+	zfree(&evsel->prev_raw_counts);
 }
 
 static void perf_evlist__free_stats(struct perf_evlist *evlist)
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 20d4212..652af0b 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -488,8 +488,7 @@ static const char *cat_backtrace(union perf_event *event,
 				 * It seems the callchain is corrupted.
 				 * Discard all.
 				 */
-				free(p);
-				p = NULL;
+				zfree(&p);
 				goto exit;
 			}
 			continue;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index f64b5b0..c5b4bc5 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -146,8 +146,7 @@ static int perf_evsel__init_tp_ptr_field(struct perf_evsel *evsel,
 
 static void perf_evsel__delete_priv(struct perf_evsel *evsel)
 {
-	free(evsel->priv);
-	evsel->priv = NULL;
+	zfree(&evsel->priv);
 	perf_evsel__delete(evsel);
 }
 
@@ -165,8 +164,7 @@ static int perf_evsel__init_syscall_tp(struct perf_evsel *evsel, void *handler)
 	return -ENOMEM;
 
 out_delete:
-	free(evsel->priv);
-	evsel->priv = NULL;
+	zfree(&evsel->priv);
 	return -ENOENT;
 }
 
@@ -1278,10 +1276,8 @@ static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
 	size_t printed = syscall_arg__scnprintf_fd(bf, size, arg);
 	struct thread_trace *ttrace = arg->thread->priv;
 
-	if (ttrace && fd >= 0 && fd <= ttrace->paths.max) {
-		free(ttrace->paths.table[fd]);
-		ttrace->paths.table[fd] = NULL;
-	}
+	if (ttrace && fd >= 0 && fd <= ttrace->paths.max)
+		zfree(&ttrace->paths.table[fd]);
 
 	return printed;
 }
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 94223d40..d11541d 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -256,8 +256,7 @@ int ui_browser__show(struct ui_browser *browser, const char *title,
 	__ui_browser__show_title(browser, title);
 
 	browser->title = title;
-	free(browser->helpline);
-	browser->helpline = NULL;
+	zfree(&browser->helpline);
 
 	va_start(ap, helpline);
 	err = vasprintf(&browser->helpline, helpline, ap);
@@ -272,8 +271,7 @@ void ui_browser__hide(struct ui_browser *browser)
 {
 	pthread_mutex_lock(&ui__lock);
 	ui_helpline__pop();
-	free(browser->helpline);
-	browser->helpline = NULL;
+	zfree(&browser->helpline);
 	pthread_mutex_unlock(&ui__lock);
 }
 
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 0d9dd99..022d173 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1267,10 +1267,8 @@ static inline void free_popup_options(char **options, int n)
 {
 	int i;
 
-	for (i = 0; i < n; ++i) {
-		free(options[i]);
-		options[i] = NULL;
-	}
+	for (i = 0; i < n; ++i)
+		zfree(&options[i]);
 }
 
 /* Check whether the browser is for 'top' or 'report' */
diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c
index 696c1fb..52e7fc4 100644
--- a/tools/perf/ui/gtk/util.c
+++ b/tools/perf/ui/gtk/util.c
@@ -23,8 +23,7 @@ int perf_gtk__deactivate_context(struct perf_gtk_context **ctx)
 	if (!perf_gtk__is_active_context(*ctx))
 		return -1;
 
-	free(*ctx);
-	*ctx = NULL;
+	zfree(ctx);
 	return 0;
 }
 
diff --git a/tools/perf/util/alias.c b/tools/perf/util/alias.c
index e6d1347..c0b43ee 100644
--- a/tools/perf/util/alias.c
+++ b/tools/perf/util/alias.c
@@ -55,8 +55,7 @@ int split_cmdline(char *cmdline, const char ***argv)
 				src++;
 				c = cmdline[src];
 				if (!c) {
-					free(*argv);
-					*argv = NULL;
+					zfree(argv);
 					return error("cmdline ends with \\");
 				}
 			}
@@ -68,8 +67,7 @@ int split_cmdline(char *cmdline, const char ***argv)
 	cmdline[dst] = 0;
 
 	if (quoted) {
-		free(*argv);
-		*argv = NULL;
+		zfree(argv);
 		return error("unclosed quote");
 	}
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 27ab7b5..a78721d 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -185,8 +185,7 @@ static int lock__parse(struct ins_operands *ops)
 	return 0;
 
 out_free_ops:
-	free(ops->locked.ops);
-	ops->locked.ops = NULL;
+	zfree(&ops->locked.ops);
 	return 0;
 }
 
@@ -256,8 +255,7 @@ static int mov__parse(struct ins_operands *ops)
 	return 0;
 
 out_free_source:
-	free(ops->source.raw);
-	ops->source.raw = NULL;
+	zfree(&ops->source.raw);
 	return -1;
 }
 
@@ -560,8 +558,7 @@ static int disasm_line__parse(char *line, char **namep, char **rawp)
 	return 0;
 
 out_free_name:
-	free(*namep);
-	*namep = NULL;
+	zfree(namep);
 	return -1;
 }
 
@@ -1113,8 +1110,7 @@ static void symbol__free_source_line(struct symbol *sym, int len)
 		src_line = (void *)src_line + sizeof_src_line;
 	}
 
-	free(notes->src->lines);
-	notes->src->lines = NULL;
+	zfree(&notes->src->lines);
 }
 
 /* Get the filename:line for the colored entries */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 4ddeecb..4045d08 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -497,21 +497,18 @@ void dso__delete(struct dso *dso)
 		symbols__delete(&dso->symbols[i]);
 
 	if (dso->short_name_allocated) {
-		free((char *)dso->short_name);
-		dso->short_name		  = NULL;
+		zfree((char **)&dso->short_name);
 		dso->short_name_allocated = false;
 	}
 
 	if (dso->long_name_allocated) {
-		free((char *)dso->long_name);
-		dso->long_name		 = NULL;
+		zfree((char **)&dso->long_name);
 		dso->long_name_allocated = false;
 	}
 
 	dso_cache__free(&dso->cache);
 	dso__free_a2l(dso);
-	free(dso->symsrc_filename);
-	dso->symsrc_filename = NULL;
+	zfree(&dso->symsrc_filename);
 	free(dso);
 }
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index da31829..b08a7ec 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -101,10 +101,8 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 
 void perf_evlist__exit(struct perf_evlist *evlist)
 {
-	free(evlist->mmap);
-	free(evlist->pollfd);
-	evlist->mmap = NULL;
-	evlist->pollfd = NULL;
+	zfree(&evlist->mmap);
+	zfree(&evlist->pollfd);
 }
 
 void perf_evlist__delete(struct perf_evlist *evlist)
@@ -587,8 +585,7 @@ void perf_evlist__munmap(struct perf_evlist *evlist)
 	for (i = 0; i < evlist->nr_mmaps; i++)
 		__perf_evlist__munmap(evlist, i);
 
-	free(evlist->mmap);
-	evlist->mmap = NULL;
+	zfree(&evlist->mmap);
 }
 
 static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 6874e04..93b6031 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -750,8 +750,7 @@ void perf_evsel__free_id(struct perf_evsel *evsel)
 {
 	xyarray__delete(evsel->sample_id);
 	evsel->sample_id = NULL;
-	free(evsel->id);
-	evsel->id = NULL;
+	zfree(&evsel->id);
 }
 
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
@@ -1960,8 +1959,7 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 		evsel->attr.type   = PERF_TYPE_SOFTWARE;
 		evsel->attr.config = PERF_COUNT_SW_CPU_CLOCK;
 
-		free(evsel->name);
-		evsel->name = NULL;
+		zfree(&evsel->name);
 		return true;
 	}
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 10730b0..20f3a9c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1324,8 +1324,7 @@ read_event_desc(struct perf_header *ph, int fd)
 		}
 	}
 out:
-	if (buf)
-		free(buf);
+	free(buf);
 	return events;
 error:
 	if (events)
diff --git a/tools/perf/util/help.c b/tools/perf/util/help.c
index 8b1f6e8..7b68978 100644
--- a/tools/perf/util/help.c
+++ b/tools/perf/util/help.c
@@ -263,9 +263,8 @@ static void add_cmd_list(struct cmdnames *cmds, struct cmdnames *old)
 
 	for (i = 0; i < old->cnt; i++)
 		cmds->names[cmds->cnt++] = old->names[i];
-	free(old->names);
+	zfree(&old->names);
 	old->cnt = 0;
-	old->names = NULL;
 }
 
 const char *help_unknown_cmd(const char *cmd)
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index c78cc84..a98538d 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -102,8 +102,7 @@ void machine__exit(struct machine *machine)
 	map_groups__exit(&machine->kmaps);
 	dsos__delete(&machine->user_dsos);
 	dsos__delete(&machine->kernel_dsos);
-	free(machine->root_dir);
-	machine->root_dir = NULL;
+	zfree(&machine->root_dir);
 }
 
 void machine__delete(struct machine *machine)
@@ -562,11 +561,10 @@ void machine__destroy_kernel_maps(struct machine *machine)
 			 * on one of them.
 			 */
 			if (type == MAP__FUNCTION) {
-				free((char *)kmap->ref_reloc_sym->name);
-				kmap->ref_reloc_sym->name = NULL;
-				free(kmap->ref_reloc_sym);
-			}
-			kmap->ref_reloc_sym = NULL;
+				zfree((char **)&kmap->ref_reloc_sym->name);
+				zfree(&kmap->ref_reloc_sym);
+			} else
+				kmap->ref_reloc_sym = NULL;
 		}
 
 		map__delete(machine->vmlinux_maps[type]);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 095a98e..4d3cd1a 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -506,15 +506,13 @@ static int get_real_path(const char *raw_path, const char *comp_dir,
 		case EFAULT:
 			raw_path = strchr(++raw_path, '/');
 			if (!raw_path) {
-				free(*new_path);
-				*new_path = NULL;
+				zfree(new_path);
 				return -ENOENT;
 			}
 			continue;
 
 		default:
-			free(*new_path);
-			*new_path = NULL;
+			zfree(new_path);
 			return -errno;
 		}
 	}
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 8c08735..6d8796e 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -226,10 +226,8 @@ struct debuginfo *debuginfo__new(const char *path)
 	if (!dbg)
 		return NULL;
 
-	if (debuginfo__init_offline_dwarf(dbg, path) < 0) {
-		free(dbg);
-		dbg = NULL;
-	}
+	if (debuginfo__init_offline_dwarf(dbg, path) < 0)
+		zfree(&dbg);
 
 	return dbg;
 }
@@ -241,10 +239,8 @@ struct debuginfo *debuginfo__new_online_kernel(unsigned long addr)
 	if (!dbg)
 		return NULL;
 
-	if (debuginfo__init_online_kernel_dwarf(dbg, (Dwarf_Addr)addr) < 0) {
-		free(dbg);
-		dbg = NULL;
-	}
+	if (debuginfo__init_online_kernel_dwarf(dbg, (Dwarf_Addr)addr) < 0)
+		zfree(&dbg);
 
 	return dbg;
 }
@@ -1302,8 +1298,7 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 
 	ret = debuginfo__find_probes(dbg, &tf.pf);
 	if (ret < 0) {
-		free(*tevs);
-		*tevs = NULL;
+		zfree(tevs);
 		return ret;
 	}
 
@@ -1417,8 +1412,7 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 			free(af.vls[af.nvls].point.symbol);
 			strlist__delete(af.vls[af.nvls].vars);
 		}
-		free(af.vls);
-		*vls = NULL;
+		zfree(vls);
 		return ret;
 	}
 
@@ -1522,8 +1516,7 @@ post:
 	if (fname) {
 		ppt->file = strdup(fname);
 		if (ppt->file == NULL) {
-			free(ppt->function);
-			ppt->function = NULL;
+			zfree(&ppt->function);
 			ret = -ENOMEM;
 			goto end;
 		}
@@ -1577,8 +1570,7 @@ static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
 		else
 			ret = 0;	/* Lines are not found */
 	else {
-		free(lf->lr->path);
-		lf->lr->path = NULL;
+		zfree(&lf->lr->path);
 	}
 	return ret;
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 923d000..fd9e1a4 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1621,13 +1621,10 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
 
 static void vmlinux_path__exit(void)
 {
-	while (--vmlinux_path__nr_entries >= 0) {
-		free(vmlinux_path[vmlinux_path__nr_entries]);
-		vmlinux_path[vmlinux_path__nr_entries] = NULL;
-	}
+	while (--vmlinux_path__nr_entries >= 0)
+		zfree(&vmlinux_path[vmlinux_path__nr_entries]);
 
-	free(vmlinux_path);
-	vmlinux_path = NULL;
+	zfree(&vmlinux_path);
 }
 
 static int vmlinux_path__init(void)
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 9b5f856..cf44644 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -9,6 +9,7 @@
 #include "strlist.h"
 #include <string.h>
 #include "thread_map.h"
+#include "util.h"
 
 /* Skip "." and ".." directories */
 static int filter(const struct dirent *dir)
@@ -138,8 +139,7 @@ out_free_namelist:
 	free(namelist);
 
 out_free_closedir:
-	free(threads);
-	threads = NULL;
+	zfree(&threads);
 	goto out_closedir;
 }
 
@@ -210,8 +210,7 @@ out_free_namelist:
 	free(namelist);
 
 out_free_threads:
-	free(threads);
-	threads = NULL;
+	zfree(&threads);
 	goto out;
 }
 
@@ -262,8 +261,7 @@ out:
 	return threads;
 
 out_free_threads:
-	free(threads);
-	threads = NULL;
+	zfree(&threads);
 	goto out;
 }
 
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index c354b95..9f73bf4 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -562,10 +562,8 @@ out:
 		output_fd = fd;
 	}
 
-	if (err) {
-		free(tdata);
-		tdata = NULL;
-	}
+	if (err)
+		zfree(&tdata);
 
 	put_tracepoints_path(tps);
 	return tdata;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 9a2c268..6995d66 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -186,6 +186,8 @@ static inline void *zalloc(size_t size)
 	return calloc(1, size);
 }
 
+#define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
+
 static inline int has_extension(const char *filename, const char *ext)
 {
 	size_t len = strlen(filename);
-- 
cgit v0.10.2


From 74cf249d5cf7de84c88cca69a2f13b13d500ff94 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 27 Dec 2013 16:55:14 -0300
Subject: perf tools: Use zfree to help detect use after free bugs

Several areas already used this technique, so do some audit to
consistently use it elsewhere.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-9sbere0kkplwe45ak6rk4a1f@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 2a85cc9..e6a0844 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -654,7 +654,7 @@ static void data__free(struct data__file *d)
 	for (col = 0; col < PERF_HPP_DIFF__MAX_INDEX; col++) {
 		struct diff_hpp_fmt *fmt = &d->fmt[col];
 
-		free(fmt->header);
+		zfree(&fmt->header);
 	}
 }
 
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 0f3c6551..6a76a07 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -469,7 +469,7 @@ static void *thread_func(void *ctx)
 	char comm2[22];
 	int fd;
 
-	free(parms);
+	zfree(&parms);
 
 	sprintf(comm2, ":%s", this_task->comm);
 	prctl(PR_SET_NAME, comm2);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 62ef190..6040000 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1102,9 +1102,9 @@ static struct script_desc *script_desc__new(const char *name)
 
 static void script_desc__delete(struct script_desc *s)
 {
-	free(s->name);
-	free(s->half_liner);
-	free(s->args);
+	zfree(&s->name);
+	zfree(&s->half_liner);
+	zfree(&s->args);
 	free(s);
 }
 
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 022d173..a7045ea 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1327,7 +1327,7 @@ static int switch_data_file(void)
 
 			abs_path[nr_options] = strdup(path);
 			if (!abs_path[nr_options]) {
-				free(options[nr_options]);
+				zfree(&options[nr_options]);
 				ui__warning("Can't search all data files due to memory shortage.\n");
 				fclose(file);
 				break;
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index c244cb5..831fbb7 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -510,7 +510,7 @@ print_entries:
 
 	free(line);
 out:
-	free(rem_sq_bracket);
+	zfree(&rem_sq_bracket);
 
 	return ret;
 }
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index a78721d..469eb67 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -26,10 +26,10 @@ static int disasm_line__parse(char *line, char **namep, char **rawp);
 
 static void ins__delete(struct ins_operands *ops)
 {
-	free(ops->source.raw);
-	free(ops->source.name);
-	free(ops->target.raw);
-	free(ops->target.name);
+	zfree(&ops->source.raw);
+	zfree(&ops->source.name);
+	zfree(&ops->target.raw);
+	zfree(&ops->target.name);
 }
 
 static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size,
@@ -204,9 +204,9 @@ static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
 
 static void lock__delete(struct ins_operands *ops)
 {
-	free(ops->locked.ops);
-	free(ops->target.raw);
-	free(ops->target.name);
+	zfree(&ops->locked.ops);
+	zfree(&ops->target.raw);
+	zfree(&ops->target.name);
 }
 
 static struct ins_ops lock_ops = {
@@ -583,7 +583,7 @@ static struct disasm_line *disasm_line__new(s64 offset, char *line, size_t privs
 	return dl;
 
 out_free_line:
-	free(dl->line);
+	zfree(&dl->line);
 out_delete:
 	free(dl);
 	return NULL;
@@ -591,8 +591,8 @@ out_delete:
 
 void disasm_line__free(struct disasm_line *dl)
 {
-	free(dl->line);
-	free(dl->name);
+	zfree(&dl->line);
+	zfree(&dl->name);
 	if (dl->ins && dl->ins->ops->free)
 		dl->ins->ops->free(&dl->ops);
 	else
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 96bbda1..0922aa4 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -133,7 +133,7 @@ void close_cgroup(struct cgroup_sel *cgrp)
 	/* XXX: not reentrant */
 	if (--cgrp->refcnt == 0) {
 		close(cgrp->fd);
-		free(cgrp->name);
+		zfree(&cgrp->name);
 		free(cgrp);
 	}
 }
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index ee0df0e..67d1e40 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -21,7 +21,7 @@ static void comm_str__put(struct comm_str *cs)
 {
 	if (!--cs->ref) {
 		rb_erase(&cs->rb_node, &comm_str_root);
-		free(cs->str);
+		zfree(&cs->str);
 		free(cs);
 	}
 }
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 93b6031..ade8d9c 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -208,7 +208,7 @@ struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int
 	return evsel;
 
 out_free:
-	free(evsel->name);
+	zfree(&evsel->name);
 	free(evsel);
 	return NULL;
 }
@@ -766,7 +766,7 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 
 void perf_evsel__free_counts(struct perf_evsel *evsel)
 {
-	free(evsel->counts);
+	zfree(&evsel->counts);
 }
 
 void perf_evsel__exit(struct perf_evsel *evsel)
@@ -780,10 +780,10 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 {
 	perf_evsel__exit(evsel);
 	close_cgroup(evsel->cgrp);
-	free(evsel->group_name);
+	zfree(&evsel->group_name);
 	if (evsel->tp_format)
 		pevent_free_format(evsel->tp_format);
-	free(evsel->name);
+	zfree(&evsel->name);
 	free(evsel);
 }
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 20f3a9c..a4a60b7 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -800,10 +800,10 @@ static void free_cpu_topo(struct cpu_topo *tp)
 		return;
 
 	for (i = 0 ; i < tp->core_sib; i++)
-		free(tp->core_siblings[i]);
+		zfree(&tp->core_siblings[i]);
 
 	for (i = 0 ; i < tp->thread_sib; i++)
-		free(tp->thread_siblings[i]);
+		zfree(&tp->thread_siblings[i]);
 
 	free(tp);
 }
@@ -1232,8 +1232,8 @@ static void free_event_desc(struct perf_evsel *events)
 		return;
 
 	for (evsel = events; evsel->attr.size; evsel++) {
-		free(evsel->name);
-		free(evsel->id);
+		zfree(&evsel->name);
+		zfree(&evsel->id);
 	}
 
 	free(events);
@@ -2105,7 +2105,7 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused,
 	ret = 0;
 out_free:
 	for (i = 0; i < nr_groups; i++)
-		free(desc[i].name);
+		zfree(&desc[i].name);
 	free(desc);
 
 	return ret;
diff --git a/tools/perf/util/help.c b/tools/perf/util/help.c
index 7b68978..86c37c4 100644
--- a/tools/perf/util/help.c
+++ b/tools/perf/util/help.c
@@ -22,8 +22,8 @@ static void clean_cmdnames(struct cmdnames *cmds)
 	unsigned int i;
 
 	for (i = 0; i < cmds->cnt; ++i)
-		free(cmds->names[i]);
-	free(cmds->names);
+		zfree(&cmds->names[i]);
+	zfree(&cmds->names);
 	cmds->cnt = 0;
 	cmds->alloc = 0;
 }
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6cd4823..4ed3e88 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -372,7 +372,7 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 			 * This mem info was allocated from machine__resolve_mem
 			 * and will not be used anymore.
 			 */
-			free(entry->mem_info);
+			zfree(&entry->mem_info);
 
 			/* If the map of an existing hist_entry has
 			 * become out-of-date due to an exec() or
@@ -475,8 +475,8 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 
 void hist_entry__free(struct hist_entry *he)
 {
-	free(he->branch_info);
-	free(he->mem_info);
+	zfree(&he->branch_info);
+	zfree(&he->mem_info);
 	free_srcline(he->srcline);
 	free(he);
 }
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 094c28b..0153435 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -204,7 +204,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 				}
 				path->name = malloc(MAX_EVENT_LENGTH);
 				if (!path->name) {
-					free(path->system);
+					zfree(&path->system);
 					free(path);
 					return NULL;
 				}
@@ -236,8 +236,8 @@ struct tracepoint_path *tracepoint_name_to_path(const char *name)
 	path->name = strdup(str+1);
 
 	if (path->system == NULL || path->name == NULL) {
-		free(path->system);
-		free(path->name);
+		zfree(&path->system);
+		zfree(&path->name);
 		free(path);
 		path = NULL;
 	}
@@ -917,7 +917,7 @@ int parse_events_terms(struct list_head *terms, const char *str)
 	ret = parse_events__scanner(str, &data, PE_START_TERMS);
 	if (!ret) {
 		list_splice(data.terms, terms);
-		free(data.terms);
+		zfree(&data.terms);
 		return 0;
 	}
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 56fc10a..0934d64 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -755,7 +755,7 @@ void print_pmu_events(const char *event_glob, bool name_only)
 			continue;
 		}
 		printf("  %-50s [Kernel PMU event]\n", aliases[j]);
-		free(aliases[j]);
+		zfree(&aliases[j]);
 		printed++;
 	}
 	if (printed)
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 4d3cd1a..86ed858 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -356,7 +356,7 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
 		offset = tevs[i].point.address - stext;
 		offset += tevs[i].point.offset;
 		tevs[i].point.offset = 0;
-		free(tevs[i].point.symbol);
+		zfree(&tevs[i].point.symbol);
 		ret = e_snprintf(buf, 32, "0x%lx", offset);
 		if (ret < 0)
 			break;
@@ -683,7 +683,7 @@ static int show_available_vars_at(struct debuginfo *dinfo,
 		 */
 		fprintf(stdout, "\t@<%s+%lu>\n", vl->point.symbol,
 			vl->point.offset);
-		free(vl->point.symbol);
+		zfree(&vl->point.symbol);
 		nvars = 0;
 		if (vl->vars) {
 			strlist__for_each(node, vl->vars) {
@@ -1592,7 +1592,7 @@ void clear_perf_probe_event(struct perf_probe_event *pev)
 		field = pev->args[i].field;
 		while (field) {
 			next = field->next;
-			free(field->name);
+			zfree(&field->name);
 			free(field);
 			field = next;
 		}
@@ -2153,7 +2153,7 @@ end:
 	for (i = 0; i < npevs; i++) {
 		for (j = 0; j < pkgs[i].ntevs; j++)
 			clear_probe_trace_event(&pkgs[i].tevs[j]);
-		free(pkgs[i].tevs);
+		zfree(&pkgs[i].tevs);
 	}
 	free(pkgs);
 
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 6d8796e..061edb1 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1409,7 +1409,7 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 	if (ret < 0) {
 		/* Free vlist for error */
 		while (af.nvls--) {
-			free(af.vls[af.nvls].point.symbol);
+			zfree(&af.vls[af.nvls].point.symbol);
 			strlist__delete(af.vls[af.nvls].vars);
 		}
 		zfree(vls);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index d3a857be..8ffe29c 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -132,18 +132,18 @@ static void perf_session__delete_threads(struct perf_session *session)
 
 static void perf_session_env__delete(struct perf_session_env *env)
 {
-	free(env->hostname);
-	free(env->os_release);
-	free(env->version);
-	free(env->arch);
-	free(env->cpu_desc);
-	free(env->cpuid);
-
-	free(env->cmdline);
-	free(env->sibling_cores);
-	free(env->sibling_threads);
-	free(env->numa_nodes);
-	free(env->pmu_mappings);
+	zfree(&env->hostname);
+	zfree(&env->os_release);
+	zfree(&env->version);
+	zfree(&env->arch);
+	zfree(&env->cpu_desc);
+	zfree(&env->cpuid);
+
+	zfree(&env->cmdline);
+	zfree(&env->sibling_cores);
+	zfree(&env->sibling_threads);
+	zfree(&env->numa_nodes);
+	zfree(&env->pmu_mappings);
 }
 
 void perf_session__delete(struct perf_session *session)
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 58b2bd8..7e67879 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -129,7 +129,7 @@ static struct a2l_data *addr2line_init(const char *path)
 
 out:
 	if (a2l) {
-		free((void *)a2l->input);
+		zfree((void **)&a2l->input);
 		free(a2l);
 	}
 	bfd_close(abfd);
@@ -140,8 +140,8 @@ static void addr2line_cleanup(struct a2l_data *a2l)
 {
 	if (a2l->abfd)
 		bfd_close(a2l->abfd);
-	free((void *)a2l->input);
-	free(a2l->syms);
+	zfree((void **)&a2l->input);
+	zfree(&a2l->syms);
 	free(a2l);
 }
 
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index cfa9068..4abe235 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -28,7 +28,7 @@ void strbuf_init(struct strbuf *sb, ssize_t hint)
 void strbuf_release(struct strbuf *sb)
 {
 	if (sb->alloc) {
-		free(sb->buf);
+		zfree(&sb->buf);
 		strbuf_init(sb, 0);
 	}
 }
diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c
index 3edd053..79a757a 100644
--- a/tools/perf/util/strfilter.c
+++ b/tools/perf/util/strfilter.c
@@ -14,7 +14,7 @@ static void strfilter_node__delete(struct strfilter_node *node)
 {
 	if (node) {
 		if (node->p && !is_operator(*node->p))
-			free((char *)node->p);
+			zfree((char **)&node->p);
 		strfilter_node__delete(node->l);
 		strfilter_node__delete(node->r);
 		free(node);
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index f0b0c00..2553e5b 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -128,7 +128,7 @@ void argv_free(char **argv)
 {
 	char **p;
 	for (p = argv; *p; p++)
-		free(*p);
+		zfree(p);
 
 	free(argv);
 }
diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c
index eabdce0..61a90bf 100644
--- a/tools/perf/util/strlist.c
+++ b/tools/perf/util/strlist.c
@@ -5,6 +5,7 @@
  */
 
 #include "strlist.h"
+#include "util.h"
 #include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -38,7 +39,7 @@ out_delete:
 static void str_node__delete(struct str_node *snode, bool dupstr)
 {
 	if (dupstr)
-		free((void *)snode->s);
+		zfree((void **)&snode->s);
 	free(snode);
 }
 
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 56a84f2..43262b8 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -21,6 +21,7 @@
 
 #include "perf.h"
 #include "svghelper.h"
+#include "util.h"
 #include "cpumap.h"
 
 static u64 first_time, last_time;
@@ -708,8 +709,8 @@ int svg_build_topology_map(char *sib_core, int sib_core_nr,
 	return 0;
 
 exit:
-	free(t.sib_core);
-	free(t.sib_thr);
+	zfree(&t.sib_core);
+	zfree(&t.sib_thr);
 
 	return -1;
 }
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index bf0ce29..4b0a127 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -554,7 +554,7 @@ bool symsrc__has_symtab(struct symsrc *ss)
 
 void symsrc__destroy(struct symsrc *ss)
 {
-	free(ss->name);
+	zfree(&ss->name);
 	elf_end(ss->elf);
 	close(ss->fd);
 }
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index ac7070a..bd15f49 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -1,4 +1,5 @@
 #include "symbol.h"
+#include "util.h"
 
 #include <stdio.h>
 #include <fcntl.h>
@@ -275,7 +276,7 @@ bool symsrc__has_symtab(struct symsrc *ss __maybe_unused)
 
 void symsrc__destroy(struct symsrc *ss)
 {
-	free(ss->name);
+	zfree(&ss->name);
 	close(ss->fd);
 }
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index fd9e1a4..39ce9ad 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -796,7 +796,7 @@ static void delete_modules(struct rb_root *modules)
 		mi = rb_entry(next, struct module_info, rb_node);
 		next = rb_next(&mi->rb_node);
 		rb_erase(&mi->rb_node, modules);
-		free(mi->name);
+		zfree(&mi->name);
 		free(mi);
 	}
 }
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index cf44644..5d32159 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -41,7 +41,7 @@ struct thread_map *thread_map__new_by_pid(pid_t pid)
 	}
 
 	for (i=0; i<items; i++)
-		free(namelist[i]);
+		zfree(&namelist[i]);
 	free(namelist);
 
 	return threads;
@@ -118,7 +118,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 			threads->map[threads->nr + i] = atoi(namelist[i]->d_name);
 
 		for (i = 0; i < items; i++)
-			free(namelist[i]);
+			zfree(&namelist[i]);
 		free(namelist);
 
 		threads->nr += items;
@@ -135,7 +135,7 @@ out_free_threads:
 
 out_free_namelist:
 	for (i = 0; i < items; i++)
-		free(namelist[i]);
+		zfree(&namelist[i]);
 	free(namelist);
 
 out_free_closedir:
@@ -194,7 +194,7 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
 
 		for (i = 0; i < items; i++) {
 			threads->map[j++] = atoi(namelist[i]->d_name);
-			free(namelist[i]);
+			zfree(&namelist[i]);
 		}
 		threads->nr = total_tasks;
 		free(namelist);
@@ -206,7 +206,7 @@ out:
 
 out_free_namelist:
 	for (i = 0; i < items; i++)
-		free(namelist[i]);
+		zfree(&namelist[i]);
 	free(namelist);
 
 out_free_threads:
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 9f73bf4..7e6fcfe 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -397,8 +397,8 @@ put_tracepoints_path(struct tracepoint_path *tps)
 		struct tracepoint_path *t = tps;
 
 		tps = tps->next;
-		free(t->name);
-		free(t->system);
+		zfree(&t->name);
+		zfree(&t->system);
 		free(t);
 	}
 }
diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c
index 697c8b4..0fb3c1f 100644
--- a/tools/perf/util/values.c
+++ b/tools/perf/util/values.c
@@ -31,14 +31,14 @@ void perf_read_values_destroy(struct perf_read_values *values)
 		return;
 
 	for (i = 0; i < values->threads; i++)
-		free(values->value[i]);
-	free(values->value);
-	free(values->pid);
-	free(values->tid);
-	free(values->counterrawid);
+		zfree(&values->value[i]);
+	zfree(&values->value);
+	zfree(&values->pid);
+	zfree(&values->tid);
+	zfree(&values->counterrawid);
 	for (i = 0; i < values->counters; i++)
-		free(values->countername[i]);
-	free(values->countername);
+		zfree(&values->countername[i]);
+	zfree(&values->countername);
 }
 
 static void perf_read_values__enlarge_threads(struct perf_read_values *values)
-- 
cgit v0.10.2


From ebcc943c11f48617a7536a132c64d2637075e407 Mon Sep 17 00:00:00 2001
From: Steve French <smfrench@gmail.com>
Date: Mon, 9 Dec 2013 09:18:09 -0600
Subject: Add missing end of line termination to some cifs messages

Signed-off-by: Steve French <smfrench@gmail.com>
Signed-off-by: Gregor Beck <gbeck@sernet.de>
Reviewed-by: Jeff Layton <jlayton@redhat.com>

diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 124aa02..d707edb 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -4010,7 +4010,7 @@ QFileInfoRetry:
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cifs_dbg(FYI, "Send error in QPathInfo = %d\n", rc);
+		cifs_dbg(FYI, "Send error in QFileInfo = %d", rc);
 	} else {		/* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
@@ -4179,7 +4179,7 @@ UnixQFileInfoRetry:
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cifs_dbg(FYI, "Send error in QPathInfo = %d\n", rc);
+		cifs_dbg(FYI, "Send error in UnixQFileInfo = %d", rc);
 	} else {		/* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
@@ -4263,7 +4263,7 @@ UnixQPathInfoRetry:
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
 			 (struct smb_hdr *) pSMBr, &bytes_returned, 0);
 	if (rc) {
-		cifs_dbg(FYI, "Send error in QPathInfo = %d\n", rc);
+		cifs_dbg(FYI, "Send error in UnixQPathInfo = %d", rc);
 	} else {		/* decode response */
 		rc = validate_t2((struct smb_t2_rsp *)pSMBr);
 
-- 
cgit v0.10.2


From 750b8de6c4277d7034061e1da50663aa1b0479e4 Mon Sep 17 00:00:00 2001
From: Sachin Prabhu <sprabhu@redhat.com>
Date: Mon, 25 Nov 2013 17:09:48 +0000
Subject: cifs: We do not drop reference to tlink in CIFSCheckMFSymlink()

When we obtain tcon from cifs_sb, we use cifs_sb_tlink() to first obtain
tlink which also grabs a reference to it. We do not drop this reference
to tlink once we are done with the call.

The patch fixes this issue by instead passing tcon as a parameter and
avoids having to obtain a reference to the tlink. A lookup for the tcon
is already made in the calling functions and this way we avoid having to
re-run the lookup. This is also consistent with the argument list for
other similar calls for M-F symlinks.

We should also return an ENOSYS when we do not find a protocol specific
function to lookup the MF Symlink data.

Signed-off-by: Sachin Prabhu <sprabhu@redhat.com>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
CC: Stable <stable@kernel.org>
Signed-off-by: Steve French <smfrench@gmail.com>

diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index aa33976..2c29db6 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -477,9 +477,10 @@ extern int CIFSGetExtAttr(const unsigned int xid, struct cifs_tcon *tcon,
 			const int netfid, __u64 *pExtAttrBits, __u64 *pMask);
 extern void cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb);
 extern bool CIFSCouldBeMFSymlink(const struct cifs_fattr *fattr);
-extern int CIFSCheckMFSymlink(struct cifs_fattr *fattr,
-		const unsigned char *path,
-		struct cifs_sb_info *cifs_sb, unsigned int xid);
+extern int CIFSCheckMFSymlink(unsigned int xid, struct cifs_tcon *tcon,
+			      struct cifs_sb_info *cifs_sb,
+			      struct cifs_fattr *fattr,
+			      const unsigned char *path);
 extern int mdfour(unsigned char *, unsigned char *, int);
 extern int E_md4hash(const unsigned char *passwd, unsigned char *p16,
 			const struct nls_table *codepage);
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 36f9ebb..49719b8 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -383,7 +383,8 @@ int cifs_get_inode_info_unix(struct inode **pinode,
 
 	/* check for Minshall+French symlinks */
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
-		int tmprc = CIFSCheckMFSymlink(&fattr, full_path, cifs_sb, xid);
+		int tmprc = CIFSCheckMFSymlink(xid, tcon, cifs_sb, &fattr,
+					       full_path);
 		if (tmprc)
 			cifs_dbg(FYI, "CIFSCheckMFSymlink: %d\n", tmprc);
 	}
@@ -799,7 +800,8 @@ cifs_get_inode_info(struct inode **inode, const char *full_path,
 
 	/* check for Minshall+French symlinks */
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
-		tmprc = CIFSCheckMFSymlink(&fattr, full_path, cifs_sb, xid);
+		tmprc = CIFSCheckMFSymlink(xid, tcon, cifs_sb, &fattr,
+					   full_path);
 		if (tmprc)
 			cifs_dbg(FYI, "CIFSCheckMFSymlink: %d\n", tmprc);
 	}
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index cc023471..92aee08 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -354,34 +354,30 @@ open_query_close_cifs_symlink(const unsigned char *path, char *pbuf,
 
 
 int
-CIFSCheckMFSymlink(struct cifs_fattr *fattr,
-		   const unsigned char *path,
-		   struct cifs_sb_info *cifs_sb, unsigned int xid)
+CIFSCheckMFSymlink(unsigned int xid, struct cifs_tcon *tcon,
+		   struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr,
+		   const unsigned char *path)
 {
-	int rc = 0;
+	int rc;
 	u8 *buf = NULL;
 	unsigned int link_len = 0;
 	unsigned int bytes_read = 0;
-	struct cifs_tcon *ptcon;
 
 	if (!CIFSCouldBeMFSymlink(fattr))
 		/* it's not a symlink */
 		return 0;
 
 	buf = kmalloc(CIFS_MF_SYMLINK_FILE_SIZE, GFP_KERNEL);
-	if (!buf) {
-		rc = -ENOMEM;
-		goto out;
-	}
+	if (!buf)
+		return -ENOMEM;
 
-	ptcon = tlink_tcon(cifs_sb_tlink(cifs_sb));
-	if ((ptcon->ses) && (ptcon->ses->server->ops->query_mf_symlink))
-		rc = ptcon->ses->server->ops->query_mf_symlink(path, buf,
-						 &bytes_read, cifs_sb, xid);
+	if (tcon->ses->server->ops->query_mf_symlink)
+		rc = tcon->ses->server->ops->query_mf_symlink(path, buf,
+						&bytes_read, cifs_sb, xid);
 	else
-		goto out;
+		rc = -ENOSYS;
 
-	if (rc != 0)
+	if (rc)
 		goto out;
 
 	if (bytes_read == 0) /* not a symlink */
-- 
cgit v0.10.2


From f1e3268126a35b9d3cb8bf67487fcc6cd13991d8 Mon Sep 17 00:00:00 2001
From: Shirish Pargaonkar <shirishpargaonkar@gmail.com>
Date: Wed, 11 Dec 2013 16:29:53 -0600
Subject: cifs: set FILE_CREATED

Set FILE_CREATED on O_CREAT|O_EXCL.

cifs code didn't change during commit 116cc0225381415b96551f725455d067f63a76a0

Kernel bugzilla 66251

Signed-off-by: Shirish Pargaonkar <spargaonkar@suse.com>
Acked-by: Jeff Layton <jlayton@redhat.com>
CC: Stable <stable@kernel.org>
Signed-off-by: Steve French <smfrench@gmail.com>

diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 11ff5f1..a514e0a 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -193,7 +193,7 @@ check_name(struct dentry *direntry)
 static int
 cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid,
 	       struct tcon_link *tlink, unsigned oflags, umode_t mode,
-	       __u32 *oplock, struct cifs_fid *fid, int *created)
+	       __u32 *oplock, struct cifs_fid *fid)
 {
 	int rc = -ENOENT;
 	int create_options = CREATE_NOT_DIR;
@@ -349,7 +349,6 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid,
 				.device	= 0,
 		};
 
-		*created |= FILE_CREATED;
 		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
 			args.uid = current_fsuid();
 			if (inode->i_mode & S_ISGID)
@@ -480,13 +479,16 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 	cifs_add_pending_open(&fid, tlink, &open);
 
 	rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode,
-			    &oplock, &fid, opened);
+			    &oplock, &fid);
 
 	if (rc) {
 		cifs_del_pending_open(&open);
 		goto out;
 	}
 
+	if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
+		*opened |= FILE_CREATED;
+
 	rc = finish_open(file, direntry, generic_file_open, opened);
 	if (rc) {
 		if (server->ops->close)
@@ -529,7 +531,6 @@ int cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode,
 	struct TCP_Server_Info *server;
 	struct cifs_fid fid;
 	__u32 oplock;
-	int created = FILE_CREATED;
 
 	cifs_dbg(FYI, "cifs_create parent inode = 0x%p name is: %s and dentry = 0x%p\n",
 		 inode, direntry->d_name.name, direntry);
@@ -546,7 +547,7 @@ int cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode,
 		server->ops->new_lease_key(&fid);
 
 	rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode,
-			    &oplock, &fid, &created);
+			    &oplock, &fid);
 	if (!rc && server->ops->close)
 		server->ops->close(xid, tcon, &fid);
 
-- 
cgit v0.10.2


From c5fe5d80680e2949ffe102180f5fc6cefc0d145f Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 27 Dec 2013 15:30:58 -0800
Subject: x86: Replace assembly access_ok() with a C variant

It turns out that the assembly variant doesn't actually produce that
good code, presumably partly because it creates a long dependency
chain with no scheduling, and partly because we cannot get a flags
result out of gcc (which could be fixed with asm goto, but it turns
out not to be worth it.)

The C code allows gcc to schedule and generate multiple (easily
predictable) branches, and as a side benefit we can really optimize
the case where the size is constant.

Link: http://lkml.kernel.org/r/CA%2B55aFzPBdbfKovMT8Edr4SmE2_=%2BOKJFac9XW2awegogTkVTA@mail.gmail.com
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 8ec57c0..84ecf1d 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -40,22 +40,28 @@
 /*
  * Test whether a block of memory is a valid user space address.
  * Returns 0 if the range is valid, nonzero otherwise.
- *
- * This is equivalent to the following test:
- * (u33)addr + (u33)size > (u33)current->addr_limit.seg (u65 for x86_64)
- *
- * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
  */
+static inline int __chk_range_not_ok(unsigned long addr, unsigned long size, unsigned long limit)
+{
+	/*
+	 * If we have used "sizeof()" for the size,
+	 * we know it won't overflow the limit (but
+	 * it might overflow the 'addr', so it's
+	 * important to subtract the size from the
+	 * limit, not add it to the address).
+	 */
+	if (__builtin_constant_p(size))
+		return addr > limit - size;
+
+	/* Arbitrary sizes? Be careful about overflow */
+	addr += size;
+	return (addr < size) || (addr > limit);
+}
 
 #define __range_not_ok(addr, size, limit)				\
 ({									\
-	unsigned long flag, roksum;					\
 	__chk_user_ptr(addr);						\
-	asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0"		\
-	    : "=&r" (flag), "=r" (roksum)				\
-	    : "1" (addr), "g" ((long)(size)),				\
-	      "rm" (limit));						\
-	flag;								\
+	__chk_range_not_ok((unsigned long __force)(addr), size, limit); \
 })
 
 /**
-- 
cgit v0.10.2


From a740576a4abf933de8f50787f24f24456cebd761 Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@zytor.com>
Date: Fri, 27 Dec 2013 16:52:47 -0800
Subject: x86: Slightly tweak the access_ok() C variant for better code

gcc can under very specific circumstances realize that the code
sequence:

	foo += bar;
	if (foo < bar) ...

... is equivalent to a carry out from the addition.  Tweak the
implementation of access_ok() (specifically __chk_range_not_ok()) to
make it more likely that gcc will make that connection.  It isn't
fool-proof (sometimes gcc seems to think it can make better code with
lea, and ends up with a second comparison), still, but it seems to be
able to connect the two more frequently this way.

Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/CA%2B55aFzPBdbfKovMT8Edr4SmE2_=%2BOKJFac9XW2awegogTkVTA@mail.gmail.com
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 84ecf1d..6f1bb74 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -41,7 +41,7 @@
  * Test whether a block of memory is a valid user space address.
  * Returns 0 if the range is valid, nonzero otherwise.
  */
-static inline int __chk_range_not_ok(unsigned long addr, unsigned long size, unsigned long limit)
+static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, unsigned long limit)
 {
 	/*
 	 * If we have used "sizeof()" for the size,
@@ -55,7 +55,9 @@ static inline int __chk_range_not_ok(unsigned long addr, unsigned long size, uns
 
 	/* Arbitrary sizes? Be careful about overflow */
 	addr += size;
-	return (addr < size) || (addr > limit);
+	if (addr < size)
+		return true;
+	return addr > limit;
 }
 
 #define __range_not_ok(addr, size, limit)				\
@@ -84,7 +86,7 @@ static inline int __chk_range_not_ok(unsigned long addr, unsigned long size, uns
  * this function, memory access functions may still return -EFAULT.
  */
 #define access_ok(type, addr, size) \
-	(likely(__range_not_ok(addr, size, user_addr_max()) == 0))
+	likely(!__range_not_ok(addr, size, user_addr_max()))
 
 /*
  * The exception table consists of pairs of addresses relative to the
-- 
cgit v0.10.2


From e38195bf32d7ccb2ae3f56f36b895daf455ffd94 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 24 Dec 2013 18:32:35 +0100
Subject: netfilter: nf_tables: fix dumping with large number of sets

If not table name is specified, the dumping of the existing sets
may be incomplete with a sufficiently large number of sets and
tables. This patch fixes missing reset of the cursors after
finding the location of the last object that has been included
in the previous multi-part message.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index f93b7d0..d9fcd27 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2098,17 +2098,21 @@ static int nf_tables_dump_sets_all(struct nft_ctx *ctx, struct sk_buff *skb,
 				   struct netlink_callback *cb)
 {
 	const struct nft_set *set;
-	unsigned int idx = 0, s_idx = cb->args[0];
+	unsigned int idx, s_idx = cb->args[0];
 	struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2];
 
 	if (cb->args[1])
 		return skb->len;
 
 	list_for_each_entry(table, &ctx->afi->tables, list) {
-		if (cur_table && cur_table != table)
-			continue;
+		if (cur_table) {
+			if (cur_table != table)
+				continue;
 
+			cur_table = NULL;
+		}
 		ctx->table = table;
+		idx = 0;
 		list_for_each_entry(set, &ctx->table->sets, list) {
 			if (idx < s_idx)
 				goto cont;
-- 
cgit v0.10.2


From d2012975619251bdfeb7a5159faa7727ea9cddd3 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 27 Dec 2013 10:44:23 +0100
Subject: netfilter: nf_tables: fix oops when updating table with user chains

This patch fixes a crash while trying to deactivate a table that
contains user chains. You can reproduce it via:

% nft add table table1
% nft add chain table1 chain1
% nft-table-upd ip table1 dormant

[  253.021026] BUG: unable to handle kernel NULL pointer dereference at 0000000000000030
[  253.021114] IP: [<ffffffff8134cebd>] nf_register_hook+0x35/0x6f
[  253.021167] PGD 30fa5067 PUD 30fa2067 PMD 0
[  253.021208] Oops: 0000 [#1] SMP
[...]
[  253.023305] Call Trace:
[  253.023331]  [<ffffffffa0885020>] nf_tables_newtable+0x11c/0x258 [nf_tables]
[  253.023385]  [<ffffffffa0878592>] nfnetlink_rcv_msg+0x1f4/0x226 [nfnetlink]
[  253.023438]  [<ffffffffa0878418>] ? nfnetlink_rcv_msg+0x7a/0x226 [nfnetlink]
[  253.023491]  [<ffffffffa087839e>] ? nfnetlink_bind+0x45/0x45 [nfnetlink]
[  253.023542]  [<ffffffff8134b47e>] netlink_rcv_skb+0x3c/0x88
[  253.023586]  [<ffffffffa0878973>] nfnetlink_rcv+0x3af/0x3e4 [nfnetlink]
[  253.023638]  [<ffffffff813fb0d4>] ? _raw_read_unlock+0x22/0x34
[  253.023683]  [<ffffffff8134af17>] netlink_unicast+0xe2/0x161
[  253.023727]  [<ffffffff8134b29a>] netlink_sendmsg+0x304/0x332
[  253.023773]  [<ffffffff8130d250>] __sock_sendmsg_nosec+0x25/0x27
[  253.023820]  [<ffffffff8130fb93>] sock_sendmsg+0x5a/0x7b
[  253.023861]  [<ffffffff8130d5d5>] ? copy_from_user+0x2a/0x2c
[  253.023905]  [<ffffffff8131066f>] ? move_addr_to_kernel+0x35/0x60
[  253.023952]  [<ffffffff813107b3>] SYSC_sendto+0x119/0x15c
[  253.023995]  [<ffffffff81401107>] ? sysret_check+0x1b/0x56
[  253.024039]  [<ffffffff8108dc30>] ? trace_hardirqs_on_caller+0x140/0x1db
[  253.024090]  [<ffffffff8120164e>] ? trace_hardirqs_on_thunk+0x3a/0x3f
[  253.024141]  [<ffffffff81310caf>] SyS_sendto+0x9/0xb
[  253.026219]  [<ffffffff814010e2>] system_call_fastpath+0x16/0x1b

Reported-by: Alex Wei <alex.kern.mentor@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index d9fcd27..d65c80b 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -312,6 +312,9 @@ static int nf_tables_table_enable(struct nft_table *table)
 	int err, i = 0;
 
 	list_for_each_entry(chain, &table->chains, list) {
+		if (!(chain->flags & NFT_BASE_CHAIN))
+			continue;
+
 		err = nf_register_hook(&nft_base_chain(chain)->ops);
 		if (err < 0)
 			goto err;
@@ -321,6 +324,9 @@ static int nf_tables_table_enable(struct nft_table *table)
 	return 0;
 err:
 	list_for_each_entry(chain, &table->chains, list) {
+		if (!(chain->flags & NFT_BASE_CHAIN))
+			continue;
+
 		if (i-- <= 0)
 			break;
 
@@ -333,8 +339,10 @@ static int nf_tables_table_disable(struct nft_table *table)
 {
 	struct nft_chain *chain;
 
-	list_for_each_entry(chain, &table->chains, list)
-		nf_unregister_hook(&nft_base_chain(chain)->ops);
+	list_for_each_entry(chain, &table->chains, list) {
+		if (chain->flags & NFT_BASE_CHAIN)
+			nf_unregister_hook(&nft_base_chain(chain)->ops);
+	}
 
 	return 0;
 }
-- 
cgit v0.10.2


From 46b76e0b8b5e21fa5a2387d6f72b193514e7f722 Mon Sep 17 00:00:00 2001
From: Simon Wunderlich <sw@simonwunderlich.de>
Date: Mon, 2 Dec 2013 20:38:30 +0100
Subject: batman-adv: fix alignment for batadv_coded_packet

The compiler may decide to pad the structure, and then it does not
have the expected size of 46 byte. Fix this by moving it in the
pragma pack(2) part of the code.

Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>

diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h
index 207459b..10597a6 100644
--- a/net/batman-adv/packet.h
+++ b/net/batman-adv/packet.h
@@ -315,8 +315,6 @@ struct batadv_bcast_packet {
 	 */
 };
 
-#pragma pack()
-
 /**
  * struct batadv_coded_packet - network coded packet
  * @header: common batman packet header and ttl of first included packet
@@ -349,6 +347,8 @@ struct batadv_coded_packet {
 	__be16   coded_len;
 };
 
+#pragma pack()
+
 /**
  * struct batadv_unicast_tvlv - generic unicast packet with tvlv payload
  * @header: common batman packet header
-- 
cgit v0.10.2


From a40d9b075c21f06872de3f05cc2eb3d06665e2ff Mon Sep 17 00:00:00 2001
From: Simon Wunderlich <sw@simonwunderlich.de>
Date: Mon, 2 Dec 2013 20:38:31 +0100
Subject: batman-adv: fix header alignment by unrolling batadv_header

The size of the batadv_header of 3 is problematic on some architectures
which automatically pad all structures to a 32 bit boundary. To not lose
performance by packing this struct, better embed it into the various
host structures.

Reported-by: Russell King <linux@arm.linux.org.uk>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>

diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index a2b480a..b9c8a6e 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -307,9 +307,9 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface)
 	hard_iface->bat_iv.ogm_buff = ogm_buff;
 
 	batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff;
-	batadv_ogm_packet->header.packet_type = BATADV_IV_OGM;
-	batadv_ogm_packet->header.version = BATADV_COMPAT_VERSION;
-	batadv_ogm_packet->header.ttl = 2;
+	batadv_ogm_packet->packet_type = BATADV_IV_OGM;
+	batadv_ogm_packet->version = BATADV_COMPAT_VERSION;
+	batadv_ogm_packet->ttl = 2;
 	batadv_ogm_packet->flags = BATADV_NO_FLAGS;
 	batadv_ogm_packet->reserved = 0;
 	batadv_ogm_packet->tq = BATADV_TQ_MAX_VALUE;
@@ -346,7 +346,7 @@ batadv_iv_ogm_primary_iface_set(struct batadv_hard_iface *hard_iface)
 
 	batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff;
 	batadv_ogm_packet->flags = BATADV_PRIMARIES_FIRST_HOP;
-	batadv_ogm_packet->header.ttl = BATADV_TTL;
+	batadv_ogm_packet->ttl = BATADV_TTL;
 }
 
 /* when do we schedule our own ogm to be sent */
@@ -435,7 +435,7 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet,
 			   fwd_str, (packet_num > 0 ? "aggregated " : ""),
 			   batadv_ogm_packet->orig,
 			   ntohl(batadv_ogm_packet->seqno),
-			   batadv_ogm_packet->tq, batadv_ogm_packet->header.ttl,
+			   batadv_ogm_packet->tq, batadv_ogm_packet->ttl,
 			   (batadv_ogm_packet->flags & BATADV_DIRECTLINK ?
 			    "on" : "off"),
 			   hard_iface->net_dev->name,
@@ -491,7 +491,7 @@ static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet)
 	/* multihomed peer assumed
 	 * non-primary OGMs are only broadcasted on their interface
 	 */
-	if ((directlink && (batadv_ogm_packet->header.ttl == 1)) ||
+	if ((directlink && (batadv_ogm_packet->ttl == 1)) ||
 	    (forw_packet->own && (forw_packet->if_incoming != primary_if))) {
 		/* FIXME: what about aggregated packets ? */
 		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
@@ -499,7 +499,7 @@ static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet)
 			   (forw_packet->own ? "Sending own" : "Forwarding"),
 			   batadv_ogm_packet->orig,
 			   ntohl(batadv_ogm_packet->seqno),
-			   batadv_ogm_packet->header.ttl,
+			   batadv_ogm_packet->ttl,
 			   forw_packet->if_incoming->net_dev->name,
 			   forw_packet->if_incoming->net_dev->dev_addr);
 
@@ -572,7 +572,7 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet,
 		 */
 		if ((!directlink) &&
 		    (!(batadv_ogm_packet->flags & BATADV_DIRECTLINK)) &&
-		    (batadv_ogm_packet->header.ttl != 1) &&
+		    (batadv_ogm_packet->ttl != 1) &&
 
 		    /* own packets originating non-primary
 		     * interfaces leave only that interface
@@ -587,7 +587,7 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet,
 		 * interface only - we still can aggregate
 		 */
 		if ((directlink) &&
-		    (new_bat_ogm_packet->header.ttl == 1) &&
+		    (new_bat_ogm_packet->ttl == 1) &&
 		    (forw_packet->if_incoming == if_incoming) &&
 
 		    /* packets from direct neighbors or
@@ -778,7 +778,7 @@ static void batadv_iv_ogm_forward(struct batadv_orig_node *orig_node,
 	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
 	uint16_t tvlv_len;
 
-	if (batadv_ogm_packet->header.ttl <= 1) {
+	if (batadv_ogm_packet->ttl <= 1) {
 		batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "ttl exceeded\n");
 		return;
 	}
@@ -798,7 +798,7 @@ static void batadv_iv_ogm_forward(struct batadv_orig_node *orig_node,
 
 	tvlv_len = ntohs(batadv_ogm_packet->tvlv_len);
 
-	batadv_ogm_packet->header.ttl--;
+	batadv_ogm_packet->ttl--;
 	memcpy(batadv_ogm_packet->prev_sender, ethhdr->h_source, ETH_ALEN);
 
 	/* apply hop penalty */
@@ -807,7 +807,7 @@ static void batadv_iv_ogm_forward(struct batadv_orig_node *orig_node,
 
 	batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
 		   "Forwarding packet: tq: %i, ttl: %i\n",
-		   batadv_ogm_packet->tq, batadv_ogm_packet->header.ttl);
+		   batadv_ogm_packet->tq, batadv_ogm_packet->ttl);
 
 	/* switch of primaries first hop flag when forwarding */
 	batadv_ogm_packet->flags &= ~BATADV_PRIMARIES_FIRST_HOP;
@@ -972,8 +972,8 @@ batadv_iv_ogm_orig_update(struct batadv_priv *bat_priv,
 	spin_unlock_bh(&neigh_node->bat_iv.lq_update_lock);
 
 	if (dup_status == BATADV_NO_DUP) {
-		orig_node->last_ttl = batadv_ogm_packet->header.ttl;
-		neigh_node->last_ttl = batadv_ogm_packet->header.ttl;
+		orig_node->last_ttl = batadv_ogm_packet->ttl;
+		neigh_node->last_ttl = batadv_ogm_packet->ttl;
 	}
 
 	batadv_bonding_candidate_add(bat_priv, orig_node, neigh_node);
@@ -1247,7 +1247,7 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr,
 	 * packet in an aggregation.  Here we expect that the padding
 	 * is always zero (or not 0x01)
 	 */
-	if (batadv_ogm_packet->header.packet_type != BATADV_IV_OGM)
+	if (batadv_ogm_packet->packet_type != BATADV_IV_OGM)
 		return;
 
 	/* could be changed by schedule_own_packet() */
@@ -1267,8 +1267,8 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr,
 		   if_incoming->net_dev->dev_addr, batadv_ogm_packet->orig,
 		   batadv_ogm_packet->prev_sender,
 		   ntohl(batadv_ogm_packet->seqno), batadv_ogm_packet->tq,
-		   batadv_ogm_packet->header.ttl,
-		   batadv_ogm_packet->header.version, has_directlink_flag);
+		   batadv_ogm_packet->ttl,
+		   batadv_ogm_packet->version, has_directlink_flag);
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
@@ -1433,7 +1433,7 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr,
 	 * seqno and similar ttl as the non-duplicate
 	 */
 	sameseq = orig_node->last_real_seqno == ntohl(batadv_ogm_packet->seqno);
-	similar_ttl = orig_node->last_ttl - 3 <= batadv_ogm_packet->header.ttl;
+	similar_ttl = orig_node->last_ttl - 3 <= batadv_ogm_packet->ttl;
 	if (is_bidirect && ((dup_status == BATADV_NO_DUP) ||
 			    (sameseq && similar_ttl)))
 		batadv_iv_ogm_orig_update(bat_priv, orig_node, ethhdr,
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index 6c8c393..b316a4c 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -349,7 +349,7 @@ static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb,
 
 	unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data;
 
-	switch (unicast_4addr_packet->u.header.packet_type) {
+	switch (unicast_4addr_packet->u.packet_type) {
 	case BATADV_UNICAST:
 		batadv_dbg(BATADV_DBG_DAT, bat_priv,
 			   "* encapsulated within a UNICAST packet\n");
@@ -374,7 +374,7 @@ static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb,
 			break;
 		default:
 			batadv_dbg(BATADV_DBG_DAT, bat_priv, "* type: Unknown (%u)!\n",
-				   unicast_4addr_packet->u.header.packet_type);
+				   unicast_4addr_packet->u.packet_type);
 		}
 		break;
 	case BATADV_BCAST:
@@ -387,7 +387,7 @@ static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb,
 	default:
 		batadv_dbg(BATADV_DBG_DAT, bat_priv,
 			   "* encapsulated within an unknown packet type (0x%x)\n",
-			   unicast_4addr_packet->u.header.packet_type);
+			   unicast_4addr_packet->u.packet_type);
 	}
 }
 
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 271d321..6ddb614 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -355,7 +355,7 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb,
 		batadv_add_counter(bat_priv, BATADV_CNT_FRAG_FWD_BYTES,
 				   skb->len + ETH_HLEN);
 
-		packet->header.ttl--;
+		packet->ttl--;
 		batadv_send_skb_packet(skb, neigh_node->if_incoming,
 				       neigh_node->addr);
 		ret = true;
@@ -444,9 +444,9 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
 		goto out_err;
 
 	/* Create one header to be copied to all fragments */
-	frag_header.header.packet_type = BATADV_UNICAST_FRAG;
-	frag_header.header.version = BATADV_COMPAT_VERSION;
-	frag_header.header.ttl = BATADV_TTL;
+	frag_header.packet_type = BATADV_UNICAST_FRAG;
+	frag_header.version = BATADV_COMPAT_VERSION;
+	frag_header.ttl = BATADV_TTL;
 	frag_header.seqno = htons(atomic_inc_return(&bat_priv->frag_seqno));
 	frag_header.reserved = 0;
 	frag_header.no = 0;
diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c
index 29ae4ef..130cc32 100644
--- a/net/batman-adv/icmp_socket.c
+++ b/net/batman-adv/icmp_socket.c
@@ -194,7 +194,7 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff,
 		goto free_skb;
 	}
 
-	if (icmp_header->header.packet_type != BATADV_ICMP) {
+	if (icmp_header->packet_type != BATADV_ICMP) {
 		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
 			   "Error - can't send packet from char device: got bogus packet type (expected: BAT_ICMP)\n");
 		len = -EINVAL;
@@ -243,9 +243,9 @@ static ssize_t batadv_socket_write(struct file *file, const char __user *buff,
 
 	icmp_header->uid = socket_client->index;
 
-	if (icmp_header->header.version != BATADV_COMPAT_VERSION) {
+	if (icmp_header->version != BATADV_COMPAT_VERSION) {
 		icmp_header->msg_type = BATADV_PARAMETER_PROBLEM;
-		icmp_header->header.version = BATADV_COMPAT_VERSION;
+		icmp_header->version = BATADV_COMPAT_VERSION;
 		batadv_socket_add_packet(socket_client, icmp_header,
 					 packet_len);
 		goto free_skb;
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index c51a5e5..d87778b 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -383,17 +383,17 @@ int batadv_batman_skb_recv(struct sk_buff *skb, struct net_device *dev,
 
 	batadv_ogm_packet = (struct batadv_ogm_packet *)skb->data;
 
-	if (batadv_ogm_packet->header.version != BATADV_COMPAT_VERSION) {
+	if (batadv_ogm_packet->version != BATADV_COMPAT_VERSION) {
 		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
 			   "Drop packet: incompatible batman version (%i)\n",
-			   batadv_ogm_packet->header.version);
+			   batadv_ogm_packet->version);
 		goto err_free;
 	}
 
 	/* all receive handlers return whether they received or reused
 	 * the supplied skb. if not, we have to free the skb.
 	 */
-	idx = batadv_ogm_packet->header.packet_type;
+	idx = batadv_ogm_packet->packet_type;
 	ret = (*batadv_rx_handler[idx])(skb, hard_iface);
 
 	if (ret == NET_RX_DROP)
@@ -1119,9 +1119,9 @@ void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, uint8_t *src,
 	skb_reserve(skb, ETH_HLEN);
 	tvlv_buff = skb_put(skb, sizeof(*unicast_tvlv_packet) + tvlv_len);
 	unicast_tvlv_packet = (struct batadv_unicast_tvlv_packet *)tvlv_buff;
-	unicast_tvlv_packet->header.packet_type = BATADV_UNICAST_TVLV;
-	unicast_tvlv_packet->header.version = BATADV_COMPAT_VERSION;
-	unicast_tvlv_packet->header.ttl = BATADV_TTL;
+	unicast_tvlv_packet->packet_type = BATADV_UNICAST_TVLV;
+	unicast_tvlv_packet->version = BATADV_COMPAT_VERSION;
+	unicast_tvlv_packet->ttl = BATADV_TTL;
 	unicast_tvlv_packet->reserved = 0;
 	unicast_tvlv_packet->tvlv_len = htons(tvlv_len);
 	unicast_tvlv_packet->align = 0;
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index 351e199..511d7e1 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -722,7 +722,7 @@ static bool batadv_can_nc_with_orig(struct batadv_priv *bat_priv,
 {
 	if (orig_node->last_real_seqno != ntohl(ogm_packet->seqno))
 		return false;
-	if (orig_node->last_ttl != ogm_packet->header.ttl + 1)
+	if (orig_node->last_ttl != ogm_packet->ttl + 1)
 		return false;
 	if (!batadv_compare_eth(ogm_packet->orig, ogm_packet->prev_sender))
 		return false;
@@ -1082,9 +1082,9 @@ static bool batadv_nc_code_packets(struct batadv_priv *bat_priv,
 	coded_packet = (struct batadv_coded_packet *)skb_dest->data;
 	skb_reset_mac_header(skb_dest);
 
-	coded_packet->header.packet_type = BATADV_CODED;
-	coded_packet->header.version = BATADV_COMPAT_VERSION;
-	coded_packet->header.ttl = packet1->header.ttl;
+	coded_packet->packet_type = BATADV_CODED;
+	coded_packet->version = BATADV_COMPAT_VERSION;
+	coded_packet->ttl = packet1->ttl;
 
 	/* Info about first unicast packet */
 	memcpy(coded_packet->first_source, first_source, ETH_ALEN);
@@ -1097,7 +1097,7 @@ static bool batadv_nc_code_packets(struct batadv_priv *bat_priv,
 	memcpy(coded_packet->second_source, second_source, ETH_ALEN);
 	memcpy(coded_packet->second_orig_dest, packet2->dest, ETH_ALEN);
 	coded_packet->second_crc = packet_id2;
-	coded_packet->second_ttl = packet2->header.ttl;
+	coded_packet->second_ttl = packet2->ttl;
 	coded_packet->second_ttvn = packet2->ttvn;
 	coded_packet->coded_len = htons(coding_len);
 
@@ -1452,7 +1452,7 @@ bool batadv_nc_skb_forward(struct sk_buff *skb,
 	/* We only handle unicast packets */
 	payload = skb_network_header(skb);
 	packet = (struct batadv_unicast_packet *)payload;
-	if (packet->header.packet_type != BATADV_UNICAST)
+	if (packet->packet_type != BATADV_UNICAST)
 		goto out;
 
 	/* Try to find a coding opportunity and send the skb if one is found */
@@ -1505,7 +1505,7 @@ void batadv_nc_skb_store_for_decoding(struct batadv_priv *bat_priv,
 	/* Check for supported packet type */
 	payload = skb_network_header(skb);
 	packet = (struct batadv_unicast_packet *)payload;
-	if (packet->header.packet_type != BATADV_UNICAST)
+	if (packet->packet_type != BATADV_UNICAST)
 		goto out;
 
 	/* Find existing nc_path or create a new */
@@ -1623,7 +1623,7 @@ batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb,
 		ttvn = coded_packet_tmp.second_ttvn;
 	} else {
 		orig_dest = coded_packet_tmp.first_orig_dest;
-		ttl = coded_packet_tmp.header.ttl;
+		ttl = coded_packet_tmp.ttl;
 		ttvn = coded_packet_tmp.first_ttvn;
 	}
 
@@ -1648,9 +1648,9 @@ batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb,
 
 	/* Create decoded unicast packet */
 	unicast_packet = (struct batadv_unicast_packet *)skb->data;
-	unicast_packet->header.packet_type = BATADV_UNICAST;
-	unicast_packet->header.version = BATADV_COMPAT_VERSION;
-	unicast_packet->header.ttl = ttl;
+	unicast_packet->packet_type = BATADV_UNICAST;
+	unicast_packet->version = BATADV_COMPAT_VERSION;
+	unicast_packet->ttl = ttl;
 	memcpy(unicast_packet->dest, orig_dest, ETH_ALEN);
 	unicast_packet->ttvn = ttvn;
 
diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h
index 10597a6..175ce7d 100644
--- a/net/batman-adv/packet.h
+++ b/net/batman-adv/packet.h
@@ -164,23 +164,18 @@ struct batadv_bla_claim_dst {
 	__be16 group;		/* group id */
 };
 
-struct batadv_header {
-	uint8_t  packet_type;
-	uint8_t  version;  /* batman version field */
-	uint8_t  ttl;
-	/* the parent struct has to add a byte after the header to make
-	 * everything 4 bytes aligned again
-	 */
-};
-
 /**
  * struct batadv_ogm_packet - ogm (routing protocol) packet
- * @header: common batman packet header
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
  * @flags: contains routing relevant flags - see enum batadv_iv_flags
  * @tvlv_len: length of tvlv data following the ogm header
  */
 struct batadv_ogm_packet {
-	struct batadv_header header;
+	uint8_t  packet_type;
+	uint8_t  version;
+	uint8_t  ttl;
 	uint8_t  flags;
 	__be32   seqno;
 	uint8_t  orig[ETH_ALEN];
@@ -197,14 +192,18 @@ struct batadv_ogm_packet {
 
 /**
  * batadv_icmp_header - common ICMP header
- * @header: common batman header
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
  * @msg_type: ICMP packet type
  * @dst: address of the destination node
  * @orig: address of the source node
  * @uid: local ICMP socket identifier
  */
 struct batadv_icmp_header {
-	struct batadv_header header;
+	uint8_t  packet_type;
+	uint8_t  version;
+	uint8_t  ttl;
 	uint8_t  msg_type; /* see ICMP message types above */
 	uint8_t  dst[ETH_ALEN];
 	uint8_t  orig[ETH_ALEN];
@@ -253,8 +252,18 @@ struct batadv_icmp_packet_rr {
  */
 #pragma pack(2)
 
+/**
+ * struct batadv_unicast_packet - unicast packet for network payload
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
+ * @ttvn: translation table version number
+ * @dest: originator destination of the unicast packet
+ */
 struct batadv_unicast_packet {
-	struct batadv_header header;
+	uint8_t  packet_type;
+	uint8_t  version;
+	uint8_t  ttl;
 	uint8_t  ttvn; /* destination translation table version number */
 	uint8_t  dest[ETH_ALEN];
 	/* "4 bytes boundary + 2 bytes" long to make the payload after the
@@ -280,7 +289,9 @@ struct batadv_unicast_4addr_packet {
 
 /**
  * struct batadv_frag_packet - fragmented packet
- * @header: common batman packet header with type, compatversion, and ttl
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
  * @dest: final destination used when routing fragments
  * @orig: originator of the fragment used when merging the packet
  * @no: fragment number within this sequence
@@ -289,7 +300,9 @@ struct batadv_unicast_4addr_packet {
  * @total_size: size of the merged packet
  */
 struct batadv_frag_packet {
-	struct  batadv_header header;
+	uint8_t packet_type;
+	uint8_t version;  /* batman version field */
+	uint8_t ttl;
 #if defined(__BIG_ENDIAN_BITFIELD)
 	uint8_t no:4;
 	uint8_t reserved:4;
@@ -305,8 +318,19 @@ struct batadv_frag_packet {
 	__be16  total_size;
 };
 
+/**
+ * struct batadv_bcast_packet - broadcast packet for network payload
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
+ * @reserved: reserved byte for alignment
+ * @seqno: sequence identification
+ * @orig: originator of the broadcast packet
+ */
 struct batadv_bcast_packet {
-	struct batadv_header header;
+	uint8_t  packet_type;
+	uint8_t  version;  /* batman version field */
+	uint8_t  ttl;
 	uint8_t  reserved;
 	__be32   seqno;
 	uint8_t  orig[ETH_ALEN];
@@ -317,7 +341,9 @@ struct batadv_bcast_packet {
 
 /**
  * struct batadv_coded_packet - network coded packet
- * @header: common batman packet header and ttl of first included packet
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
  * @reserved: Align following fields to 2-byte boundaries
  * @first_source: original source of first included packet
  * @first_orig_dest: original destinal of first included packet
@@ -332,7 +358,9 @@ struct batadv_bcast_packet {
  * @coded_len: length of network coded part of the payload
  */
 struct batadv_coded_packet {
-	struct batadv_header header;
+	uint8_t  packet_type;
+	uint8_t  version;  /* batman version field */
+	uint8_t  ttl;
 	uint8_t  first_ttvn;
 	/* uint8_t  first_dest[ETH_ALEN]; - saved in mac header destination */
 	uint8_t  first_source[ETH_ALEN];
@@ -351,7 +379,9 @@ struct batadv_coded_packet {
 
 /**
  * struct batadv_unicast_tvlv - generic unicast packet with tvlv payload
- * @header: common batman packet header
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
  * @reserved: reserved field (for packet alignment)
  * @src: address of the source
  * @dst: address of the destination
@@ -359,7 +389,9 @@ struct batadv_coded_packet {
  * @align: 2 bytes to align the header to a 4 byte boundry
  */
 struct batadv_unicast_tvlv_packet {
-	struct batadv_header header;
+	uint8_t  packet_type;
+	uint8_t  version;  /* batman version field */
+	uint8_t  ttl;
 	uint8_t  reserved;
 	uint8_t  dst[ETH_ALEN];
 	uint8_t  src[ETH_ALEN];
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index d4114d7..5b52d71 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -308,7 +308,7 @@ static int batadv_recv_my_icmp_packet(struct batadv_priv *bat_priv,
 		memcpy(icmph->dst, icmph->orig, ETH_ALEN);
 		memcpy(icmph->orig, primary_if->net_dev->dev_addr, ETH_ALEN);
 		icmph->msg_type = BATADV_ECHO_REPLY;
-		icmph->header.ttl = BATADV_TTL;
+		icmph->ttl = BATADV_TTL;
 
 		res = batadv_send_skb_to_orig(skb, orig_node, NULL);
 		if (res != NET_XMIT_DROP)
@@ -363,7 +363,7 @@ static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv,
 	memcpy(icmp_packet->icmph.orig, primary_if->net_dev->dev_addr,
 	       ETH_ALEN);
 	icmp_packet->icmph.msg_type = BATADV_TTL_EXCEEDED;
-	icmp_packet->icmph.header.ttl = BATADV_TTL;
+	icmp_packet->icmph.ttl = BATADV_TTL;
 
 	if (batadv_send_skb_to_orig(skb, orig_node, NULL) != NET_XMIT_DROP)
 		ret = NET_RX_SUCCESS;
@@ -434,7 +434,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb,
 		return batadv_recv_my_icmp_packet(bat_priv, skb);
 
 	/* TTL exceeded */
-	if (icmph->header.ttl < 2)
+	if (icmph->ttl < 2)
 		return batadv_recv_icmp_ttl_exceeded(bat_priv, skb);
 
 	/* get routing information */
@@ -449,7 +449,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb,
 	icmph = (struct batadv_icmp_header *)skb->data;
 
 	/* decrement ttl */
-	icmph->header.ttl--;
+	icmph->ttl--;
 
 	/* route it */
 	if (batadv_send_skb_to_orig(skb, orig_node, recv_if) != NET_XMIT_DROP)
@@ -709,7 +709,7 @@ static int batadv_route_unicast_packet(struct sk_buff *skb,
 	unicast_packet = (struct batadv_unicast_packet *)skb->data;
 
 	/* TTL exceeded */
-	if (unicast_packet->header.ttl < 2) {
+	if (unicast_packet->ttl < 2) {
 		pr_debug("Warning - can't forward unicast packet from %pM to %pM: ttl exceeded\n",
 			 ethhdr->h_source, unicast_packet->dest);
 		goto out;
@@ -727,9 +727,9 @@ static int batadv_route_unicast_packet(struct sk_buff *skb,
 
 	/* decrement ttl */
 	unicast_packet = (struct batadv_unicast_packet *)skb->data;
-	unicast_packet->header.ttl--;
+	unicast_packet->ttl--;
 
-	switch (unicast_packet->header.packet_type) {
+	switch (unicast_packet->packet_type) {
 	case BATADV_UNICAST_4ADDR:
 		hdr_len = sizeof(struct batadv_unicast_4addr_packet);
 		break;
@@ -970,7 +970,7 @@ int batadv_recv_unicast_packet(struct sk_buff *skb,
 	unicast_packet = (struct batadv_unicast_packet *)skb->data;
 	unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data;
 
-	is4addr = unicast_packet->header.packet_type == BATADV_UNICAST_4ADDR;
+	is4addr = unicast_packet->packet_type == BATADV_UNICAST_4ADDR;
 	/* the caller function should have already pulled 2 bytes */
 	if (is4addr)
 		hdr_size = sizeof(*unicast_4addr_packet);
@@ -1160,7 +1160,7 @@ int batadv_recv_bcast_packet(struct sk_buff *skb,
 	if (batadv_is_my_mac(bat_priv, bcast_packet->orig))
 		goto out;
 
-	if (bcast_packet->header.ttl < 2)
+	if (bcast_packet->ttl < 2)
 		goto out;
 
 	orig_node = batadv_orig_hash_find(bat_priv, bcast_packet->orig);
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index c83be5e..fba4dcf 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -161,11 +161,11 @@ batadv_send_skb_push_fill_unicast(struct sk_buff *skb, int hdr_size,
 		return false;
 
 	unicast_packet = (struct batadv_unicast_packet *)skb->data;
-	unicast_packet->header.version = BATADV_COMPAT_VERSION;
+	unicast_packet->version = BATADV_COMPAT_VERSION;
 	/* batman packet type: unicast */
-	unicast_packet->header.packet_type = BATADV_UNICAST;
+	unicast_packet->packet_type = BATADV_UNICAST;
 	/* set unicast ttl */
-	unicast_packet->header.ttl = BATADV_TTL;
+	unicast_packet->ttl = BATADV_TTL;
 	/* copy the destination for faster routing */
 	memcpy(unicast_packet->dest, orig_node->orig, ETH_ALEN);
 	/* set the destination tt version number */
@@ -221,7 +221,7 @@ bool batadv_send_skb_prepare_unicast_4addr(struct batadv_priv *bat_priv,
 		goto out;
 
 	uc_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data;
-	uc_4addr_packet->u.header.packet_type = BATADV_UNICAST_4ADDR;
+	uc_4addr_packet->u.packet_type = BATADV_UNICAST_4ADDR;
 	memcpy(uc_4addr_packet->src, primary_if->net_dev->dev_addr, ETH_ALEN);
 	uc_4addr_packet->subtype = packet_subtype;
 	uc_4addr_packet->reserved = 0;
@@ -436,7 +436,7 @@ int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv,
 
 	/* as we have a copy now, it is safe to decrease the TTL */
 	bcast_packet = (struct batadv_bcast_packet *)newskb->data;
-	bcast_packet->header.ttl--;
+	bcast_packet->ttl--;
 
 	skb_reset_mac_header(newskb);
 
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 36f0508..b4881f8 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -264,11 +264,11 @@ static int batadv_interface_tx(struct sk_buff *skb,
 			goto dropped;
 
 		bcast_packet = (struct batadv_bcast_packet *)skb->data;
-		bcast_packet->header.version = BATADV_COMPAT_VERSION;
-		bcast_packet->header.ttl = BATADV_TTL;
+		bcast_packet->version = BATADV_COMPAT_VERSION;
+		bcast_packet->ttl = BATADV_TTL;
 
 		/* batman packet type: broadcast */
-		bcast_packet->header.packet_type = BATADV_BCAST;
+		bcast_packet->packet_type = BATADV_BCAST;
 		bcast_packet->reserved = 0;
 
 		/* hw address of first interface is the orig mac because only
@@ -328,7 +328,7 @@ void batadv_interface_rx(struct net_device *soft_iface,
 			 struct sk_buff *skb, struct batadv_hard_iface *recv_if,
 			 int hdr_size, struct batadv_orig_node *orig_node)
 {
-	struct batadv_header *batadv_header = (struct batadv_header *)skb->data;
+	struct batadv_bcast_packet *batadv_bcast_packet;
 	struct batadv_priv *bat_priv = netdev_priv(soft_iface);
 	__be16 ethertype = htons(ETH_P_BATMAN);
 	struct vlan_ethhdr *vhdr;
@@ -336,7 +336,8 @@ void batadv_interface_rx(struct net_device *soft_iface,
 	unsigned short vid;
 	bool is_bcast;
 
-	is_bcast = (batadv_header->packet_type == BATADV_BCAST);
+	batadv_bcast_packet = (struct batadv_bcast_packet *)skb->data;
+	is_bcast = (batadv_bcast_packet->packet_type == BATADV_BCAST);
 
 	/* check if enough space is available for pulling, and pull */
 	if (!pskb_may_pull(skb, hdr_size))
-- 
cgit v0.10.2


From 27a417e6badac911487c10990e04f5ccbb11b1b2 Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@meshcoding.com>
Date: Thu, 5 Dec 2013 15:33:00 +0100
Subject: batman-adv: fix size of batadv_icmp_header

struct batadv_icmp_header currently has a size of 17, which
will be padded to 20 on some architectures. Fix this by
unrolling the header into the parent structures.

Moreover keep the ICMP parsing functions as generic as they
are now by using a stub icmp_header struct during packet
parsing.

Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>

diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index d87778b..1511f64 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -426,8 +426,8 @@ static void batadv_recv_handler_init(void)
 	BUILD_BUG_ON(offsetof(struct batadv_unicast_packet, dest) != 4);
 	BUILD_BUG_ON(offsetof(struct batadv_unicast_tvlv_packet, dst) != 4);
 	BUILD_BUG_ON(offsetof(struct batadv_frag_packet, dest) != 4);
-	BUILD_BUG_ON(offsetof(struct batadv_icmp_packet, icmph.dst) != 4);
-	BUILD_BUG_ON(offsetof(struct batadv_icmp_packet_rr, icmph.dst) != 4);
+	BUILD_BUG_ON(offsetof(struct batadv_icmp_packet, dst) != 4);
+	BUILD_BUG_ON(offsetof(struct batadv_icmp_packet_rr, dst) != 4);
 
 	/* broadcast packet */
 	batadv_rx_handler[BATADV_BCAST] = batadv_recv_bcast_packet;
diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h
index 175ce7d..2a857ed 100644
--- a/net/batman-adv/packet.h
+++ b/net/batman-adv/packet.h
@@ -191,7 +191,7 @@ struct batadv_ogm_packet {
 #define BATADV_OGM_HLEN sizeof(struct batadv_ogm_packet)
 
 /**
- * batadv_icmp_header - common ICMP header
+ * batadv_icmp_header - common members among all the ICMP packets
  * @packet_type: batman-adv packet type, part of the general header
  * @version: batman-adv protocol version, part of the genereal header
  * @ttl: time to live for this packet, part of the genereal header
@@ -199,6 +199,11 @@ struct batadv_ogm_packet {
  * @dst: address of the destination node
  * @orig: address of the source node
  * @uid: local ICMP socket identifier
+ * @align: not used - useful for alignment purposes only
+ *
+ * This structure is used for ICMP packets parsing only and it is never sent
+ * over the wire. The alignment field at the end is there to ensure that
+ * members are padded the same way as they are in real packets.
  */
 struct batadv_icmp_header {
 	uint8_t  packet_type;
@@ -208,16 +213,29 @@ struct batadv_icmp_header {
 	uint8_t  dst[ETH_ALEN];
 	uint8_t  orig[ETH_ALEN];
 	uint8_t  uid;
+	uint8_t  align[3];
 };
 
 /**
  * batadv_icmp_packet - ICMP packet
- * @icmph: common ICMP header
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
+ * @msg_type: ICMP packet type
+ * @dst: address of the destination node
+ * @orig: address of the source node
+ * @uid: local ICMP socket identifier
  * @reserved: not used - useful for alignment
  * @seqno: ICMP sequence number
  */
 struct batadv_icmp_packet {
-	struct batadv_icmp_header icmph;
+	uint8_t  packet_type;
+	uint8_t  version;
+	uint8_t  ttl;
+	uint8_t  msg_type; /* see ICMP message types above */
+	uint8_t  dst[ETH_ALEN];
+	uint8_t  orig[ETH_ALEN];
+	uint8_t  uid;
 	uint8_t  reserved;
 	__be16   seqno;
 };
@@ -226,13 +244,25 @@ struct batadv_icmp_packet {
 
 /**
  * batadv_icmp_packet_rr - ICMP RouteRecord packet
- * @icmph: common ICMP header
+ * @packet_type: batman-adv packet type, part of the general header
+ * @version: batman-adv protocol version, part of the genereal header
+ * @ttl: time to live for this packet, part of the genereal header
+ * @msg_type: ICMP packet type
+ * @dst: address of the destination node
+ * @orig: address of the source node
+ * @uid: local ICMP socket identifier
  * @rr_cur: number of entries the rr array
  * @seqno: ICMP sequence number
  * @rr: route record array
  */
 struct batadv_icmp_packet_rr {
-	struct batadv_icmp_header icmph;
+	uint8_t  packet_type;
+	uint8_t  version;
+	uint8_t  ttl;
+	uint8_t  msg_type; /* see ICMP message types above */
+	uint8_t  dst[ETH_ALEN];
+	uint8_t  orig[ETH_ALEN];
+	uint8_t  uid;
 	uint8_t  rr_cur;
 	__be16   seqno;
 	uint8_t  rr[BATADV_RR_LEN][ETH_ALEN];
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index 5b52d71..46278bf 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -338,9 +338,9 @@ static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv,
 	icmp_packet = (struct batadv_icmp_packet *)skb->data;
 
 	/* send TTL exceeded if packet is an echo request (traceroute) */
-	if (icmp_packet->icmph.msg_type != BATADV_ECHO_REQUEST) {
+	if (icmp_packet->msg_type != BATADV_ECHO_REQUEST) {
 		pr_debug("Warning - can't forward icmp packet from %pM to %pM: ttl exceeded\n",
-			 icmp_packet->icmph.orig, icmp_packet->icmph.dst);
+			 icmp_packet->orig, icmp_packet->dst);
 		goto out;
 	}
 
@@ -349,7 +349,7 @@ static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv,
 		goto out;
 
 	/* get routing information */
-	orig_node = batadv_orig_hash_find(bat_priv, icmp_packet->icmph.orig);
+	orig_node = batadv_orig_hash_find(bat_priv, icmp_packet->orig);
 	if (!orig_node)
 		goto out;
 
@@ -359,11 +359,11 @@ static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv,
 
 	icmp_packet = (struct batadv_icmp_packet *)skb->data;
 
-	memcpy(icmp_packet->icmph.dst, icmp_packet->icmph.orig, ETH_ALEN);
-	memcpy(icmp_packet->icmph.orig, primary_if->net_dev->dev_addr,
+	memcpy(icmp_packet->dst, icmp_packet->orig, ETH_ALEN);
+	memcpy(icmp_packet->orig, primary_if->net_dev->dev_addr,
 	       ETH_ALEN);
-	icmp_packet->icmph.msg_type = BATADV_TTL_EXCEEDED;
-	icmp_packet->icmph.ttl = BATADV_TTL;
+	icmp_packet->msg_type = BATADV_TTL_EXCEEDED;
+	icmp_packet->ttl = BATADV_TTL;
 
 	if (batadv_send_skb_to_orig(skb, orig_node, NULL) != NET_XMIT_DROP)
 		ret = NET_RX_SUCCESS;
-- 
cgit v0.10.2


From 2f7a318219186485c175339758ac42a03644200b Mon Sep 17 00:00:00 2001
From: Simon Wunderlich <sw@simonwunderlich.de>
Date: Mon, 2 Dec 2013 20:38:33 +0100
Subject: batman-adv: fix size of batadv_bla_claim_dst

Since this is a mac address and always 48 bit, and we can assume that
it is always aligned to 2-byte boundaries, add a pack(2) pragma.

Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>

diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h
index 2a857ed..04cf27c 100644
--- a/net/batman-adv/packet.h
+++ b/net/batman-adv/packet.h
@@ -155,6 +155,7 @@ enum batadv_tvlv_type {
 	BATADV_TVLV_ROAM	= 0x05,
 };
 
+#pragma pack(2)
 /* the destination hardware field in the ARP frame is used to
  * transport the claim type and the group id
  */
@@ -163,6 +164,7 @@ struct batadv_bla_claim_dst {
 	uint8_t type;		/* bla_claimframe */
 	__be16 group;		/* group id */
 };
+#pragma pack()
 
 /**
  * struct batadv_ogm_packet - ogm (routing protocol) packet
-- 
cgit v0.10.2


From ca6630464454d74ae1d430e99007a1139f4a2aba Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@meshcoding.com>
Date: Sun, 15 Dec 2013 13:26:55 +0100
Subject: batman-adv: fix alignment for batadv_tvlv_tt_change

Make struct batadv_tvlv_tt_change a multiple 4 bytes long
to avoid padding on any architecture.

Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>

diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h
index 04cf27c..2dd8f24 100644
--- a/net/batman-adv/packet.h
+++ b/net/batman-adv/packet.h
@@ -484,13 +484,13 @@ struct batadv_tvlv_tt_vlan_data {
  * struct batadv_tvlv_tt_change - translation table diff data
  * @flags: status indicators concerning the non-mesh client (see
  *  batadv_tt_client_flags)
- * @reserved: reserved field
+ * @reserved: reserved field - useful for alignment purposes only
  * @addr: mac address of non-mesh client that triggered this tt change
  * @vid: VLAN identifier
  */
 struct batadv_tvlv_tt_change {
 	uint8_t flags;
-	uint8_t reserved;
+	uint8_t reserved[3];
 	uint8_t addr[ETH_ALEN];
 	__be16 vid;
 };
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 4add57d..ff625fe 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -333,7 +333,8 @@ static void batadv_tt_local_event(struct batadv_priv *bat_priv,
 		return;
 
 	tt_change_node->change.flags = flags;
-	tt_change_node->change.reserved = 0;
+	memset(tt_change_node->change.reserved, 0,
+	       sizeof(tt_change_node->change.reserved));
 	memcpy(tt_change_node->change.addr, common->addr, ETH_ALEN);
 	tt_change_node->change.vid = htons(common->vid);
 
@@ -2221,7 +2222,8 @@ static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv,
 			       ETH_ALEN);
 			tt_change->flags = tt_common_entry->flags;
 			tt_change->vid = htons(tt_common_entry->vid);
-			tt_change->reserved = 0;
+			memset(tt_change->reserved, 0,
+			       sizeof(tt_change->reserved));
 
 			tt_num_entries++;
 			tt_change++;
-- 
cgit v0.10.2


From 55883fd1048e09f5b6e1edaf0caf7e4f6f31f971 Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@meshcoding.com>
Date: Mon, 23 Dec 2013 01:28:05 +0100
Subject: batman-adv: clean nf state when removing protocol header

If an interface enslaved into batman-adv is a bridge (or a
virtual interface built on top of a bridge) the nf_bridge
member of the skbs reaching the soft-interface is filled
with the state about "netfilter bridge" operations.

Then, if one of such skbs is locally delivered, the nf_bridge
member should be cleaned up to avoid that the old state
could mess up with other "netfilter bridge" operations when
entering a second bridge.
This is needed because batman-adv is an encapsulation
protocol.

However at the moment skb->nf_bridge is not released at all
leading to bogus "netfilter bridge" behaviours.

Fix this by cleaning the netfilter state of the skb before
it gets delivered to the upper layer in interface_rx().

Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>

diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index b4881f8..875a702 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -346,6 +346,11 @@ void batadv_interface_rx(struct net_device *soft_iface,
 	skb_pull_rcsum(skb, hdr_size);
 	skb_reset_mac_header(skb);
 
+	/* clean the netfilter state now that the batman-adv header has been
+	 * removed
+	 */
+	nf_reset(skb);
+
 	vid = batadv_get_vid(skb, hdr_size);
 	ethhdr = eth_hdr(skb);
 
-- 
cgit v0.10.2


From 2b1e2cb3594df80446dc33bb8e12230da11f38ff Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@meshcoding.com>
Date: Mon, 23 Dec 2013 21:43:39 +0100
Subject: batman-adv: fix vlan header access

When batadv_get_vid() is invoked in interface_rx() the
batman-adv header has already been removed, therefore
the header_len argument has to be 0.

Introduced by c018ad3de61a1dc4194879a53e5559e094aa7b1a
("batman-adv: add the VLAN ID attribute to the TT entry")

Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>

diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 875a702..a8f99d1 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -351,7 +351,7 @@ void batadv_interface_rx(struct net_device *soft_iface,
 	 */
 	nf_reset(skb);
 
-	vid = batadv_get_vid(skb, hdr_size);
+	vid = batadv_get_vid(skb, 0);
 	ethhdr = eth_hdr(skb);
 
 	switch (ntohs(ethhdr->h_proto)) {
-- 
cgit v0.10.2


From 2ee0d3c80fdb7974cfa1c7e25b5048e9fcaf69b6 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Sat, 28 Dec 2013 00:59:38 +0100
Subject: netfilter: nf_tables: fix wrong datatype in nft_validate_data_load()

This patch fixes dictionary mappings, eg.

 add rule ip filter input meta dnat set tcp dport map { 22 => 1.1.1.1, 23 => 2.2.2.2 }

The kernel was returning -EINVAL in nft_validate_data_load() since
the type of the set element data that is passed was the real userspace
datatype instead of NFT_DATA_VALUE.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index d65c80b..71a9f49 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2382,7 +2382,9 @@ static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx,
 	enum nft_registers dreg;
 
 	dreg = nft_type_to_reg(set->dtype);
-	return nft_validate_data_load(ctx, dreg, &elem->data, set->dtype);
+	return nft_validate_data_load(ctx, dreg, &elem->data,
+				      set->dtype == NFT_DATA_VERDICT ?
+				      NFT_DATA_VERDICT : NFT_DATA_VALUE);
 }
 
 int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
-- 
cgit v0.10.2


From 4ff859fe1dc0da0f87bbdfff78f527898878fa4a Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Sun, 29 Dec 2013 12:39:50 +0000
Subject: ARM: fix footbridge clockevent device

The clockevents code was being told that the footbridge clock event
device ticks at 16x the rate which it actually does.  This leads to
timekeeping problems since it allows the clocksource to wrap before
the kernel notices.  Fix this by using the correct clock.

Fixes: 4e8d76373c9fd ("ARM: footbridge: convert to clockevents/clocksource")
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Cc: <stable@vger.kernel.org>

diff --git a/arch/arm/mach-footbridge/dc21285-timer.c b/arch/arm/mach-footbridge/dc21285-timer.c
index 9ee78f7..782f6c7 100644
--- a/arch/arm/mach-footbridge/dc21285-timer.c
+++ b/arch/arm/mach-footbridge/dc21285-timer.c
@@ -96,11 +96,12 @@ static struct irqaction footbridge_timer_irq = {
 void __init footbridge_timer_init(void)
 {
 	struct clock_event_device *ce = &ckevt_dc21285;
+	unsigned rate = DIV_ROUND_CLOSEST(mem_fclk_21285, 16);
 
-	clocksource_register_hz(&cksrc_dc21285, (mem_fclk_21285 + 8) / 16);
+	clocksource_register_hz(&cksrc_dc21285, rate);
 
 	setup_irq(ce->irq, &footbridge_timer_irq);
 
 	ce->cpumask = cpumask_of(smp_processor_id());
-	clockevents_config_and_register(ce, mem_fclk_21285, 0x4, 0xffffff);
+	clockevents_config_and_register(ce, rate, 0x4, 0xffffff);
 }
-- 
cgit v0.10.2


From 2a7cfcbc0553365d75716f69ee7b704cac7c9248 Mon Sep 17 00:00:00 2001
From: Steven Capper <steve.capper@linaro.org>
Date: Mon, 16 Dec 2013 17:25:52 +0100
Subject: ARM: 7923/1: mm: fix dcache flush logic for compound high pages

When given a compound high page, __flush_dcache_page will only flush
the first page of the compound page repeatedly rather than the entire
set of constituent pages.

This error was introduced by:
   0b19f93 ARM: mm: Add support for flushing HugeTLB pages.

This patch corrects the logic such that all constituent pages are now
flushed.

Cc: stable@vger.kernel.org # 3.10+
Signed-off-by: Steve Capper <steve.capper@linaro.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 6d5ba9a..3387e60 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -175,16 +175,16 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page)
 		unsigned long i;
 		if (cache_is_vipt_nonaliasing()) {
 			for (i = 0; i < (1 << compound_order(page)); i++) {
-				void *addr = kmap_atomic(page);
+				void *addr = kmap_atomic(page + i);
 				__cpuc_flush_dcache_area(addr, PAGE_SIZE);
 				kunmap_atomic(addr);
 			}
 		} else {
 			for (i = 0; i < (1 << compound_order(page)); i++) {
-				void *addr = kmap_high_get(page);
+				void *addr = kmap_high_get(page + i);
 				if (addr) {
 					__cpuc_flush_dcache_area(addr, PAGE_SIZE);
-					kunmap_high(page);
+					kunmap_high(page + i);
 				}
 			}
 		}
-- 
cgit v0.10.2


From efea3403d4b7c6d1dd5d5ac3234c161e8b314d66 Mon Sep 17 00:00:00 2001
From: Laura Abbott <lauraa@codeaurora.org>
Date: Sat, 21 Dec 2013 01:03:06 +0100
Subject: ARM: 7931/1: Correct virt_addr_valid

The definition of virt_addr_valid is that virt_addr_valid should
return true if and only if virt_to_page returns a valid pointer.
The current definition of virt_addr_valid only checks against the
virtual address range. There's no guarantee that just because a
virtual address falls bewteen PAGE_OFFSET and high_memory the
associated physical memory has a valid backing struct page. Follow
the example of other architectures and convert to pfn_valid to
verify that the virtual address is actually valid. The check for
an address between PAGE_OFFSET and high_memory is still necessary
as vmalloc/highmem addresses are not valid with virt_to_page.

Cc: Will Deacon <will.deacon@arm.com>
Cc: Nicolas Pitre <nico@linaro.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Laura Abbott <lauraa@codeaurora.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 6976b03..8756e4b 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -347,7 +347,8 @@ static inline __deprecated void *bus_to_virt(unsigned long x)
 #define ARCH_PFN_OFFSET		PHYS_PFN_OFFSET
 
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
-#define virt_addr_valid(kaddr)	((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory)
+#define virt_addr_valid(kaddr)	(((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory) \
+					&& pfn_valid(__pa(kaddr) >> PAGE_SHIFT) )
 
 #endif
 
-- 
cgit v0.10.2


From 1fec0533693cd74f2d1a46edd29449cfee429df0 Mon Sep 17 00:00:00 2001
From: Dave Young <dyoung@redhat.com>
Date: Fri, 20 Dec 2013 18:02:19 +0800
Subject: x86/efi: Pass necessary EFI data for kexec via setup_data

Add a new setup_data type SETUP_EFI for kexec use.  Passing the saved
fw_vendor, runtime, config tables and EFI runtime mappings.

When entering virtual mode, directly mapping the EFI runtime regions
which we passed in previously. And skip the step to call
SetVirtualAddressMap().

Specially for HP z420 workstation we need save the smbios physical
address.  The kernel boot sequence proceeds in the following order.
Step 2 requires efi.smbios to be the physical address.  However, I found
that on HP z420 EFI system table has a virtual address of SMBIOS in step
1.  Hence, we need set it back to the physical address with the smbios
in efi_setup_data.  (When it is still the physical address, it simply
sets the same value.)

1. efi_init() - Set efi.smbios from EFI system table
2. dmi_scan_machine() - Temporary map efi.smbios to access SMBIOS table
3. efi_enter_virtual_mode() - Map EFI ranges

Tested on ovmf+qemu, lenovo thinkpad, a dell laptop and an
HP z420 workstation.

Signed-off-by: Dave Young <dyoung@redhat.com>
Tested-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 9fbaeb2..4d1ba80 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -133,6 +133,18 @@ extern void efi_sync_low_kernel_mappings(void);
 extern void efi_setup_page_tables(void);
 extern void __init old_map_region(efi_memory_desc_t *md);
 
+struct efi_setup_data {
+	u64 fw_vendor;
+	u64 runtime;
+	u64 tables;
+	u64 smbios;
+	u64 reserved[8];
+};
+
+extern u64 efi_setup;
+extern u32 efi_data_len;
+extern void parse_efi_setup(u64 phys_addr, u32 data_len);
+
 #ifdef CONFIG_EFI
 
 static inline bool efi_is_native(void)
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 9c3733c..64fe421 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -6,6 +6,7 @@
 #define SETUP_E820_EXT			1
 #define SETUP_DTB			2
 #define SETUP_PCI			3
+#define SETUP_EFI			4
 
 /* ram_size flags */
 #define RAMDISK_IMAGE_START_MASK	0x07FF
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index cb233bc..24536f7 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -447,6 +447,9 @@ static void __init parse_setup_data(void)
 		case SETUP_DTB:
 			add_dtb(pa_data);
 			break;
+		case SETUP_EFI:
+			parse_efi_setup(pa_data, data_len);
+			break;
 		default:
 			break;
 		}
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 74fe7a7..9965ff4 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -78,6 +78,8 @@ static __initdata efi_config_table_type_t arch_tables[] = {
 
 static void *efi_runtime_map;
 static int nr_efi_runtime_map;
+u64 efi_setup;		/* efi setup_data physical address */
+u32 efi_data_len;	/* efi setup_data payload length */
 
 /*
  * Returns 1 if 'facility' is enabled, 0 otherwise.
@@ -115,7 +117,6 @@ static int __init setup_storage_paranoia(char *arg)
 }
 early_param("efi_no_storage_paranoia", setup_storage_paranoia);
 
-
 static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 {
 	unsigned long flags;
@@ -494,18 +495,27 @@ static int __init efi_systab_init(void *phys)
 {
 	if (efi_enabled(EFI_64BIT)) {
 		efi_system_table_64_t *systab64;
+		struct efi_setup_data *data = NULL;
 		u64 tmp = 0;
 
+		if (efi_setup) {
+			data = early_memremap(efi_setup, sizeof(*data));
+			if (!data)
+				return -ENOMEM;
+		}
 		systab64 = early_ioremap((unsigned long)phys,
 					 sizeof(*systab64));
 		if (systab64 == NULL) {
 			pr_err("Couldn't map the system table!\n");
+			if (data)
+				early_iounmap(data, sizeof(*data));
 			return -ENOMEM;
 		}
 
 		efi_systab.hdr = systab64->hdr;
-		efi_systab.fw_vendor = systab64->fw_vendor;
-		tmp |= systab64->fw_vendor;
+		efi_systab.fw_vendor = data ? (unsigned long)data->fw_vendor :
+					      systab64->fw_vendor;
+		tmp |= data ? data->fw_vendor : systab64->fw_vendor;
 		efi_systab.fw_revision = systab64->fw_revision;
 		efi_systab.con_in_handle = systab64->con_in_handle;
 		tmp |= systab64->con_in_handle;
@@ -519,15 +529,20 @@ static int __init efi_systab_init(void *phys)
 		tmp |= systab64->stderr_handle;
 		efi_systab.stderr = systab64->stderr;
 		tmp |= systab64->stderr;
-		efi_systab.runtime = (void *)(unsigned long)systab64->runtime;
-		tmp |= systab64->runtime;
+		efi_systab.runtime = data ?
+				     (void *)(unsigned long)data->runtime :
+				     (void *)(unsigned long)systab64->runtime;
+		tmp |= data ? data->runtime : systab64->runtime;
 		efi_systab.boottime = (void *)(unsigned long)systab64->boottime;
 		tmp |= systab64->boottime;
 		efi_systab.nr_tables = systab64->nr_tables;
-		efi_systab.tables = systab64->tables;
-		tmp |= systab64->tables;
+		efi_systab.tables = data ? (unsigned long)data->tables :
+					   systab64->tables;
+		tmp |= data ? data->tables : systab64->tables;
 
 		early_iounmap(systab64, sizeof(*systab64));
+		if (data)
+			early_iounmap(data, sizeof(*data));
 #ifdef CONFIG_X86_32
 		if (tmp >> 32) {
 			pr_err("EFI data located above 4GB, disabling EFI.\n");
@@ -631,6 +646,71 @@ static int __init efi_memmap_init(void)
 	return 0;
 }
 
+/*
+ * A number of config table entries get remapped to virtual addresses
+ * after entering EFI virtual mode. However, the kexec kernel requires
+ * their physical addresses therefore we pass them via setup_data and
+ * correct those entries to their respective physical addresses here.
+ *
+ * Currently only handles smbios which is necessary for some firmware
+ * implementation.
+ */
+static int __init efi_reuse_config(u64 tables, int nr_tables)
+{
+	int i, sz, ret = 0;
+	void *p, *tablep;
+	struct efi_setup_data *data;
+
+	if (!efi_setup)
+		return 0;
+
+	if (!efi_enabled(EFI_64BIT))
+		return 0;
+
+	data = early_memremap(efi_setup, sizeof(*data));
+	if (!data) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	if (!data->smbios)
+		goto out_memremap;
+
+	sz = sizeof(efi_config_table_64_t);
+
+	p = tablep = early_memremap(tables, nr_tables * sz);
+	if (!p) {
+		pr_err("Could not map Configuration table!\n");
+		ret = -ENOMEM;
+		goto out_memremap;
+	}
+
+	for (i = 0; i < efi.systab->nr_tables; i++) {
+		efi_guid_t guid;
+
+		guid = ((efi_config_table_64_t *)p)->guid;
+
+		if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID))
+			((efi_config_table_64_t *)p)->table = data->smbios;
+		p += sz;
+	}
+	early_iounmap(tablep, nr_tables * sz);
+
+out_memremap:
+	early_iounmap(data, sizeof(*data));
+out:
+	return ret;
+}
+
+static void get_nr_runtime_map(void)
+{
+	if (!efi_setup)
+		return;
+
+	nr_efi_runtime_map = (efi_data_len - sizeof(struct efi_setup_data)) /
+			     sizeof(efi_memory_desc_t);
+}
+
 void __init efi_init(void)
 {
 	efi_char16_t *c16;
@@ -638,6 +718,7 @@ void __init efi_init(void)
 	int i = 0;
 	void *tmp;
 
+	get_nr_runtime_map();
 #ifdef CONFIG_X86_32
 	if (boot_params.efi_info.efi_systab_hi ||
 	    boot_params.efi_info.efi_memmap_hi) {
@@ -676,6 +757,9 @@ void __init efi_init(void)
 		efi.systab->hdr.revision >> 16,
 		efi.systab->hdr.revision & 0xffff, vendor);
 
+	if (efi_reuse_config(efi.systab->tables, efi.systab->nr_tables))
+		return;
+
 	if (efi_config_init(arch_tables))
 		return;
 
@@ -861,6 +945,23 @@ out:
 }
 
 /*
+ * Map efi regions which were passed via setup_data. The virt_addr is a fixed
+ * addr which was used in first kernel of a kexec boot.
+ */
+static void __init efi_map_regions_fixed(void)
+{
+	void *p;
+	efi_memory_desc_t *md;
+
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		md = p;
+		efi_map_region_fixed(md); /* FIXME: add error handling */
+		get_systab_virt_addr(md);
+	}
+
+}
+
+/*
  * Map efi memory ranges for runtime serivce and update new_memmap with virtual
  * addresses.
  */
@@ -914,6 +1015,10 @@ out:
  * so that we're in a different address space when calling a runtime
  * function. For function arguments passing we do copy the PGDs of the
  * kernel page table into ->trampoline_pgd prior to each call.
+ *
+ * Specially for kexec boot, efi runtime maps in previous kernel should
+ * be passed in via setup_data. In that case runtime ranges will be mapped
+ * to the same virtual addresses as the first kernel.
  */
 void __init efi_enter_virtual_mode(void)
 {
@@ -932,12 +1037,15 @@ void __init efi_enter_virtual_mode(void)
 		return;
 	}
 
-	efi_merge_regions();
-
-	new_memmap = efi_map_regions(&count);
-	if (!new_memmap) {
-		pr_err("Error reallocating memory, EFI runtime non-functional!\n");
-		return;
+	if (efi_setup) {
+		efi_map_regions_fixed();
+	} else {
+		efi_merge_regions();
+		new_memmap = efi_map_regions(&count);
+		if (!new_memmap) {
+			pr_err("Error reallocating memory, EFI runtime non-functional!\n");
+			return;
+		}
 	}
 
 	err = save_runtime_map();
@@ -949,16 +1057,18 @@ void __init efi_enter_virtual_mode(void)
 	efi_setup_page_tables();
 	efi_sync_low_kernel_mappings();
 
-	status = phys_efi_set_virtual_address_map(
-		memmap.desc_size * count,
-		memmap.desc_size,
-		memmap.desc_version,
-		(efi_memory_desc_t *)__pa(new_memmap));
-
-	if (status != EFI_SUCCESS) {
-		pr_alert("Unable to switch EFI into virtual mode "
-			 "(status=%lx)!\n", status);
-		panic("EFI call to SetVirtualAddressMap() failed!");
+	if (!efi_setup) {
+		status = phys_efi_set_virtual_address_map(
+			memmap.desc_size * count,
+			memmap.desc_size,
+			memmap.desc_version,
+			(efi_memory_desc_t *)__pa(new_memmap));
+
+		if (status != EFI_SUCCESS) {
+			pr_alert("Unable to switch EFI into virtual mode (status=%lx)!\n",
+				 status);
+			panic("EFI call to SetVirtualAddressMap() failed!");
+		}
 	}
 
 	/*
@@ -993,8 +1103,6 @@ void __init efi_enter_virtual_mode(void)
 			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
 			 EFI_VARIABLE_RUNTIME_ACCESS,
 			 0, NULL);
-
-	return;
 }
 
 /*
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index 7b3ec6e..249b183 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -48,6 +48,7 @@ void __init efi_map_region(efi_memory_desc_t *md)
 }
 
 void __init efi_map_region_fixed(efi_memory_desc_t *md) {}
+void __init parse_efi_setup(u64 phys_addr, u32 data_len) {}
 
 void efi_call_phys_prelog(void)
 {
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index ff08cb1..324b651 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -228,3 +228,9 @@ void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
 
 	return (void __iomem *)__va(phys_addr);
 }
+
+void __init parse_efi_setup(u64 phys_addr, u32 data_len)
+{
+	efi_setup = phys_addr + sizeof(struct setup_data);
+	efi_data_len = data_len - sizeof(struct setup_data);
+}
-- 
cgit v0.10.2


From 456a29ddada79198c5965300e04103c40c481f62 Mon Sep 17 00:00:00 2001
From: Dave Young <dyoung@redhat.com>
Date: Fri, 20 Dec 2013 18:02:20 +0800
Subject: x86: Add xloadflags bit for EFI runtime support on kexec

Old kexec-tools can not load new kernels. The reason is kexec-tools does
not fill efi_info in x86 setup header previously, thus EFI failed to
initialize.  In new kexec-tools it will by default to fill efi_info and
pass other EFI required infomation to 2nd kernel so kexec kernel EFI
initialization can succeed finally.

To prevent from breaking userspace, add a new xloadflags bit so
kexec-tools can check the flag and switch to old logic.

Signed-off-by: Dave Young <dyoung@redhat.com>
Acked-by: Borislav Petkov <bp@suse.de>
Tested-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt
index f4f268c..cb81741d 100644
--- a/Documentation/x86/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -608,6 +608,9 @@ Protocol:       2.12+
 	- If 1, the kernel supports the 64-bit EFI handoff entry point
           given at handover_offset + 0x200.
 
+  Bit 4 (read): XLF_EFI_KEXEC
+	- If 1, the kernel supports kexec EFI boot with EFI runtime support.
+
 Field name:	cmdline_size
 Type:		read
 Offset/size:	0x238/4
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 9ec06a1..ec3b8ba 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -391,7 +391,14 @@ xloadflags:
 #else
 # define XLF23 0
 #endif
-			.word XLF0 | XLF1 | XLF23
+
+#if defined(CONFIG_X86_64) && defined(CONFIG_EFI) && defined(CONFIG_KEXEC)
+# define XLF4 XLF_EFI_KEXEC
+#else
+# define XLF4 0
+#endif
+
+			.word XLF0 | XLF1 | XLF23 | XLF4
 
 cmdline_size:   .long   COMMAND_LINE_SIZE-1     #length of the command line,
                                                 #added with boot protocol
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 64fe421..225b098 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -24,6 +24,7 @@
 #define XLF_CAN_BE_LOADED_ABOVE_4G	(1<<1)
 #define XLF_EFI_HANDOVER_32		(1<<2)
 #define XLF_EFI_HANDOVER_64		(1<<3)
+#define XLF_EFI_KEXEC			(1<<4)
 
 #ifndef __ASSEMBLY__
 
-- 
cgit v0.10.2


From 5039e316dde3fb71c79e95e97c5bca8e4724d8f2 Mon Sep 17 00:00:00 2001
From: Dave Young <dyoung@redhat.com>
Date: Fri, 20 Dec 2013 18:02:21 +0800
Subject: x86: Export x86 boot_params to sysfs

kexec-tools use boot_params for getting the 1st kernel hardware_subarch,
the kexec kernel EFI runtime support also needs to read the old efi_info
from boot_params. Currently it exists in debugfs which is not a good
place for such infomation. Per HPA, we should avoid "sploit debugfs".

In this patch /sys/kernel/boot_params are exported, also the setup_data is
exported as a subdirectory. kexec-tools is using debugfs for hardware_subarch
for a long time now so we're not removing it yet.

Structure is like below:

/sys/kernel/boot_params
|__ data                /* boot_params in binary*/
|__ setup_data
|   |__ 0               /* the first setup_data node */
|   |   |__ data        /* setup_data node 0 in binary*/
|   |   |__ type        /* setup_data type of setup_data node 0, hex string */
[snip]
|__ version             /* boot protocal version (in hex, "0x" prefixed)*/

Signed-off-by: Dave Young <dyoung@redhat.com>
Acked-by: Borislav Petkov <bp@suse.de>
Tested-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/Documentation/ABI/testing/sysfs-kernel-boot_params b/Documentation/ABI/testing/sysfs-kernel-boot_params
new file mode 100644
index 0000000..eca38ce
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-boot_params
@@ -0,0 +1,38 @@
+What:		/sys/kernel/boot_params
+Date:		December 2013
+Contact:	Dave Young <dyoung@redhat.com>
+Description:	The /sys/kernel/boot_params directory contains two
+		files: "data" and "version" and one subdirectory "setup_data".
+		It is used to export the kernel boot parameters of an x86
+		platform to userspace for kexec and debugging purpose.
+
+		If there's no setup_data in boot_params the subdirectory will
+		not be created.
+
+		"data" file is the binary representation of struct boot_params.
+
+		"version" file is the string representation of boot
+		protocol version.
+
+		"setup_data" subdirectory contains the setup_data data
+		structure in boot_params. setup_data is maintained in kernel
+		as a link list. In "setup_data" subdirectory there's one
+		subdirectory for each link list node named with the number
+		of the list nodes. The list node subdirectory contains two
+		files "type" and "data". "type" file is the string
+		representation of setup_data type. "data" file is the binary
+		representation of setup_data payload.
+
+		The whole boot_params directory structure is like below:
+		/sys/kernel/boot_params
+		|__ data
+		|__ setup_data
+		|   |__ 0
+		|   |   |__ data
+		|   |   |__ type
+		|   |__ 1
+		|       |__ data
+		|       |__ type
+		|__ version
+
+Users:		Kexec
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 9b0a34e..510cca5 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -29,6 +29,7 @@ obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-y			+= syscall_$(BITS).o
 obj-$(CONFIG_X86_64)	+= vsyscall_64.o
 obj-$(CONFIG_X86_64)	+= vsyscall_emu_64.o
+obj-$(CONFIG_SYSFS)	+= ksysfs.o
 obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o hw_breakpoint.o
diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c
new file mode 100644
index 0000000..eb53d15
--- /dev/null
+++ b/arch/x86/kernel/ksysfs.c
@@ -0,0 +1,339 @@
+/*
+ * Architecture specific sysfs attributes in /sys/kernel
+ *
+ * Copyright (C) 2007, Intel Corp.
+ *      Huang Ying <ying.huang@intel.com>
+ * Copyright (C) 2013, 2013 Red Hat, Inc.
+ *      Dave Young <dyoung@redhat.com>
+ *
+ * This file is released under the GPLv2
+ */
+
+#include <linux/kobject.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/init.h>
+#include <linux/stat.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+
+#include <asm/setup.h>
+
+static ssize_t version_show(struct kobject *kobj,
+			    struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "0x%04x\n", boot_params.hdr.version);
+}
+
+static struct kobj_attribute boot_params_version_attr = __ATTR_RO(version);
+
+static ssize_t boot_params_data_read(struct file *fp, struct kobject *kobj,
+				     struct bin_attribute *bin_attr,
+				     char *buf, loff_t off, size_t count)
+{
+	memcpy(buf, (void *)&boot_params + off, count);
+	return count;
+}
+
+static struct bin_attribute boot_params_data_attr = {
+	.attr = {
+		.name = "data",
+		.mode = S_IRUGO,
+	},
+	.read = boot_params_data_read,
+	.size = sizeof(boot_params),
+};
+
+static struct attribute *boot_params_version_attrs[] = {
+	&boot_params_version_attr.attr,
+	NULL,
+};
+
+static struct bin_attribute *boot_params_data_attrs[] = {
+	&boot_params_data_attr,
+	NULL,
+};
+
+static struct attribute_group boot_params_attr_group = {
+	.attrs = boot_params_version_attrs,
+	.bin_attrs = boot_params_data_attrs,
+};
+
+static int kobj_to_setup_data_nr(struct kobject *kobj, int *nr)
+{
+	const char *name;
+
+	name = kobject_name(kobj);
+	return kstrtoint(name, 10, nr);
+}
+
+static int get_setup_data_paddr(int nr, u64 *paddr)
+{
+	int i = 0;
+	struct setup_data *data;
+	u64 pa_data = boot_params.hdr.setup_data;
+
+	while (pa_data) {
+		if (nr == i) {
+			*paddr = pa_data;
+			return 0;
+		}
+		data = ioremap_cache(pa_data, sizeof(*data));
+		if (!data)
+			return -ENOMEM;
+
+		pa_data = data->next;
+		iounmap(data);
+		i++;
+	}
+	return -EINVAL;
+}
+
+static int __init get_setup_data_size(int nr, size_t *size)
+{
+	int i = 0;
+	struct setup_data *data;
+	u64 pa_data = boot_params.hdr.setup_data;
+
+	while (pa_data) {
+		data = ioremap_cache(pa_data, sizeof(*data));
+		if (!data)
+			return -ENOMEM;
+		if (nr == i) {
+			*size = data->len;
+			iounmap(data);
+			return 0;
+		}
+
+		pa_data = data->next;
+		iounmap(data);
+		i++;
+	}
+	return -EINVAL;
+}
+
+static ssize_t type_show(struct kobject *kobj,
+			 struct kobj_attribute *attr, char *buf)
+{
+	int nr, ret;
+	u64 paddr;
+	struct setup_data *data;
+
+	ret = kobj_to_setup_data_nr(kobj, &nr);
+	if (ret)
+		return ret;
+
+	ret = get_setup_data_paddr(nr, &paddr);
+	if (ret)
+		return ret;
+	data = ioremap_cache(paddr, sizeof(*data));
+	if (!data)
+		return -ENOMEM;
+
+	ret = sprintf(buf, "0x%x\n", data->type);
+	iounmap(data);
+	return ret;
+}
+
+static ssize_t setup_data_data_read(struct file *fp,
+				    struct kobject *kobj,
+				    struct bin_attribute *bin_attr,
+				    char *buf,
+				    loff_t off, size_t count)
+{
+	int nr, ret = 0;
+	u64 paddr;
+	struct setup_data *data;
+	void *p;
+
+	ret = kobj_to_setup_data_nr(kobj, &nr);
+	if (ret)
+		return ret;
+
+	ret = get_setup_data_paddr(nr, &paddr);
+	if (ret)
+		return ret;
+	data = ioremap_cache(paddr, sizeof(*data));
+	if (!data)
+		return -ENOMEM;
+
+	if (off > data->len) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (count > data->len - off)
+		count = data->len - off;
+
+	if (!count)
+		goto out;
+
+	ret = count;
+	p = ioremap_cache(paddr + sizeof(*data), data->len);
+	if (!p) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	memcpy(buf, p + off, count);
+	iounmap(p);
+out:
+	iounmap(data);
+	return ret;
+}
+
+static struct kobj_attribute type_attr = __ATTR_RO(type);
+
+static struct bin_attribute data_attr = {
+	.attr = {
+		.name = "data",
+		.mode = S_IRUGO,
+	},
+	.read = setup_data_data_read,
+};
+
+static struct attribute *setup_data_type_attrs[] = {
+	&type_attr.attr,
+	NULL,
+};
+
+static struct bin_attribute *setup_data_data_attrs[] = {
+	&data_attr,
+	NULL,
+};
+
+static struct attribute_group setup_data_attr_group = {
+	.attrs = setup_data_type_attrs,
+	.bin_attrs = setup_data_data_attrs,
+};
+
+static int __init create_setup_data_node(struct kobject *parent,
+					 struct kobject **kobjp, int nr)
+{
+	int ret = 0;
+	size_t size;
+	struct kobject *kobj;
+	char name[16]; /* should be enough for setup_data nodes numbers */
+	snprintf(name, 16, "%d", nr);
+
+	kobj = kobject_create_and_add(name, parent);
+	if (!kobj)
+		return -ENOMEM;
+
+	ret = get_setup_data_size(nr, &size);
+	if (ret)
+		goto out_kobj;
+
+	data_attr.size = size;
+	ret = sysfs_create_group(kobj, &setup_data_attr_group);
+	if (ret)
+		goto out_kobj;
+	*kobjp = kobj;
+
+	return 0;
+out_kobj:
+	kobject_put(kobj);
+	return ret;
+}
+
+static void __init cleanup_setup_data_node(struct kobject *kobj)
+{
+	sysfs_remove_group(kobj, &setup_data_attr_group);
+	kobject_put(kobj);
+}
+
+static int __init get_setup_data_total_num(u64 pa_data, int *nr)
+{
+	int ret = 0;
+	struct setup_data *data;
+
+	*nr = 0;
+	while (pa_data) {
+		*nr += 1;
+		data = ioremap_cache(pa_data, sizeof(*data));
+		if (!data) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		pa_data = data->next;
+		iounmap(data);
+	}
+
+out:
+	return ret;
+}
+
+static int __init create_setup_data_nodes(struct kobject *parent)
+{
+	struct kobject *setup_data_kobj, **kobjp;
+	u64 pa_data;
+	int i, j, nr, ret = 0;
+
+	pa_data = boot_params.hdr.setup_data;
+	if (!pa_data)
+		return 0;
+
+	setup_data_kobj = kobject_create_and_add("setup_data", parent);
+	if (!setup_data_kobj) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = get_setup_data_total_num(pa_data, &nr);
+	if (ret)
+		goto out_setup_data_kobj;
+
+	kobjp = kmalloc(sizeof(*kobjp) * nr, GFP_KERNEL);
+	if (!kobjp) {
+		ret = -ENOMEM;
+		goto out_setup_data_kobj;
+	}
+
+	for (i = 0; i < nr; i++) {
+		ret = create_setup_data_node(setup_data_kobj, kobjp + i, i);
+		if (ret)
+			goto out_clean_nodes;
+	}
+
+	kfree(kobjp);
+	return 0;
+
+out_clean_nodes:
+	for (j = i - 1; j > 0; j--)
+		cleanup_setup_data_node(*(kobjp + j));
+	kfree(kobjp);
+out_setup_data_kobj:
+	kobject_put(setup_data_kobj);
+out:
+	return ret;
+}
+
+static int __init boot_params_ksysfs_init(void)
+{
+	int ret;
+	struct kobject *boot_params_kobj;
+
+	boot_params_kobj = kobject_create_and_add("boot_params",
+						  kernel_kobj);
+	if (!boot_params_kobj) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = sysfs_create_group(boot_params_kobj, &boot_params_attr_group);
+	if (ret)
+		goto out_boot_params_kobj;
+
+	ret = create_setup_data_nodes(boot_params_kobj);
+	if (ret)
+		goto out_create_group;
+
+	return 0;
+out_create_group:
+	sysfs_remove_group(boot_params_kobj, &boot_params_attr_group);
+out_boot_params_kobj:
+	kobject_put(boot_params_kobj);
+out:
+	return ret;
+}
+
+arch_initcall(boot_params_ksysfs_init);
-- 
cgit v0.10.2


From 77ea8c948953a90401e436e7c05973b2d5529804 Mon Sep 17 00:00:00 2001
From: Dave Young <dyoung@redhat.com>
Date: Fri, 20 Dec 2013 18:02:22 +0800
Subject: x86: Reserve setup_data ranges late after parsing memmap cmdline

Currently e820_reserve_setup_data() is called before parsing early
params, it works in normal case. But for memmap=exactmap, the final
memory ranges are created after parsing memmap= cmdline params, so the
previous e820_reserve_setup_data() has no effect. For example,
setup_data ranges will still be marked as normal system ram, thus when
later sysfs driver ioremap them kernel will warn about mapping normal
ram.

This patch fix it by moving the e820_reserve_setup_data() callback after
parsing early params so they can be set as reserved ranges and later
ioremap will be fine with it.

Signed-off-by: Dave Young <dyoung@redhat.com>
Acked-by: Borislav Petkov <bp@suse.de>
Tested-by: Toshi Kani <toshi.kani@hp.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 24536f7..be4b456 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -927,8 +927,6 @@ void __init setup_arch(char **cmdline_p)
 	iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
 	setup_memory_map();
 	parse_setup_data();
-	/* update the e820_saved too */
-	e820_reserve_setup_data();
 
 	copy_edd();
 
@@ -990,6 +988,8 @@ void __init setup_arch(char **cmdline_p)
 		early_dump_pci_devices();
 #endif
 
+	/* update the e820_saved too */
+	e820_reserve_setup_data();
 	finish_e820_parsing();
 
 	if (efi_enabled(EFI_BOOT))
-- 
cgit v0.10.2


From 518548abd61808ea1e31614ccbdae34d3c32dfa4 Mon Sep 17 00:00:00 2001
From: Matt Fleming <matt.fleming@intel.com>
Date: Sat, 21 Dec 2013 16:09:46 +0000
Subject: x86/efi: Delete superfluous global variables

There's no need to save the runtime map details in global variables, the
values are only required to pass to efi_runtime_map_setup().

And because 'nr_efi_runtime_map' isn't needed, get_nr_runtime_map() can
be deleted along with 'efi_data_len'.

Cc: Dave Young <dyoung@redhat.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 9965ff4..7ed3ecf 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -76,10 +76,7 @@ static __initdata efi_config_table_type_t arch_tables[] = {
 	{NULL_GUID, NULL, NULL},
 };
 
-static void *efi_runtime_map;
-static int nr_efi_runtime_map;
 u64 efi_setup;		/* efi setup_data physical address */
-u32 efi_data_len;	/* efi setup_data payload length */
 
 /*
  * Returns 1 if 'facility' is enabled, 0 otherwise.
@@ -702,15 +699,6 @@ out:
 	return ret;
 }
 
-static void get_nr_runtime_map(void)
-{
-	if (!efi_setup)
-		return;
-
-	nr_efi_runtime_map = (efi_data_len - sizeof(struct efi_setup_data)) /
-			     sizeof(efi_memory_desc_t);
-}
-
 void __init efi_init(void)
 {
 	efi_char16_t *c16;
@@ -718,7 +706,6 @@ void __init efi_init(void)
 	int i = 0;
 	void *tmp;
 
-	get_nr_runtime_map();
 #ifdef CONFIG_X86_32
 	if (boot_params.efi_info.efi_systab_hi ||
 	    boot_params.efi_info.efi_memmap_hi) {
@@ -933,10 +920,7 @@ static int __init save_runtime_map(void)
 		count++;
 	}
 
-	efi_runtime_map = q;
-	nr_efi_runtime_map = count;
-	efi_runtime_map_setup(efi_runtime_map, nr_efi_runtime_map,
-			      boot_params.efi_info.efi_memdesc_size);
+	efi_runtime_map_setup(q, count, memmap.desc_size);
 
 	return 0;
 out:
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 324b651..6284f15 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -232,5 +232,4 @@ void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
 void __init parse_efi_setup(u64 phys_addr, u32 data_len)
 {
 	efi_setup = phys_addr + sizeof(struct setup_data);
-	efi_data_len = data_len - sizeof(struct setup_data);
 }
-- 
cgit v0.10.2


From 72368d122c7479aa6e14fbbd334717b8a0c157a6 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 27 Dec 2013 01:07:11 +0100
Subject: cpufreq: Clean up after a failing light-weight initialization
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If cpufreq_policy_restore() returns NULL during system resume,
__cpufreq_add_dev() should just fall back to the full initialization
instead of returning an error, because that may actually make things
work.  Moreover, it should not leave stale fallback data behind after
it has failed to restore a previously existing policy.

This change is based on Viresh Kumar's work.

Fixes: 5302c3fb2e62 ("cpufreq: Perform light-weight init/teardown during suspend/resume")
Reported-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: 3.12+ <stable@vger.kernel.org> # 3.12+

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 16d7b4a..f13a663 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1016,15 +1016,17 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,
 	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
 #endif
 
-	if (frozen)
-		/* Restore the saved policy when doing light-weight init */
-		policy = cpufreq_policy_restore(cpu);
-	else
+	/*
+	 * Restore the saved policy when doing light-weight init and fall back
+	 * to the full init if that fails.
+	 */
+	policy = frozen ? cpufreq_policy_restore(cpu) : NULL;
+	if (!policy) {
+		frozen = false;
 		policy = cpufreq_policy_alloc();
-
-	if (!policy)
-		goto nomem_out;
-
+		if (!policy)
+			goto nomem_out;
+	}
 
 	/*
 	 * In the resume path, since we restore a saved policy, the assignment
@@ -1118,8 +1120,11 @@ err_get_freq:
 	if (cpufreq_driver->exit)
 		cpufreq_driver->exit(policy);
 err_set_policy_cpu:
-	if (frozen)
+	if (frozen) {
+		/* Do not leave stale fallback data behind. */
+		per_cpu(cpufreq_cpu_data_fallback, cpu) = NULL;
 		cpufreq_policy_put_kobj(policy);
+	}
 	cpufreq_policy_free(policy);
 
 nomem_out:
-- 
cgit v0.10.2


From 08fd8c1cf0a99abf34e09a8b99b74872e0d73a23 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 24 Dec 2013 07:11:01 +0530
Subject: cpufreq: preserve user_policy across suspend/resume
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prevent __cpufreq_add_dev() from overwriting the existing values of
user_policy.{min|max|policy|governor} with defaults during resume
from system suspend.

Fixes: 5302c3fb2e62 ("cpufreq: Perform light-weight init/teardown during suspend/resume")
Reported-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: 3.12+ <stable@vger.kernel.org> # 3.12+
[rjw: Changelog]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index f13a663..8d19f7c 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -839,9 +839,6 @@ static void cpufreq_init_policy(struct cpufreq_policy *policy)
 
 	/* set default policy */
 	ret = cpufreq_set_policy(policy, &new_policy);
-	policy->user_policy.policy = policy->policy;
-	policy->user_policy.governor = policy->governor;
-
 	if (ret) {
 		pr_debug("setting policy failed\n");
 		if (cpufreq_driver->exit)
@@ -1071,8 +1068,10 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,
 	 */
 	cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);
 
-	policy->user_policy.min = policy->min;
-	policy->user_policy.max = policy->max;
+	if (!frozen) {
+		policy->user_policy.min = policy->min;
+		policy->user_policy.max = policy->max;
+	}
 
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 				     CPUFREQ_START, policy);
@@ -1103,6 +1102,11 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif,
 
 	cpufreq_init_policy(policy);
 
+	if (!frozen) {
+		policy->user_policy.policy = policy->policy;
+		policy->user_policy.governor = policy->governor;
+	}
+
 	kobject_uevent(&policy->kobj, KOBJ_ADD);
 	up_read(&cpufreq_rwsem);
 
-- 
cgit v0.10.2


From f084280cd34e375cd9736d14b023cfc7df3374bb Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Sun, 29 Dec 2013 23:37:15 +0100
Subject: PCI / ACPI: Install wakeup notify handlers for all PCI devs with ACPI

It turns out that some BIOSes don't report wakeup GPEs through
_PRW, but use them for signaling wakeup anyway, which causes GPE
storms to occur on some systems after resume from system suspend.
This issue has been uncovered by commit d2e5f0c16ad6 (ACPI / PCI:
Rework the setup and cleanup of device wakeup) during the 3.9
development cycle.

Work around the problem by installing wakeup notify handlers for all
PCI devices with ACPI support (i.e. having ACPI companions) regardless
of whether or not the BIOS reports ACPI wakeup support for them.  The
presence of the wakeup notify handlers alone is not harmful in any
way if there are no events for them to handle (they are simply never
executed then), but on some systems they are needed to take care of
spurious events.

Fixes: d2e5f0c16ad6 (ACPI / PCI: Rework the setup and cleanup of device wakeup)
References: https://bugzilla.kernel.org/show_bug.cgi?id=63021
Reported-and-tested-by: Agustin Barto <abarto@gmail.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 577074e..f7ebdba 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -330,29 +330,32 @@ static int acpi_pci_find_device(struct device *dev, acpi_handle *handle)
 static void pci_acpi_setup(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
-	acpi_handle handle = ACPI_HANDLE(dev);
-	struct acpi_device *adev;
+	struct acpi_device *adev = ACPI_COMPANION(dev);
 
-	if (acpi_bus_get_device(handle, &adev) || !adev->wakeup.flags.valid)
+	if (!adev)
+		return;
+
+	pci_acpi_add_pm_notifier(adev, pci_dev);
+	if (!adev->wakeup.flags.valid)
 		return;
 
 	device_set_wakeup_capable(dev, true);
 	acpi_pci_sleep_wake(pci_dev, false);
-
-	pci_acpi_add_pm_notifier(adev, pci_dev);
 	if (adev->wakeup.flags.run_wake)
 		device_set_run_wake(dev, true);
 }
 
 static void pci_acpi_cleanup(struct device *dev)
 {
-	acpi_handle handle = ACPI_HANDLE(dev);
-	struct acpi_device *adev;
+	struct acpi_device *adev = ACPI_COMPANION(dev);
+
+	if (!adev)
+		return;
 
-	if (!acpi_bus_get_device(handle, &adev) && adev->wakeup.flags.valid) {
+	pci_acpi_remove_pm_notifier(adev);
+	if (adev->wakeup.flags.valid) {
 		device_set_wakeup_capable(dev, false);
 		device_set_run_wake(dev, false);
-		pci_acpi_remove_pm_notifier(adev);
 	}
 }
 
-- 
cgit v0.10.2


From 90ff5d688e61f49f23545ffab6228bd7e87e6dc7 Mon Sep 17 00:00:00 2001
From: Michael Neuling <mikey@neuling.org>
Date: Mon, 16 Dec 2013 15:12:43 +1100
Subject: powerpc: Fix bad stack check in exception entry

In EXCEPTION_PROLOG_COMMON() we check to see if the stack pointer (r1)
is valid when coming from the kernel.  If it's not valid, we die but
with a nice oops message.

Currently we allocate a stack frame (subtract INT_FRAME_SIZE) before we
check to see if the stack pointer is negative.  Unfortunately, this
won't detect a bad stack where r1 is less than INT_FRAME_SIZE.

This patch fixes the check to compare the modified r1 with
-INT_FRAME_SIZE.  With this, bad kernel stack pointers (including NULL
pointers) are correctly detected again.

Kudos to Paulus for finding this.

Signed-off-by: Michael Neuling <mikey@neuling.org>
cc: stable@vger.kernel.org
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 894662a..243ce69 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -284,7 +284,7 @@ do_kvm_##n:								\
 	subi	r1,r1,INT_FRAME_SIZE;	/* alloc frame on kernel stack	*/ \
 	beq-	1f;							   \
 	ld	r1,PACAKSAVE(r13);	/* kernel stack to use		*/ \
-1:	cmpdi	cr1,r1,0;		/* check if r1 is in userspace	*/ \
+1:	cmpdi	cr1,r1,-INT_FRAME_SIZE;	/* check if r1 is in userspace	*/ \
 	blt+	cr1,3f;			/* abort if it is		*/ \
 	li	r1,(n);			/* will be reloaded later	*/ \
 	sth	r1,PACA_TRAP_SAVE(r13);					   \
-- 
cgit v0.10.2


From e8a00ad5e238421ded856ea39f692b94c2d324eb Mon Sep 17 00:00:00 2001
From: Rajesh B Prathipati <rprathip@linux.vnet.ibm.com>
Date: Mon, 16 Dec 2013 18:58:22 +1100
Subject: powerpc: Make unaligned accesses endian-safe for powerpc

The generic put_unaligned/get_unaligned macros were made endian-safe by
calling the appropriate endian dependent macros based on the endian type
of the powerpc processor.

Signed-off-by: Rajesh B Prathipati <rprathip@linux.vnet.ibm.com>
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

diff --git a/arch/powerpc/include/asm/unaligned.h b/arch/powerpc/include/asm/unaligned.h
index 5f1b1e3..8296381 100644
--- a/arch/powerpc/include/asm/unaligned.h
+++ b/arch/powerpc/include/asm/unaligned.h
@@ -4,13 +4,18 @@
 #ifdef __KERNEL__
 
 /*
- * The PowerPC can do unaligned accesses itself in big endian mode.
+ * The PowerPC can do unaligned accesses itself based on its endian mode.
  */
 #include <linux/unaligned/access_ok.h>
 #include <linux/unaligned/generic.h>
 
+#ifdef __LITTLE_ENDIAN__
+#define get_unaligned	__get_unaligned_le
+#define put_unaligned	__put_unaligned_le
+#else
 #define get_unaligned	__get_unaligned_be
 #define put_unaligned	__put_unaligned_be
+#endif
 
 #endif	/* __KERNEL__ */
 #endif	/* _ASM_POWERPC_UNALIGNED_H */
-- 
cgit v0.10.2


From 20151169f1de4b170368fdb574024027620d0d49 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 18 Dec 2013 09:29:57 +1100
Subject: powerpc: Make 64-bit non-VMX __copy_tofrom_user bi-endian

The powerpc 64-bit __copy_tofrom_user() function uses shifts to handle
unaligned invocations.  However, these shifts were designed for
big-endian systems: On little-endian systems, they must shift in the
opposite direction.

This commit relies on the C preprocessor to insert the correct shifts
into the assembly code.

[ This is a rare but nasty LE issue. Most of the time we use the POWER7
optimised __copy_tofrom_user_power7 loop, but when it hits an exception
we fall back to the base __copy_tofrom_user loop. - Anton ]

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index d73a590..596a285 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -9,6 +9,14 @@
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
 
+#ifdef __BIG_ENDIAN__
+#define sLd sld		/* Shift towards low-numbered address. */
+#define sHd srd		/* Shift towards high-numbered address. */
+#else
+#define sLd srd		/* Shift towards low-numbered address. */
+#define sHd sld		/* Shift towards high-numbered address. */
+#endif
+
 	.align	7
 _GLOBAL(__copy_tofrom_user)
 BEGIN_FTR_SECTION
@@ -118,10 +126,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 
 24:	ld	r9,0(r4)	/* 3+2n loads, 2+2n stores */
 25:	ld	r0,8(r4)
-	sld	r6,r9,r10
+	sLd	r6,r9,r10
 26:	ldu	r9,16(r4)
-	srd	r7,r0,r11
-	sld	r8,r0,r10
+	sHd	r7,r0,r11
+	sLd	r8,r0,r10
 	or	r7,r7,r6
 	blt	cr6,79f
 27:	ld	r0,8(r4)
@@ -129,35 +137,35 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 
 28:	ld	r0,0(r4)	/* 4+2n loads, 3+2n stores */
 29:	ldu	r9,8(r4)
-	sld	r8,r0,r10
+	sLd	r8,r0,r10
 	addi	r3,r3,-8
 	blt	cr6,5f
 30:	ld	r0,8(r4)
-	srd	r12,r9,r11
-	sld	r6,r9,r10
+	sHd	r12,r9,r11
+	sLd	r6,r9,r10
 31:	ldu	r9,16(r4)
 	or	r12,r8,r12
-	srd	r7,r0,r11
-	sld	r8,r0,r10
+	sHd	r7,r0,r11
+	sLd	r8,r0,r10
 	addi	r3,r3,16
 	beq	cr6,78f
 
 1:	or	r7,r7,r6
 32:	ld	r0,8(r4)
 76:	std	r12,8(r3)
-2:	srd	r12,r9,r11
-	sld	r6,r9,r10
+2:	sHd	r12,r9,r11
+	sLd	r6,r9,r10
 33:	ldu	r9,16(r4)
 	or	r12,r8,r12
 77:	stdu	r7,16(r3)
-	srd	r7,r0,r11
-	sld	r8,r0,r10
+	sHd	r7,r0,r11
+	sLd	r8,r0,r10
 	bdnz	1b
 
 78:	std	r12,8(r3)
 	or	r7,r7,r6
 79:	std	r7,16(r3)
-5:	srd	r12,r9,r11
+5:	sHd	r12,r9,r11
 	or	r12,r8,r12
 80:	std	r12,24(r3)
 	bne	6f
@@ -165,23 +173,38 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 	blr
 6:	cmpwi	cr1,r5,8
 	addi	r3,r3,32
-	sld	r9,r9,r10
+	sLd	r9,r9,r10
 	ble	cr1,7f
 34:	ld	r0,8(r4)
-	srd	r7,r0,r11
+	sHd	r7,r0,r11
 	or	r9,r7,r9
 7:
 	bf	cr7*4+1,1f
+#ifdef __BIG_ENDIAN__
 	rotldi	r9,r9,32
+#endif
 94:	stw	r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+	rotrdi	r9,r9,32
+#endif
 	addi	r3,r3,4
 1:	bf	cr7*4+2,2f
+#ifdef __BIG_ENDIAN__
 	rotldi	r9,r9,16
+#endif
 95:	sth	r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+	rotrdi	r9,r9,16
+#endif
 	addi	r3,r3,2
 2:	bf	cr7*4+3,3f
+#ifdef __BIG_ENDIAN__
 	rotldi	r9,r9,8
+#endif
 96:	stb	r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+	rotrdi	r9,r9,8
+#endif
 3:	li	r3,0
 	blr
 
-- 
cgit v0.10.2


From 20acebdfaec3e15d8a27ab25bf4a2f91b2afa757 Mon Sep 17 00:00:00 2001
From: Brian W Hart <hartb@linux.vnet.ibm.com>
Date: Thu, 19 Dec 2013 17:14:07 -0600
Subject: powernv/eeh: Fix possible buffer overrun in ioda_eeh_phb_diag()

PHB diagnostic buffer may be smaller than PAGE_SIZE, especially when
PAGE_SIZE > 4KB.

Signed-off-by: Brian W Hart <hartb@linux.vnet.ibm.com>
Acked-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index 02245ce..8184ef5 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -820,14 +820,15 @@ static void ioda_eeh_phb_diag(struct pci_controller *hose)
 	struct OpalIoPhbErrorCommon *common;
 	long rc;
 
-	common = (struct OpalIoPhbErrorCommon *)phb->diag.blob;
-	rc = opal_pci_get_phb_diag_data2(phb->opal_id, common, PAGE_SIZE);
+	rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
+					 PNV_PCI_DIAG_BUF_SIZE);
 	if (rc != OPAL_SUCCESS) {
 		pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
 			    __func__, hose->global_number, rc);
 		return;
 	}
 
+	common = (struct OpalIoPhbErrorCommon *)phb->diag.blob;
 	switch (common->ioType) {
 	case OPAL_PHB_ERROR_DATA_TYPE_P7IOC:
 		ioda_eeh_p7ioc_phb_diag(hose, common);
-- 
cgit v0.10.2


From ca1de5deb782e1636ed5b898e215a8840ae39230 Mon Sep 17 00:00:00 2001
From: Brian W Hart <hartb@linux.vnet.ibm.com>
Date: Fri, 20 Dec 2013 13:06:01 -0600
Subject: powernv/eeh: Add buffer for P7IOC hub error data

Prevent ioda_eeh_hub_diag() from clobbering itself when called by supplying
a per-PHB buffer for P7IOC hub diagnostic data.  Take care to inform OPAL of
the correct size for the buffer.

[Small style change to the use of sizeof -- BenH]

Signed-off-by: Brian W Hart <hartb@linux.vnet.ibm.com>
Acked-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index 8184ef5..d7ddcee 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -36,7 +36,6 @@
 #include "powernv.h"
 #include "pci.h"
 
-static char *hub_diag = NULL;
 static int ioda_eeh_nb_init = 0;
 
 static int ioda_eeh_event(struct notifier_block *nb,
@@ -140,15 +139,6 @@ static int ioda_eeh_post_init(struct pci_controller *hose)
 		ioda_eeh_nb_init = 1;
 	}
 
-	/* We needn't HUB diag-data on PHB3 */
-	if (phb->type == PNV_PHB_IODA1 && !hub_diag) {
-		hub_diag = (char *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
-		if (!hub_diag) {
-			pr_err("%s: Out of memory !\n", __func__);
-			return -ENOMEM;
-		}
-	}
-
 #ifdef CONFIG_DEBUG_FS
 	if (phb->dbgfs) {
 		debugfs_create_file("err_injct_outbound", 0600,
@@ -633,11 +623,10 @@ static void ioda_eeh_hub_diag_common(struct OpalIoP7IOCErrorData *data)
 static void ioda_eeh_hub_diag(struct pci_controller *hose)
 {
 	struct pnv_phb *phb = hose->private_data;
-	struct OpalIoP7IOCErrorData *data;
+	struct OpalIoP7IOCErrorData *data = &phb->diag.hub_diag;
 	long rc;
 
-	data = (struct OpalIoP7IOCErrorData *)ioda_eeh_hub_diag;
-	rc = opal_pci_get_hub_diag_data(phb->hub_id, data, PAGE_SIZE);
+	rc = opal_pci_get_hub_diag_data(phb->hub_id, data, sizeof(*data));
 	if (rc != OPAL_SUCCESS) {
 		pr_warning("%s: Failed to get HUB#%llx diag-data (%ld)\n",
 			   __func__, phb->hub_id, rc);
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 911c24e..1ed8d5f 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -172,11 +172,13 @@ struct pnv_phb {
 		} ioda;
 	};
 
-	/* PHB status structure */
+	/* PHB and hub status structure */
 	union {
 		unsigned char			blob[PNV_PCI_DIAG_BUF_SIZE];
 		struct OpalIoP7IOCPhbErrorData	p7ioc;
+		struct OpalIoP7IOCErrorData 	hub_diag;
 	} diag;
+
 };
 
 extern struct pci_ops pnv_pci_ops;
-- 
cgit v0.10.2


From 286e4f90a72c0b0621dde0294af6ed4b0baddabb Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Mon, 23 Dec 2013 12:19:51 +1100
Subject: powerpc: Align p_end

p_end is an 8 byte value embedded in the text section. This means it
is only 4 byte aligned when it should be 8 byte aligned. Fix this
by adding an explicit alignment.

This fixes an issue where POWER7 little endian builds with
CONFIG_RELOCATABLE=y fail to boot.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 2ae41ab..fad2abd 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -470,6 +470,7 @@ _STATIC(__after_prom_start)
 	mtctr	r8
 	bctr
 
+.balign 8
 p_end:	.llong	_end - _stext
 
 4:	/* Now copy the rest of the kernel up to _end */
-- 
cgit v0.10.2


From 7d4151b5098fb0bf7f6f8d1156e1ab9d83260580 Mon Sep 17 00:00:00 2001
From: Olof Johansson <olof@lixom.net>
Date: Sat, 28 Dec 2013 13:01:47 -0800
Subject: powerpc: Fix alignment of secondary cpu spin vars

Commit 5c0484e25ec0 ('powerpc: Endian safe trampoline') resulted in
losing proper alignment of the spinlock variables used when booting
secondary CPUs, causing some quite odd issues with failing to boot on
PA Semi-based systems.

This showed itself on ppc64_defconfig, but not on pasemi_defconfig,
so it had gone unnoticed when I initially tested the LE patch set.

Fix is to add explicit alignment instead of relying on good luck. :)

[ It appears that there is a different issue with PA Semi systems
  however this fix is definitely correct so applying anyway -- BenH
]

Fixes: 5c0484e25ec0 ('powerpc: Endian safe trampoline')
Reported-by: Christian Zigotzky <chzigotzky@xenosoft.de>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=67811
Signed-off-by: Olof Johansson <olof@lixom.net>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index fad2abd..4f0946d 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -80,6 +80,7 @@ END_FTR_SECTION(0, 1)
 	 * of the function that the cpu should jump to to continue
 	 * initialization.
 	 */
+	.balign 8
 	.globl  __secondary_hold_spinloop
 __secondary_hold_spinloop:
 	.llong	0x0
-- 
cgit v0.10.2


From 84602761ca4495dd409be936dfa93ed20c946684 Mon Sep 17 00:00:00 2001
From: Ying Xue <ying.xue@windriver.com>
Date: Fri, 27 Dec 2013 10:18:28 +0800
Subject: tipc: fix deadlock during socket release

A deadlock might occur if name table is withdrawn in socket release
routine, and while packets are still being received from bearer.

       CPU0                       CPU1
T0:   recv_msg()               release()
T1:   tipc_recv_msg()          tipc_withdraw()
T2:   [grab node lock]         [grab port lock]
T3:   tipc_link_wakeup_ports() tipc_nametbl_withdraw()
T4:   [grab port lock]*        named_cluster_distribute()
T5:   wakeupdispatch()         tipc_link_send()
T6:                            [grab node lock]*

The opposite order of holding port lock and node lock on above two
different paths may result in a deadlock. If socket lock instead of
port lock is used to protect port instance in tipc_withdraw(), the
reverse order of holding port lock and node lock will be eliminated,
as a result, the deadlock is killed as well.

Reported-by: Lars Everbrand <lars.everbrand@ericsson.com>
Reviewed-by: Erik Hugne <erik.hugne@ericsson.com>
Signed-off-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/tipc/port.c b/net/tipc/port.c
index c081a76..d43f318 100644
--- a/net/tipc/port.c
+++ b/net/tipc/port.c
@@ -251,18 +251,15 @@ struct tipc_port *tipc_createport(struct sock *sk,
 	return p_ptr;
 }
 
-int tipc_deleteport(u32 ref)
+int tipc_deleteport(struct tipc_port *p_ptr)
 {
-	struct tipc_port *p_ptr;
 	struct sk_buff *buf = NULL;
 
-	tipc_withdraw(ref, 0, NULL);
-	p_ptr = tipc_port_lock(ref);
-	if (!p_ptr)
-		return -EINVAL;
+	tipc_withdraw(p_ptr, 0, NULL);
 
-	tipc_ref_discard(ref);
-	tipc_port_unlock(p_ptr);
+	spin_lock_bh(p_ptr->lock);
+	tipc_ref_discard(p_ptr->ref);
+	spin_unlock_bh(p_ptr->lock);
 
 	k_cancel_timer(&p_ptr->timer);
 	if (p_ptr->connected) {
@@ -704,47 +701,36 @@ int tipc_set_portimportance(u32 ref, unsigned int imp)
 }
 
 
-int tipc_publish(u32 ref, unsigned int scope, struct tipc_name_seq const *seq)
+int tipc_publish(struct tipc_port *p_ptr, unsigned int scope,
+		 struct tipc_name_seq const *seq)
 {
-	struct tipc_port *p_ptr;
 	struct publication *publ;
 	u32 key;
-	int res = -EINVAL;
 
-	p_ptr = tipc_port_lock(ref);
-	if (!p_ptr)
+	if (p_ptr->connected)
 		return -EINVAL;
+	key = p_ptr->ref + p_ptr->pub_count + 1;
+	if (key == p_ptr->ref)
+		return -EADDRINUSE;
 
-	if (p_ptr->connected)
-		goto exit;
-	key = ref + p_ptr->pub_count + 1;
-	if (key == ref) {
-		res = -EADDRINUSE;
-		goto exit;
-	}
 	publ = tipc_nametbl_publish(seq->type, seq->lower, seq->upper,
 				    scope, p_ptr->ref, key);
 	if (publ) {
 		list_add(&publ->pport_list, &p_ptr->publications);
 		p_ptr->pub_count++;
 		p_ptr->published = 1;
-		res = 0;
+		return 0;
 	}
-exit:
-	tipc_port_unlock(p_ptr);
-	return res;
+	return -EINVAL;
 }
 
-int tipc_withdraw(u32 ref, unsigned int scope, struct tipc_name_seq const *seq)
+int tipc_withdraw(struct tipc_port *p_ptr, unsigned int scope,
+		  struct tipc_name_seq const *seq)
 {
-	struct tipc_port *p_ptr;
 	struct publication *publ;
 	struct publication *tpubl;
 	int res = -EINVAL;
 
-	p_ptr = tipc_port_lock(ref);
-	if (!p_ptr)
-		return -EINVAL;
 	if (!seq) {
 		list_for_each_entry_safe(publ, tpubl,
 					 &p_ptr->publications, pport_list) {
@@ -771,7 +757,6 @@ int tipc_withdraw(u32 ref, unsigned int scope, struct tipc_name_seq const *seq)
 	}
 	if (list_empty(&p_ptr->publications))
 		p_ptr->published = 0;
-	tipc_port_unlock(p_ptr);
 	return res;
 }
 
diff --git a/net/tipc/port.h b/net/tipc/port.h
index 9122535..34f12bd 100644
--- a/net/tipc/port.h
+++ b/net/tipc/port.h
@@ -116,7 +116,7 @@ int tipc_reject_msg(struct sk_buff *buf, u32 err);
 
 void tipc_acknowledge(u32 port_ref, u32 ack);
 
-int tipc_deleteport(u32 portref);
+int tipc_deleteport(struct tipc_port *p_ptr);
 
 int tipc_portimportance(u32 portref, unsigned int *importance);
 int tipc_set_portimportance(u32 portref, unsigned int importance);
@@ -127,9 +127,9 @@ int tipc_set_portunreliable(u32 portref, unsigned int isunreliable);
 int tipc_portunreturnable(u32 portref, unsigned int *isunreturnable);
 int tipc_set_portunreturnable(u32 portref, unsigned int isunreturnable);
 
-int tipc_publish(u32 portref, unsigned int scope,
+int tipc_publish(struct tipc_port *p_ptr, unsigned int scope,
 		 struct tipc_name_seq const *name_seq);
-int tipc_withdraw(u32 portref, unsigned int scope,
+int tipc_withdraw(struct tipc_port *p_ptr, unsigned int scope,
 		  struct tipc_name_seq const *name_seq);
 
 int tipc_connect(u32 portref, struct tipc_portid const *port);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 3b61851..e741416 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -354,7 +354,7 @@ static int release(struct socket *sock)
 	 * Delete TIPC port; this ensures no more messages are queued
 	 * (also disconnects an active connection & sends a 'FIN-' to peer)
 	 */
-	res = tipc_deleteport(tport->ref);
+	res = tipc_deleteport(tport);
 
 	/* Discard any remaining (connection-based) messages in receive queue */
 	__skb_queue_purge(&sk->sk_receive_queue);
@@ -386,30 +386,46 @@ static int release(struct socket *sock)
  */
 static int bind(struct socket *sock, struct sockaddr *uaddr, int uaddr_len)
 {
+	struct sock *sk = sock->sk;
 	struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
-	u32 portref = tipc_sk_port(sock->sk)->ref;
+	struct tipc_port *tport = tipc_sk_port(sock->sk);
+	int res = -EINVAL;
 
-	if (unlikely(!uaddr_len))
-		return tipc_withdraw(portref, 0, NULL);
+	lock_sock(sk);
+	if (unlikely(!uaddr_len)) {
+		res = tipc_withdraw(tport, 0, NULL);
+		goto exit;
+	}
 
-	if (uaddr_len < sizeof(struct sockaddr_tipc))
-		return -EINVAL;
-	if (addr->family != AF_TIPC)
-		return -EAFNOSUPPORT;
+	if (uaddr_len < sizeof(struct sockaddr_tipc)) {
+		res = -EINVAL;
+		goto exit;
+	}
+	if (addr->family != AF_TIPC) {
+		res = -EAFNOSUPPORT;
+		goto exit;
+	}
 
 	if (addr->addrtype == TIPC_ADDR_NAME)
 		addr->addr.nameseq.upper = addr->addr.nameseq.lower;
-	else if (addr->addrtype != TIPC_ADDR_NAMESEQ)
-		return -EAFNOSUPPORT;
+	else if (addr->addrtype != TIPC_ADDR_NAMESEQ) {
+		res = -EAFNOSUPPORT;
+		goto exit;
+	}
 
 	if ((addr->addr.nameseq.type < TIPC_RESERVED_TYPES) &&
 	    (addr->addr.nameseq.type != TIPC_TOP_SRV) &&
-	    (addr->addr.nameseq.type != TIPC_CFG_SRV))
-		return -EACCES;
+	    (addr->addr.nameseq.type != TIPC_CFG_SRV)) {
+		res = -EACCES;
+		goto exit;
+	}
 
-	return (addr->scope > 0) ?
-		tipc_publish(portref, addr->scope, &addr->addr.nameseq) :
-		tipc_withdraw(portref, -addr->scope, &addr->addr.nameseq);
+	res = (addr->scope > 0) ?
+		tipc_publish(tport, addr->scope, &addr->addr.nameseq) :
+		tipc_withdraw(tport, -addr->scope, &addr->addr.nameseq);
+exit:
+	release_sock(sk);
+	return res;
 }
 
 /**
-- 
cgit v0.10.2


From 7a399e3a2e05bc580a78ea72371b3896827f72e1 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@freescale.com>
Date: Tue, 24 Dec 2013 12:16:01 -0200
Subject: fec: Do not assume that PHY reset is active low

We should not assume that the PHY reset is always active low.

Retrieve this information from the device tree instead, so that the PHY reset
can work on both cases.

Reported-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Fabio Estevam <fabio.estevam@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 50bb71c..45b8b22 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2049,6 +2049,8 @@ static void fec_reset_phy(struct platform_device *pdev)
 	int err, phy_reset;
 	int msec = 1;
 	struct device_node *np = pdev->dev.of_node;
+	enum of_gpio_flags flags;
+	bool port;
 
 	if (!np)
 		return;
@@ -2058,18 +2060,22 @@ static void fec_reset_phy(struct platform_device *pdev)
 	if (msec > 1000)
 		msec = 1;
 
-	phy_reset = of_get_named_gpio(np, "phy-reset-gpios", 0);
+	phy_reset = of_get_named_gpio_flags(np, "phy-reset-gpios", 0, &flags);
 	if (!gpio_is_valid(phy_reset))
 		return;
 
-	err = devm_gpio_request_one(&pdev->dev, phy_reset,
-				    GPIOF_OUT_INIT_LOW, "phy-reset");
+	if (flags & OF_GPIO_ACTIVE_LOW)
+		port = GPIOF_OUT_INIT_LOW;
+	else
+		port = GPIOF_OUT_INIT_HIGH;
+
+	err = devm_gpio_request_one(&pdev->dev, phy_reset, port, "phy-reset");
 	if (err) {
 		dev_err(&pdev->dev, "failed to get phy-reset-gpios: %d\n", err);
 		return;
 	}
 	msleep(msec);
-	gpio_set_value(phy_reset, 1);
+	gpio_set_value(phy_reset, !port);
 }
 #else /* CONFIG_OF */
 static void fec_reset_phy(struct platform_device *pdev)
-- 
cgit v0.10.2


From ac3d5ac277352fe6e27809286768e9f1f8aa388d Mon Sep 17 00:00:00 2001
From: Paul Durrant <Paul.Durrant@citrix.com>
Date: Mon, 23 Dec 2013 09:27:17 +0000
Subject: xen-netback: fix guest-receive-side array sizes

The sizes chosen for the metadata and grant_copy_op arrays on the guest
receive size are wrong;

- The meta array is needlessly twice the ring size, when we only ever
  consume a single array element per RX ring slot
- The grant_copy_op array is way too small. It's sized based on a bogus
  assumption: that at most two copy ops will be used per ring slot. This
  may have been true at some point in the past but it's clear from looking
  at start_new_rx_buffer() that a new ring slot is only consumed if a frag
  would overflow the current slot (plus some other conditions) so the actual
  limit is MAX_SKB_FRAGS grant_copy_ops per ring slot.

This patch fixes those two sizing issues and, because grant_copy_ops grows
so much, it pulls it out into a separate chunk of vmalloc()ed memory.

Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 08ae01b..c47794b 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -101,6 +101,13 @@ struct xenvif_rx_meta {
 
 #define MAX_PENDING_REQS 256
 
+/* It's possible for an skb to have a maximal number of frags
+ * but still be less than MAX_BUFFER_OFFSET in size. Thus the
+ * worst-case number of copy operations is MAX_SKB_FRAGS per
+ * ring slot.
+ */
+#define MAX_GRANT_COPY_OPS (MAX_SKB_FRAGS * XEN_NETIF_RX_RING_SIZE)
+
 struct xenvif {
 	/* Unique identifier for this interface. */
 	domid_t          domid;
@@ -143,13 +150,13 @@ struct xenvif {
 	 */
 	RING_IDX rx_req_cons_peek;
 
-	/* Given MAX_BUFFER_OFFSET of 4096 the worst case is that each
-	 * head/fragment page uses 2 copy operations because it
-	 * straddles two buffers in the frontend.
-	 */
-	struct gnttab_copy grant_copy_op[2*XEN_NETIF_RX_RING_SIZE];
-	struct xenvif_rx_meta meta[2*XEN_NETIF_RX_RING_SIZE];
+	/* This array is allocated seperately as it is large */
+	struct gnttab_copy *grant_copy_op;
 
+	/* We create one meta structure per ring request we consume, so
+	 * the maximum number is the same as the ring size.
+	 */
+	struct xenvif_rx_meta meta[XEN_NETIF_RX_RING_SIZE];
 
 	u8               fe_dev_addr[6];
 
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 870f1fa..34ca4e5 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -307,6 +307,15 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
 	SET_NETDEV_DEV(dev, parent);
 
 	vif = netdev_priv(dev);
+
+	vif->grant_copy_op = vmalloc(sizeof(struct gnttab_copy) *
+				     MAX_GRANT_COPY_OPS);
+	if (vif->grant_copy_op == NULL) {
+		pr_warn("Could not allocate grant copy space for %s\n", name);
+		free_netdev(dev);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	vif->domid  = domid;
 	vif->handle = handle;
 	vif->can_sg = 1;
@@ -487,6 +496,7 @@ void xenvif_free(struct xenvif *vif)
 
 	unregister_netdev(vif->dev);
 
+	vfree(vif->grant_copy_op);
 	free_netdev(vif->dev);
 
 	module_put(THIS_MODULE);
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 7b4fd93..7842555 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -608,7 +608,7 @@ void xenvif_rx_action(struct xenvif *vif)
 	if (!npo.copy_prod)
 		return;
 
-	BUG_ON(npo.copy_prod > ARRAY_SIZE(vif->grant_copy_op));
+	BUG_ON(npo.copy_prod > MAX_GRANT_COPY_OPS);
 	gnttab_batch_copy(vif->grant_copy_op, npo.copy_prod);
 
 	while ((skb = __skb_dequeue(&rxq)) != NULL) {
-- 
cgit v0.10.2


From f81152e35001e91997ec74a7b4e040e6ab0acccf Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 23 Dec 2013 00:32:31 +0100
Subject: net: rose: restore old recvmsg behavior

recvmsg handler in net/rose/af_rose.c performs size-check ->msg_namelen.

After commit f3d3342602f8bcbf37d7c46641cb9bca7618eb1c
(net: rework recvmsg handler msg_name and msg_namelen logic), we now
always take the else branch due to namelen being initialized to 0.

Digging in netdev-vger-cvs git repo shows that msg_namelen was
initialized with a fixed-size since at least 1995, so the else branch
was never taken.

Compile tested only.

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 33af772..62ced65 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1253,6 +1253,7 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 	if (msg->msg_name) {
 		struct sockaddr_rose *srose;
+		struct full_sockaddr_rose *full_srose = msg->msg_name;
 
 		memset(msg->msg_name, 0, sizeof(struct full_sockaddr_rose));
 		srose = msg->msg_name;
@@ -1260,18 +1261,9 @@ static int rose_recvmsg(struct kiocb *iocb, struct socket *sock,
 		srose->srose_addr   = rose->dest_addr;
 		srose->srose_call   = rose->dest_call;
 		srose->srose_ndigis = rose->dest_ndigis;
-		if (msg->msg_namelen >= sizeof(struct full_sockaddr_rose)) {
-			struct full_sockaddr_rose *full_srose = (struct full_sockaddr_rose *)msg->msg_name;
-			for (n = 0 ; n < rose->dest_ndigis ; n++)
-				full_srose->srose_digis[n] = rose->dest_digis[n];
-			msg->msg_namelen = sizeof(struct full_sockaddr_rose);
-		} else {
-			if (rose->dest_ndigis >= 1) {
-				srose->srose_ndigis = 1;
-				srose->srose_digi = rose->dest_digis[0];
-			}
-			msg->msg_namelen = sizeof(struct sockaddr_rose);
-		}
+		for (n = 0 ; n < rose->dest_ndigis ; n++)
+			full_srose->srose_digis[n] = rose->dest_digis[n];
+		msg->msg_namelen = sizeof(struct full_sockaddr_rose);
 	}
 
 	skb_free_datagram(sk, skb);
-- 
cgit v0.10.2


From 33c133cc7598e60976a069344910d63e56cc4401 Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Fri, 20 Dec 2013 22:09:04 +0300
Subject: phy: IRQ cannot be shared

With the way PHY IRQ handler is implemented (all real handling being pushed to
the workqueue and returning IRQ_HANDLED all the time PHY is active), we cannot
really claim that PHY IRQ can be shared when calling request_irq().

Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 36c6994..98434b8 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -565,10 +565,8 @@ int phy_start_interrupts(struct phy_device *phydev)
 	int err = 0;
 
 	atomic_set(&phydev->irq_disable, 0);
-	if (request_irq(phydev->irq, phy_interrupt,
-				IRQF_SHARED,
-				"phy_interrupt",
-				phydev) < 0) {
+	if (request_irq(phydev->irq, phy_interrupt, 0, "phy_interrupt",
+			phydev) < 0) {
 		pr_warn("%s: Can't get IRQ %d (PHY)\n",
 			phydev->bus->name, phydev->irq);
 		phydev->irq = PHY_POLL;
-- 
cgit v0.10.2


From 7cd013992335b1c5156059248ee765fb3b14d154 Mon Sep 17 00:00:00 2001
From: Vince Bridgers <vbridgers2013@gmail.com>
Date: Fri, 20 Dec 2013 11:19:34 -0600
Subject: stmmac: Fix incorrect spinlock release and PTP cap detection.

This patch corrects a problem in stmmac_ptp.c, functions
stmmac_adjust_time and stmmac_adjust_freq where the incorrect spinlocks
were released. This patch also addresses a problem in stmmac_main,
function stmmac_init_ptp where the capability detection for
advanced timestamping was masked by message masking.

This patch was touch tested using linuxptp, and runs without the previously
observed instabilities. More extensive testing is ongoing.

Vince

Signed-off-by: Vince Bridgers <vbridgers2013@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 8a7a23a..797b56a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -622,17 +622,15 @@ static int stmmac_init_ptp(struct stmmac_priv *priv)
 	if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp))
 		return -EOPNOTSUPP;
 
-	if (netif_msg_hw(priv)) {
-		if (priv->dma_cap.time_stamp) {
-			pr_debug("IEEE 1588-2002 Time Stamp supported\n");
-			priv->adv_ts = 0;
-		}
-		if (priv->dma_cap.atime_stamp && priv->extend_desc) {
-			pr_debug
-			    ("IEEE 1588-2008 Advanced Time Stamp supported\n");
-			priv->adv_ts = 1;
-		}
-	}
+	priv->adv_ts = 0;
+	if (priv->dma_cap.atime_stamp && priv->extend_desc)
+		priv->adv_ts = 1;
+
+	if (netif_msg_hw(priv) && priv->dma_cap.time_stamp)
+		pr_debug("IEEE 1588-2002 Time Stamp supported\n");
+
+	if (netif_msg_hw(priv) && priv->adv_ts)
+		pr_debug("IEEE 1588-2008 Advanced Time Stamp supported\n");
 
 	priv->hw->ptp = &stmmac_ptp;
 	priv->hwts_tx_en = 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index b8b0eee..7680581 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -56,7 +56,7 @@ static int stmmac_adjust_freq(struct ptp_clock_info *ptp, s32 ppb)
 
 	priv->hw->ptp->config_addend(priv->ioaddr, addend);
 
-	spin_unlock_irqrestore(&priv->lock, flags);
+	spin_unlock_irqrestore(&priv->ptp_lock, flags);
 
 	return 0;
 }
@@ -91,7 +91,7 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta)
 
 	priv->hw->ptp->adjust_systime(priv->ioaddr, sec, nsec, neg_adj);
 
-	spin_unlock_irqrestore(&priv->lock, flags);
+	spin_unlock_irqrestore(&priv->ptp_lock, flags);
 
 	return 0;
 }
-- 
cgit v0.10.2


From fcf2f402937a6696f6fa2a1aa882c5075e5fac34 Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@linux.vnet.ibm.com>
Date: Wed, 18 Dec 2013 16:46:02 +0100
Subject: s390/pci: obtain function handle in hotplug notifier

When using the CLP interface to enable or disable a pci device a
valid function handle needs to be delivered. So far our assumption
was that we always have an up-to-date version of the function handle
(since it doesn't change when the device is in use). This assumption
is incorrect if the pci device is enabled or disabled outside of our
control. When we are notified about such a change we already receive
the new function handle. Just use it.

Reviewed-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 800f064..0696072 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -75,6 +75,7 @@ void zpci_event_availability(void *data)
 		if (!zdev || zdev->state == ZPCI_FN_STATE_CONFIGURED)
 			break;
 		zdev->state = ZPCI_FN_STATE_CONFIGURED;
+		zdev->fh = ccdf->fh;
 		ret = zpci_enable_device(zdev);
 		if (ret)
 			break;
@@ -101,6 +102,7 @@ void zpci_event_availability(void *data)
 		if (pdev)
 			pci_stop_and_remove_bus_device(pdev);
 
+		zdev->fh = ccdf->fh;
 		zpci_disable_device(zdev);
 		zdev->state = ZPCI_FN_STATE_STANDBY;
 		break;
-- 
cgit v0.10.2


From c1dcc927dae01dfd4904ee82ce2c00b50eab6dc3 Mon Sep 17 00:00:00 2001
From: Soren Brinkmann <soren.brinkmann@xilinx.com>
Date: Tue, 26 Nov 2013 17:04:50 -0800
Subject: clocksource: cadence_ttc: Fix mutex taken inside interrupt context

When the kernel is compiled with:
CONFIG_HIGH_RES_TIMERS=no
CONFIG_HZ_PERIODIC=yes
CONFIG_DEBUG_ATOMIC_SLEEP=yes

The following WARN appears:

WARNING: CPU: 1 PID: 0 at linux/kernel/mutex.c:856 mutex_trylock+0x70/0x1fc()
DEBUG_LOCKS_WARN_ON(in_interrupt())
Modules linked in:
CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.12.0-xilinx-dirty #93
[<c0014a78>] (unwind_backtrace+0x0/0x11c) from [<c0011b6c>] (show_stack+0x10/0x14)
[<c0011b6c>] (show_stack+0x10/0x14) from [<c039120c>] (dump_stack+0x7c/0xc0)
[<c039120c>] (dump_stack+0x7c/0xc0) from [<c001fda4>] (warn_slowpath_common+0x60/0x84)
[<c001fda4>] (warn_slowpath_common+0x60/0x84) from [<c001fe48>] (warn_slowpath_fmt+0x2c/0x3c)
[<c001fe48>] (warn_slowpath_fmt+0x2c/0x3c) from [<c0392658>] (mutex_trylock+0x70/0x1fc)
[<c0392658>] (mutex_trylock+0x70/0x1fc) from [<c02dfc08>] (clk_prepare_lock+0xc/0xe4)
[<c02dfc08>] (clk_prepare_lock+0xc/0xe4) from [<c02e099c>] (clk_get_rate+0xc/0x44)
[<c02e099c>] (clk_get_rate+0xc/0x44) from [<c02d0394>] (ttc_set_mode+0x34/0x78)
[<c02d0394>] (ttc_set_mode+0x34/0x78) from [<c005f794>] (clockevents_set_mode+0x28/0x5c)
[<c005f794>] (clockevents_set_mode+0x28/0x5c) from [<c00607fc>] (tick_broadcast_on_off+0x190/0x1c0)
[<c00607fc>] (tick_broadcast_on_off+0x190/0x1c0) from [<c005f168>] (clockevents_notify+0x58/0x1ac)
[<c005f168>] (clockevents_notify+0x58/0x1ac) from [<c02b99dc>] (cpuidle_setup_broadcast_timer+0x20/0x24)
[<c02b99dc>] (cpuidle_setup_broadcast_timer+0x20/0x24) from [<c006cd04>] (generic_smp_call_function_single_interrupt+0)
[<c006cd04>] (generic_smp_call_function_single_interrupt+0xe0/0x130) from [<c00138c8>] (handle_IPI+0x88/0x118)
[<c00138c8>] (handle_IPI+0x88/0x118) from [<c0008504>] (gic_handle_irq+0x58/0x60)
[<c0008504>] (gic_handle_irq+0x58/0x60) from [<c0012644>] (__irq_svc+0x44/0x78)
Exception stack(0xef099fa0 to 0xef099fe8)
9fa0: 00000001 ef092100 00000000 ef092100 ef098000 00000015 c0399f2c c0579d74
9fc0: 0000406a 413fc090 00000000 00000000 00000000 ef099fe8 c00666ec c000f46c
9fe0: 20000113 ffffffff
[<c0012644>] (__irq_svc+0x44/0x78) from [<c000f46c>] (arch_cpu_idle+0x34/0x3c)
[<c000f46c>] (arch_cpu_idle+0x34/0x3c) from [<c0053980>] (cpu_startup_entry+0xa8/0x10c)
[<c0053980>] (cpu_startup_entry+0xa8/0x10c) from [<000085a4>] (0x85a4)

We are in an interrupt context (IPI) and we are calling clk_get_rate in the
set_mode function which in turn ends up by getting a mutex... Even if that
does not hang, it is a potential kernel deadlock.

It is not allowed to call clk_get_rate() from interrupt context. To
avoid such calls the timer input frequency is stored in the driver's
data struct which makes it accessible to the driver in any context.

[dlezcano] completed the changelog with the WARN trace and added a more
detailed description. Tested on zync zc702.

Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Tested-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Soren Brinkmann <soren.brinkmann@xilinx.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/drivers/clocksource/cadence_ttc_timer.c b/drivers/clocksource/cadence_ttc_timer.c
index b2bb3a4b..a92350b 100644
--- a/drivers/clocksource/cadence_ttc_timer.c
+++ b/drivers/clocksource/cadence_ttc_timer.c
@@ -67,11 +67,13 @@
  * struct ttc_timer - This definition defines local timer structure
  *
  * @base_addr:	Base address of timer
+ * @freq:	Timer input clock frequency
  * @clk:	Associated clock source
  * @clk_rate_change_nb	Notifier block for clock rate changes
  */
 struct ttc_timer {
 	void __iomem *base_addr;
+	unsigned long freq;
 	struct clk *clk;
 	struct notifier_block clk_rate_change_nb;
 };
@@ -196,9 +198,8 @@ static void ttc_set_mode(enum clock_event_mode mode,
 
 	switch (mode) {
 	case CLOCK_EVT_MODE_PERIODIC:
-		ttc_set_interval(timer,
-				DIV_ROUND_CLOSEST(clk_get_rate(ttce->ttc.clk),
-					PRESCALE * HZ));
+		ttc_set_interval(timer, DIV_ROUND_CLOSEST(ttce->ttc.freq,
+						PRESCALE * HZ));
 		break;
 	case CLOCK_EVT_MODE_ONESHOT:
 	case CLOCK_EVT_MODE_UNUSED:
@@ -273,6 +274,8 @@ static void __init ttc_setup_clocksource(struct clk *clk, void __iomem *base)
 		return;
 	}
 
+	ttccs->ttc.freq = clk_get_rate(ttccs->ttc.clk);
+
 	ttccs->ttc.clk_rate_change_nb.notifier_call =
 		ttc_rate_change_clocksource_cb;
 	ttccs->ttc.clk_rate_change_nb.next = NULL;
@@ -298,16 +301,14 @@ static void __init ttc_setup_clocksource(struct clk *clk, void __iomem *base)
 	__raw_writel(CNT_CNTRL_RESET,
 		     ttccs->ttc.base_addr + TTC_CNT_CNTRL_OFFSET);
 
-	err = clocksource_register_hz(&ttccs->cs,
-			clk_get_rate(ttccs->ttc.clk) / PRESCALE);
+	err = clocksource_register_hz(&ttccs->cs, ttccs->ttc.freq / PRESCALE);
 	if (WARN_ON(err)) {
 		kfree(ttccs);
 		return;
 	}
 
 	ttc_sched_clock_val_reg = base + TTC_COUNT_VAL_OFFSET;
-	setup_sched_clock(ttc_sched_clock_read, 16,
-			clk_get_rate(ttccs->ttc.clk) / PRESCALE);
+	setup_sched_clock(ttc_sched_clock_read, 16, ttccs->ttc.freq / PRESCALE);
 }
 
 static int ttc_rate_change_clockevent_cb(struct notifier_block *nb,
@@ -334,6 +335,9 @@ static int ttc_rate_change_clockevent_cb(struct notifier_block *nb,
 				ndata->new_rate / PRESCALE);
 		local_irq_restore(flags);
 
+		/* update cached frequency */
+		ttc->freq = ndata->new_rate;
+
 		/* fall through */
 	}
 	case PRE_RATE_CHANGE:
@@ -367,6 +371,7 @@ static void __init ttc_setup_clockevent(struct clk *clk,
 	if (clk_notifier_register(ttcce->ttc.clk,
 				&ttcce->ttc.clk_rate_change_nb))
 		pr_warn("Unable to register clock notifier.\n");
+	ttcce->ttc.freq = clk_get_rate(ttcce->ttc.clk);
 
 	ttcce->ttc.base_addr = base;
 	ttcce->ce.name = "ttc_clockevent";
@@ -396,7 +401,7 @@ static void __init ttc_setup_clockevent(struct clk *clk,
 	}
 
 	clockevents_config_and_register(&ttcce->ce,
-			clk_get_rate(ttcce->ttc.clk) / PRESCALE, 1, 0xfffe);
+			ttcce->ttc.freq / PRESCALE, 1, 0xfffe);
 }
 
 /**
-- 
cgit v0.10.2


From 5781532ebecd9e0b7b5fc25d78030bdec635f4ac Mon Sep 17 00:00:00 2001
From: Andre Przywara <andre.przywara@linaro.org>
Date: Fri, 13 Dec 2013 21:49:19 +0100
Subject: ARM/cpuidle: remove __init tag from Calxeda cpuidle probe function

Commit 60a66e370007e8535b7a561353b07b37deaf35ba changed the Calxeda
cpuidle driver to a platform driver, copying the __init tag from the
_init() to the newly used _probe() function. However, "probe should
not be __init." (Rob said ;-)
Remove the __init tag to fix a section mismatch in the Calxeda
cpuidle driver.

Signed-off-by: Andre Przywara <andre.przywara@linaro.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>

diff --git a/drivers/cpuidle/cpuidle-calxeda.c b/drivers/cpuidle/cpuidle-calxeda.c
index 3679563..6e51114 100644
--- a/drivers/cpuidle/cpuidle-calxeda.c
+++ b/drivers/cpuidle/cpuidle-calxeda.c
@@ -65,7 +65,7 @@ static struct cpuidle_driver calxeda_idle_driver = {
 	.state_count = 2,
 };
 
-static int __init calxeda_cpuidle_probe(struct platform_device *pdev)
+static int calxeda_cpuidle_probe(struct platform_device *pdev)
 {
 	return cpuidle_register(&calxeda_idle_driver, NULL);
 }
-- 
cgit v0.10.2


From 13fcca8f25f4e9ce7f55da9cd353bb743236e212 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Sun, 29 Dec 2013 19:37:43 -0600
Subject: Revert "of/address: Handle #address-cells > 2 specially"

This reverts commit e38c0a1fbc5803cbacdaac0557c70ac8ca5152e7.

Nikita Yushchenko reports:
While trying to make freescale p2020ds and  mpc8572ds boards working
with mainline kernel, I faced that commit e38c0a1f (Handle

Both these boards have uli1575 chip.
Corresponding part in device tree is something like

                uli1575@0 {
                        reg = <0x0 0x0 0x0 0x0 0x0>;
                        #size-cells = <2>;
                        #address-cells = <3>;
                        ranges = <0x2000000 0x0 0x80000000
                                  0x2000000 0x0 0x80000000
                                  0x0 0x20000000

                                  0x1000000 0x0 0x0
                                  0x1000000 0x0 0x0
                                  0x0 0x10000>;
                        isa@1e {
...

I.e. it has #address-cells = <3>

With commit e38c0a1f reverted, devices under uli1575 are registered
correctly, e.g. for rtc

OF: ** translation for device /pcie@ffe09000/pcie@0/uli1575@0/isa@1e/rtc@70 **
OF: bus is isa (na=2, ns=1) on /pcie@ffe09000/pcie@0/uli1575@0/isa@1e
OF: translating address: 00000001 00000070
OF: parent bus is default (na=3, ns=2) on /pcie@ffe09000/pcie@0/uli1575@0
OF: walking ranges...
OF: ISA map, cp=0, s=1000, da=70
OF: parent translation for: 01000000 00000000 00000000
OF: with offset: 70
OF: one level translation: 00000000 00000000 00000070
OF: parent bus is pci (na=3, ns=2) on /pcie@ffe09000/pcie@0
OF: walking ranges...
OF: default map, cp=a0000000, s=20000000, da=70
OF: default map, cp=0, s=10000, da=70
OF: parent translation for: 01000000 00000000 00000000
OF: with offset: 70
OF: one level translation: 01000000 00000000 00000070
OF: parent bus is pci (na=3, ns=2) on /pcie@ffe09000
OF: walking ranges...
OF: PCI map, cp=0, s=10000, da=70
OF: parent translation for: 01000000 00000000 00000000
OF: with offset: 70
OF: one level translation: 01000000 00000000 00000070
OF: parent bus is default (na=2, ns=2) on /
OF: walking ranges...
OF: PCI map, cp=0, s=10000, da=70
OF: parent translation for: 00000000 ffc10000
OF: with offset: 70
OF: one level translation: 00000000 ffc10070
OF: reached root node

With commit e38c0a1f in place, address translation fails:

OF: ** translation for device /pcie@ffe09000/pcie@0/uli1575@0/isa@1e/rtc@70 **
OF: bus is isa (na=2, ns=1) on /pcie@ffe09000/pcie@0/uli1575@0/isa@1e
OF: translating address: 00000001 00000070
OF: parent bus is default (na=3, ns=2) on /pcie@ffe09000/pcie@0/uli1575@0
OF: walking ranges...
OF: ISA map, cp=0, s=1000, da=70
OF: parent translation for: 01000000 00000000 00000000
OF: with offset: 70
OF: one level translation: 00000000 00000000 00000070
OF: parent bus is pci (na=3, ns=2) on /pcie@ffe09000/pcie@0
OF: walking ranges...
OF: default map, cp=a0000000, s=20000000, da=70
OF: default map, cp=0, s=10000, da=70
OF: not found !

Thierry Reding confirmed this commit was not needed after all:
"We ended up merging a different address representation for Tegra PCIe
and I've confirmed that reverting this commit doesn't cause any obvious
regressions. I think all other drivers in drivers/pci/host ended up
copying what we did on Tegra, so I wouldn't expect any other breakage
either."

There doesn't appear to be a simple way to support both behaviours, so
reverting this as nothing should be depending on the new behaviour.

Cc: stable@vger.kernel.org # v3.7+
Signed-off-by: Rob Herring <robh@kernel.org>

diff --git a/drivers/of/address.c b/drivers/of/address.c
index 4b9317b..d3dd41c 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -69,14 +69,6 @@ static u64 of_bus_default_map(__be32 *addr, const __be32 *range,
 		 (unsigned long long)cp, (unsigned long long)s,
 		 (unsigned long long)da);
 
-	/*
-	 * If the number of address cells is larger than 2 we assume the
-	 * mapping doesn't specify a physical address. Rather, the address
-	 * specifies an identifier that must match exactly.
-	 */
-	if (na > 2 && memcmp(range, addr, na * 4) != 0)
-		return OF_BAD_ADDR;
-
 	if (da < cp || da >= (cp + s))
 		return OF_BAD_ADDR;
 	return da - cp;
-- 
cgit v0.10.2


From 5d9270869b6cd3cb098ad9393c0cb62ab184e35e Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@linux-m68k.org>
Date: Tue, 24 Dec 2013 21:06:01 +0100
Subject: of/Kconfig: Spelling s/one/once/

Signed-off-by: Geert Uytterhoeven <geert+renesas@linux-m68k.org>
Signed-off-by: Rob Herring <robh@kernel.org>

diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index de6f899..c6973f1 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -20,7 +20,7 @@ config OF_SELFTEST
 	depends on OF_IRQ
 	help
 	  This option builds in test cases for the device tree infrastructure
-	  that are executed one at boot time, and the results dumped to the
+	  that are executed once at boot time, and the results dumped to the
 	  console.
 
 	  If unsure, say N here, but this option is safe to enable.
-- 
cgit v0.10.2


From 2f53a713c4b6c1d2f32d87c532d47ad17861053a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= <clg@fr.ibm.com>
Date: Tue, 17 Dec 2013 18:32:53 +0100
Subject: of/irq: Fix device_node refcount in of_irq_parse_raw()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 2361613206e6, "of/irq: Refactor interrupt-map parsing" changed
the refcount on the device_node causing an error in of_node_put():

ERROR: Bad of_node_put() on /pci@800000020000000
CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.13.0-rc3-dirty #2
Call Trace:
[c00000003e403500] [c0000000000144fc] .show_stack+0x7c/0x1f0 (unreliable)
[c00000003e4035d0] [c00000000070f250] .dump_stack+0x88/0xb4
[c00000003e403650] [c0000000005e8768] .of_node_release+0xd8/0xf0
[c00000003e4036e0] [c0000000005eeafc] .of_irq_parse_one+0x10c/0x280
[c00000003e4037a0] [c0000000005efd4c] .of_irq_parse_pci+0x3c/0x1d0
[c00000003e403840] [c000000000038240] .pcibios_setup_device+0xa0/0x2e0
[c00000003e403910] [c0000000000398f0] .pcibios_setup_bus_devices+0x60/0xd0
[c00000003e403990] [c00000000003b3a4] .__of_scan_bus+0x1a4/0x2b0
[c00000003e403a80] [c00000000003a62c] .pcibios_scan_phb+0x30c/0x410
[c00000003e403b60] [c0000000009fe430] .pcibios_init+0x7c/0xd4

This patch adjusts the refcount in the walk of the interrupt tree.
When a match is found, there is no need to increase the refcount
on 'out_irq->np' as 'newpar' is already holding a ref. The refcount
balance between 'ipar' and 'newpar' is maintained in the skiplevel:
goto label.

This patch also removes the usage of the device_node variable 'old'
which seems useless after the latest changes.

Signed-off-by: Cédric Le Goater <clg@fr.ibm.com>
Signed-off-by: Rob Herring <robh@kernel.org>

diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 786b0b4..2721240 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -165,7 +165,6 @@ int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq)
 		if (of_get_property(ipar, "interrupt-controller", NULL) !=
 				NULL) {
 			pr_debug(" -> got it !\n");
-			of_node_put(old);
 			return 0;
 		}
 
@@ -250,8 +249,7 @@ int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq)
 		 * Successfully parsed an interrrupt-map translation; copy new
 		 * interrupt specifier into the out_irq structure
 		 */
-		of_node_put(out_irq->np);
-		out_irq->np = of_node_get(newpar);
+		out_irq->np = newpar;
 
 		match_array = imap - newaddrsize - newintsize;
 		for (i = 0; i < newintsize; i++)
@@ -268,7 +266,6 @@ int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq)
 	}
  fail:
 	of_node_put(ipar);
-	of_node_put(out_irq->np);
 	of_node_put(newpar);
 
 	return -EINVAL;
-- 
cgit v0.10.2


From 5fdd1b56be51b1ec4dbde5b213d649ac717442da Mon Sep 17 00:00:00 2001
From: Seung-Woo Kim <sw0312.kim@samsung.com>
Date: Fri, 22 Nov 2013 14:21:08 +0900
Subject: clk: samsung: exynos4: Correct SRC_MFC register

The SRC_MFC register offset was incorrect, which could cause have caused
wrong calculation of rate of sclk_mfc clock, that could in turn lead to
incorrect operation of MFC. This patch corrects it.

Signed-off-by: Seung-Woo Kim <sw0312.kim@samsung.com>
Acked-by: Mike Turquette <mturquette@linaro.org>
[t.figa: Updated patch description]
Signed-off-by: Tomasz Figa <t.figa@samsung.com>

diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
index ad5ff50..1a7c1b9 100644
--- a/drivers/clk/samsung/clk-exynos4.c
+++ b/drivers/clk/samsung/clk-exynos4.c
@@ -39,7 +39,7 @@
 #define SRC_TOP1		0xc214
 #define SRC_CAM			0xc220
 #define SRC_TV			0xc224
-#define SRC_MFC			0xcc28
+#define SRC_MFC			0xc228
 #define SRC_G3D			0xc22c
 #define E4210_SRC_IMAGE		0xc230
 #define SRC_LCD0		0xc234
-- 
cgit v0.10.2


From 97c3557c3e0413efb1f021f582d1459760e22727 Mon Sep 17 00:00:00 2001
From: Andrew Bresticker <abrestic@chromium.org>
Date: Fri, 8 Nov 2013 15:44:07 +0530
Subject: clk: exynos5250: fix sysmmu_mfc{l,r} gate clocks

The gate clocks for the MFC sysmmus appear to be flipped, i.e.
GATE_IP_MFC[2] gates sysmmu_mfcl and GATE_IP_MFC[1] gates sysmmu_mfcr.
Fix this so that the MFC will start up.

Signed-off-by: Andrew Bresticker <abrestic@chromium.org>
Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Acked-by: Mike Turquette <mturquette@linaro.org>
Signed-off-by: Tomasz Figa <t.figa@samsung.com>

diff --git a/drivers/clk/samsung/clk-exynos5250.c b/drivers/clk/samsung/clk-exynos5250.c
index adf3234..f862ad8 100644
--- a/drivers/clk/samsung/clk-exynos5250.c
+++ b/drivers/clk/samsung/clk-exynos5250.c
@@ -354,8 +354,8 @@ static struct samsung_gate_clock exynos5250_gate_clks[] __initdata = {
 	GATE(smmu_gscl2, "smmu_gscl2", "aclk266", GATE_IP_GSCL, 9, 0, 0),
 	GATE(smmu_gscl3, "smmu_gscl3", "aclk266", GATE_IP_GSCL, 10, 0, 0),
 	GATE(mfc, "mfc", "aclk333", GATE_IP_MFC, 0, 0, 0),
-	GATE(smmu_mfcl, "smmu_mfcl", "aclk333", GATE_IP_MFC, 1, 0, 0),
-	GATE(smmu_mfcr, "smmu_mfcr", "aclk333", GATE_IP_MFC, 2, 0, 0),
+	GATE(smmu_mfcl, "smmu_mfcl", "aclk333", GATE_IP_MFC, 2, 0, 0),
+	GATE(smmu_mfcr, "smmu_mfcr", "aclk333", GATE_IP_MFC, 1, 0, 0),
 	GATE(rotator, "rotator", "aclk266", GATE_IP_GEN, 1, 0, 0),
 	GATE(jpeg, "jpeg", "aclk166", GATE_IP_GEN, 2, 0, 0),
 	GATE(mdma1, "mdma1", "aclk266", GATE_IP_GEN, 4, 0, 0),
-- 
cgit v0.10.2


From 3bf34666a0cce5234ac677ed2fbe5cea82c71329 Mon Sep 17 00:00:00 2001
From: Abhilash Kesavan <a.kesavan@samsung.com>
Date: Thu, 12 Dec 2013 08:32:00 +0530
Subject: clk: samsung: exynos5250: Fix ACP gate register offset

The CLK_GATE_IP_ACP register offset is incorrectly listed making
definition of g2d clock incorrect, which may lead to system failures
when trying to use G2D on systems on which firmware gates this clock
by default. Fix this and the register ordering as well.

Signed-off-by: Abhilash Kesavan <a.kesavan@samsung.com>
Acked-by: Mike Turquette <mturquette@linaro.org>
[t.figa: Updated patch description.]
Signed-off-by: Tomasz Figa <t.figa@samsung.com>

diff --git a/drivers/clk/samsung/clk-exynos5250.c b/drivers/clk/samsung/clk-exynos5250.c
index f862ad8..3859023 100644
--- a/drivers/clk/samsung/clk-exynos5250.c
+++ b/drivers/clk/samsung/clk-exynos5250.c
@@ -25,6 +25,7 @@
 #define MPLL_LOCK		0x4000
 #define MPLL_CON0		0x4100
 #define SRC_CORE1		0x4204
+#define GATE_IP_ACP		0x8800
 #define CPLL_LOCK		0x10020
 #define EPLL_LOCK		0x10030
 #define VPLL_LOCK		0x10040
@@ -75,7 +76,6 @@
 #define SRC_CDREX		0x20200
 #define PLL_DIV2_SEL		0x20a24
 #define GATE_IP_DISP1		0x10928
-#define GATE_IP_ACP		0x10000
 
 /* list of PLLs to be registered */
 enum exynos5250_plls {
-- 
cgit v0.10.2


From 8fb9aeb7a71ef4f3e0613d459a2e1366a7a90469 Mon Sep 17 00:00:00 2001
From: Abhilash Kesavan <a.kesavan@samsung.com>
Date: Thu, 12 Dec 2013 08:32:01 +0530
Subject: clk: samsung: exynos5250: Add MDMA0 clocks

Adds gate clock for MDMA0 on Exynos5250 SoC. This is needed to ensure
that the clock is enabled when MDMA0 is used on systems on which
firmware gates the clockby default.

Signed-off-by: Abhilash Kesavan <a.kesavan@samsung.com>
Acked-by: Mike Turquette <mturquette@linaro.org>
[t.figa: Updated patch description.]
Signed-off-by: Tomasz Figa <t.figa@samsung.com>

diff --git a/Documentation/devicetree/bindings/clock/exynos5250-clock.txt b/Documentation/devicetree/bindings/clock/exynos5250-clock.txt
index 24765c1..5883ec8 100644
--- a/Documentation/devicetree/bindings/clock/exynos5250-clock.txt
+++ b/Documentation/devicetree/bindings/clock/exynos5250-clock.txt
@@ -159,6 +159,8 @@ clock which they consume.
   mixer			343
   hdmi			344
   g2d			345
+  mdma0			346
+  smmu_mdma0		347
 
 
    [Clock Muxes]
diff --git a/drivers/clk/samsung/clk-exynos5250.c b/drivers/clk/samsung/clk-exynos5250.c
index 3859023..03cbc0f 100644
--- a/drivers/clk/samsung/clk-exynos5250.c
+++ b/drivers/clk/samsung/clk-exynos5250.c
@@ -120,7 +120,8 @@ enum exynos5250_clks {
 	spi2, i2s1, i2s2, pcm1, pcm2, pwm, spdif, ac97, hsi2c0, hsi2c1, hsi2c2,
 	hsi2c3, chipid, sysreg, pmu, cmu_top, cmu_core, cmu_mem, tzpc0, tzpc1,
 	tzpc2, tzpc3, tzpc4, tzpc5, tzpc6, tzpc7, tzpc8, tzpc9, hdmi_cec, mct,
-	wdt, rtc, tmu, fimd1, mie1, dsim0, dp, mixer, hdmi, g2d,
+	wdt, rtc, tmu, fimd1, mie1, dsim0, dp, mixer, hdmi, g2d, mdma0,
+	smmu_mdma0,
 
 	/* mux clocks */
 	mout_hdmi = 1024,
@@ -492,6 +493,8 @@ static struct samsung_gate_clock exynos5250_gate_clks[] __initdata = {
 	GATE(mixer, "mixer", "mout_aclk200_disp1", GATE_IP_DISP1, 5, 0, 0),
 	GATE(hdmi, "hdmi", "mout_aclk200_disp1", GATE_IP_DISP1, 6, 0, 0),
 	GATE(g2d, "g2d", "aclk200", GATE_IP_ACP, 3, 0, 0),
+	GATE(mdma0, "mdma0", "aclk266", GATE_IP_ACP, 1, 0, 0),
+	GATE(smmu_mdma0, "smmu_mdma0", "aclk266", GATE_IP_ACP, 5, 0, 0),
 };
 
 static struct samsung_pll_rate_table vpll_24mhz_tbl[] __initdata = {
-- 
cgit v0.10.2


From 8777539479abd7b3efeb691685415dc2b057d0e0 Mon Sep 17 00:00:00 2001
From: Abhilash Kesavan <a.kesavan@samsung.com>
Date: Thu, 12 Dec 2013 08:32:02 +0530
Subject: ARM: dts: exynos5250: Fix MDMA0 clock number

Due to incorrect clock specified in MDMA0 node, using MDMA0 controller
could cause system failures, due to wrong clock being controlled. This
patch fixes this by specifying correct clock.

Signed-off-by: Abhilash Kesavan <a.kesavan@samsung.com>
Acked-by: Mike Turquette <mturquette@linaro.org>
[t.figa: Corrected commit message and description.]
Signed-off-by: Tomasz Figa <t.figa@samsung.com>

diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi
index 9db5047..177becd 100644
--- a/arch/arm/boot/dts/exynos5250.dtsi
+++ b/arch/arm/boot/dts/exynos5250.dtsi
@@ -559,7 +559,7 @@
 			compatible = "arm,pl330", "arm,primecell";
 			reg = <0x10800000 0x1000>;
 			interrupts = <0 33 0>;
-			clocks = <&clock 271>;
+			clocks = <&clock 346>;
 			clock-names = "apb_pclk";
 			#dma-cells = <1>;
 			#dma-channels = <8>;
-- 
cgit v0.10.2


From 5d3ad8a63844f496f5c3a1f8bc3d25dc374c8360 Mon Sep 17 00:00:00 2001
From: Rob Herring <rob.herring@calxeda.com>
Date: Tue, 3 Dec 2013 10:20:16 -0600
Subject: MAINTAINERS: Update Rob Herring's email address

My Calxeda email address is going away.

Signed-off-by: Rob Herring <rob.herring@calxeda.com>
Signed-off-by: Rob Herring <robh@kernel.org>

diff --git a/MAINTAINERS b/MAINTAINERS
index d5e4ff3..21c038f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -783,7 +783,7 @@ F:	arch/arm/boot/dts/sama*.dts
 F:	arch/arm/boot/dts/sama*.dtsi
 
 ARM/CALXEDA HIGHBANK ARCHITECTURE
-M:	Rob Herring <rob.herring@calxeda.com>
+M:	Rob Herring <robh@kernel.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/mach-highbank/
@@ -6256,7 +6256,7 @@ F:	drivers/i2c/busses/i2c-ocores.c
 
 OPEN FIRMWARE AND FLATTENED DEVICE TREE
 M:	Grant Likely <grant.likely@linaro.org>
-M:	Rob Herring <rob.herring@calxeda.com>
+M:	Rob Herring <robh+dt@kernel.org>
 L:	devicetree@vger.kernel.org
 W:	http://fdt.secretlab.ca
 T:	git git://git.secretlab.ca/git/linux-2.6.git
@@ -6268,7 +6268,7 @@ K:	of_get_property
 K:	of_match_table
 
 OPEN FIRMWARE AND FLATTENED DEVICE TREE BINDINGS
-M:	Rob Herring <rob.herring@calxeda.com>
+M:	Rob Herring <robh+dt@kernel.org>
 M:	Pawel Moll <pawel.moll@arm.com>
 M:	Mark Rutland <mark.rutland@arm.com>
 M:	Ian Campbell <ijc+devicetree@hellion.org.uk>
-- 
cgit v0.10.2


From 2feed5aecf5f367b92bd6b6e92afe9e3de466907 Mon Sep 17 00:00:00 2001
From: Abhilash Kesavan <a.kesavan@samsung.com>
Date: Wed, 11 Dec 2013 17:27:05 +0530
Subject: clk: samsung: exynos5250: Add CLK_IGNORE_UNUSED flag for the sysreg
 clock

The sysreg (system register) generates control signals for various blocks
like disp1blk, i2c, mipi, usb etc. However, it gets disabled as an unused
clock at boot-up. This can lead to failures in operation of above blocks,
because they can not be configured properly if this clock is disabled.

Signed-off-by: Abhilash Kesavan <a.kesavan@samsung.com>
Acked-by: Mike Turquette <mturquette@linaro.org>
[t.figa: Updated patch description.]
Signed-off-by: Tomasz Figa <t.figa@samsung.com>

diff --git a/drivers/clk/samsung/clk-exynos5250.c b/drivers/clk/samsung/clk-exynos5250.c
index 03cbc0f..e52359c 100644
--- a/drivers/clk/samsung/clk-exynos5250.c
+++ b/drivers/clk/samsung/clk-exynos5250.c
@@ -407,7 +407,8 @@ static struct samsung_gate_clock exynos5250_gate_clks[] __initdata = {
 	GATE(hsi2c2, "hsi2c2", "aclk66", GATE_IP_PERIC, 30, 0, 0),
 	GATE(hsi2c3, "hsi2c3", "aclk66", GATE_IP_PERIC, 31, 0, 0),
 	GATE(chipid, "chipid", "aclk66", GATE_IP_PERIS, 0, 0, 0),
-	GATE(sysreg, "sysreg", "aclk66", GATE_IP_PERIS, 1, 0, 0),
+	GATE(sysreg, "sysreg", "aclk66",
+			GATE_IP_PERIS, 1, CLK_IGNORE_UNUSED, 0),
 	GATE(pmu, "pmu", "aclk66", GATE_IP_PERIS, 2, CLK_IGNORE_UNUSED, 0),
 	GATE(tzpc0, "tzpc0", "aclk66", GATE_IP_PERIS, 6, 0, 0),
 	GATE(tzpc1, "tzpc1", "aclk66", GATE_IP_PERIS, 7, 0, 0),
-- 
cgit v0.10.2


From 3fd68c99f3026f4fe3a1b7b6fb75e5638b2032fd Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Date: Tue, 17 Dec 2013 10:56:39 +0100
Subject: clk: exynos: File scope reg_save array should depend on PM_SLEEP
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move reg_save[] into CONFIG_PM_SLEEP dependency block as it is used only
by suspend and resume functions.

This fixes the warning on CONFIG_PM_SLEEP=n:
drivers/clk/samsung/clk-exynos-audss.c:29:22: warning: ‘reg_save’ defined but not used [-Wunused-variable]

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Acked-by: Mike Turquette <mturquette@linaro.org>
Signed-off-by: Tomasz Figa <t.figa@samsung.com>

diff --git a/drivers/clk/samsung/clk-exynos-audss.c b/drivers/clk/samsung/clk-exynos-audss.c
index 39b40aa..68e515d 100644
--- a/drivers/clk/samsung/clk-exynos-audss.c
+++ b/drivers/clk/samsung/clk-exynos-audss.c
@@ -26,17 +26,17 @@ static struct clk_onecell_data clk_data;
 #define ASS_CLK_DIV 0x4
 #define ASS_CLK_GATE 0x8
 
+/* list of all parent clock list */
+static const char *mout_audss_p[] = { "fin_pll", "fout_epll" };
+static const char *mout_i2s_p[] = { "mout_audss", "cdclk0", "sclk_audio0" };
+
+#ifdef CONFIG_PM_SLEEP
 static unsigned long reg_save[][2] = {
 	{ASS_CLK_SRC,  0},
 	{ASS_CLK_DIV,  0},
 	{ASS_CLK_GATE, 0},
 };
 
-/* list of all parent clock list */
-static const char *mout_audss_p[] = { "fin_pll", "fout_epll" };
-static const char *mout_i2s_p[] = { "mout_audss", "cdclk0", "sclk_audio0" };
-
-#ifdef CONFIG_PM_SLEEP
 static int exynos_audss_clk_suspend(void)
 {
 	int i;
-- 
cgit v0.10.2


From 9da4a8d9197e42d532f2e2af072d8219105139b2 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Mon, 9 Dec 2013 11:38:08 +0100
Subject: m68k/defconfig: Disable /sbin/hotplug fork-bomb by default

Cfr. commit 7934779a69f1184f29d786b89e77dd14519bd226 ("Driver-Core: disable
/sbin/hotplug by default").

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 1f87c07..1b95317 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -198,7 +198,6 @@ CONFIG_ATALK=m
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
 # CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_FW_LOADER_USER_HELPER is not set
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index ea5b647..bc3b9ae 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -196,7 +196,6 @@ CONFIG_ATALK=m
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
 # CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_FW_LOADER_USER_HELPER is not set
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 0c3d280..264c844 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -195,7 +195,6 @@ CONFIG_ATALK=m
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
 # CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_FW_LOADER_USER_HELPER is not set
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 9b6b515..2462c93 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -194,7 +194,6 @@ CONFIG_ATALK=m
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
 # CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_FW_LOADER_USER_HELPER is not set
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index efffa68..9e6d582 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -196,7 +196,6 @@ CONFIG_ATALK=m
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
 # CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_FW_LOADER_USER_HELPER is not set
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 73a8565..7f6be05 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -199,7 +199,6 @@ CONFIG_IPDDP_DECAP=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
 # CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_FW_LOADER_USER_HELPER is not set
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 19c7939..265abf4 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -208,7 +208,6 @@ CONFIG_IPDDP_DECAP=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
 # CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_FW_LOADER_USER_HELPER is not set
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 81fab00..6df0acd 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -193,7 +193,6 @@ CONFIG_ATALK=m
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
 # CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_FW_LOADER_USER_HELPER is not set
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index df07837..4108303 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -194,7 +194,6 @@ CONFIG_ATALK=m
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
 # CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_FW_LOADER_USER_HELPER is not set
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index f64c896..f7bdca0 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -194,7 +194,6 @@ CONFIG_ATALK=m
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
 # CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_FW_LOADER_USER_HELPER is not set
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 99bcc60..e578dd8 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -191,7 +191,6 @@ CONFIG_ATALK=m
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
 # CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_FW_LOADER_USER_HELPER is not set
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 2023a91..f5c91e1 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -191,7 +191,6 @@ CONFIG_ATALK=m
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
 # CONFIG_WIRELESS is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 # CONFIG_FW_LOADER_USER_HELPER is not set
-- 
cgit v0.10.2


From 4e25c0e92f8eaf69bc51d1d523bcb7268e7dd162 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Tue, 10 Dec 2013 11:35:47 +0100
Subject: m68k/mm: Check for mm != NULL in do_page_fault() debug code

When DEBUG is enabled, do_page_fault() may dereference a NULL pointer,
causing recursive bus errors.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index eb1d61f..c7725f1 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -77,8 +77,7 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 
 #ifdef DEBUG
 	printk ("do page fault:\nregs->sr=%#x, regs->pc=%#lx, address=%#lx, %ld, %p\n",
-		regs->sr, regs->pc, address, error_code,
-		current->mm->pgd);
+		regs->sr, regs->pc, address, error_code, mm ? mm->pgd : NULL);
 #endif
 
 	/*
-- 
cgit v0.10.2


From 8e398f638179d5968df41ad8eff8f27684454dc4 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Tue, 10 Dec 2013 12:04:16 +0100
Subject: m68k: Convert arch/m68k/mm/fault.c to pr_*()

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index c7725f1..2bd7487 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -25,9 +25,8 @@ int send_fault_sig(struct pt_regs *regs)
 	siginfo.si_signo = current->thread.signo;
 	siginfo.si_code = current->thread.code;
 	siginfo.si_addr = (void *)current->thread.faddr;
-#ifdef DEBUG
-	printk("send_fault_sig: %p,%d,%d\n", siginfo.si_addr, siginfo.si_signo, siginfo.si_code);
-#endif
+	pr_debug("send_fault_sig: %p,%d,%d\n", siginfo.si_addr,
+		 siginfo.si_signo, siginfo.si_code);
 
 	if (user_mode(regs)) {
 		force_sig_info(siginfo.si_signo,
@@ -45,10 +44,10 @@ int send_fault_sig(struct pt_regs *regs)
 		 * terminate things with extreme prejudice.
 		 */
 		if ((unsigned long)siginfo.si_addr < PAGE_SIZE)
-			printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference");
+			pr_alert("Unable to handle kernel NULL pointer dereference");
 		else
-			printk(KERN_ALERT "Unable to handle kernel access");
-		printk(" at virtual address %p\n", siginfo.si_addr);
+			pr_alert("Unable to handle kernel access");
+		pr_cont(" at virtual address %p\n", siginfo.si_addr);
 		die_if_kernel("Oops", regs, 0 /*error_code*/);
 		do_exit(SIGKILL);
 	}
@@ -75,10 +74,8 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	int fault;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
-#ifdef DEBUG
-	printk ("do page fault:\nregs->sr=%#x, regs->pc=%#lx, address=%#lx, %ld, %p\n",
+	pr_debug("do page fault:\nregs->sr=%#x, regs->pc=%#lx, address=%#lx, %ld, %p\n",
 		regs->sr, regs->pc, address, error_code, mm ? mm->pgd : NULL);
-#endif
 
 	/*
 	 * If we're in an interrupt or have no user
@@ -117,9 +114,7 @@ retry:
  * we can handle it..
  */
 good_area:
-#ifdef DEBUG
-	printk("do_page_fault: good_area\n");
-#endif
+	pr_debug("do_page_fault: good_area\n");
 	switch (error_code & 3) {
 		default:	/* 3: write, present */
 			/* fall through */
@@ -142,9 +137,7 @@ good_area:
 	 */
 
 	fault = handle_mm_fault(mm, vma, address, flags);
-#ifdef DEBUG
-	printk("handle_mm_fault returns %d\n",fault);
-#endif
+	pr_debug("handle_mm_fault returns %d\n", fault);
 
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
 		return 0;
-- 
cgit v0.10.2


From 245b815c3faf4a0509948618c35f993160e193a9 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Tue, 10 Dec 2013 11:38:34 +0100
Subject: m68k: Convert arch/m68k/kernel/traps.c to pr_*()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Also fix a few printf-style formats, to get rid of the following compiler
warnings when DEBUG is enabled:

arch/m68k/kernel/traps.c: In function ‘access_error060’:
arch/m68k/kernel/traps.c:166: warning: format ‘%d’ expects type ‘int’, but argument 2 has type ‘long unsigned int’
arch/m68k/kernel/traps.c: In function ‘bus_error030’:
arch/m68k/kernel/traps.c:568: warning: format ‘%#lx’ expects type ‘long unsigned int’, but argument 2 has type ‘void *’
arch/m68k/kernel/traps.c:682: warning: format ‘%#lx’ expects type ‘long unsigned int’, but argument 2 has type ‘void *’

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c
index 88fcd8c..6c9ca24 100644
--- a/arch/m68k/kernel/traps.c
+++ b/arch/m68k/kernel/traps.c
@@ -133,9 +133,7 @@ static inline void access_error060 (struct frame *fp)
 {
 	unsigned long fslw = fp->un.fmt4.pc; /* is really FSLW for access error */
 
-#ifdef DEBUG
-	printk("fslw=%#lx, fa=%#lx\n", fslw, fp->un.fmt4.effaddr);
-#endif
+	pr_debug("fslw=%#lx, fa=%#lx\n", fslw, fp->un.fmt4.effaddr);
 
 	if (fslw & MMU060_BPE) {
 		/* branch prediction error -> clear branch cache */
@@ -162,9 +160,7 @@ static inline void access_error060 (struct frame *fp)
 		}
 		if (fslw & MMU060_W)
 			errorcode |= 2;
-#ifdef DEBUG
-		printk("errorcode = %d\n", errorcode );
-#endif
+		pr_debug("errorcode = %ld\n", errorcode);
 		do_page_fault(&fp->ptregs, addr, errorcode);
 	} else if (fslw & (MMU060_SEE)){
 		/* Software Emulation Error.
@@ -173,8 +169,9 @@ static inline void access_error060 (struct frame *fp)
 		send_fault_sig(&fp->ptregs);
 	} else if (!(fslw & (MMU060_RE|MMU060_WE)) ||
 		   send_fault_sig(&fp->ptregs) > 0) {
-		printk("pc=%#lx, fa=%#lx\n", fp->ptregs.pc, fp->un.fmt4.effaddr);
-		printk( "68060 access error, fslw=%lx\n", fslw );
+		pr_err("pc=%#lx, fa=%#lx\n", fp->ptregs.pc,
+		       fp->un.fmt4.effaddr);
+		pr_err("68060 access error, fslw=%lx\n", fslw);
 		trap_c( fp );
 	}
 }
@@ -225,9 +222,7 @@ static inline int do_040writeback1(unsigned short wbs, unsigned long wba,
 	set_fs(old_fs);
 
 
-#ifdef DEBUG
-	printk("do_040writeback1, res=%d\n",res);
-#endif
+	pr_debug("do_040writeback1, res=%d\n", res);
 
 	return res;
 }
@@ -249,7 +244,7 @@ static inline void do_040writebacks(struct frame *fp)
 	int res = 0;
 #if 0
 	if (fp->un.fmt7.wb1s & WBV_040)
-		printk("access_error040: cannot handle 1st writeback. oops.\n");
+		pr_err("access_error040: cannot handle 1st writeback. oops.\n");
 #endif
 
 	if ((fp->un.fmt7.wb2s & WBV_040) &&
@@ -302,14 +297,12 @@ static inline void access_error040(struct frame *fp)
 	unsigned short ssw = fp->un.fmt7.ssw;
 	unsigned long mmusr;
 
-#ifdef DEBUG
-	printk("ssw=%#x, fa=%#lx\n", ssw, fp->un.fmt7.faddr);
-        printk("wb1s=%#x, wb2s=%#x, wb3s=%#x\n", fp->un.fmt7.wb1s,
+	pr_debug("ssw=%#x, fa=%#lx\n", ssw, fp->un.fmt7.faddr);
+	pr_debug("wb1s=%#x, wb2s=%#x, wb3s=%#x\n", fp->un.fmt7.wb1s,
 		fp->un.fmt7.wb2s, fp->un.fmt7.wb3s);
-	printk ("wb2a=%lx, wb3a=%lx, wb2d=%lx, wb3d=%lx\n",
+	pr_debug("wb2a=%lx, wb3a=%lx, wb2d=%lx, wb3d=%lx\n",
 		fp->un.fmt7.wb2a, fp->un.fmt7.wb3a,
 		fp->un.fmt7.wb2d, fp->un.fmt7.wb3d);
-#endif
 
 	if (ssw & ATC_040) {
 		unsigned long addr = fp->un.fmt7.faddr;
@@ -324,9 +317,7 @@ static inline void access_error040(struct frame *fp)
 
 		/* MMU error, get the MMUSR info for this access */
 		mmusr = probe040(!(ssw & RW_040), addr, ssw);
-#ifdef DEBUG
-		printk("mmusr = %lx\n", mmusr);
-#endif
+		pr_debug("mmusr = %lx\n", mmusr);
 		errorcode = 1;
 		if (!(mmusr & MMU_R_040)) {
 			/* clear the invalid atc entry */
@@ -340,14 +331,10 @@ static inline void access_error040(struct frame *fp)
 			errorcode |= 2;
 
 		if (do_page_fault(&fp->ptregs, addr, errorcode)) {
-#ifdef DEBUG
-			printk("do_page_fault() !=0\n");
-#endif
+			pr_debug("do_page_fault() !=0\n");
 			if (user_mode(&fp->ptregs)){
 				/* delay writebacks after signal delivery */
-#ifdef DEBUG
-			        printk(".. was usermode - return\n");
-#endif
+				pr_debug(".. was usermode - return\n");
 				return;
 			}
 			/* disable writeback into user space from kernel
@@ -355,9 +342,7 @@ static inline void access_error040(struct frame *fp)
                          * the writeback won't do good)
 			 */
 disable_wb:
-#ifdef DEBUG
-			printk(".. disabling wb2\n");
-#endif
+			pr_debug(".. disabling wb2\n");
 			if (fp->un.fmt7.wb2a == fp->un.fmt7.faddr)
 				fp->un.fmt7.wb2s &= ~WBV_040;
 			if (fp->un.fmt7.wb3a == fp->un.fmt7.faddr)
@@ -371,7 +356,7 @@ disable_wb:
 		current->thread.signo = SIGBUS;
 		current->thread.faddr = fp->un.fmt7.faddr;
 		if (send_fault_sig(&fp->ptregs) >= 0)
-			printk("68040 bus error (ssw=%x, faddr=%lx)\n", ssw,
+			pr_err("68040 bus error (ssw=%x, faddr=%lx)\n", ssw,
 			       fp->un.fmt7.faddr);
 		goto disable_wb;
 	}
@@ -394,19 +379,17 @@ static inline void bus_error030 (struct frame *fp)
 	unsigned short ssw = fp->un.fmtb.ssw;
 	extern unsigned long _sun3_map_test_start, _sun3_map_test_end;
 
-#ifdef DEBUG
 	if (ssw & (FC | FB))
-		printk ("Instruction fault at %#010lx\n",
+		pr_debug("Instruction fault at %#010lx\n",
 			ssw & FC ?
 			fp->ptregs.format == 0xa ? fp->ptregs.pc + 2 : fp->un.fmtb.baddr - 2
 			:
 			fp->ptregs.format == 0xa ? fp->ptregs.pc + 4 : fp->un.fmtb.baddr);
 	if (ssw & DF)
-		printk ("Data %s fault at %#010lx in %s (pc=%#lx)\n",
+		pr_debug("Data %s fault at %#010lx in %s (pc=%#lx)\n",
 			ssw & RW ? "read" : "write",
 			fp->un.fmtb.daddr,
 			space_names[ssw & DFC], fp->ptregs.pc);
-#endif
 
 	/*
 	 * Check if this page should be demand-mapped. This needs to go before
@@ -429,7 +412,7 @@ static inline void bus_error030 (struct frame *fp)
 			  return;
 			/* instruction fault or kernel data fault! */
 			if (ssw & (FC | FB))
-				printk ("Instruction fault at %#010lx\n",
+				pr_err("Instruction fault at %#010lx\n",
 					fp->ptregs.pc);
 			if (ssw & DF) {
 				/* was this fault incurred testing bus mappings? */
@@ -439,12 +422,12 @@ static inline void bus_error030 (struct frame *fp)
 					return;
 				}
 
-				printk ("Data %s fault at %#010lx in %s (pc=%#lx)\n",
+				pr_err("Data %s fault at %#010lx in %s (pc=%#lx)\n",
 					ssw & RW ? "read" : "write",
 					fp->un.fmtb.daddr,
 					space_names[ssw & DFC], fp->ptregs.pc);
 			}
-			printk ("BAD KERNEL BUSERR\n");
+			pr_err("BAD KERNEL BUSERR\n");
 
 			die_if_kernel("Oops", &fp->ptregs,0);
 			force_sig(SIGKILL, current);
@@ -473,12 +456,11 @@ static inline void bus_error030 (struct frame *fp)
 		else if (buserr_type & SUN3_BUSERR_INVALID)
 			errorcode = 0x00;
 		else {
-#ifdef DEBUG
-			printk ("*** unexpected busfault type=%#04x\n", buserr_type);
-			printk ("invalid %s access at %#lx from pc %#lx\n",
-				!(ssw & RW) ? "write" : "read", addr,
-				fp->ptregs.pc);
-#endif
+			pr_debug("*** unexpected busfault type=%#04x\n",
+				 buserr_type);
+			pr_debug("invalid %s access at %#lx from pc %#lx\n",
+				 !(ssw & RW) ? "write" : "read", addr,
+				 fp->ptregs.pc);
 			die_if_kernel ("Oops", &fp->ptregs, buserr_type);
 			force_sig (SIGBUS, current);
 			return;
@@ -509,9 +491,7 @@ static inline void bus_error030 (struct frame *fp)
 		if (!mmu_emu_handle_fault(addr, 1, 0))
 			do_page_fault (&fp->ptregs, addr, 0);
        } else {
-#ifdef DEBUG
-		printk ("protection fault on insn access (segv).\n");
-#endif
+		pr_debug("protection fault on insn access (segv).\n");
 		force_sig (SIGSEGV, current);
        }
 }
@@ -525,22 +505,22 @@ static inline void bus_error030 (struct frame *fp)
 	unsigned short ssw = fp->un.fmtb.ssw;
 #ifdef DEBUG
 	unsigned long desc;
+#endif
 
-	printk ("pid = %x  ", current->pid);
-	printk ("SSW=%#06x  ", ssw);
+	pr_debug("pid = %x  ", current->pid);
+	pr_debug("SSW=%#06x  ", ssw);
 
 	if (ssw & (FC | FB))
-		printk ("Instruction fault at %#010lx\n",
+		pr_debug("Instruction fault at %#010lx\n",
 			ssw & FC ?
 			fp->ptregs.format == 0xa ? fp->ptregs.pc + 2 : fp->un.fmtb.baddr - 2
 			:
 			fp->ptregs.format == 0xa ? fp->ptregs.pc + 4 : fp->un.fmtb.baddr);
 	if (ssw & DF)
-		printk ("Data %s fault at %#010lx in %s (pc=%#lx)\n",
+		pr_debug("Data %s fault at %#010lx in %s (pc=%#lx)\n",
 			ssw & RW ? "read" : "write",
 			fp->un.fmtb.daddr,
 			space_names[ssw & DFC], fp->ptregs.pc);
-#endif
 
 	/* ++andreas: If a data fault and an instruction fault happen
 	   at the same time map in both pages.  */
@@ -554,27 +534,23 @@ static inline void bus_error030 (struct frame *fp)
 			      "pmove %%psr,%1"
 			      : "=a&" (desc), "=m" (temp)
 			      : "a" (addr), "d" (ssw));
+		pr_debug("mmusr is %#x for addr %#lx in task %p\n",
+			 temp, addr, current);
+		pr_debug("descriptor address is 0x%p, contents %#lx\n",
+			 __va(desc), *(unsigned long *)__va(desc));
 #else
 		asm volatile ("ptestr %2,%1@,#7\n\t"
 			      "pmove %%psr,%0"
 			      : "=m" (temp) : "a" (addr), "d" (ssw));
 #endif
 		mmusr = temp;
-
-#ifdef DEBUG
-		printk("mmusr is %#x for addr %#lx in task %p\n",
-		       mmusr, addr, current);
-		printk("descriptor address is %#lx, contents %#lx\n",
-		       __va(desc), *(unsigned long *)__va(desc));
-#endif
-
 		errorcode = (mmusr & MMU_I) ? 0 : 1;
 		if (!(ssw & RW) || (ssw & RM))
 			errorcode |= 2;
 
 		if (mmusr & (MMU_I | MMU_WP)) {
 			if (ssw & 4) {
-				printk("Data %s fault at %#010lx in %s (pc=%#lx)\n",
+				pr_err("Data %s fault at %#010lx in %s (pc=%#lx)\n",
 				       ssw & RW ? "read" : "write",
 				       fp->un.fmtb.daddr,
 				       space_names[ssw & DFC], fp->ptregs.pc);
@@ -587,9 +563,10 @@ static inline void bus_error030 (struct frame *fp)
 		} else if (!(mmusr & MMU_I)) {
 			/* probably a 020 cas fault */
 			if (!(ssw & RM) && send_fault_sig(&fp->ptregs) > 0)
-				printk("unexpected bus error (%#x,%#x)\n", ssw, mmusr);
+				pr_err("unexpected bus error (%#x,%#x)\n", ssw,
+				       mmusr);
 		} else if (mmusr & (MMU_B|MMU_L|MMU_S)) {
-			printk("invalid %s access at %#lx from pc %#lx\n",
+			pr_err("invalid %s access at %#lx from pc %#lx\n",
 			       !(ssw & RW) ? "write" : "read", addr,
 			       fp->ptregs.pc);
 			die_if_kernel("Oops",&fp->ptregs,mmusr);
@@ -600,7 +577,7 @@ static inline void bus_error030 (struct frame *fp)
 			static volatile long tlong;
 #endif
 
-			printk("weird %s access at %#lx from pc %#lx (ssw is %#x)\n",
+			pr_err("weird %s access at %#lx from pc %#lx (ssw is %#x)\n",
 			       !(ssw & RW) ? "write" : "read", addr,
 			       fp->ptregs.pc, ssw);
 			asm volatile ("ptestr #1,%1@,#0\n\t"
@@ -609,18 +586,16 @@ static inline void bus_error030 (struct frame *fp)
 				      : "a" (addr));
 			mmusr = temp;
 
-			printk ("level 0 mmusr is %#x\n", mmusr);
+			pr_err("level 0 mmusr is %#x\n", mmusr);
 #if 0
 			asm volatile ("pmove %%tt0,%0"
 				      : "=m" (tlong));
-			printk("tt0 is %#lx, ", tlong);
+			pr_debug("tt0 is %#lx, ", tlong);
 			asm volatile ("pmove %%tt1,%0"
 				      : "=m" (tlong));
-			printk("tt1 is %#lx\n", tlong);
-#endif
-#ifdef DEBUG
-			printk("Unknown SIGSEGV - 1\n");
+			pr_debug("tt1 is %#lx\n", tlong);
 #endif
+			pr_debug("Unknown SIGSEGV - 1\n");
 			die_if_kernel("Oops",&fp->ptregs,mmusr);
 			force_sig(SIGSEGV, current);
 			return;
@@ -641,10 +616,9 @@ static inline void bus_error030 (struct frame *fp)
 		return;
 
 	if (fp->ptregs.sr & PS_S) {
-		printk("Instruction fault at %#010lx\n",
-			fp->ptregs.pc);
+		pr_err("Instruction fault at %#010lx\n", fp->ptregs.pc);
 	buserr:
-		printk ("BAD KERNEL BUSERR\n");
+		pr_err("BAD KERNEL BUSERR\n");
 		die_if_kernel("Oops",&fp->ptregs,0);
 		force_sig(SIGKILL, current);
 		return;
@@ -668,28 +642,22 @@ static inline void bus_error030 (struct frame *fp)
 		      "pmove %%psr,%1"
 		      : "=a&" (desc), "=m" (temp)
 		      : "a" (addr));
+	pr_debug("mmusr is %#x for addr %#lx in task %p\n",
+		temp, addr, current);
+	pr_debug("descriptor address is 0x%p, contents %#lx\n",
+		__va(desc), *(unsigned long *)__va(desc));
 #else
 	asm volatile ("ptestr #1,%1@,#7\n\t"
 		      "pmove %%psr,%0"
 		      : "=m" (temp) : "a" (addr));
 #endif
 	mmusr = temp;
-
-#ifdef DEBUG
-	printk ("mmusr is %#x for addr %#lx in task %p\n",
-		mmusr, addr, current);
-	printk ("descriptor address is %#lx, contents %#lx\n",
-		__va(desc), *(unsigned long *)__va(desc));
-#endif
-
 	if (mmusr & MMU_I)
 		do_page_fault (&fp->ptregs, addr, 0);
 	else if (mmusr & (MMU_B|MMU_L|MMU_S)) {
-		printk ("invalid insn access at %#lx from pc %#lx\n",
+		pr_err("invalid insn access at %#lx from pc %#lx\n",
 			addr, fp->ptregs.pc);
-#ifdef DEBUG
-		printk("Unknown SIGSEGV - 2\n");
-#endif
+		pr_debug("Unknown SIGSEGV - 2\n");
 		die_if_kernel("Oops",&fp->ptregs,mmusr);
 		force_sig(SIGSEGV, current);
 		return;
@@ -791,9 +759,7 @@ asmlinkage void buserr_c(struct frame *fp)
 	if (user_mode(&fp->ptregs))
 		current->thread.esp0 = (unsigned long) fp;
 
-#ifdef DEBUG
-	printk ("*** Bus Error *** Format is %x\n", fp->ptregs.format);
-#endif
+	pr_debug("*** Bus Error *** Format is %x\n", fp->ptregs.format);
 
 #if defined(CONFIG_COLDFIRE) && defined(CONFIG_MMU)
 	if (CPU_IS_COLDFIRE) {
@@ -836,9 +802,7 @@ asmlinkage void buserr_c(struct frame *fp)
 #endif
 	default:
 	  die_if_kernel("bad frame format",&fp->ptregs,0);
-#ifdef DEBUG
-	  printk("Unknown SIGSEGV - 4\n");
-#endif
+	  pr_debug("Unknown SIGSEGV - 4\n");
 	  force_sig(SIGSEGV, current);
 	}
 }
@@ -852,7 +816,7 @@ void show_trace(unsigned long *stack)
 	unsigned long addr;
 	int i;
 
-	printk("Call Trace:");
+	pr_info("Call Trace:");
 	addr = (unsigned long)stack + THREAD_SIZE - 1;
 	endstack = (unsigned long *)(addr & -THREAD_SIZE);
 	i = 0;
@@ -869,13 +833,13 @@ void show_trace(unsigned long *stack)
 		if (__kernel_text_address(addr)) {
 #ifndef CONFIG_KALLSYMS
 			if (i % 5 == 0)
-				printk("\n       ");
+				pr_cont("\n       ");
 #endif
-			printk(" [<%08lx>] %pS\n", addr, (void *)addr);
+			pr_cont(" [<%08lx>] %pS\n", addr, (void *)addr);
 			i++;
 		}
 	}
-	printk("\n");
+	pr_cont("\n");
 }
 
 void show_registers(struct pt_regs *regs)
@@ -887,81 +851,87 @@ void show_registers(struct pt_regs *regs)
 	int i;
 
 	print_modules();
-	printk("PC: [<%08lx>] %pS\n", regs->pc, (void *)regs->pc);
-	printk("SR: %04x  SP: %p  a2: %08lx\n", regs->sr, regs, regs->a2);
-	printk("d0: %08lx    d1: %08lx    d2: %08lx    d3: %08lx\n",
+	pr_info("PC: [<%08lx>] %pS\n", regs->pc, (void *)regs->pc);
+	pr_info("SR: %04x  SP: %p  a2: %08lx\n", regs->sr, regs, regs->a2);
+	pr_info("d0: %08lx    d1: %08lx    d2: %08lx    d3: %08lx\n",
 	       regs->d0, regs->d1, regs->d2, regs->d3);
-	printk("d4: %08lx    d5: %08lx    a0: %08lx    a1: %08lx\n",
+	pr_info("d4: %08lx    d5: %08lx    a0: %08lx    a1: %08lx\n",
 	       regs->d4, regs->d5, regs->a0, regs->a1);
 
-	printk("Process %s (pid: %d, task=%p)\n",
+	pr_info("Process %s (pid: %d, task=%p)\n",
 		current->comm, task_pid_nr(current), current);
 	addr = (unsigned long)&fp->un;
-	printk("Frame format=%X ", regs->format);
+	pr_info("Frame format=%X ", regs->format);
 	switch (regs->format) {
 	case 0x2:
-		printk("instr addr=%08lx\n", fp->un.fmt2.iaddr);
+		pr_cont("instr addr=%08lx\n", fp->un.fmt2.iaddr);
 		addr += sizeof(fp->un.fmt2);
 		break;
 	case 0x3:
-		printk("eff addr=%08lx\n", fp->un.fmt3.effaddr);
+		pr_cont("eff addr=%08lx\n", fp->un.fmt3.effaddr);
 		addr += sizeof(fp->un.fmt3);
 		break;
 	case 0x4:
-		printk((CPU_IS_060 ? "fault addr=%08lx fslw=%08lx\n"
-			: "eff addr=%08lx pc=%08lx\n"),
-			fp->un.fmt4.effaddr, fp->un.fmt4.pc);
+		if (CPU_IS_060)
+			pr_cont("fault addr=%08lx fslw=%08lx\n",
+				fp->un.fmt4.effaddr, fp->un.fmt4.pc);
+		else
+			pr_cont("eff addr=%08lx pc=%08lx\n",
+				fp->un.fmt4.effaddr, fp->un.fmt4.pc);
 		addr += sizeof(fp->un.fmt4);
 		break;
 	case 0x7:
-		printk("eff addr=%08lx ssw=%04x faddr=%08lx\n",
+		pr_cont("eff addr=%08lx ssw=%04x faddr=%08lx\n",
 			fp->un.fmt7.effaddr, fp->un.fmt7.ssw, fp->un.fmt7.faddr);
-		printk("wb 1 stat/addr/data: %04x %08lx %08lx\n",
+		pr_info("wb 1 stat/addr/data: %04x %08lx %08lx\n",
 			fp->un.fmt7.wb1s, fp->un.fmt7.wb1a, fp->un.fmt7.wb1dpd0);
-		printk("wb 2 stat/addr/data: %04x %08lx %08lx\n",
+		pr_info("wb 2 stat/addr/data: %04x %08lx %08lx\n",
 			fp->un.fmt7.wb2s, fp->un.fmt7.wb2a, fp->un.fmt7.wb2d);
-		printk("wb 3 stat/addr/data: %04x %08lx %08lx\n",
+		pr_info("wb 3 stat/addr/data: %04x %08lx %08lx\n",
 			fp->un.fmt7.wb3s, fp->un.fmt7.wb3a, fp->un.fmt7.wb3d);
-		printk("push data: %08lx %08lx %08lx %08lx\n",
+		pr_info("push data: %08lx %08lx %08lx %08lx\n",
 			fp->un.fmt7.wb1dpd0, fp->un.fmt7.pd1, fp->un.fmt7.pd2,
 			fp->un.fmt7.pd3);
 		addr += sizeof(fp->un.fmt7);
 		break;
 	case 0x9:
-		printk("instr addr=%08lx\n", fp->un.fmt9.iaddr);
+		pr_cont("instr addr=%08lx\n", fp->un.fmt9.iaddr);
 		addr += sizeof(fp->un.fmt9);
 		break;
 	case 0xa:
-		printk("ssw=%04x isc=%04x isb=%04x daddr=%08lx dobuf=%08lx\n",
+		pr_cont("ssw=%04x isc=%04x isb=%04x daddr=%08lx dobuf=%08lx\n",
 			fp->un.fmta.ssw, fp->un.fmta.isc, fp->un.fmta.isb,
 			fp->un.fmta.daddr, fp->un.fmta.dobuf);
 		addr += sizeof(fp->un.fmta);
 		break;
 	case 0xb:
-		printk("ssw=%04x isc=%04x isb=%04x daddr=%08lx dobuf=%08lx\n",
+		pr_cont("ssw=%04x isc=%04x isb=%04x daddr=%08lx dobuf=%08lx\n",
 			fp->un.fmtb.ssw, fp->un.fmtb.isc, fp->un.fmtb.isb,
 			fp->un.fmtb.daddr, fp->un.fmtb.dobuf);
-		printk("baddr=%08lx dibuf=%08lx ver=%x\n",
+		pr_info("baddr=%08lx dibuf=%08lx ver=%x\n",
 			fp->un.fmtb.baddr, fp->un.fmtb.dibuf, fp->un.fmtb.ver);
 		addr += sizeof(fp->un.fmtb);
 		break;
 	default:
-		printk("\n");
+		pr_cont("\n");
 	}
 	show_stack(NULL, (unsigned long *)addr);
 
-	printk("Code:");
+	pr_info("Code:");
 	set_fs(KERNEL_DS);
 	cp = (u16 *)regs->pc;
 	for (i = -8; i < 16; i++) {
 		if (get_user(c, cp + i) && i >= 0) {
-			printk(" Bad PC value.");
+			pr_cont(" Bad PC value.");
 			break;
 		}
-		printk(i ? " %04x" : " <%04x>", c);
+		if (i)
+			pr_cont(" %04x", c);
+		else
+			pr_cont(" <%04x>", c);
 	}
 	set_fs(old_fs);
-	printk ("\n");
+	pr_cont("\n");
 }
 
 void show_stack(struct task_struct *task, unsigned long *stack)
@@ -978,16 +948,16 @@ void show_stack(struct task_struct *task, unsigned long *stack)
 	}
 	endstack = (unsigned long *)(((unsigned long)stack + THREAD_SIZE - 1) & -THREAD_SIZE);
 
-	printk("Stack from %08lx:", (unsigned long)stack);
+	pr_info("Stack from %08lx:", (unsigned long)stack);
 	p = stack;
 	for (i = 0; i < kstack_depth_to_print; i++) {
 		if (p + 1 > endstack)
 			break;
 		if (i % 8 == 0)
-			printk("\n       ");
-		printk(" %08lx", *p++);
+			pr_cont("\n       ");
+		pr_cont(" %08lx", *p++);
 	}
-	printk("\n");
+	pr_cont("\n");
 	show_trace(stack);
 }
 
@@ -1005,32 +975,32 @@ void bad_super_trap (struct frame *fp)
 
 	console_verbose();
 	if (vector < ARRAY_SIZE(vec_names))
-		printk ("*** %s ***   FORMAT=%X\n",
+		pr_err("*** %s ***   FORMAT=%X\n",
 			vec_names[vector],
 			fp->ptregs.format);
 	else
-		printk ("*** Exception %d ***   FORMAT=%X\n",
+		pr_err("*** Exception %d ***   FORMAT=%X\n",
 			vector, fp->ptregs.format);
 	if (vector == VEC_ADDRERR && CPU_IS_020_OR_030) {
 		unsigned short ssw = fp->un.fmtb.ssw;
 
-		printk ("SSW=%#06x  ", ssw);
+		pr_err("SSW=%#06x  ", ssw);
 
 		if (ssw & RC)
-			printk ("Pipe stage C instruction fault at %#010lx\n",
+			pr_err("Pipe stage C instruction fault at %#010lx\n",
 				(fp->ptregs.format) == 0xA ?
 				fp->ptregs.pc + 2 : fp->un.fmtb.baddr - 2);
 		if (ssw & RB)
-			printk ("Pipe stage B instruction fault at %#010lx\n",
+			pr_err("Pipe stage B instruction fault at %#010lx\n",
 				(fp->ptregs.format) == 0xA ?
 				fp->ptregs.pc + 4 : fp->un.fmtb.baddr);
 		if (ssw & DF)
-			printk ("Data %s fault at %#010lx in %s (pc=%#lx)\n",
+			pr_err("Data %s fault at %#010lx in %s (pc=%#lx)\n",
 				ssw & RW ? "read" : "write",
 				fp->un.fmtb.daddr, space_names[ssw & DFC],
 				fp->ptregs.pc);
 	}
-	printk ("Current process id is %d\n", task_pid_nr(current));
+	pr_err("Current process id is %d\n", task_pid_nr(current));
 	die_if_kernel("BAD KERNEL TRAP", &fp->ptregs, 0);
 }
 
@@ -1162,7 +1132,7 @@ void die_if_kernel (char *str, struct pt_regs *fp, int nr)
 		return;
 
 	console_verbose();
-	printk("%s: %08x\n",str,nr);
+	pr_crit("%s: %08x\n", str, nr);
 	show_registers(fp);
 	add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE);
 	do_exit(SIGSEGV);
-- 
cgit v0.10.2


From f6fc30dbb720e34e4ae796857b479d0e0af7cfb4 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Tue, 17 Dec 2013 11:24:58 +0100
Subject: m68k/mm: kmap spelling/grammar fixes

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/mm/kmap.c b/arch/m68k/mm/kmap.c
index 568cfad..6e4955b 100644
--- a/arch/m68k/mm/kmap.c
+++ b/arch/m68k/mm/kmap.c
@@ -27,9 +27,9 @@
 
 /*
  * For 040/060 we can use the virtual memory area like other architectures,
- * but for 020/030 we want to use early termination page descriptor and we
+ * but for 020/030 we want to use early termination page descriptors and we
  * can't mix this with normal page descriptors, so we have to copy that code
- * (mm/vmalloc.c) and return appriorate aligned addresses.
+ * (mm/vmalloc.c) and return appropriately aligned addresses.
  */
 
 #ifdef CPU_M68040_OR_M68060_ONLY
@@ -224,7 +224,7 @@ void __iomem *__ioremap(unsigned long physaddr, unsigned long size, int cachefla
 EXPORT_SYMBOL(__ioremap);
 
 /*
- * Unmap a ioremap()ed region again
+ * Unmap an ioremap()ed region again
  */
 void iounmap(void __iomem *addr)
 {
@@ -241,8 +241,8 @@ EXPORT_SYMBOL(iounmap);
 
 /*
  * __iounmap unmaps nearly everything, so be careful
- * it doesn't free currently pointer/page tables anymore but it
- * wans't used anyway and might be added later.
+ * Currently it doesn't free pointer/page tables anymore but this
+ * wasn't used anyway and might be added later.
  */
 void __iounmap(void *addr, unsigned long size)
 {
-- 
cgit v0.10.2


From bbb519cd5ca9d84a96f7ea9a5826f57091eade02 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Sun, 18 Aug 2013 12:00:50 +0200
Subject: m68k/defconfig: Enable EARLY_PRINTK

It's too valuable for debugging to be disabled.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 7f6be05..2d1e468 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -421,6 +421,7 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
+CONFIG_EARLY_PRINTK=y
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 265abf4..f83b2c4 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -499,6 +499,7 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
+CONFIG_EARLY_PRINTK=y
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 4108303..9cb7e4d 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -388,6 +388,7 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
+CONFIG_EARLY_PRINTK=y
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
-- 
cgit v0.10.2


From a16f9a42a557dcf33eaee4c5ba3e09eb7e655c70 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Fri, 17 May 2013 17:25:39 +0200
Subject: m68k: Update defconfigs for v3.13-rc1

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 1b95317..559ff3a 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -52,7 +52,6 @@ CONFIG_IP_PNP_RARP=y
 CONFIG_NET_IPIP=m
 CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
-CONFIG_SYN_COOKIES=y
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
@@ -63,11 +62,11 @@ CONFIG_INET_XFRM_MODE_BEET=m
 # CONFIG_INET_LRO is not set
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
-CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
@@ -85,6 +84,17 @@ CONFIG_NF_CONNTRACK_PPTP=m
 CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_EXTHDR=m
+CONFIG_NFT_META=m
+CONFIG_NFT_CT=m
+CONFIG_NFT_RBTREE=m
+CONFIG_NFT_HASH=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_LOG=m
+CONFIG_NFT_LIMIT=m
+CONFIG_NFT_NAT=m
+CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -98,6 +108,7 @@ CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
+CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
@@ -130,6 +141,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m
 CONFIG_NETFILTER_XT_MATCH_RATEEST=m
 CONFIG_NETFILTER_XT_MATCH_REALM=m
 CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
 CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
@@ -144,11 +156,18 @@ CONFIG_IP_SET_HASH_IP=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
+CONFIG_IP_SET_HASH_NETNET=m
 CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_TABLES_IPV4=m
+CONFIG_NFT_REJECT_IPV4=m
+CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
+CONFIG_NF_TABLES_ARP=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -156,6 +175,7 @@ CONFIG_IP_NF_MATCH_RPFILTER=m
 CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_TARGET_SYNPROXY=m
 CONFIG_IP_NF_TARGET_ULOG=m
 CONFIG_NF_NAT_IPV4=m
 CONFIG_IP_NF_TARGET_MASQUERADE=m
@@ -170,6 +190,9 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_TABLES_IPV6=m
+CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -183,11 +206,13 @@ CONFIG_IP6_NF_MATCH_RT=m
 CONFIG_IP6_NF_TARGET_HL=m
 CONFIG_IP6_NF_FILTER=m
 CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_TARGET_SYNPROXY=m
 CONFIG_IP6_NF_MANGLE=m
 CONFIG_IP6_NF_RAW=m
 CONFIG_NF_NAT_IPV6=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
+CONFIG_NF_TABLES_BRIDGE=m
 CONFIG_IP_DCCP=m
 # CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
@@ -195,8 +220,12 @@ CONFIG_RDS=m
 CONFIG_RDS_TCP=m
 CONFIG_L2TP=m
 CONFIG_ATALK=m
+CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
+CONFIG_BATMAN_ADV_NC=y
+CONFIG_NETLINK_DIAG=m
+CONFIG_NET_MPLS_GSO=m
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -215,6 +244,7 @@ CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
+CONFIG_DUMMY_IRQ=m
 CONFIG_IDE=y
 CONFIG_IDE_GD_ATAPI=y
 CONFIG_BLK_DEV_IDECD=y
@@ -261,6 +291,7 @@ CONFIG_EQUALIZER=m
 CONFIG_NET_TEAM=m
 CONFIG_NET_TEAM_MODE_BROADCAST=m
 CONFIG_NET_TEAM_MODE_ROUNDROBIN=m
+CONFIG_NET_TEAM_MODE_RANDOM=m
 CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m
 CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_VXLAN=m
@@ -270,10 +301,10 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_3COM is not set
 CONFIG_A2065=y
 CONFIG_ARIADNE=y
+# CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_CIRRUS is not set
-# CONFIG_NET_VENDOR_FUJITSU is not set
 # CONFIG_NET_VENDOR_HP is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
@@ -284,6 +315,7 @@ CONFIG_ZORRO8390=y
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
@@ -310,7 +342,6 @@ CONFIG_JOYSTICK_AMIGA=m
 CONFIG_INPUT_MISC=y
 CONFIG_INPUT_M68K_BEEP=m
 # CONFIG_SERIO is not set
-CONFIG_VT_HW_CONSOLE_BINDING=y
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 CONFIG_PRINTER=m
@@ -439,10 +470,10 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
+CONFIG_TEST_STRING_HELPERS=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
-CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
@@ -475,6 +506,8 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_LZ4=m
+CONFIG_CRYPTO_LZ4HC=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index bc3b9ae..cb1f55d 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -50,7 +50,6 @@ CONFIG_IP_PNP_RARP=y
 CONFIG_NET_IPIP=m
 CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
-CONFIG_SYN_COOKIES=y
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
@@ -61,11 +60,11 @@ CONFIG_INET_XFRM_MODE_BEET=m
 # CONFIG_INET_LRO is not set
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
-CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
@@ -83,6 +82,17 @@ CONFIG_NF_CONNTRACK_PPTP=m
 CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_EXTHDR=m
+CONFIG_NFT_META=m
+CONFIG_NFT_CT=m
+CONFIG_NFT_RBTREE=m
+CONFIG_NFT_HASH=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_LOG=m
+CONFIG_NFT_LIMIT=m
+CONFIG_NFT_NAT=m
+CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -96,6 +106,7 @@ CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
+CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
@@ -128,6 +139,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m
 CONFIG_NETFILTER_XT_MATCH_RATEEST=m
 CONFIG_NETFILTER_XT_MATCH_REALM=m
 CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
 CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
@@ -142,11 +154,18 @@ CONFIG_IP_SET_HASH_IP=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
+CONFIG_IP_SET_HASH_NETNET=m
 CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_TABLES_IPV4=m
+CONFIG_NFT_REJECT_IPV4=m
+CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
+CONFIG_NF_TABLES_ARP=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -154,6 +173,7 @@ CONFIG_IP_NF_MATCH_RPFILTER=m
 CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_TARGET_SYNPROXY=m
 CONFIG_IP_NF_TARGET_ULOG=m
 CONFIG_NF_NAT_IPV4=m
 CONFIG_IP_NF_TARGET_MASQUERADE=m
@@ -168,6 +188,9 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_TABLES_IPV6=m
+CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -181,11 +204,13 @@ CONFIG_IP6_NF_MATCH_RT=m
 CONFIG_IP6_NF_TARGET_HL=m
 CONFIG_IP6_NF_FILTER=m
 CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_TARGET_SYNPROXY=m
 CONFIG_IP6_NF_MANGLE=m
 CONFIG_IP6_NF_RAW=m
 CONFIG_NF_NAT_IPV6=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
+CONFIG_NF_TABLES_BRIDGE=m
 CONFIG_IP_DCCP=m
 # CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
@@ -193,8 +218,12 @@ CONFIG_RDS=m
 CONFIG_RDS_TCP=m
 CONFIG_L2TP=m
 CONFIG_ATALK=m
+CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
+CONFIG_BATMAN_ADV_NC=y
+CONFIG_NETLINK_DIAG=m
+CONFIG_NET_MPLS_GSO=m
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -207,6 +236,7 @@ CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
+CONFIG_DUMMY_IRQ=m
 CONFIG_RAID_ATTRS=m
 CONFIG_SCSI=y
 CONFIG_SCSI_TGT=m
@@ -243,12 +273,14 @@ CONFIG_EQUALIZER=m
 CONFIG_NET_TEAM=m
 CONFIG_NET_TEAM_MODE_BROADCAST=m
 CONFIG_NET_TEAM_MODE_ROUNDROBIN=m
+CONFIG_NET_TEAM_MODE_RANDOM=m
 CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m
 CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_VXLAN=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
+# CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_INTEL is not set
@@ -257,6 +289,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
@@ -278,7 +311,6 @@ CONFIG_INPUT_EVDEV=m
 # CONFIG_MOUSE_PS2 is not set
 CONFIG_MOUSE_SERIAL=m
 CONFIG_SERIO=m
-CONFIG_VT_HW_CONSOLE_BINDING=y
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 # CONFIG_HW_RANDOM is not set
@@ -396,10 +428,10 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
+CONFIG_TEST_STRING_HELPERS=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
-CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
@@ -432,6 +464,8 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_LZ4=m
+CONFIG_CRYPTO_LZ4HC=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 264c844..e880cfb 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -49,7 +49,6 @@ CONFIG_IP_PNP_RARP=y
 CONFIG_NET_IPIP=m
 CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
-CONFIG_SYN_COOKIES=y
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
@@ -60,11 +59,11 @@ CONFIG_INET_XFRM_MODE_BEET=m
 # CONFIG_INET_LRO is not set
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
-CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
@@ -82,6 +81,17 @@ CONFIG_NF_CONNTRACK_PPTP=m
 CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_EXTHDR=m
+CONFIG_NFT_META=m
+CONFIG_NFT_CT=m
+CONFIG_NFT_RBTREE=m
+CONFIG_NFT_HASH=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_LOG=m
+CONFIG_NFT_LIMIT=m
+CONFIG_NFT_NAT=m
+CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -95,6 +105,7 @@ CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
+CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
@@ -127,6 +138,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m
 CONFIG_NETFILTER_XT_MATCH_RATEEST=m
 CONFIG_NETFILTER_XT_MATCH_REALM=m
 CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
 CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
@@ -141,11 +153,18 @@ CONFIG_IP_SET_HASH_IP=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
+CONFIG_IP_SET_HASH_NETNET=m
 CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_TABLES_IPV4=m
+CONFIG_NFT_REJECT_IPV4=m
+CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
+CONFIG_NF_TABLES_ARP=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -153,6 +172,7 @@ CONFIG_IP_NF_MATCH_RPFILTER=m
 CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_TARGET_SYNPROXY=m
 CONFIG_IP_NF_TARGET_ULOG=m
 CONFIG_NF_NAT_IPV4=m
 CONFIG_IP_NF_TARGET_MASQUERADE=m
@@ -167,6 +187,9 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_TABLES_IPV6=m
+CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -180,11 +203,13 @@ CONFIG_IP6_NF_MATCH_RT=m
 CONFIG_IP6_NF_TARGET_HL=m
 CONFIG_IP6_NF_FILTER=m
 CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_TARGET_SYNPROXY=m
 CONFIG_IP6_NF_MANGLE=m
 CONFIG_IP6_NF_RAW=m
 CONFIG_NF_NAT_IPV6=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
+CONFIG_NF_TABLES_BRIDGE=m
 CONFIG_IP_DCCP=m
 # CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
@@ -192,8 +217,12 @@ CONFIG_RDS=m
 CONFIG_RDS_TCP=m
 CONFIG_L2TP=m
 CONFIG_ATALK=m
+CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
+CONFIG_BATMAN_ADV_NC=y
+CONFIG_NETLINK_DIAG=m
+CONFIG_NET_MPLS_GSO=m
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -210,6 +239,7 @@ CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
+CONFIG_DUMMY_IRQ=m
 CONFIG_IDE=y
 CONFIG_IDE_GD_ATAPI=y
 CONFIG_BLK_DEV_IDECD=y
@@ -248,10 +278,10 @@ CONFIG_TCM_PSCSI=m
 CONFIG_NETDEVICES=y
 CONFIG_DUMMY=m
 CONFIG_EQUALIZER=m
-CONFIG_MII=y
 CONFIG_NET_TEAM=m
 CONFIG_NET_TEAM_MODE_BROADCAST=m
 CONFIG_NET_TEAM_MODE_ROUNDROBIN=m
+CONFIG_NET_TEAM_MODE_RANDOM=m
 CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m
 CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_VXLAN=m
@@ -259,6 +289,7 @@ CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 CONFIG_ATARILANCE=y
+# CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_INTEL is not set
@@ -266,6 +297,7 @@ CONFIG_ATARILANCE=y
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
@@ -290,7 +322,6 @@ CONFIG_MOUSE_ATARI=m
 CONFIG_INPUT_MISC=y
 CONFIG_INPUT_M68K_BEEP=m
 # CONFIG_SERIO is not set
-CONFIG_VT_HW_CONSOLE_BINDING=y
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 CONFIG_PRINTER=m
@@ -414,10 +445,10 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
+CONFIG_TEST_STRING_HELPERS=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
-CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
@@ -450,6 +481,8 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_LZ4=m
+CONFIG_CRYPTO_LZ4HC=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 2462c93..4aa4f45 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -48,7 +48,6 @@ CONFIG_IP_PNP_RARP=y
 CONFIG_NET_IPIP=m
 CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
-CONFIG_SYN_COOKIES=y
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
@@ -59,11 +58,11 @@ CONFIG_INET_XFRM_MODE_BEET=m
 # CONFIG_INET_LRO is not set
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
-CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
@@ -81,6 +80,17 @@ CONFIG_NF_CONNTRACK_PPTP=m
 CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_EXTHDR=m
+CONFIG_NFT_META=m
+CONFIG_NFT_CT=m
+CONFIG_NFT_RBTREE=m
+CONFIG_NFT_HASH=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_LOG=m
+CONFIG_NFT_LIMIT=m
+CONFIG_NFT_NAT=m
+CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -94,6 +104,7 @@ CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
+CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
@@ -126,6 +137,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m
 CONFIG_NETFILTER_XT_MATCH_RATEEST=m
 CONFIG_NETFILTER_XT_MATCH_REALM=m
 CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
 CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
@@ -140,11 +152,18 @@ CONFIG_IP_SET_HASH_IP=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
+CONFIG_IP_SET_HASH_NETNET=m
 CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_TABLES_IPV4=m
+CONFIG_NFT_REJECT_IPV4=m
+CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
+CONFIG_NF_TABLES_ARP=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -152,6 +171,7 @@ CONFIG_IP_NF_MATCH_RPFILTER=m
 CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_TARGET_SYNPROXY=m
 CONFIG_IP_NF_TARGET_ULOG=m
 CONFIG_NF_NAT_IPV4=m
 CONFIG_IP_NF_TARGET_MASQUERADE=m
@@ -166,6 +186,9 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_TABLES_IPV6=m
+CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -179,11 +202,13 @@ CONFIG_IP6_NF_MATCH_RT=m
 CONFIG_IP6_NF_TARGET_HL=m
 CONFIG_IP6_NF_FILTER=m
 CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_TARGET_SYNPROXY=m
 CONFIG_IP6_NF_MANGLE=m
 CONFIG_IP6_NF_RAW=m
 CONFIG_NF_NAT_IPV6=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
+CONFIG_NF_TABLES_BRIDGE=m
 CONFIG_IP_DCCP=m
 # CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
@@ -191,8 +216,12 @@ CONFIG_RDS=m
 CONFIG_RDS_TCP=m
 CONFIG_L2TP=m
 CONFIG_ATALK=m
+CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
+CONFIG_BATMAN_ADV_NC=y
+CONFIG_NETLINK_DIAG=m
+CONFIG_NET_MPLS_GSO=m
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -205,6 +234,7 @@ CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
+CONFIG_DUMMY_IRQ=m
 CONFIG_RAID_ATTRS=m
 CONFIG_SCSI=y
 CONFIG_SCSI_TGT=m
@@ -242,12 +272,14 @@ CONFIG_EQUALIZER=m
 CONFIG_NET_TEAM=m
 CONFIG_NET_TEAM_MODE_BROADCAST=m
 CONFIG_NET_TEAM_MODE_ROUNDROBIN=m
+CONFIG_NET_TEAM_MODE_RANDOM=m
 CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m
 CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_VXLAN=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
+# CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 CONFIG_BVME6000_NET=y
@@ -256,6 +288,7 @@ CONFIG_BVME6000_NET=y
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
@@ -388,10 +421,10 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
+CONFIG_TEST_STRING_HELPERS=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
-CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
@@ -424,6 +457,8 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_LZ4=m
+CONFIG_CRYPTO_LZ4HC=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 9e6d582..7cd9d9f 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -50,7 +50,6 @@ CONFIG_IP_PNP_RARP=y
 CONFIG_NET_IPIP=m
 CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
-CONFIG_SYN_COOKIES=y
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
@@ -61,11 +60,11 @@ CONFIG_INET_XFRM_MODE_BEET=m
 # CONFIG_INET_LRO is not set
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
-CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
@@ -83,6 +82,17 @@ CONFIG_NF_CONNTRACK_PPTP=m
 CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_EXTHDR=m
+CONFIG_NFT_META=m
+CONFIG_NFT_CT=m
+CONFIG_NFT_RBTREE=m
+CONFIG_NFT_HASH=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_LOG=m
+CONFIG_NFT_LIMIT=m
+CONFIG_NFT_NAT=m
+CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -96,6 +106,7 @@ CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
+CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
@@ -128,6 +139,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m
 CONFIG_NETFILTER_XT_MATCH_RATEEST=m
 CONFIG_NETFILTER_XT_MATCH_REALM=m
 CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
 CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
@@ -142,11 +154,18 @@ CONFIG_IP_SET_HASH_IP=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
+CONFIG_IP_SET_HASH_NETNET=m
 CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_TABLES_IPV4=m
+CONFIG_NFT_REJECT_IPV4=m
+CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
+CONFIG_NF_TABLES_ARP=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -154,6 +173,7 @@ CONFIG_IP_NF_MATCH_RPFILTER=m
 CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_TARGET_SYNPROXY=m
 CONFIG_IP_NF_TARGET_ULOG=m
 CONFIG_NF_NAT_IPV4=m
 CONFIG_IP_NF_TARGET_MASQUERADE=m
@@ -168,6 +188,9 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_TABLES_IPV6=m
+CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -181,11 +204,13 @@ CONFIG_IP6_NF_MATCH_RT=m
 CONFIG_IP6_NF_TARGET_HL=m
 CONFIG_IP6_NF_FILTER=m
 CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_TARGET_SYNPROXY=m
 CONFIG_IP6_NF_MANGLE=m
 CONFIG_IP6_NF_RAW=m
 CONFIG_NF_NAT_IPV6=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
+CONFIG_NF_TABLES_BRIDGE=m
 CONFIG_IP_DCCP=m
 # CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
@@ -193,8 +218,12 @@ CONFIG_RDS=m
 CONFIG_RDS_TCP=m
 CONFIG_L2TP=m
 CONFIG_ATALK=m
+CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
+CONFIG_BATMAN_ADV_NC=y
+CONFIG_NETLINK_DIAG=m
+CONFIG_NET_MPLS_GSO=m
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -207,6 +236,7 @@ CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
+CONFIG_DUMMY_IRQ=m
 CONFIG_RAID_ATTRS=m
 CONFIG_SCSI=y
 CONFIG_SCSI_TGT=m
@@ -243,6 +273,7 @@ CONFIG_EQUALIZER=m
 CONFIG_NET_TEAM=m
 CONFIG_NET_TEAM_MODE_BROADCAST=m
 CONFIG_NET_TEAM_MODE_ROUNDROBIN=m
+CONFIG_NET_TEAM_MODE_RANDOM=m
 CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m
 CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_VXLAN=m
@@ -250,6 +281,7 @@ CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 CONFIG_HPLANCE=y
+# CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_INTEL is not set
@@ -258,6 +290,7 @@ CONFIG_HPLANCE=y
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
@@ -281,7 +314,6 @@ CONFIG_MOUSE_SERIAL=m
 CONFIG_INPUT_MISC=y
 CONFIG_HP_SDC_RTC=m
 CONFIG_SERIO_SERPORT=m
-CONFIG_VT_HW_CONSOLE_BINDING=y
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 # CONFIG_HW_RANDOM is not set
@@ -398,10 +430,10 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
+CONFIG_TEST_STRING_HELPERS=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
-CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
@@ -434,6 +466,8 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_LZ4=m
+CONFIG_CRYPTO_LZ4HC=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 2d1e468..31f5bd0 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -49,7 +49,6 @@ CONFIG_IP_PNP_RARP=y
 CONFIG_NET_IPIP=m
 CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
-CONFIG_SYN_COOKIES=y
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
@@ -60,11 +59,11 @@ CONFIG_INET_XFRM_MODE_BEET=m
 # CONFIG_INET_LRO is not set
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
-CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
@@ -82,6 +81,17 @@ CONFIG_NF_CONNTRACK_PPTP=m
 CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_EXTHDR=m
+CONFIG_NFT_META=m
+CONFIG_NFT_CT=m
+CONFIG_NFT_RBTREE=m
+CONFIG_NFT_HASH=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_LOG=m
+CONFIG_NFT_LIMIT=m
+CONFIG_NFT_NAT=m
+CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -95,6 +105,7 @@ CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
+CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
@@ -127,6 +138,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m
 CONFIG_NETFILTER_XT_MATCH_RATEEST=m
 CONFIG_NETFILTER_XT_MATCH_REALM=m
 CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
 CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
@@ -141,11 +153,18 @@ CONFIG_IP_SET_HASH_IP=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
+CONFIG_IP_SET_HASH_NETNET=m
 CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_TABLES_IPV4=m
+CONFIG_NFT_REJECT_IPV4=m
+CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
+CONFIG_NF_TABLES_ARP=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -153,6 +172,7 @@ CONFIG_IP_NF_MATCH_RPFILTER=m
 CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_TARGET_SYNPROXY=m
 CONFIG_IP_NF_TARGET_ULOG=m
 CONFIG_NF_NAT_IPV4=m
 CONFIG_IP_NF_TARGET_MASQUERADE=m
@@ -167,6 +187,9 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_TABLES_IPV6=m
+CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -180,11 +203,13 @@ CONFIG_IP6_NF_MATCH_RT=m
 CONFIG_IP6_NF_TARGET_HL=m
 CONFIG_IP6_NF_FILTER=m
 CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_TARGET_SYNPROXY=m
 CONFIG_IP6_NF_MANGLE=m
 CONFIG_IP6_NF_RAW=m
 CONFIG_NF_NAT_IPV6=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
+CONFIG_NF_TABLES_BRIDGE=m
 CONFIG_IP_DCCP=m
 # CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
@@ -195,9 +220,12 @@ CONFIG_ATALK=m
 CONFIG_DEV_APPLETALK=m
 CONFIG_IPDDP=m
 CONFIG_IPDDP_ENCAP=y
-CONFIG_IPDDP_DECAP=y
+CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
+CONFIG_BATMAN_ADV_NC=y
+CONFIG_NETLINK_DIAG=m
+CONFIG_NET_MPLS_GSO=m
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -211,6 +239,7 @@ CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
+CONFIG_DUMMY_IRQ=m
 CONFIG_IDE=y
 CONFIG_IDE_GD_ATAPI=y
 CONFIG_BLK_DEV_IDECD=y
@@ -260,6 +289,7 @@ CONFIG_EQUALIZER=m
 CONFIG_NET_TEAM=m
 CONFIG_NET_TEAM_MODE_BROADCAST=m
 CONFIG_NET_TEAM_MODE_ROUNDROBIN=m
+CONFIG_NET_TEAM_MODE_RANDOM=m
 CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m
 CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_VXLAN=m
@@ -267,6 +297,7 @@ CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 CONFIG_MACMACE=y
+# CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 CONFIG_MAC89x0=y
@@ -278,6 +309,7 @@ CONFIG_MAC8390=y
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
@@ -301,7 +333,6 @@ CONFIG_MOUSE_SERIAL=m
 CONFIG_INPUT_MISC=y
 CONFIG_INPUT_M68K_BEEP=m
 CONFIG_SERIO=m
-CONFIG_VT_HW_CONSOLE_BINDING=y
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_PMACZILOG=y
@@ -421,11 +452,11 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
+CONFIG_TEST_STRING_HELPERS=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
-CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
@@ -458,6 +489,8 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_LZ4=m
+CONFIG_CRYPTO_LZ4HC=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index f83b2c4..4e5adff 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -58,7 +58,6 @@ CONFIG_IP_PNP_RARP=y
 CONFIG_NET_IPIP=m
 CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
-CONFIG_SYN_COOKIES=y
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
@@ -69,11 +68,11 @@ CONFIG_INET_XFRM_MODE_BEET=m
 # CONFIG_INET_LRO is not set
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
-CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
@@ -91,6 +90,17 @@ CONFIG_NF_CONNTRACK_PPTP=m
 CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_EXTHDR=m
+CONFIG_NFT_META=m
+CONFIG_NFT_CT=m
+CONFIG_NFT_RBTREE=m
+CONFIG_NFT_HASH=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_LOG=m
+CONFIG_NFT_LIMIT=m
+CONFIG_NFT_NAT=m
+CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -104,6 +114,7 @@ CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
+CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
@@ -136,6 +147,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m
 CONFIG_NETFILTER_XT_MATCH_RATEEST=m
 CONFIG_NETFILTER_XT_MATCH_REALM=m
 CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
 CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
@@ -150,11 +162,18 @@ CONFIG_IP_SET_HASH_IP=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
+CONFIG_IP_SET_HASH_NETNET=m
 CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_TABLES_IPV4=m
+CONFIG_NFT_REJECT_IPV4=m
+CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
+CONFIG_NF_TABLES_ARP=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -162,6 +181,7 @@ CONFIG_IP_NF_MATCH_RPFILTER=m
 CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_TARGET_SYNPROXY=m
 CONFIG_IP_NF_TARGET_ULOG=m
 CONFIG_NF_NAT_IPV4=m
 CONFIG_IP_NF_TARGET_MASQUERADE=m
@@ -176,6 +196,9 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_TABLES_IPV6=m
+CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -189,11 +212,13 @@ CONFIG_IP6_NF_MATCH_RT=m
 CONFIG_IP6_NF_TARGET_HL=m
 CONFIG_IP6_NF_FILTER=m
 CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_TARGET_SYNPROXY=m
 CONFIG_IP6_NF_MANGLE=m
 CONFIG_IP6_NF_RAW=m
 CONFIG_NF_NAT_IPV6=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
+CONFIG_NF_TABLES_BRIDGE=m
 CONFIG_IP_DCCP=m
 # CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
@@ -204,9 +229,12 @@ CONFIG_ATALK=m
 CONFIG_DEV_APPLETALK=m
 CONFIG_IPDDP=m
 CONFIG_IPDDP_ENCAP=y
-CONFIG_IPDDP_DECAP=y
+CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
+CONFIG_BATMAN_ADV_NC=y
+CONFIG_NETLINK_DIAG=m
+CONFIG_NET_MPLS_GSO=m
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -229,6 +257,7 @@ CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
+CONFIG_DUMMY_IRQ=m
 CONFIG_IDE=y
 CONFIG_IDE_GD_ATAPI=y
 CONFIG_BLK_DEV_IDECD=y
@@ -289,10 +318,10 @@ CONFIG_MAC_EMUMOUSEBTN=y
 CONFIG_NETDEVICES=y
 CONFIG_DUMMY=m
 CONFIG_EQUALIZER=m
-CONFIG_MII=y
 CONFIG_NET_TEAM=m
 CONFIG_NET_TEAM_MODE_BROADCAST=m
 CONFIG_NET_TEAM_MODE_ROUNDROBIN=m
+CONFIG_NET_TEAM_MODE_RANDOM=m
 CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m
 CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_VXLAN=m
@@ -307,10 +336,10 @@ CONFIG_HPLANCE=y
 CONFIG_MVME147_NET=y
 CONFIG_SUN3LANCE=y
 CONFIG_MACMACE=y
+# CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 CONFIG_MAC89x0=y
-# CONFIG_NET_VENDOR_FUJITSU is not set
 # CONFIG_NET_VENDOR_HP is not set
 CONFIG_BVME6000_NET=y
 CONFIG_MVME16x_NET=y
@@ -324,6 +353,7 @@ CONFIG_APNE=y
 CONFIG_ZORRO8390=y
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PLIP=m
 CONFIG_PPP=m
@@ -356,7 +386,6 @@ CONFIG_INPUT_MISC=y
 CONFIG_INPUT_M68K_BEEP=m
 CONFIG_HP_SDC_RTC=m
 CONFIG_SERIO_Q40KBD=y
-CONFIG_VT_HW_CONSOLE_BINDING=y
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_PMACZILOG=y
@@ -499,11 +528,11 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
+CONFIG_TEST_STRING_HELPERS=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
-CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
@@ -536,6 +565,8 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_LZ4=m
+CONFIG_CRYPTO_LZ4HC=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 6df0acd..02cdbac 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -47,7 +47,6 @@ CONFIG_IP_PNP_RARP=y
 CONFIG_NET_IPIP=m
 CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
-CONFIG_SYN_COOKIES=y
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
@@ -58,11 +57,11 @@ CONFIG_INET_XFRM_MODE_BEET=m
 # CONFIG_INET_LRO is not set
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
-CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
@@ -80,6 +79,17 @@ CONFIG_NF_CONNTRACK_PPTP=m
 CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_EXTHDR=m
+CONFIG_NFT_META=m
+CONFIG_NFT_CT=m
+CONFIG_NFT_RBTREE=m
+CONFIG_NFT_HASH=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_LOG=m
+CONFIG_NFT_LIMIT=m
+CONFIG_NFT_NAT=m
+CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -93,6 +103,7 @@ CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
+CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
@@ -125,6 +136,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m
 CONFIG_NETFILTER_XT_MATCH_RATEEST=m
 CONFIG_NETFILTER_XT_MATCH_REALM=m
 CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
 CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
@@ -139,11 +151,18 @@ CONFIG_IP_SET_HASH_IP=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
+CONFIG_IP_SET_HASH_NETNET=m
 CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_TABLES_IPV4=m
+CONFIG_NFT_REJECT_IPV4=m
+CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
+CONFIG_NF_TABLES_ARP=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -151,6 +170,7 @@ CONFIG_IP_NF_MATCH_RPFILTER=m
 CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_TARGET_SYNPROXY=m
 CONFIG_IP_NF_TARGET_ULOG=m
 CONFIG_NF_NAT_IPV4=m
 CONFIG_IP_NF_TARGET_MASQUERADE=m
@@ -165,6 +185,9 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_TABLES_IPV6=m
+CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -178,11 +201,13 @@ CONFIG_IP6_NF_MATCH_RT=m
 CONFIG_IP6_NF_TARGET_HL=m
 CONFIG_IP6_NF_FILTER=m
 CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_TARGET_SYNPROXY=m
 CONFIG_IP6_NF_MANGLE=m
 CONFIG_IP6_NF_RAW=m
 CONFIG_NF_NAT_IPV6=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
+CONFIG_NF_TABLES_BRIDGE=m
 CONFIG_IP_DCCP=m
 # CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
@@ -190,8 +215,12 @@ CONFIG_RDS=m
 CONFIG_RDS_TCP=m
 CONFIG_L2TP=m
 CONFIG_ATALK=m
+CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
+CONFIG_BATMAN_ADV_NC=y
+CONFIG_NETLINK_DIAG=m
+CONFIG_NET_MPLS_GSO=m
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -204,6 +233,7 @@ CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
+CONFIG_DUMMY_IRQ=m
 CONFIG_RAID_ATTRS=m
 CONFIG_SCSI=y
 CONFIG_SCSI_TGT=m
@@ -241,6 +271,7 @@ CONFIG_EQUALIZER=m
 CONFIG_NET_TEAM=m
 CONFIG_NET_TEAM_MODE_BROADCAST=m
 CONFIG_NET_TEAM_MODE_ROUNDROBIN=m
+CONFIG_NET_TEAM_MODE_RANDOM=m
 CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m
 CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_VXLAN=m
@@ -248,6 +279,7 @@ CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 CONFIG_MVME147_NET=y
+# CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_INTEL is not set
@@ -256,6 +288,7 @@ CONFIG_MVME147_NET=y
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
@@ -388,10 +421,10 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
+CONFIG_TEST_STRING_HELPERS=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
-CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
@@ -424,6 +457,8 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_LZ4=m
+CONFIG_CRYPTO_LZ4HC=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 9cb7e4d..05a990a 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -48,7 +48,6 @@ CONFIG_IP_PNP_RARP=y
 CONFIG_NET_IPIP=m
 CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
-CONFIG_SYN_COOKIES=y
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
@@ -59,11 +58,11 @@ CONFIG_INET_XFRM_MODE_BEET=m
 # CONFIG_INET_LRO is not set
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
-CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
@@ -81,6 +80,17 @@ CONFIG_NF_CONNTRACK_PPTP=m
 CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_EXTHDR=m
+CONFIG_NFT_META=m
+CONFIG_NFT_CT=m
+CONFIG_NFT_RBTREE=m
+CONFIG_NFT_HASH=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_LOG=m
+CONFIG_NFT_LIMIT=m
+CONFIG_NFT_NAT=m
+CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -94,6 +104,7 @@ CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
+CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
@@ -126,6 +137,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m
 CONFIG_NETFILTER_XT_MATCH_RATEEST=m
 CONFIG_NETFILTER_XT_MATCH_REALM=m
 CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
 CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
@@ -140,11 +152,18 @@ CONFIG_IP_SET_HASH_IP=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
+CONFIG_IP_SET_HASH_NETNET=m
 CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_TABLES_IPV4=m
+CONFIG_NFT_REJECT_IPV4=m
+CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
+CONFIG_NF_TABLES_ARP=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -152,6 +171,7 @@ CONFIG_IP_NF_MATCH_RPFILTER=m
 CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_TARGET_SYNPROXY=m
 CONFIG_IP_NF_TARGET_ULOG=m
 CONFIG_NF_NAT_IPV4=m
 CONFIG_IP_NF_TARGET_MASQUERADE=m
@@ -166,6 +186,9 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_TABLES_IPV6=m
+CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -179,11 +202,13 @@ CONFIG_IP6_NF_MATCH_RT=m
 CONFIG_IP6_NF_TARGET_HL=m
 CONFIG_IP6_NF_FILTER=m
 CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_TARGET_SYNPROXY=m
 CONFIG_IP6_NF_MANGLE=m
 CONFIG_IP6_NF_RAW=m
 CONFIG_NF_NAT_IPV6=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
+CONFIG_NF_TABLES_BRIDGE=m
 CONFIG_IP_DCCP=m
 # CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
@@ -191,8 +216,12 @@ CONFIG_RDS=m
 CONFIG_RDS_TCP=m
 CONFIG_L2TP=m
 CONFIG_ATALK=m
+CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
+CONFIG_BATMAN_ADV_NC=y
+CONFIG_NETLINK_DIAG=m
+CONFIG_NET_MPLS_GSO=m
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -205,6 +234,7 @@ CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
+CONFIG_DUMMY_IRQ=m
 CONFIG_RAID_ATTRS=m
 CONFIG_SCSI=y
 CONFIG_SCSI_TGT=m
@@ -242,12 +272,14 @@ CONFIG_EQUALIZER=m
 CONFIG_NET_TEAM=m
 CONFIG_NET_TEAM_MODE_BROADCAST=m
 CONFIG_NET_TEAM_MODE_ROUNDROBIN=m
+CONFIG_NET_TEAM_MODE_RANDOM=m
 CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m
 CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_VXLAN=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
+# CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 CONFIG_MVME16x_NET=y
@@ -256,6 +288,7 @@ CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
@@ -388,11 +421,11 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
+CONFIG_TEST_STRING_HELPERS=m
 CONFIG_EARLY_PRINTK=y
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
-CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
@@ -425,6 +458,8 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_LZ4=m
+CONFIG_CRYPTO_LZ4HC=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index f7bdca0..568e2a9 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -48,7 +48,6 @@ CONFIG_IP_PNP_RARP=y
 CONFIG_NET_IPIP=m
 CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
-CONFIG_SYN_COOKIES=y
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
@@ -59,11 +58,11 @@ CONFIG_INET_XFRM_MODE_BEET=m
 # CONFIG_INET_LRO is not set
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
-CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
@@ -81,6 +80,17 @@ CONFIG_NF_CONNTRACK_PPTP=m
 CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_EXTHDR=m
+CONFIG_NFT_META=m
+CONFIG_NFT_CT=m
+CONFIG_NFT_RBTREE=m
+CONFIG_NFT_HASH=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_LOG=m
+CONFIG_NFT_LIMIT=m
+CONFIG_NFT_NAT=m
+CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -94,6 +104,7 @@ CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
+CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
@@ -126,6 +137,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m
 CONFIG_NETFILTER_XT_MATCH_RATEEST=m
 CONFIG_NETFILTER_XT_MATCH_REALM=m
 CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
 CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
@@ -140,11 +152,18 @@ CONFIG_IP_SET_HASH_IP=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
+CONFIG_IP_SET_HASH_NETNET=m
 CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_TABLES_IPV4=m
+CONFIG_NFT_REJECT_IPV4=m
+CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
+CONFIG_NF_TABLES_ARP=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -152,6 +171,7 @@ CONFIG_IP_NF_MATCH_RPFILTER=m
 CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_TARGET_SYNPROXY=m
 CONFIG_IP_NF_TARGET_ULOG=m
 CONFIG_NF_NAT_IPV4=m
 CONFIG_IP_NF_TARGET_MASQUERADE=m
@@ -166,6 +186,9 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_TABLES_IPV6=m
+CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -179,11 +202,13 @@ CONFIG_IP6_NF_MATCH_RT=m
 CONFIG_IP6_NF_TARGET_HL=m
 CONFIG_IP6_NF_FILTER=m
 CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_TARGET_SYNPROXY=m
 CONFIG_IP6_NF_MANGLE=m
 CONFIG_IP6_NF_RAW=m
 CONFIG_NF_NAT_IPV6=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
+CONFIG_NF_TABLES_BRIDGE=m
 CONFIG_IP_DCCP=m
 # CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
@@ -191,8 +216,12 @@ CONFIG_RDS=m
 CONFIG_RDS_TCP=m
 CONFIG_L2TP=m
 CONFIG_ATALK=m
+CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
+CONFIG_BATMAN_ADV_NC=y
+CONFIG_NETLINK_DIAG=m
+CONFIG_NET_MPLS_GSO=m
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -208,6 +237,7 @@ CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
+CONFIG_DUMMY_IRQ=m
 CONFIG_IDE=y
 CONFIG_IDE_GD_ATAPI=y
 CONFIG_BLK_DEV_IDECD=y
@@ -248,6 +278,7 @@ CONFIG_EQUALIZER=m
 CONFIG_NET_TEAM=m
 CONFIG_NET_TEAM_MODE_BROADCAST=m
 CONFIG_NET_TEAM_MODE_ROUNDROBIN=m
+CONFIG_NET_TEAM_MODE_RANDOM=m
 CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m
 CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_VXLAN=m
@@ -256,10 +287,10 @@ CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 # CONFIG_NET_VENDOR_3COM is not set
 # CONFIG_NET_VENDOR_AMD is not set
+# CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_CIRRUS is not set
-# CONFIG_NET_VENDOR_FUJITSU is not set
 # CONFIG_NET_VENDOR_HP is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
@@ -268,6 +299,7 @@ CONFIG_NE2000=m
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PLIP=m
 CONFIG_PPP=m
@@ -292,7 +324,6 @@ CONFIG_MOUSE_SERIAL=m
 CONFIG_INPUT_MISC=y
 CONFIG_INPUT_M68K_BEEP=m
 CONFIG_SERIO_Q40KBD=y
-CONFIG_VT_HW_CONSOLE_BINDING=y
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 CONFIG_PRINTER=m
@@ -412,10 +443,10 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
+CONFIG_TEST_STRING_HELPERS=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
-CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
@@ -448,6 +479,8 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_LZ4=m
+CONFIG_CRYPTO_LZ4HC=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index e578dd8..60b0aea 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -45,7 +45,6 @@ CONFIG_IP_PNP_RARP=y
 CONFIG_NET_IPIP=m
 CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
-CONFIG_SYN_COOKIES=y
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
@@ -56,11 +55,11 @@ CONFIG_INET_XFRM_MODE_BEET=m
 # CONFIG_INET_LRO is not set
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
-CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
@@ -78,6 +77,17 @@ CONFIG_NF_CONNTRACK_PPTP=m
 CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_EXTHDR=m
+CONFIG_NFT_META=m
+CONFIG_NFT_CT=m
+CONFIG_NFT_RBTREE=m
+CONFIG_NFT_HASH=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_LOG=m
+CONFIG_NFT_LIMIT=m
+CONFIG_NFT_NAT=m
+CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -91,6 +101,7 @@ CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
+CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
@@ -123,6 +134,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m
 CONFIG_NETFILTER_XT_MATCH_RATEEST=m
 CONFIG_NETFILTER_XT_MATCH_REALM=m
 CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
 CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
@@ -137,11 +149,18 @@ CONFIG_IP_SET_HASH_IP=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
+CONFIG_IP_SET_HASH_NETNET=m
 CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_TABLES_IPV4=m
+CONFIG_NFT_REJECT_IPV4=m
+CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
+CONFIG_NF_TABLES_ARP=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -149,6 +168,7 @@ CONFIG_IP_NF_MATCH_RPFILTER=m
 CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_TARGET_SYNPROXY=m
 CONFIG_IP_NF_TARGET_ULOG=m
 CONFIG_NF_NAT_IPV4=m
 CONFIG_IP_NF_TARGET_MASQUERADE=m
@@ -163,6 +183,9 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_TABLES_IPV6=m
+CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -176,11 +199,13 @@ CONFIG_IP6_NF_MATCH_RT=m
 CONFIG_IP6_NF_TARGET_HL=m
 CONFIG_IP6_NF_FILTER=m
 CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_TARGET_SYNPROXY=m
 CONFIG_IP6_NF_MANGLE=m
 CONFIG_IP6_NF_RAW=m
 CONFIG_NF_NAT_IPV6=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
+CONFIG_NF_TABLES_BRIDGE=m
 CONFIG_IP_DCCP=m
 # CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
@@ -188,8 +213,12 @@ CONFIG_RDS=m
 CONFIG_RDS_TCP=m
 CONFIG_L2TP=m
 CONFIG_ATALK=m
+CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
+CONFIG_BATMAN_ADV_NC=y
+CONFIG_NETLINK_DIAG=m
+CONFIG_NET_MPLS_GSO=m
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -202,6 +231,7 @@ CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
+CONFIG_DUMMY_IRQ=m
 CONFIG_RAID_ATTRS=m
 CONFIG_SCSI=y
 CONFIG_SCSI_TGT=m
@@ -239,6 +269,7 @@ CONFIG_EQUALIZER=m
 CONFIG_NET_TEAM=m
 CONFIG_NET_TEAM_MODE_BROADCAST=m
 CONFIG_NET_TEAM_MODE_ROUNDROBIN=m
+CONFIG_NET_TEAM_MODE_RANDOM=m
 CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m
 CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_VXLAN=m
@@ -246,6 +277,7 @@ CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 CONFIG_SUN3LANCE=y
+# CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 CONFIG_SUN3_82586=y
 # CONFIG_NET_VENDOR_MARVELL is not set
@@ -254,6 +286,7 @@ CONFIG_SUN3_82586=y
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
 # CONFIG_NET_VENDOR_SUN is not set
+# CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
@@ -275,7 +308,6 @@ CONFIG_INPUT_EVDEV=m
 CONFIG_KEYBOARD_SUNKBD=y
 # CONFIG_MOUSE_PS2 is not set
 CONFIG_MOUSE_SERIAL=m
-CONFIG_VT_HW_CONSOLE_BINDING=y
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 # CONFIG_HW_RANDOM is not set
@@ -390,10 +422,10 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
+CONFIG_TEST_STRING_HELPERS=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
-CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
@@ -426,6 +458,8 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_LZ4=m
+CONFIG_CRYPTO_LZ4HC=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index f5c91e1..21bda33 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -45,7 +45,6 @@ CONFIG_IP_PNP_RARP=y
 CONFIG_NET_IPIP=m
 CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
-CONFIG_SYN_COOKIES=y
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
@@ -56,11 +55,11 @@ CONFIG_INET_XFRM_MODE_BEET=m
 # CONFIG_INET_LRO is not set
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
-CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
@@ -78,6 +77,17 @@ CONFIG_NF_CONNTRACK_PPTP=m
 CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_EXTHDR=m
+CONFIG_NFT_META=m
+CONFIG_NFT_CT=m
+CONFIG_NFT_RBTREE=m
+CONFIG_NFT_HASH=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_LOG=m
+CONFIG_NFT_LIMIT=m
+CONFIG_NFT_NAT=m
+CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
@@ -91,6 +101,7 @@ CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
+CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
@@ -123,6 +134,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m
 CONFIG_NETFILTER_XT_MATCH_RATEEST=m
 CONFIG_NETFILTER_XT_MATCH_REALM=m
 CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
 CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
@@ -137,11 +149,18 @@ CONFIG_IP_SET_HASH_IP=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
+CONFIG_IP_SET_HASH_NETNET=m
 CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_TABLES_IPV4=m
+CONFIG_NFT_REJECT_IPV4=m
+CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
+CONFIG_NF_TABLES_ARP=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -149,6 +168,7 @@ CONFIG_IP_NF_MATCH_RPFILTER=m
 CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_TARGET_SYNPROXY=m
 CONFIG_IP_NF_TARGET_ULOG=m
 CONFIG_NF_NAT_IPV4=m
 CONFIG_IP_NF_TARGET_MASQUERADE=m
@@ -163,6 +183,9 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_TABLES_IPV6=m
+CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -176,11 +199,13 @@ CONFIG_IP6_NF_MATCH_RT=m
 CONFIG_IP6_NF_TARGET_HL=m
 CONFIG_IP6_NF_FILTER=m
 CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_TARGET_SYNPROXY=m
 CONFIG_IP6_NF_MANGLE=m
 CONFIG_IP6_NF_RAW=m
 CONFIG_NF_NAT_IPV6=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
+CONFIG_NF_TABLES_BRIDGE=m
 CONFIG_IP_DCCP=m
 # CONFIG_IP_DCCP_CCID3 is not set
 CONFIG_SCTP_COOKIE_HMAC_SHA1=y
@@ -188,8 +213,12 @@ CONFIG_RDS=m
 CONFIG_RDS_TCP=m
 CONFIG_L2TP=m
 CONFIG_ATALK=m
+CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
 CONFIG_BATMAN_ADV_DAT=y
+CONFIG_BATMAN_ADV_NC=y
+CONFIG_NETLINK_DIAG=m
+CONFIG_NET_MPLS_GSO=m
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
@@ -202,6 +231,7 @@ CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_ATA_OVER_ETH=m
+CONFIG_DUMMY_IRQ=m
 CONFIG_RAID_ATTRS=m
 CONFIG_SCSI=y
 CONFIG_SCSI_TGT=m
@@ -239,6 +269,7 @@ CONFIG_EQUALIZER=m
 CONFIG_NET_TEAM=m
 CONFIG_NET_TEAM_MODE_BROADCAST=m
 CONFIG_NET_TEAM_MODE_ROUNDROBIN=m
+CONFIG_NET_TEAM_MODE_RANDOM=m
 CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=m
 CONFIG_NET_TEAM_MODE_LOADBALANCE=m
 CONFIG_VXLAN=m
@@ -246,6 +277,7 @@ CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 CONFIG_SUN3LANCE=y
+# CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_INTEL is not set
@@ -254,6 +286,7 @@ CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
@@ -275,7 +308,6 @@ CONFIG_INPUT_EVDEV=m
 CONFIG_KEYBOARD_SUNKBD=y
 # CONFIG_MOUSE_PS2 is not set
 CONFIG_MOUSE_SERIAL=m
-CONFIG_VT_HW_CONSOLE_BINDING=y
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 # CONFIG_HW_RANDOM is not set
@@ -390,10 +422,10 @@ CONFIG_NLS_MAC_TURKISH=m
 CONFIG_DLM=m
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_ASYNC_RAID6_TEST=m
+CONFIG_TEST_STRING_HELPERS=m
 CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_MANAGER=y
 CONFIG_CRYPTO_USER=m
-CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CCM=m
@@ -426,6 +458,8 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_ZLIB=m
 CONFIG_CRYPTO_LZO=m
+CONFIG_CRYPTO_LZ4=m
+CONFIG_CRYPTO_LZ4HC=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
-- 
cgit v0.10.2


From e66d2ae7c67bd9ac982a3d1890564de7f7eabf4b Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Sun, 29 Dec 2013 02:29:30 +0100
Subject: KVM: x86: Fix APIC map calculation after re-enabling

Update arch.apic_base before triggering recalculate_apic_map. Otherwise
the recalculation will work against the previous state of the APIC and
will fail to build the correct map when an APIC is hardware-enabled
again.

This fixes a regression of 1e08ec4a13.

Cc: stable@vger.kernel.org
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index dec48bf..1673940 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1350,6 +1350,10 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 		return;
 	}
 
+	if (!kvm_vcpu_is_bsp(apic->vcpu))
+		value &= ~MSR_IA32_APICBASE_BSP;
+	vcpu->arch.apic_base = value;
+
 	/* update jump label if enable bit changes */
 	if ((vcpu->arch.apic_base ^ value) & MSR_IA32_APICBASE_ENABLE) {
 		if (value & MSR_IA32_APICBASE_ENABLE)
@@ -1359,10 +1363,6 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 		recalculate_apic_map(vcpu->kvm);
 	}
 
-	if (!kvm_vcpu_is_bsp(apic->vcpu))
-		value &= ~MSR_IA32_APICBASE_BSP;
-
-	vcpu->arch.apic_base = value;
 	if ((old_value ^ value) & X2APIC_ENABLE) {
 		if (value & X2APIC_ENABLE) {
 			u32 id = kvm_apic_id(apic);
-- 
cgit v0.10.2


From e098f5cbe9d410e7878b50f524dce36cc83ec40e Mon Sep 17 00:00:00 2001
From: Simon Guinot <sguinot@lacie.com>
Date: Mon, 23 Dec 2013 13:24:35 +0100
Subject: ahci: add PCI ID for Marvell 88SE9170 SATA controller

This patch adds support for the PCI ID provided by the Marvell 88SE9170
SATA controller.

Signed-off-by: Simon Guinot <sguinot@lacie.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: stable@vger.kernel.org

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index c0ed4f27..e3a92a6 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -427,6 +427,9 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	  .driver_data = board_ahci_yes_fbs },			/* 88se9128 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9125),
 	  .driver_data = board_ahci_yes_fbs },			/* 88se9125 */
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_MARVELL_EXT, 0x9178,
+			 PCI_VENDOR_ID_MARVELL_EXT, 0x9170),
+	  .driver_data = board_ahci_yes_fbs },			/* 88se9170 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x917a),
 	  .driver_data = board_ahci_yes_fbs },			/* 88se9172 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x9172),
-- 
cgit v0.10.2


From 98a947abdd54e5de909bebadfced1696ccad30cf Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 31 Dec 2013 13:37:46 +0100
Subject: intel_pstate: Fail initialization if P-state information is missing

If pstate.current_pstate is 0 after the initial
intel_pstate_get_cpu_pstates(), this means that we were unable to
obtain any useful P-state information and there is no reason to
continue, so free memory and return an error in that case.

This fixes the following divide error occuring in a nested KVM
guest:

Intel P-state driver initializing.
Intel pstate controlling: cpu 0
cpufreq: __cpufreq_add_dev: ->get() failed
divide error: 0000 [#1] SMP
Modules linked in:
CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.13.0-0.rc4.git5.1.fc21.x86_64 #1
Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
task: ffff88001ea20000 ti: ffff88001e9bc000 task.ti: ffff88001e9bc000
RIP: 0010:[<ffffffff815c551d>]  [<ffffffff815c551d>] intel_pstate_timer_func+0x11d/0x2b0
RSP: 0000:ffff88001ee03e18  EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffff88001a454348 RCX: 0000000000006100
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
RBP: ffff88001ee03e38 R08: 0000000000000000 R09: 0000000000000000
R10: ffff88001ea20000 R11: 0000000000000000 R12: 00000c0a1ea20000
R13: 1ea200001ea20000 R14: ffffffff815c5400 R15: ffff88001a454348
FS:  0000000000000000(0000) GS:ffff88001ee00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 0000000000000000 CR3: 0000000001c0c000 CR4: 00000000000006f0
Stack:
 fffffffb1a454390 ffffffff821a4500 ffff88001a454390 0000000000000100
 ffff88001ee03ea8 ffffffff81083e9a ffffffff81083e15 ffffffff82d5ed40
 ffffffff8258cc60 0000000000000000 ffffffff81ac39de 0000000000000000
Call Trace:
 <IRQ>
 [<ffffffff81083e9a>] call_timer_fn+0x8a/0x310
 [<ffffffff81083e15>] ? call_timer_fn+0x5/0x310
 [<ffffffff815c5400>] ? pid_param_set+0x130/0x130
 [<ffffffff81084354>] run_timer_softirq+0x234/0x380
 [<ffffffff8107aee4>] __do_softirq+0x104/0x430
 [<ffffffff8107b5fd>] irq_exit+0xcd/0xe0
 [<ffffffff81770645>] smp_apic_timer_interrupt+0x45/0x60
 [<ffffffff8176efb2>] apic_timer_interrupt+0x72/0x80
 <EOI>
 [<ffffffff810e15cd>] ? vprintk_emit+0x1dd/0x5e0
 [<ffffffff81757719>] printk+0x67/0x69
 [<ffffffff815c1493>] __cpufreq_add_dev.isra.13+0x883/0x8d0
 [<ffffffff815c14f0>] cpufreq_add_dev+0x10/0x20
 [<ffffffff814a14d1>] subsys_interface_register+0xb1/0xf0
 [<ffffffff815bf5cf>] cpufreq_register_driver+0x9f/0x210
 [<ffffffff81fb19af>] intel_pstate_init+0x27d/0x3be
 [<ffffffff81761e3e>] ? mutex_unlock+0xe/0x10
 [<ffffffff81fb1732>] ? cpufreq_gov_dbs_init+0x12/0x12
 [<ffffffff8100214a>] do_one_initcall+0xfa/0x1b0
 [<ffffffff8109dbf5>] ? parse_args+0x225/0x3f0
 [<ffffffff81f64193>] kernel_init_freeable+0x1fc/0x287
 [<ffffffff81f638d0>] ? do_early_param+0x88/0x88
 [<ffffffff8174b530>] ? rest_init+0x150/0x150
 [<ffffffff8174b53e>] kernel_init+0xe/0x130
 [<ffffffff8176e27c>] ret_from_fork+0x7c/0xb0
 [<ffffffff8174b530>] ? rest_init+0x150/0x150
Code: c1 e0 05 48 63 bc 03 10 01 00 00 48 63 83 d0 00 00 00 48 63 d6 48 c1 e2 08 c1 e1 08 4c 63 c2 48 c1 e0 08 48 98 48 c1 e0 08 48 99 <49> f7 f8 48 98 48 0f af f8 48 c1 ff 08 29 f9 89 ca c1 fa 1f 89
RIP  [<ffffffff815c551d>] intel_pstate_timer_func+0x11d/0x2b0
 RSP <ffff88001ee03e18>
---[ end trace f166110ed22cc37a ]---
Kernel panic - not syncing: Fatal exception in interrupt

Reported-and-tested-by: Kashyap Chamarthy <kchamart@redhat.com>
Cc: Josh Boyer <jwboyer@fedoraproject.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: All applicable <stable@vger.kernel.org>

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 5f1cbae..f9d561e 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -614,6 +614,11 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 	cpu = all_cpu_data[cpunum];
 
 	intel_pstate_get_cpu_pstates(cpu);
+	if (!cpu->pstate.current_pstate) {
+		all_cpu_data[cpunum] = NULL;
+		kfree(cpu);
+		return -ENODATA;
+	}
 
 	cpu->cpu = cpunum;
 
-- 
cgit v0.10.2


From f244d8b623dae7a7bc695b0336f67729b95a9736 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 31 Dec 2013 13:39:42 +0100
Subject: ACPIPHP / radeon / nouveau: Fix VGA switcheroo problem related to
 hotplug
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The changes in the ACPI-based PCI hotplug (ACPIPHP) subsystem made
during the 3.12 development cycle uncovered a problem with VGA
switcheroo that on some systems, when the device-specific method
(ATPX in the radeon case, _DSM in the nouveau case) is used to turn
off the discrete graphics, the BIOS generates ACPI hotplug events for
that device and those events cause ACPIPHP to attempt to remove the
device from the system (they are events for a device that was present
previously and is not present any more, so that's what should be done
according to the spec).  Then, the system stops functioning correctly.

Since the hotplug events in question were simply silently ignored
previously, the least intrusive way to address that problem is to
make ACPIPHP ignore them again.  For this purpose, introduce a new
ACPI device flag, no_hotplug, and modify ACPIPHP to ignore hotplug
events for PCI devices whose ACPI companions have that flag set.
Next, make the radeon and nouveau switcheroo detection code set the
no_hotplug flag for the discrete graphics' ACPI companion.

Fixes: bbd34fcdd1b2 (ACPI / hotplug / PCI: Register all devices under the given bridge)
References: https://bugzilla.kernel.org/show_bug.cgi?id=61891
References: https://bugzilla.kernel.org/show_bug.cgi?id=64891
Reported-and-tested-by: Mike Lothian <mike@fireburn.co.uk>
Reported-and-tested-by: <madcatx@atlas.cz>
Reported-and-tested-by: Joaquín Aramendía <samsagax@gmail.com>
Cc: Alex Deucher <alexdeucher@gmail.com>
Cc: Dave Airlie <airlied@linux.ie>
Cc: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: 3.12+ <stable@vger.kernel.org> # 3.12+

diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index bba9b72..0710004 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -156,6 +156,16 @@ int acpi_bus_get_private_data(acpi_handle handle, void **data)
 }
 EXPORT_SYMBOL(acpi_bus_get_private_data);
 
+void acpi_bus_no_hotplug(acpi_handle handle)
+{
+	struct acpi_device *adev = NULL;
+
+	acpi_bus_get_device(handle, &adev);
+	if (adev)
+		adev->flags.no_hotplug = true;
+}
+EXPORT_SYMBOL_GPL(acpi_bus_no_hotplug);
+
 static void acpi_print_osc_error(acpi_handle handle,
 	struct acpi_osc_context *context, char *error)
 {
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index 95c7404..ba0183f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -51,6 +51,7 @@ static struct nouveau_dsm_priv {
 	bool dsm_detected;
 	bool optimus_detected;
 	acpi_handle dhandle;
+	acpi_handle other_handle;
 	acpi_handle rom_handle;
 } nouveau_dsm_priv;
 
@@ -260,9 +261,10 @@ static int nouveau_dsm_pci_probe(struct pci_dev *pdev)
 	if (!dhandle)
 		return false;
 
-	if (!acpi_has_method(dhandle, "_DSM"))
+	if (!acpi_has_method(dhandle, "_DSM")) {
+		nouveau_dsm_priv.other_handle = dhandle;
 		return false;
-
+	}
 	if (nouveau_test_dsm(dhandle, nouveau_dsm, NOUVEAU_DSM_POWER))
 		retval |= NOUVEAU_DSM_HAS_MUX;
 
@@ -338,6 +340,16 @@ static bool nouveau_dsm_detect(void)
 		printk(KERN_INFO "VGA switcheroo: detected DSM switching method %s handle\n",
 			acpi_method_name);
 		nouveau_dsm_priv.dsm_detected = true;
+		/*
+		 * On some systems hotplug events are generated for the device
+		 * being switched off when _DSM is executed.  They cause ACPI
+		 * hotplug to trigger and attempt to remove the device from
+		 * the system, which causes it to break down.  Prevent that from
+		 * happening by setting the no_hotplug flag for the involved
+		 * ACPI device objects.
+		 */
+		acpi_bus_no_hotplug(nouveau_dsm_priv.dhandle);
+		acpi_bus_no_hotplug(nouveau_dsm_priv.other_handle);
 		ret = true;
 	}
 
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index 9d302ea..485848f 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -33,6 +33,7 @@ static struct radeon_atpx_priv {
 	bool atpx_detected;
 	/* handle for device - and atpx */
 	acpi_handle dhandle;
+	acpi_handle other_handle;
 	struct radeon_atpx atpx;
 } radeon_atpx_priv;
 
@@ -451,9 +452,10 @@ static bool radeon_atpx_pci_probe_handle(struct pci_dev *pdev)
 		return false;
 
 	status = acpi_get_handle(dhandle, "ATPX", &atpx_handle);
-	if (ACPI_FAILURE(status))
+	if (ACPI_FAILURE(status)) {
+		radeon_atpx_priv.other_handle = dhandle;
 		return false;
-
+	}
 	radeon_atpx_priv.dhandle = dhandle;
 	radeon_atpx_priv.atpx.handle = atpx_handle;
 	return true;
@@ -530,6 +532,16 @@ static bool radeon_atpx_detect(void)
 		printk(KERN_INFO "VGA switcheroo: detected switching method %s handle\n",
 		       acpi_method_name);
 		radeon_atpx_priv.atpx_detected = true;
+		/*
+		 * On some systems hotplug events are generated for the device
+		 * being switched off when ATPX is executed.  They cause ACPI
+		 * hotplug to trigger and attempt to remove the device from
+		 * the system, which causes it to break down.  Prevent that from
+		 * happening by setting the no_hotplug flag for the involved
+		 * ACPI device objects.
+		 */
+		acpi_bus_no_hotplug(radeon_atpx_priv.dhandle);
+		acpi_bus_no_hotplug(radeon_atpx_priv.other_handle);
 		return true;
 	}
 	return false;
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 438a4d0..e864392 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -645,6 +645,24 @@ static void disable_slot(struct acpiphp_slot *slot)
 	slot->flags &= (~SLOT_ENABLED);
 }
 
+static bool acpiphp_no_hotplug(acpi_handle handle)
+{
+	struct acpi_device *adev = NULL;
+
+	acpi_bus_get_device(handle, &adev);
+	return adev && adev->flags.no_hotplug;
+}
+
+static bool slot_no_hotplug(struct acpiphp_slot *slot)
+{
+	struct acpiphp_func *func;
+
+	list_for_each_entry(func, &slot->funcs, sibling)
+		if (acpiphp_no_hotplug(func_to_handle(func)))
+			return true;
+
+	return false;
+}
 
 /**
  * get_slot_status - get ACPI slot status
@@ -703,7 +721,8 @@ static void trim_stale_devices(struct pci_dev *dev)
 		unsigned long long sta;
 
 		status = acpi_evaluate_integer(handle, "_STA", NULL, &sta);
-		alive = ACPI_SUCCESS(status) && sta == ACPI_STA_ALL;
+		alive = (ACPI_SUCCESS(status) && sta == ACPI_STA_ALL)
+			|| acpiphp_no_hotplug(handle);
 	}
 	if (!alive) {
 		u32 v;
@@ -743,8 +762,9 @@ static void acpiphp_check_bridge(struct acpiphp_bridge *bridge)
 		struct pci_dev *dev, *tmp;
 
 		mutex_lock(&slot->crit_sect);
-		/* wake up all functions */
-		if (get_slot_status(slot) == ACPI_STA_ALL) {
+		if (slot_no_hotplug(slot)) {
+			; /* do nothing */
+		} else if (get_slot_status(slot) == ACPI_STA_ALL) {
 			/* remove stale devices if any */
 			list_for_each_entry_safe(dev, tmp, &bus->devices,
 						 bus_list)
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 7b2de02..ca49ebd 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -168,7 +168,8 @@ struct acpi_device_flags {
 	u32 ejectable:1;
 	u32 power_manageable:1;
 	u32 match_driver:1;
-	u32 reserved:27;
+	u32 no_hotplug:1;
+	u32 reserved:26;
 };
 
 /* File System */
@@ -343,6 +344,7 @@ extern struct kobject *acpi_kobj;
 extern int acpi_bus_generate_netlink_event(const char*, const char*, u8, int);
 void acpi_bus_private_data_handler(acpi_handle, void *);
 int acpi_bus_get_private_data(acpi_handle, void **);
+void acpi_bus_no_hotplug(acpi_handle handle);
 extern int acpi_notifier_call_chain(struct acpi_device *, u32, u32);
 extern int register_acpi_notifier(struct notifier_block *);
 extern int unregister_acpi_notifier(struct notifier_block *);
-- 
cgit v0.10.2


From efc5520c4224479967b7381775a63fb48283b082 Mon Sep 17 00:00:00 2001
From: Oren Givon <oren.givon@intel.com>
Date: Thu, 19 Dec 2013 05:07:21 +0200
Subject: iwlwifi: add new devices for 7265 series

Add new device / subdevice ID for 7265 series.
Fix 2 mistakes on the way.

Signed-off-by: Oren Givon <oren.givon@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>

diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c
index 8660502..e627254 100644
--- a/drivers/net/wireless/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/iwlwifi/pcie/drv.c
@@ -357,21 +357,27 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = {
 	{IWL_PCI_DEVICE(0x095B, 0x5310, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095B, 0x5302, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095B, 0x5210, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095B, 0x5012, iwl7265_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x095B, 0x500A, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5012, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x500A, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5410, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5400, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x1010, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5000, iwl7265_2n_cfg)},
 	{IWL_PCI_DEVICE(0x095B, 0x5200, iwl7265_2n_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5002, iwl7265_n_cfg)},
 	{IWL_PCI_DEVICE(0x095B, 0x5202, iwl7265_n_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9010, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x9110, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9210, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x9510, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x9310, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x9410, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5020, iwl7265_2n_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x502A, iwl7265_2n_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5420, iwl7265_2n_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5090, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5190, iwl7265_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x095A, 0x5590, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095B, 0x5290, iwl7265_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x095A, 0x5490, iwl7265_2ac_cfg)},
 #endif /* CONFIG_IWLMVM */
-- 
cgit v0.10.2


From 28a2a2e1aedbe2d8b2301e6e0e4e63f6e4177aca Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Thu, 26 Dec 2013 17:44:29 -0800
Subject: Input: allocate absinfo data when setting ABS capability

We need to make sure we allocate absinfo data when we are setting one of
EV_ABS/ABS_XXX capabilities, otherwise we may bomb when we try to emit this
event.

Rested-by: Paul Cercueil <pcercuei@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>

diff --git a/drivers/input/input.c b/drivers/input/input.c
index 846ccdd..d2965e4 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -1871,6 +1871,10 @@ void input_set_capability(struct input_dev *dev, unsigned int type, unsigned int
 		break;
 
 	case EV_ABS:
+		input_alloc_absinfo(dev);
+		if (!dev->absinfo)
+			return;
+
 		__set_bit(code, dev->absbit);
 		break;
 
-- 
cgit v0.10.2


From 2205369a314e12fcec4781cc73ac9c08fc2b47de Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 31 Dec 2013 16:23:35 -0500
Subject: vlan: Fix header ops passthru when doing TX VLAN offload.

When the vlan code detects that the real device can do TX VLAN offloads
in hardware, it tries to arrange for the real device's header_ops to
be invoked directly.

But it does so illegally, by simply hooking the real device's
header_ops up to the VLAN device.

This doesn't work because we will end up invoking a set of header_ops
routines which expect a device type which matches the real device, but
will see a VLAN device instead.

Fix this by providing a pass-thru set of header_ops which will arrange
to pass the proper real device instead.

To facilitate this add a dev_rebuild_header().  There are
implementations which provide a ->cache and ->create but not a
->rebuild (f.e. PLIP).  So we need a helper function just like
dev_hard_header() to avoid crashes.

Use this helper in the one existing place where the
header_ops->rebuild was being invoked, the neighbour code.

With lots of help from Florian Westphal.

Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d9a550b..7514b9c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1912,6 +1912,15 @@ static inline int dev_parse_header(const struct sk_buff *skb,
 	return dev->header_ops->parse(skb, haddr);
 }
 
+static inline int dev_rebuild_header(struct sk_buff *skb)
+{
+	const struct net_device *dev = skb->dev;
+
+	if (!dev->header_ops || !dev->header_ops->rebuild)
+		return 0;
+	return dev->header_ops->rebuild(skb);
+}
+
 typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len);
 int register_gifconf(unsigned int family, gifconf_func_t *gifconf);
 static inline int unregister_gifconf(unsigned int family)
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 762896e..47c908f 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -530,6 +530,23 @@ static const struct header_ops vlan_header_ops = {
 	.parse	 = eth_header_parse,
 };
 
+static int vlan_passthru_hard_header(struct sk_buff *skb, struct net_device *dev,
+				     unsigned short type,
+				     const void *daddr, const void *saddr,
+				     unsigned int len)
+{
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	struct net_device *real_dev = vlan->real_dev;
+
+	return dev_hard_header(skb, real_dev, type, daddr, saddr, len);
+}
+
+static const struct header_ops vlan_passthru_header_ops = {
+	.create	 = vlan_passthru_hard_header,
+	.rebuild = dev_rebuild_header,
+	.parse	 = eth_header_parse,
+};
+
 static struct device_type vlan_type = {
 	.name	= "vlan",
 };
@@ -573,7 +590,7 @@ static int vlan_dev_init(struct net_device *dev)
 
 	dev->needed_headroom = real_dev->needed_headroom;
 	if (real_dev->features & NETIF_F_HW_VLAN_CTAG_TX) {
-		dev->header_ops      = real_dev->header_ops;
+		dev->header_ops      = &vlan_passthru_header_ops;
 		dev->hard_header_len = real_dev->hard_header_len;
 	} else {
 		dev->header_ops      = &vlan_header_ops;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 36b1443..932c6d7 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1275,7 +1275,7 @@ int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb)
 
 	if (dev_hard_header(skb, dev, ntohs(skb->protocol), NULL, NULL,
 			    skb->len) < 0 &&
-	    dev->header_ops->rebuild(skb))
+	    dev_rebuild_header(skb))
 		return 0;
 
 	return dev_queue_xmit(skb);
-- 
cgit v0.10.2


From 8d88bbffcbac2e7ceba04a9cdff97241b6b5f1db Mon Sep 17 00:00:00 2001
From: Octavian Purdila <octavian.purdila@intel.com>
Date: Mon, 23 Dec 2013 19:06:31 +0200
Subject: usbnet: mcs7830: rework link state detection

Even with the quirks in commit dabdaf0c (mcs7830: Fix link state
detection) there are still spurious link-down events for some chips
where the false link-down events count go over a few hundreds.

This patch takes a more conservative approach and only looks at
link-down events where the link-down state is not combined with other
states (e.g. half/full speed, pending frames in SRAM or TX status
information valid). In all other cases we assume the link is up.

Tested on MCS7830CV-DA (USB ID 9710:7830).

Cc: Ondrej Zary <linux@rainbow-software.org>
Cc: Michael Leun <lkml20120218@newton.leun.net>
Cc: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Octavian Purdila <octavian.purdila@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c
index 03832d3..f546378 100644
--- a/drivers/net/usb/mcs7830.c
+++ b/drivers/net/usb/mcs7830.c
@@ -117,7 +117,6 @@ enum {
 struct mcs7830_data {
 	u8 multi_filter[8];
 	u8 config;
-	u8 link_counter;
 };
 
 static const char driver_name[] = "MOSCHIP usb-ethernet driver";
@@ -561,26 +560,16 @@ static void mcs7830_status(struct usbnet *dev, struct urb *urb)
 {
 	u8 *buf = urb->transfer_buffer;
 	bool link, link_changed;
-	struct mcs7830_data *data = mcs7830_get_data(dev);
 
 	if (urb->actual_length < 16)
 		return;
 
-	link = !(buf[1] & 0x20);
+	link = !(buf[1] == 0x20);
 	link_changed = netif_carrier_ok(dev->net) != link;
 	if (link_changed) {
-		data->link_counter++;
-		/*
-		   track link state 20 times to guard against erroneous
-		   link state changes reported sometimes by the chip
-		 */
-		if (data->link_counter > 20) {
-			data->link_counter = 0;
-			usbnet_link_change(dev, link, 0);
-			netdev_dbg(dev->net, "Link Status is: %d\n", link);
-		}
-	} else
-		data->link_counter = 0;
+		usbnet_link_change(dev, link, 0);
+		netdev_dbg(dev->net, "Link Status is: %d\n", link);
+	}
 }
 
 static const struct driver_info moschip_info = {
-- 
cgit v0.10.2


From efb753b8e0136fe66b507e8e1e42b5a2df7ba44d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Krzysztof=20Ha=C5=82asa?= <khalasa@piap.pl>
Date: Tue, 31 Dec 2013 11:51:16 +0100
Subject: crypto: ixp4xx - Fix kernel compile error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

drivers/crypto/ixp4xx_crypto.c: In function 'ixp_module_init':
drivers/crypto/ixp4xx_crypto.c:1419:2: error: 'dev' undeclared (first use in this function)

Now builds. Not tested on real hw.

Signed-off-by: Krzysztof Hałasa <khalasa@piap.pl>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index 9dd6e01..f757a0f 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -1410,14 +1410,12 @@ static const struct platform_device_info ixp_dev_info __initdata = {
 static int __init ixp_module_init(void)
 {
 	int num = ARRAY_SIZE(ixp4xx_algos);
-	int i, err ;
+	int i, err;
 
 	pdev = platform_device_register_full(&ixp_dev_info);
 	if (IS_ERR(pdev))
 		return PTR_ERR(pdev);
 
-	dev = &pdev->dev;
-
 	spin_lock_init(&desc_lock);
 	spin_lock_init(&emerg_lock);
 
-- 
cgit v0.10.2


From 55c82a6c2a513de1d8a20c3b3a769129a1a14d50 Mon Sep 17 00:00:00 2001
From: Alan <gnomes@lxorguk.ukuu.org.uk>
Date: Wed, 1 Jan 2014 20:13:45 +0000
Subject: sata_sis: missing PM support

sata_sis has no suspend/resume methods. The default ones will do fine and
are needed on some systems.

Signed-off-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

diff --git a/drivers/ata/sata_sis.c b/drivers/ata/sata_sis.c
index fe3ca09..1ad2f62 100644
--- a/drivers/ata/sata_sis.c
+++ b/drivers/ata/sata_sis.c
@@ -83,6 +83,10 @@ static struct pci_driver sis_pci_driver = {
 	.id_table		= sis_pci_tbl,
 	.probe			= sis_init_one,
 	.remove			= ata_pci_remove_one,
+#ifdef CONFIG_PM
+	.suspend		= ata_pci_device_suspend,
+	.resume			= ata_pci_device_resume,
+#endif
 };
 
 static struct scsi_host_template sis_sht = {
-- 
cgit v0.10.2


From b899e698fca1de16921525e347f6e81539fdedcf Mon Sep 17 00:00:00 2001
From: Yaniv Rosner <yanivr@broadcom.com>
Date: Wed, 1 Jan 2014 11:06:41 +0200
Subject: bnx2x: Fix 578xx-KR 1G link

Fix a problem where 578xx-KR is unable to get link when connected to 1G link
partner. Two fixes were required:
One was to force CL37 sync_status low to prevent Warpcore from getting stuck in
CL73 parallel detect loop while link partner is sending.
Second fix was to enable auto-detect mode, thus allowing the Warpcore to select
the higher speed protocol between 10G-KR (over CL73), or go down to 1G over CL73
when there's indication for it.

Signed-off-by: Yaniv Rosner <yanivr@broadcom.com>
Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 20dcc02..efbf729 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -3865,6 +3865,19 @@ static void bnx2x_warpcore_enable_AN_KR(struct bnx2x_phy *phy,
 
 		bnx2x_warpcore_enable_AN_KR2(phy, params, vars);
 	} else {
+		/* Enable Auto-Detect to support 1G over CL37 as well */
+		bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
+				 MDIO_WC_REG_SERDESDIGITAL_CONTROL1000X1, 0x10);
+
+		/* Force cl48 sync_status LOW to avoid getting stuck in CL73
+		 * parallel-detect loop when CL73 and CL37 are enabled.
+		 */
+		CL22_WR_OVER_CL45(bp, phy, MDIO_REG_BANK_AER_BLOCK,
+				  MDIO_AER_BLOCK_AER_REG, 0);
+		bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
+				 MDIO_WC_REG_RXB_ANA_RX_CONTROL_PCI, 0x0800);
+		bnx2x_set_aer_mmd(params, phy);
+
 		bnx2x_disable_kr2(params, vars, phy);
 	}
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
index 3efbb35..14ffb6e 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
@@ -7179,6 +7179,7 @@ Theotherbitsarereservedandshouldbezero*/
 #define MDIO_WC_REG_RX1_PCI_CTRL			0x80ca
 #define MDIO_WC_REG_RX2_PCI_CTRL			0x80da
 #define MDIO_WC_REG_RX3_PCI_CTRL			0x80ea
+#define MDIO_WC_REG_RXB_ANA_RX_CONTROL_PCI		0x80fa
 #define MDIO_WC_REG_XGXSBLK2_UNICORE_MODE_10G		0x8104
 #define MDIO_WC_REG_XGXS_STATUS3			0x8129
 #define MDIO_WC_REG_PAR_DET_10G_STATUS			0x8130
-- 
cgit v0.10.2


From e803d33a32213f2c28456faaa62b2a88f91de2ea Mon Sep 17 00:00:00 2001
From: Yaniv Rosner <yanivr@broadcom.com>
Date: Wed, 1 Jan 2014 11:06:42 +0200
Subject: bnx2x: Fix passive DAC cable detection

Fix Passive DAC detection for specific cables, such that even in case
SFP_CABLE_TECHNOLOGY option is not set in the EEPROM (offset 8), treat it as a
passive DAC cable, since some cables don't have this indication.

Signed-off-by: Yaniv Rosner <yanivr@broadcom.com>
Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index efbf729..000b6ee 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -8133,17 +8133,20 @@ static int bnx2x_get_edc_mode(struct bnx2x_phy *phy,
 				*edc_mode = EDC_MODE_ACTIVE_DAC;
 			else
 				check_limiting_mode = 1;
-		} else if (copper_module_type &
-			SFP_EEPROM_FC_TX_TECH_BITMASK_COPPER_PASSIVE) {
+		} else {
+			*edc_mode = EDC_MODE_PASSIVE_DAC;
+			/* Even in case PASSIVE_DAC indication is not set,
+			 * treat it as a passive DAC cable, since some cables
+			 * don't have this indication.
+			 */
+			if (copper_module_type &
+			    SFP_EEPROM_FC_TX_TECH_BITMASK_COPPER_PASSIVE) {
 				DP(NETIF_MSG_LINK,
 				   "Passive Copper cable detected\n");
-				*edc_mode =
-				      EDC_MODE_PASSIVE_DAC;
-		} else {
-			DP(NETIF_MSG_LINK,
-			   "Unknown copper-cable-type 0x%x !!!\n",
-			   copper_module_type);
-			return -EINVAL;
+			} else {
+				DP(NETIF_MSG_LINK,
+				   "Unknown copper-cable-type\n");
+			}
 		}
 		break;
 	}
-- 
cgit v0.10.2


From a429ec239cbc42dd3b2bc9933745103ca71d2b9d Mon Sep 17 00:00:00 2001
From: Yaniv Rosner <yanivr@broadcom.com>
Date: Wed, 1 Jan 2014 11:06:43 +0200
Subject: bnx2x: Fix Duplex setting for 54618se

BCM54618SE is used to advertise half-duplex even if HD was not requested by the
user. This change makes the legacy speed/duplex advertisement for this PHY
exactly according to the requested speed and duplex.

Signed-off-by: Yaniv Rosner <yanivr@broadcom.com>
Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 000b6ee..68417e1 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -10841,9 +10841,9 @@ static int bnx2x_54618se_config_init(struct bnx2x_phy *phy,
 			   (1<<11));
 
 	if (((phy->req_line_speed == SPEED_AUTO_NEG) &&
-			(phy->speed_cap_mask &
-			PORT_HW_CFG_SPEED_CAPABILITY_D0_1G)) ||
-			(phy->req_line_speed == SPEED_1000)) {
+	     (phy->speed_cap_mask &
+	      PORT_HW_CFG_SPEED_CAPABILITY_D0_1G)) ||
+	    (phy->req_line_speed == SPEED_1000)) {
 		an_1000_val |= (1<<8);
 		autoneg_val |= (1<<9 | 1<<12);
 		if (phy->req_duplex == DUPLEX_FULL)
@@ -10859,30 +10859,32 @@ static int bnx2x_54618se_config_init(struct bnx2x_phy *phy,
 			0x09,
 			&an_1000_val);
 
-	/* Set 100 speed advertisement */
-	if (((phy->req_line_speed == SPEED_AUTO_NEG) &&
-			(phy->speed_cap_mask &
-			(PORT_HW_CFG_SPEED_CAPABILITY_D0_100M_FULL |
-			PORT_HW_CFG_SPEED_CAPABILITY_D0_100M_HALF)))) {
-		an_10_100_val |= (1<<7);
-		/* Enable autoneg and restart autoneg for legacy speeds */
-		autoneg_val |= (1<<9 | 1<<12);
-
-		if (phy->req_duplex == DUPLEX_FULL)
-			an_10_100_val |= (1<<8);
-		DP(NETIF_MSG_LINK, "Advertising 100M\n");
-	}
-
-	/* Set 10 speed advertisement */
-	if (((phy->req_line_speed == SPEED_AUTO_NEG) &&
-			(phy->speed_cap_mask &
-			(PORT_HW_CFG_SPEED_CAPABILITY_D0_10M_FULL |
-			PORT_HW_CFG_SPEED_CAPABILITY_D0_10M_HALF)))) {
-		an_10_100_val |= (1<<5);
-		autoneg_val |= (1<<9 | 1<<12);
-		if (phy->req_duplex == DUPLEX_FULL)
+	/* Advertise 10/100 link speed */
+	if (phy->req_line_speed == SPEED_AUTO_NEG) {
+		if (phy->speed_cap_mask &
+		    PORT_HW_CFG_SPEED_CAPABILITY_D0_10M_HALF) {
+			an_10_100_val |= (1<<5);
+			autoneg_val |= (1<<9 | 1<<12);
+			DP(NETIF_MSG_LINK, "Advertising 10M-HD\n");
+		}
+		if (phy->speed_cap_mask &
+		    PORT_HW_CFG_SPEED_CAPABILITY_D0_10M_FULL) {
 			an_10_100_val |= (1<<6);
-		DP(NETIF_MSG_LINK, "Advertising 10M\n");
+			autoneg_val |= (1<<9 | 1<<12);
+			DP(NETIF_MSG_LINK, "Advertising 10M-FD\n");
+		}
+		if (phy->speed_cap_mask &
+		    PORT_HW_CFG_SPEED_CAPABILITY_D0_100M_HALF) {
+			an_10_100_val |= (1<<7);
+			autoneg_val |= (1<<9 | 1<<12);
+			DP(NETIF_MSG_LINK, "Advertising 100M-HD\n");
+		}
+		if (phy->speed_cap_mask &
+		    PORT_HW_CFG_SPEED_CAPABILITY_D0_100M_FULL) {
+			an_10_100_val |= (1<<8);
+			autoneg_val |= (1<<9 | 1<<12);
+			DP(NETIF_MSG_LINK, "Advertising 100M-FD\n");
+		}
 	}
 
 	/* Only 10/100 are allowed to work in FORCE mode */
-- 
cgit v0.10.2


From ad1d9ef3f736485ba0f49325fa4c73cd1d963853 Mon Sep 17 00:00:00 2001
From: Yaniv Rosner <yanivr@broadcom.com>
Date: Wed, 1 Jan 2014 11:06:44 +0200
Subject: bnx2x: Fix incorrect link-up report

Fix a problem where link is reported to be up when SFP+ module is plugged in
without cable. This occurs with specific module types which may generate
temporary TX_FAULT indication. Solution is to avoid changing any link parameters
when checking TX_FAULT indication while physical link is down.

Signed-off-by: Yaniv Rosner <yanivr@broadcom.com>
Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 68417e1..998cce3 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -13360,6 +13360,10 @@ static u8 bnx2x_analyze_link_error(struct link_params *params,
 	DP(NETIF_MSG_LINK, "Link changed:[%x %x]->%x\n", vars->link_up,
 	   old_status, status);
 
+	/* Do not touch the link in case physical link down */
+	if ((vars->phy_flags & PHY_PHYSICAL_LINK_FLAG) == 0)
+		return 1;
+
 	/* a. Update shmem->link_status accordingly
 	 * b. Update link_vars->link_up
 	 */
-- 
cgit v0.10.2


From f17e9fa5686ac21bce756638ef71160395880928 Mon Sep 17 00:00:00 2001
From: Yaniv Rosner <yanivr@broadcom.com>
Date: Wed, 1 Jan 2014 11:06:45 +0200
Subject: bnx2x: Fix KR2 work-around detection of BCM8073

KR2 work-around is based on detecting non-KR2 devices which may not link up
in this mode. One such link-partner is the BCM8073 which has specific
advertisement characteristics in specific mode, and this condition was not set
correctly.

Signed-off-by: Yaniv Rosner <yanivr@broadcom.com>
Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 998cce3..11fc795 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -13572,7 +13572,7 @@ static void bnx2x_check_kr2_wa(struct link_params *params,
 	 */
 	not_kr2_device = (((base_page & 0x8000) == 0) ||
 			  (((base_page & 0x8000) &&
-			    ((next_page & 0xe0) == 0x2))));
+			    ((next_page & 0xe0) == 0x20))));
 
 	/* In case KR2 is already disabled, check if we need to re-enable it */
 	if (!(vars->link_attr_sync & LINK_ATTR_SYNC_KR2_ENABLE)) {
-- 
cgit v0.10.2


From 7e0309631ecf0cd16edba72ff74747fa1b96ead3 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Wed, 1 Jan 2014 23:04:25 +0100
Subject: net: llc: fix order of evaluation in llc_conn_ac_inc_vr_by_1

Function llc_conn_ac_inc_vr_by_1() evaluates via macro
PDU_GET_NEXT_Vr() into ...

  llc_sk(sk)->vR = ++llc_sk(sk)->vR & 0xffffffffffffff7f

... but the order in which the side effects take place is
undefined because there is no intervening sequence point.

As llc_sk(sk)->vR is written in llc_sk(sk)->vR (assignment
left-hand side) and written in ++llc_sk(sk)->vR & 0xffffffffffffff7f
this might possibly yield undefined behavior.

The final value of llc_sk(sk)->vR is ambiguous, because,
depending on the order of expression evaluation, the
increment may occur before, after, or interleaved with
the assignment. In C, evaluating such an expression yields
undefined behavior.

Since we're doing the increment via PDU_GET_NEXT_Vr() macro
and the only place it is being used is from
llc_conn_ac_inc_vr_by_1(), in order to increment vR by 1
with a follow-up optimized modulo, rewrite the expression
into ((vR + 1) & CONST) in order to fix this.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h
index 31e2de7..c0f0a13 100644
--- a/include/net/llc_pdu.h
+++ b/include/net/llc_pdu.h
@@ -142,7 +142,7 @@
 #define LLC_S_PF_IS_1(pdu)     ((pdu->ctrl_2 & LLC_S_PF_BIT_MASK) ? 1 : 0)
 
 #define PDU_SUPV_GET_Nr(pdu)   ((pdu->ctrl_2 & 0xFE) >> 1)
-#define PDU_GET_NEXT_Vr(sn)    (++sn & ~LLC_2_SEQ_NBR_MODULO)
+#define PDU_GET_NEXT_Vr(sn)    (((sn) + 1) & ~LLC_2_SEQ_NBR_MODULO)
 
 /* FRMR information field macros */
 
-- 
cgit v0.10.2


From c3ac17cd6af2687d5881184edd310a5f9c4baa98 Mon Sep 17 00:00:00 2001
From: Li RongQing <roy.qing.li@gmail.com>
Date: Thu, 2 Jan 2014 08:49:36 +0800
Subject: ipv6: fix the use of pcpu_tstats in sit

when read/write the 64bit data, the correct lock should be hold.

Signed-off-by: Li RongQing <roy.qing.li@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index c874822..d3005b3 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -702,8 +702,10 @@ static int ipip6_rcv(struct sk_buff *skb)
 		}
 
 		tstats = this_cpu_ptr(tunnel->dev->tstats);
+		u64_stats_update_begin(&tstats->syncp);
 		tstats->rx_packets++;
 		tstats->rx_bytes += skb->len;
+		u64_stats_update_end(&tstats->syncp);
 
 		netif_rx(skb);
 
-- 
cgit v0.10.2


From 0b3a2c9968d453d5827e635a6f3d69129f70af66 Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Thu, 2 Jan 2014 19:52:20 +0900
Subject: GFS2: Fix unsafe dereference in dump_holder()

GLOCK_BUG_ON() might call this function without RCU read lock. Make sure that
RCU read lock is held when using task_struct returned from pid_task().

Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index c8420f7..6f7a47c 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1655,6 +1655,7 @@ static int dump_holder(struct seq_file *seq, const struct gfs2_holder *gh)
 	struct task_struct *gh_owner = NULL;
 	char flags_buf[32];
 
+	rcu_read_lock();
 	if (gh->gh_owner_pid)
 		gh_owner = pid_task(gh->gh_owner_pid, PIDTYPE_PID);
 	gfs2_print_dbg(seq, " H: s:%s f:%s e:%d p:%ld [%s] %pS\n",
@@ -1664,6 +1665,7 @@ static int dump_holder(struct seq_file *seq, const struct gfs2_holder *gh)
 		       gh->gh_owner_pid ? (long)pid_nr(gh->gh_owner_pid) : -1,
 		       gh_owner ? gh_owner->comm : "(ended)",
 		       (void *)gh->gh_ip);
+	rcu_read_unlock();
 	return 0;
 }
 
-- 
cgit v0.10.2


From 29bf08f12b2fd72b882da0d85b7385e4a438a297 Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@web.de>
Date: Sat, 28 Dec 2013 16:31:52 +0100
Subject: KVM: nVMX: Unconditionally uninit the MMU on nested vmexit

Three reasons for doing this: 1. arch.walk_mmu points to arch.mmu anyway
in case nested EPT wasn't in use. 2. this aligns VMX with SVM. But 3. is
most important: nested_cpu_has_ept(vmcs12) queries the VMCS page, and if
one guest VCPU manipulates the page of another VCPU in L2, we may be
fooled to skip over the nested_ept_uninit_mmu_context, leaving mmu in
nested state. That can crash the host later on if nested_ept_get_cr3 is
invoked while L1 already left vmxon and nested.current_vmcs12 became
NULL therefore.

Cc: stable@kernel.org
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index b2fe1c2..da7837e 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8283,8 +8283,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
 	kvm_set_cr4(vcpu, vmcs12->host_cr4);
 
-	if (nested_cpu_has_ept(vmcs12))
-		nested_ept_uninit_mmu_context(vcpu);
+	nested_ept_uninit_mmu_context(vcpu);
 
 	kvm_set_cr3(vcpu, vmcs12->host_cr3);
 	kvm_mmu_reset_context(vcpu);
-- 
cgit v0.10.2


From d9c602f033b00ba360a324c0ee5aa59a6838fb40 Mon Sep 17 00:00:00 2001
From: Manish Chopra <manish.chopra@qlogic.com>
Date: Thu, 2 Jan 2014 13:38:43 -0500
Subject: qlcnic: Fix loopback diagnostic test

o Adapter requires that if the port is in loopback mode no traffic should
  be flowing through that port, so on arrival of Link up AEN, do not advertise
  Link up to the stack until port is out of loopback mode

Signed-off-by: Manish Chopra <manish.chopra@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index 631ea0a..4dfef81 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -487,6 +487,7 @@ struct qlcnic_hardware_context {
 	struct qlcnic_mailbox *mailbox;
 	u8 extend_lb_time;
 	u8 phys_port_id[ETH_ALEN];
+	u8 lb_mode;
 };
 
 struct qlcnic_adapter_stats {
@@ -808,6 +809,7 @@ struct qlcnic_mac_list_s {
 
 #define QLCNIC_ILB_MODE		0x1
 #define QLCNIC_ELB_MODE		0x2
+#define QLCNIC_LB_MODE_MASK	0x3
 
 #define QLCNIC_LINKEVENT	0x1
 #define QLCNIC_LB_RESPONSE	0x2
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index 6055d39..f776f99 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -1684,12 +1684,6 @@ int qlcnic_83xx_loopback_test(struct net_device *netdev, u8 mode)
 		}
 	} while ((adapter->ahw->linkup && ahw->has_link_events) != 1);
 
-	/* Make sure carrier is off and queue is stopped during loopback */
-	if (netif_running(netdev)) {
-		netif_carrier_off(netdev);
-		netif_tx_stop_all_queues(netdev);
-	}
-
 	ret = qlcnic_do_lb_test(adapter, mode);
 
 	qlcnic_83xx_clear_lb_mode(adapter, mode);
@@ -2121,6 +2115,7 @@ static void qlcnic_83xx_handle_link_aen(struct qlcnic_adapter *adapter,
 	ahw->link_autoneg = MSB(MSW(data[3]));
 	ahw->module_type = MSB(LSW(data[3]));
 	ahw->has_link_events = 1;
+	ahw->lb_mode = data[4] & QLCNIC_LB_MODE_MASK;
 	qlcnic_advert_link_change(adapter, link_status);
 }
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
index eda6c69..1362976 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
@@ -689,6 +689,10 @@ void qlcnic_advert_link_change(struct qlcnic_adapter *adapter, int linkup)
 		adapter->ahw->linkup = 0;
 		netif_carrier_off(netdev);
 	} else if (!adapter->ahw->linkup && linkup) {
+		/* Do not advertise Link up if the port is in loopback mode */
+		if (qlcnic_83xx_check(adapter) && adapter->ahw->lb_mode)
+			return;
+
 		netdev_info(netdev, "NIC Link is up\n");
 		adapter->ahw->linkup = 1;
 		netif_carrier_on(netdev);
-- 
cgit v0.10.2


From f3e3ccf83bab261c5b55623bd3e9d1147b1c2e19 Mon Sep 17 00:00:00 2001
From: Manish Chopra <manish.chopra@qlogic.com>
Date: Thu, 2 Jan 2014 13:38:44 -0500
Subject: qlcnic: Fix resource allocation for TX queues

o TX queues allocation was getting distributed equally among all the
  functions of the port including VFs and PF. Which was leading to failure
  in PF's multiple TX queues creation.

o Instead of dividing queues equally allocate one TX queue for each VF as VF
  doesn't support multiple TX queues.

Signed-off-by: Manish Chopra <manish.chopra@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
index 686f460..024f816 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
@@ -75,7 +75,6 @@ static int qlcnic_sriov_pf_cal_res_limit(struct qlcnic_adapter *adapter,
 	num_vfs = sriov->num_vfs;
 	max = num_vfs + 1;
 	info->bit_offsets = 0xffff;
-	info->max_tx_ques = res->num_tx_queues / max;
 	info->max_rx_mcast_mac_filters = res->num_rx_mcast_mac_filters;
 	num_vf_macs = QLCNIC_SRIOV_VF_MAX_MAC;
 
@@ -86,6 +85,7 @@ static int qlcnic_sriov_pf_cal_res_limit(struct qlcnic_adapter *adapter,
 		info->max_tx_mac_filters = temp;
 		info->min_tx_bw = 0;
 		info->max_tx_bw = MAX_BW;
+		info->max_tx_ques = res->num_tx_queues - sriov->num_vfs;
 	} else {
 		id = qlcnic_sriov_func_to_index(adapter, func);
 		if (id < 0)
@@ -95,6 +95,7 @@ static int qlcnic_sriov_pf_cal_res_limit(struct qlcnic_adapter *adapter,
 		info->max_tx_bw = vp->max_tx_bw;
 		info->max_rx_ucast_mac_filters = num_vf_macs;
 		info->max_tx_mac_filters = num_vf_macs;
+		info->max_tx_ques = QLCNIC_SINGLE_RING;
 	}
 
 	info->max_rx_ip_addr = res->num_destip / max;
-- 
cgit v0.10.2


From 619a60ee04be33238721a15c1f9704a2a515a33e Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevich@gmail.com>
Date: Thu, 2 Jan 2014 14:39:44 -0500
Subject: sctp: Remove outqueue empty state

The SCTP outqueue structure maintains a data chunks
that are pending transmission, the list of chunks that
are pending a retransmission and a length of data in
flight.  It also tries to keep the emtpy state so that
it can performe shutdown sequence or notify user.

The problem is that the empy state is inconsistently
tracked.  It is possible to completely drain the queue
without sending anything when using PR-SCTP.  In this
case, the empty state will not be correctly state as
report by Jamal Hadi Salim <jhs@mojatatu.com>.  This
can cause an association to be perminantly stuck in the
SHUTDOWN_PENDING state.

Additionally, SCTP is incredibly inefficient when setting
the empty state.  Even though all the data is availaible
in the outqueue structure, we ignore it and walk a list
of trasnports.

In the end, we can completely remove the extra empty
state and figure out if the queue is empty by looking
at 3 things:  length of pending data, length of in-flight
data, and exisiting of retransmit data.  All of these
are already in the strucutre.

Reported-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Vlad Yasevich <vyasevich@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Tested-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 67b5d00..0a248b3 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1046,9 +1046,6 @@ struct sctp_outq {
 
 	/* Corked? */
 	char cork;
-
-	/* Is this structure empty?  */
-	char empty;
 };
 
 void sctp_outq_init(struct sctp_association *, struct sctp_outq *);
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index f51ba98..59268f6 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -208,8 +208,6 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q)
 	INIT_LIST_HEAD(&q->retransmit);
 	INIT_LIST_HEAD(&q->sacked);
 	INIT_LIST_HEAD(&q->abandoned);
-
-	q->empty = 1;
 }
 
 /* Free the outqueue structure and any related pending chunks.
@@ -332,7 +330,6 @@ int sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk)
 				SCTP_INC_STATS(net, SCTP_MIB_OUTUNORDERCHUNKS);
 			else
 				SCTP_INC_STATS(net, SCTP_MIB_OUTORDERCHUNKS);
-			q->empty = 0;
 			break;
 		}
 	} else {
@@ -654,7 +651,6 @@ redo:
 			if (chunk->fast_retransmit == SCTP_NEED_FRTX)
 				chunk->fast_retransmit = SCTP_DONT_FRTX;
 
-			q->empty = 0;
 			q->asoc->stats.rtxchunks++;
 			break;
 		}
@@ -1065,8 +1061,6 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout)
 
 			sctp_transport_reset_timers(transport);
 
-			q->empty = 0;
-
 			/* Only let one DATA chunk get bundled with a
 			 * COOKIE-ECHO chunk.
 			 */
@@ -1275,29 +1269,17 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk)
 		 "advertised peer ack point:0x%x\n", __func__, asoc, ctsn,
 		 asoc->adv_peer_ack_point);
 
-	/* See if all chunks are acked.
-	 * Make sure the empty queue handler will get run later.
-	 */
-	q->empty = (list_empty(&q->out_chunk_list) &&
-		    list_empty(&q->retransmit));
-	if (!q->empty)
-		goto finish;
-
-	list_for_each_entry(transport, transport_list, transports) {
-		q->empty = q->empty && list_empty(&transport->transmitted);
-		if (!q->empty)
-			goto finish;
-	}
-
-	pr_debug("%s: sack queue is empty\n", __func__);
-finish:
-	return q->empty;
+	return sctp_outq_is_empty(q);
 }
 
-/* Is the outqueue empty?  */
+/* Is the outqueue empty?
+ * The queue is empty when we have not pending data, no in-flight data
+ * and nothing pending retransmissions.
+ */
 int sctp_outq_is_empty(const struct sctp_outq *q)
 {
-	return q->empty;
+	return q->out_qlen == 0 && q->outstanding_bytes == 0 &&
+	       list_empty(&q->retransmit);
 }
 
 /********************************************************************
-- 
cgit v0.10.2


From c424be1cbbf852e46acc84d73162af3066cd2c86 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Thu, 2 Jan 2014 12:58:43 -0800
Subject: mm: munlock: fix a bug where THP tail page is encountered

Since commit ff6a6da60b89 ("mm: accelerate munlock() treatment of THP
pages") munlock skips tail pages of a munlocked THP page.  However, when
the head page already has PageMlocked unset, it will not skip the tail
pages.

Commit 7225522bb429 ("mm: munlock: batch non-THP page isolation and
munlock+putback using pagevec") has added a PageTransHuge() check which
contains VM_BUG_ON(PageTail(page)).  Sasha Levin found this triggered
using trinity, on the first tail page of a THP page without PageMlocked
flag.

This patch fixes the issue by skipping tail pages also in the case when
PageMlocked flag is unset.  There is still a possibility of race with
THP page split between clearing PageMlocked and determining how many
pages to skip.  The race might result in former tail pages not being
skipped, which is however no longer a bug, as during the skip the
PageTail flags are cleared.

However this race also affects correctness of NR_MLOCK accounting, which
is to be fixed in a separate patch.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/mlock.c b/mm/mlock.c
index d480cd6..c59c420 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -133,7 +133,10 @@ static void __munlock_isolation_failed(struct page *page)
 
 /**
  * munlock_vma_page - munlock a vma page
- * @page - page to be unlocked
+ * @page - page to be unlocked, either a normal page or THP page head
+ *
+ * returns the size of the page as a page mask (0 for normal page,
+ *         HPAGE_PMD_NR - 1 for THP head page)
  *
  * called from munlock()/munmap() path with page supposedly on the LRU.
  * When we munlock a page, because the vma where we found the page is being
@@ -148,21 +151,30 @@ static void __munlock_isolation_failed(struct page *page)
  */
 unsigned int munlock_vma_page(struct page *page)
 {
-	unsigned int page_mask = 0;
+	unsigned int nr_pages;
 
 	BUG_ON(!PageLocked(page));
 
 	if (TestClearPageMlocked(page)) {
-		unsigned int nr_pages = hpage_nr_pages(page);
+		nr_pages = hpage_nr_pages(page);
 		mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
-		page_mask = nr_pages - 1;
 		if (!isolate_lru_page(page))
 			__munlock_isolated_page(page);
 		else
 			__munlock_isolation_failed(page);
+	} else {
+		nr_pages = hpage_nr_pages(page);
 	}
 
-	return page_mask;
+	/*
+	 * Regardless of the original PageMlocked flag, we determine nr_pages
+	 * after touching the flag. This leaves a possible race with a THP page
+	 * split, such that a whole THP page was munlocked, but nr_pages == 1.
+	 * Returning a smaller mask due to that is OK, the worst that can
+	 * happen is subsequent useless scanning of the former tail pages.
+	 * The NR_MLOCK accounting can however become broken.
+	 */
+	return nr_pages - 1;
 }
 
 /**
@@ -440,7 +452,8 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 
 	while (start < end) {
 		struct page *page = NULL;
-		unsigned int page_mask, page_increm;
+		unsigned int page_mask;
+		unsigned long page_increm;
 		struct pagevec pvec;
 		struct zone *zone;
 		int zoneid;
@@ -490,7 +503,9 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 				goto next;
 			}
 		}
-		page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
+		/* It's a bug to munlock in the middle of a THP page */
+		VM_BUG_ON((start >> PAGE_SHIFT) & page_mask);
+		page_increm = 1 + page_mask;
 		start += page_increm * PAGE_SIZE;
 next:
 		cond_resched();
-- 
cgit v0.10.2


From 3b25df93c6e37e323b86a2a8c1e00c0a2821c6c9 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Thu, 2 Jan 2014 12:58:44 -0800
Subject: mm: munlock: fix deadlock in __munlock_pagevec()

Commit 7225522bb429 ("mm: munlock: batch non-THP page isolation and
munlock+putback using pagevec" introduced __munlock_pagevec() to speed
up munlock by holding lru_lock over multiple isolated pages.  Pages that
fail to be isolated are put_page()d immediately, also within the lock.

This can lead to deadlock when __munlock_pagevec() becomes the holder of
the last page pin and put_page() leads to __page_cache_release() which
also locks lru_lock.  The deadlock has been observed by Sasha Levin
using trinity.

This patch avoids the deadlock by deferring put_page() operations until
lru_lock is released.  Another pagevec (which is also used by later
phases of the function is reused to gather the pages for put_page()
operation.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/mlock.c b/mm/mlock.c
index c59c420..192e6ee 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -298,10 +298,12 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 {
 	int i;
 	int nr = pagevec_count(pvec);
-	int delta_munlocked = -nr;
+	int delta_munlocked;
 	struct pagevec pvec_putback;
 	int pgrescued = 0;
 
+	pagevec_init(&pvec_putback, 0);
+
 	/* Phase 1: page isolation */
 	spin_lock_irq(&zone->lru_lock);
 	for (i = 0; i < nr; i++) {
@@ -330,18 +332,21 @@ skip_munlock:
 			/*
 			 * We won't be munlocking this page in the next phase
 			 * but we still need to release the follow_page_mask()
-			 * pin.
+			 * pin. We cannot do it under lru_lock however. If it's
+			 * the last pin, __page_cache_release would deadlock.
 			 */
+			pagevec_add(&pvec_putback, pvec->pages[i]);
 			pvec->pages[i] = NULL;
-			put_page(page);
-			delta_munlocked++;
 		}
 	}
+	delta_munlocked = -nr + pagevec_count(&pvec_putback);
 	__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
 	spin_unlock_irq(&zone->lru_lock);
 
+	/* Now we can release pins of pages that we are not munlocking */
+	pagevec_release(&pvec_putback);
+
 	/* Phase 2: page munlock */
-	pagevec_init(&pvec_putback, 0);
 	for (i = 0; i < nr; i++) {
 		struct page *page = pvec->pages[i];
 
-- 
cgit v0.10.2


From 4eb919825e6c3c7fb3630d5621f6d11e98a18b3a Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Thu, 2 Jan 2014 12:58:46 -0800
Subject: mm: fix use-after-free in sys_remap_file_pages

remap_file_pages calls mmap_region, which may merge the VMA with other
existing VMAs, and free "vma".  This can lead to a use-after-free bug.
Avoid the bug by remembering vm_flags before calling mmap_region, and
not trying to dereference vma later.

Signed-off-by: Rik van Riel <riel@redhat.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Cc: PaX Team <pageexec@freemail.hu>
Cc: Kees Cook <keescook@chromium.org>
Cc: Michel Lespinasse <walken@google.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/fremap.c b/mm/fremap.c
index 5bff081..bbc4d66 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -208,9 +208,10 @@ get_write_lock:
 		if (mapping_cap_account_dirty(mapping)) {
 			unsigned long addr;
 			struct file *file = get_file(vma->vm_file);
+			/* mmap_region may free vma; grab the info now */
+			vm_flags = vma->vm_flags;
 
-			addr = mmap_region(file, start, size,
-					vma->vm_flags, pgoff);
+			addr = mmap_region(file, start, size, vm_flags, pgoff);
 			fput(file);
 			if (IS_ERR_VALUE(addr)) {
 				err = addr;
@@ -218,7 +219,7 @@ get_write_lock:
 				BUG_ON(addr != start);
 				err = 0;
 			}
-			goto out;
+			goto out_freed;
 		}
 		mutex_lock(&mapping->i_mmap_mutex);
 		flush_dcache_mmap_lock(mapping);
@@ -253,6 +254,7 @@ get_write_lock:
 out:
 	if (vma)
 		vm_flags = vma->vm_flags;
+out_freed:
 	if (likely(!has_write_lock))
 		up_read(&mm->mmap_sem);
 	else
-- 
cgit v0.10.2


From 695c60830764945cf61a2cc623eb1392d137223e Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov@parallels.com>
Date: Thu, 2 Jan 2014 12:58:47 -0800
Subject: memcg: fix memcg_size() calculation

The mem_cgroup structure contains nr_node_ids pointers to
mem_cgroup_per_node objects, not the objects themselves.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Glauber Costa <glommer@openvz.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index bf5e894..7f1a356 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -338,7 +338,7 @@ struct mem_cgroup {
 static size_t memcg_size(void)
 {
 	return sizeof(struct mem_cgroup) +
-		nr_node_ids * sizeof(struct mem_cgroup_per_node);
+		nr_node_ids * sizeof(struct mem_cgroup_per_node *);
 }
 
 /* internal only representation about the status of kmem accounting. */
-- 
cgit v0.10.2


From d0319bd52e373c661f9bc0c04dec85d6f87ac517 Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@suse.de>
Date: Thu, 2 Jan 2014 12:58:49 -0800
Subject: mm: remove bogus warning in copy_huge_pmd()

Sasha Levin reported the following warning being triggered

  WARNING: CPU: 28 PID: 35287 at mm/huge_memory.c:887 copy_huge_pmd+0x145/ 0x3a0()
  Call Trace:
    copy_huge_pmd+0x145/0x3a0
    copy_page_range+0x3f2/0x560
    dup_mmap+0x2c9/0x3d0
    dup_mm+0xad/0x150
    copy_process+0xa68/0x12e0
    do_fork+0x96/0x270
    SyS_clone+0x16/0x20
    stub_clone+0x69/0x90

This warning was introduced by "mm: numa: Avoid unnecessary disruption
of NUMA hinting during migration" for paranoia reasons but the warning
is bogus.  I was thinking of parallel races between NUMA hinting faults
and forks but this warning would also be triggered by a parallel reclaim
splitting a THP during a fork.  Remote the bogus warning.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Cc: Alex Thorlton <athorlton@sgi.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 7de1bf8..9c0b172 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -883,9 +883,6 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		goto out_unlock;
 	}
 
-	/* mmap_sem prevents this happening but warn if that changes */
-	WARN_ON(pmd_trans_migrating(pmd));
-
 	if (unlikely(pmd_trans_splitting(pmd))) {
 		/* split huge page running from under us */
 		spin_unlock(src_ptl);
-- 
cgit v0.10.2


From c2fd4e38032239746badb0e21d72c3a00438feac Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@xilinx.com>
Date: Thu, 2 Jan 2014 12:58:50 -0800
Subject: MAINTAINERS: set up proper record for Xilinx Zynq

Setup correct zynq entry.
 - Add missing cadence_ttc_timer maintainership
 - Add zynq wildcard
 - Add xilinx wildcard

Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/MAINTAINERS b/MAINTAINERS
index 21c038f..6c20792 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1368,6 +1368,9 @@ T:	git git://git.xilinx.com/linux-xlnx.git
 S:	Supported
 F:	arch/arm/mach-zynq/
 F:	drivers/cpuidle/cpuidle-zynq.c
+N:	zynq
+N:	xilinx
+F:	drivers/clocksource/cadence_ttc_timer.c
 
 ARM SMMU DRIVER
 M:	Will Deacon <will.deacon@arm.com>
-- 
cgit v0.10.2


From a3e0f9e47d5ef7858a26cc12d90ad5146e802d47 Mon Sep 17 00:00:00 2001
From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Date: Thu, 2 Jan 2014 12:58:51 -0800
Subject: mm/memory-failure.c: transfer page count from head page to tail page
 after split thp

Memory failures on thp tail pages cause kernel panic like below:

   mce: [Hardware Error]: Machine check events logged
   MCE exception done on CPU 7
   BUG: unable to handle kernel NULL pointer dereference at 0000000000000058
   IP: [<ffffffff811b7cd1>] dequeue_hwpoisoned_huge_page+0x131/0x1e0
   PGD bae42067 PUD ba47d067 PMD 0
   Oops: 0000 [#1] SMP
  ...
   CPU: 7 PID: 128 Comm: kworker/7:2 Tainted: G   M       O 3.13.0-rc4-131217-1558-00003-g83b7df08e462 #25
  ...
   Call Trace:
     me_huge_page+0x3e/0x50
     memory_failure+0x4bb/0xc20
     mce_process_work+0x3e/0x70
     process_one_work+0x171/0x420
     worker_thread+0x11b/0x3a0
     ? manage_workers.isra.25+0x2b0/0x2b0
     kthread+0xe4/0x100
     ? kthread_create_on_node+0x190/0x190
     ret_from_fork+0x7c/0xb0
     ? kthread_create_on_node+0x190/0x190
  ...
   RIP   dequeue_hwpoisoned_huge_page+0x131/0x1e0
   CR2: 0000000000000058

The reasoning of this problem is shown below:
 - when we have a memory error on a thp tail page, the memory error
   handler grabs a refcount of the head page to keep the thp under us.
 - Before unmapping the error page from processes, we split the thp,
   where page refcounts of both of head/tail pages don't change.
 - Then we call try_to_unmap() over the error page (which was a tail
   page before). We didn't pin the error page to handle the memory error,
   this error page is freed and removed from LRU list.
 - We never have the error page on LRU list, so the first page state
   check returns "unknown page," then we move to the second check
   with the saved page flag.
 - The saved page flag have PG_tail set, so the second page state check
   returns "hugepage."
 - We call me_huge_page() for freed error page, then we hit the above panic.

The root cause is that we didn't move refcount from the head page to the
tail page after split thp.  So this patch suggests to do this.

This panic was introduced by commit 524fca1e73 ("HWPOISON: fix
misjudgement of page_action() for errors on mlocked pages").  Note that we
did have the same refcount problem before this commit, but it was just
ignored because we had only first page state check which returned "unknown
page." The commit changed the refcount problem from "doesn't work" to
"kernel panic."

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Reviewed-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: <stable@vger.kernel.org>	[3.9+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index db08af9..fabe550 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -938,6 +938,16 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 				BUG_ON(!PageHWPoison(p));
 				return SWAP_FAIL;
 			}
+			/*
+			 * We pinned the head page for hwpoison handling,
+			 * now we split the thp and we are interested in
+			 * the hwpoisoned raw page, so move the refcount
+			 * to it.
+			 */
+			if (hpage != p) {
+				put_page(hpage);
+				get_page(p);
+			}
 			/* THP is split, so ppage should be the real poisoned page. */
 			ppage = p;
 		}
-- 
cgit v0.10.2


From 3532e5660fa4b610b982fe5c09d3e8ab065c55dc Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Thu, 2 Jan 2014 12:58:52 -0800
Subject: drivers/dma/ioat/dma.c: check DMA mapping error in
 ioat_dma_self_test()

Check DMA mapping return values in function ioat_dma_self_test() to get
rid of following warning message.

  ------------[ cut here ]------------
  WARNING: CPU: 0 PID: 1203 at lib/dma-debug.c:937 check_unmap+0x4c0/0x9a0()
  ioatdma 0000:00:04.0: DMA-API: device driver failed to check map error[device address=0x000000085191b000] [size=2000 bytes] [mapped as single]
  Modules linked in: ioatdma(+) mac_hid wmi acpi_pad lp parport hidd_generic usbhid hid ixgbe isci dca libsas ahci ptp libahci scsi_transport_sas meegaraid_sas pps_core mdio
  CPU: 0 PID: 1203 Comm: systemd-udevd Not tainted 3.13.0-rc4+ #8
  Hardware name: Intel Corporation BRICKLAND/BRICKLAND, BIOS BRIVTIIN1.86B.0044.L09.1311181644 11/18/2013
  Call Trace:
    dump_stack+0x4d/0x66
    warn_slowpath_common+0x7d/0xa0
    warn_slowpath_fmt+0x4c/0x50
    check_unmap+0x4c0/0x9a0
    debug_dma_unmap_page+0x81/0x90
    ioat_dma_self_test+0x3d2/0x680 [ioatdma]
    ioat3_dma_self_test+0x12/0x30 [ioatdma]
    ioat_probe+0xf4/0x110 [ioatdma]
    ioat3_dma_probe+0x268/0x410 [ioatdma]
    ioat_pci_probe+0x122/0x1b0 [ioatdma]
    local_pci_probe+0x45/0xa0
    pci_device_probe+0xd9/0x130
    driver_probe_device+0x171/0x490
    __driver_attach+0x93/0xa0
    bus_for_each_dev+0x6b/0xb0
    driver_attach+0x1e/0x20
    bus_add_driver+0x1f8/0x2b0
    driver_register+0x81/0x110
    __pci_register_driver+0x60/0x70
    ioat_init_module+0x89/0x1000 [ioatdma]
    do_one_initcall+0xe2/0x250
    load_module+0x2313/0x2a00
    SyS_init_module+0xd9/0x130
    system_call_fastpath+0x1a/0x1f
  ---[ end trace 990c591681d27c31 ]---
  Mapped at:
    debug_dma_map_page+0xbe/0x180
    ioat_dma_self_test+0x1ab/0x680 [ioatdma]
    ioat3_dma_self_test+0x12/0x30 [ioatdma]
    ioat_probe+0xf4/0x110 [ioatdma]
    ioat3_dma_probe+0x268/0x410 [ioatdma]

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Vinod Koul <vinod.koul@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Cc: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 1a49c7776..8752918 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -817,7 +817,15 @@ int ioat_dma_self_test(struct ioatdma_device *device)
 	}
 
 	dma_src = dma_map_single(dev, src, IOAT_TEST_SIZE, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, dma_src)) {
+		dev_err(dev, "mapping src buffer failed\n");
+		goto free_resources;
+	}
 	dma_dest = dma_map_single(dev, dest, IOAT_TEST_SIZE, DMA_FROM_DEVICE);
+	if (dma_mapping_error(dev, dma_dest)) {
+		dev_err(dev, "mapping dest buffer failed\n");
+		goto unmap_src;
+	}
 	flags = DMA_PREP_INTERRUPT;
 	tx = device->common.device_prep_dma_memcpy(dma_chan, dma_dest, dma_src,
 						   IOAT_TEST_SIZE, flags);
@@ -855,8 +863,9 @@ int ioat_dma_self_test(struct ioatdma_device *device)
 	}
 
 unmap_dma:
-	dma_unmap_single(dev, dma_src, IOAT_TEST_SIZE, DMA_TO_DEVICE);
 	dma_unmap_single(dev, dma_dest, IOAT_TEST_SIZE, DMA_FROM_DEVICE);
+unmap_src:
+	dma_unmap_single(dev, dma_src, IOAT_TEST_SIZE, DMA_TO_DEVICE);
 free_resources:
 	dma->device_free_chan_resources(dma_chan);
 out:
-- 
cgit v0.10.2


From ad70b029d2c678386384bd72c7fa2705c449b518 Mon Sep 17 00:00:00 2001
From: Nobuhiro Iwamatsu <nobuhiro.iwamatsu.yj@renesas.com>
Date: Thu, 2 Jan 2014 12:58:53 -0800
Subject: sh: add EXPORT_SYMBOL(min_low_pfn) and EXPORT_SYMBOL(max_low_pfn) to
 sh_ksyms_32.c

Min_low_pfn and max_low_pfn were used in pfn_valid macro if defined
CONFIG_FLATMEM.  When the functions that use the pfn_valid is used in
driver module, max_low_pfn and min_low_pfn is to undefined, and fail to
build.

  ERROR: "min_low_pfn" [drivers/block/aoe/aoe.ko] undefined!
  ERROR: "max_low_pfn" [drivers/block/aoe/aoe.ko] undefined!
  make[2]: *** [__modpost] Error 1
  make[1]: *** [modules] Error 2

This patch fix this problem.

Signed-off-by: Nobuhiro Iwamatsu <nobuhiro.iwamatsu.yj@renesas.com>
Cc: Kuninori Morimoto <kuninori.morimoto.gx@gmail.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/sh/kernel/sh_ksyms_32.c b/arch/sh/kernel/sh_ksyms_32.c
index 2a0a596..d77f2f6 100644
--- a/arch/sh/kernel/sh_ksyms_32.c
+++ b/arch/sh/kernel/sh_ksyms_32.c
@@ -20,6 +20,11 @@ EXPORT_SYMBOL(csum_partial_copy_generic);
 EXPORT_SYMBOL(copy_page);
 EXPORT_SYMBOL(__clear_user);
 EXPORT_SYMBOL(empty_zero_page);
+#ifdef CONFIG_FLATMEM
+/* need in pfn_valid macro */
+EXPORT_SYMBOL(min_low_pfn);
+EXPORT_SYMBOL(max_low_pfn);
+#endif
 
 #define DECLARE_EXPORT(name)		\
 	extern void name(void);EXPORT_SYMBOL(name)
-- 
cgit v0.10.2


From 4ff36ee94d93ddb4b7846177f1118d9aa33408e2 Mon Sep 17 00:00:00 2001
From: Jason Baron <jbaron@akamai.com>
Date: Thu, 2 Jan 2014 12:58:54 -0800
Subject: epoll: do not take the nested ep->mtx on EPOLL_CTL_DEL

The EPOLL_CTL_DEL path of epoll contains a classic, ab-ba deadlock.
That is, epoll_ctl(a, EPOLL_CTL_DEL, b, x), will deadlock with
epoll_ctl(b, EPOLL_CTL_DEL, a, x).  The deadlock was introduced with
commmit 67347fe4e632 ("epoll: do not take global 'epmutex' for simple
topologies").

The acquistion of the ep->mtx for the destination 'ep' was added such
that a concurrent EPOLL_CTL_ADD operation would see the correct state of
the ep (Specifically, the check for '!list_empty(&f.file->f_ep_links')

However, by simply not acquiring the lock, we do not serialize behind
the ep->mtx from the add path, and thus may perform a full path check
when if we had waited a little longer it may not have been necessary.
However, this is a transient state, and performing the full loop
checking in this case is not harmful.

The important point is that we wouldn't miss doing the full loop
checking when required, since EPOLL_CTL_ADD always locks any 'ep's that
its operating upon.  The reason we don't need to do lock ordering in the
add path, is that we are already are holding the global 'epmutex'
whenever we do the double lock.  Further, the original posting of this
patch, which was tested for the intended performance gains, did not
perform this additional locking.

Signed-off-by: Jason Baron <jbaron@akamai.com>
Cc: Nathan Zimmer <nzimmer@sgi.com>
Cc: Eric Wong <normalperson@yhbt.net>
Cc: Nelson Elhage <nelhage@nelhage.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Davide Libenzi <davidel@xmailserver.org>
Cc: "Paul E. McKenney" <paulmck@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 8b5e258..af90312 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1907,10 +1907,6 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 			}
 		}
 	}
-	if (op == EPOLL_CTL_DEL && is_file_epoll(tf.file)) {
-		tep = tf.file->private_data;
-		mutex_lock_nested(&tep->mtx, 1);
-	}
 
 	/*
 	 * Try to lookup the file inside our RB tree, Since we grabbed "mtx"
-- 
cgit v0.10.2


From 7a7ffbabf99445704be01bff5d7e360da908cf8e Mon Sep 17 00:00:00 2001
From: Wei-Chun Chao <weichunc@plumgrid.com>
Date: Thu, 26 Dec 2013 13:10:22 -0800
Subject: ipv4: fix tunneled VM traffic over hw VXLAN/GRE GSO NIC

VM to VM GSO traffic is broken if it goes through VXLAN or GRE
tunnel and the physical NIC on the host supports hardware VXLAN/GRE
GSO offload (e.g. bnx2x and next-gen mlx4).

Two issues -
(VXLAN) VM traffic has SKB_GSO_DODGY and SKB_GSO_UDP_TUNNEL with
SKB_GSO_TCP/UDP set depending on the inner protocol. GSO header
integrity check fails in udp4_ufo_fragment if inner protocol is
TCP. Also gso_segs is calculated incorrectly using skb->len that
includes tunnel header. Fix: robust check should only be applied
to the inner packet.

(VXLAN & GRE) Once GSO header integrity check passes, NULL segs
is returned and the original skb is sent to hardware. However the
tunnel header is already pulled. Fix: tunnel header needs to be
restored so that hardware can perform GSO properly on the original
packet.

Signed-off-by: Wei-Chun Chao <weichunc@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7514b9c..5faaadb 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3017,6 +3017,19 @@ static inline void netif_set_gso_max_size(struct net_device *dev,
 	dev->gso_max_size = size;
 }
 
+static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol,
+					int pulled_hlen, u16 mac_offset,
+					int mac_len)
+{
+	skb->protocol = protocol;
+	skb->encapsulation = 1;
+	skb_push(skb, pulled_hlen);
+	skb_reset_transport_header(skb);
+	skb->mac_header = mac_offset;
+	skb->network_header = skb->mac_header + mac_len;
+	skb->mac_len = mac_len;
+}
+
 static inline bool netif_is_macvlan(struct net_device *dev)
 {
 	return dev->priv_flags & IFF_MACVLAN;
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index e5d4361..2cd02f3 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -28,6 +28,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 	netdev_features_t enc_features;
 	int ghl = GRE_HEADER_SECTION;
 	struct gre_base_hdr *greh;
+	u16 mac_offset = skb->mac_header;
 	int mac_len = skb->mac_len;
 	__be16 protocol = skb->protocol;
 	int tnl_hlen;
@@ -58,13 +59,13 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 	} else
 		csum = false;
 
+	if (unlikely(!pskb_may_pull(skb, ghl)))
+		goto out;
+
 	/* setup inner skb. */
 	skb->protocol = greh->protocol;
 	skb->encapsulation = 0;
 
-	if (unlikely(!pskb_may_pull(skb, ghl)))
-		goto out;
-
 	__skb_pull(skb, ghl);
 	skb_reset_mac_header(skb);
 	skb_set_network_header(skb, skb_inner_network_offset(skb));
@@ -73,8 +74,10 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
 	/* segment inner packet. */
 	enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
 	segs = skb_mac_gso_segment(skb, enc_features);
-	if (!segs || IS_ERR(segs))
+	if (!segs || IS_ERR(segs)) {
+		skb_gso_error_unwind(skb, protocol, ghl, mac_offset, mac_len);
 		goto out;
+	}
 
 	skb = segs;
 	tnl_hlen = skb_tnl_header_len(skb);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index f140048..a7e4729 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2478,6 +2478,7 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 				       netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	u16 mac_offset = skb->mac_header;
 	int mac_len = skb->mac_len;
 	int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
 	__be16 protocol = skb->protocol;
@@ -2497,8 +2498,11 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
 	/* segment inner packet. */
 	enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
 	segs = skb_mac_gso_segment(skb, enc_features);
-	if (!segs || IS_ERR(segs))
+	if (!segs || IS_ERR(segs)) {
+		skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset,
+				     mac_len);
 		goto out;
+	}
 
 	outer_hlen = skb_tnl_header_len(skb);
 	skb = segs;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 83206de..79c62bd 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -41,6 +41,14 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	unsigned int mss;
+	int offset;
+	__wsum csum;
+
+	if (skb->encapsulation &&
+	    skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL) {
+		segs = skb_udp_tunnel_segment(skb, features);
+		goto out;
+	}
 
 	mss = skb_shinfo(skb)->gso_size;
 	if (unlikely(skb->len <= mss))
@@ -63,27 +71,20 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 		goto out;
 	}
 
+	/* Do software UFO. Complete and fill in the UDP checksum as
+	 * HW cannot do checksum of UDP packets sent as multiple
+	 * IP fragments.
+	 */
+	offset = skb_checksum_start_offset(skb);
+	csum = skb_checksum(skb, offset, skb->len - offset, 0);
+	offset += skb->csum_offset;
+	*(__sum16 *)(skb->data + offset) = csum_fold(csum);
+	skb->ip_summed = CHECKSUM_NONE;
+
 	/* Fragment the skb. IP headers of the fragments are updated in
 	 * inet_gso_segment()
 	 */
-	if (skb->encapsulation && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL)
-		segs = skb_udp_tunnel_segment(skb, features);
-	else {
-		int offset;
-		__wsum csum;
-
-		/* Do software UFO. Complete and fill in the UDP checksum as
-		 * HW cannot do checksum of UDP packets sent as multiple
-		 * IP fragments.
-		 */
-		offset = skb_checksum_start_offset(skb);
-		csum = skb_checksum(skb, offset, skb->len - offset, 0);
-		offset += skb->csum_offset;
-		*(__sum16 *)(skb->data + offset) = csum_fold(csum);
-		skb->ip_summed = CHECKSUM_NONE;
-
-		segs = skb_segment(skb, features);
-	}
+	segs = skb_segment(skb, features);
 out:
 	return segs;
 }
-- 
cgit v0.10.2


From 6cd4ce0099da7702f885b6fa9ebb49e3831d90b4 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Mon, 30 Dec 2013 11:34:40 +0800
Subject: virtio-net: fix refill races during restore

During restoring, try_fill_recv() was called with neither napi lock nor napi
disabled. This can lead two try_fill_recv() was called in the same time. Fix
this by refilling before trying to enable napi.

Fixes 0741bcb5584f9e2390ae6261573c4de8314999f2
(virtio: net: Add freeze, restore handlers to support S4).

Cc: Amit Shah <amit.shah@redhat.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index d208f86..5d77644 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1797,16 +1797,17 @@ static int virtnet_restore(struct virtio_device *vdev)
 	if (err)
 		return err;
 
-	if (netif_running(vi->dev))
+	if (netif_running(vi->dev)) {
+		for (i = 0; i < vi->curr_queue_pairs; i++)
+			if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
+				schedule_delayed_work(&vi->refill, 0);
+
 		for (i = 0; i < vi->max_queue_pairs; i++)
 			virtnet_napi_enable(&vi->rq[i]);
+	}
 
 	netif_device_attach(vi->dev);
 
-	for (i = 0; i < vi->curr_queue_pairs; i++)
-		if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
-			schedule_delayed_work(&vi->refill, 0);
-
 	mutex_lock(&vi->config_lock);
 	vi->config_enable = true;
 	mutex_unlock(&vi->config_lock);
-- 
cgit v0.10.2


From 4d231b76eef6c4a6bd9c96769e191517765942cb Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Mon, 30 Dec 2013 23:40:50 +0100
Subject: net: llc: fix use after free in llc_ui_recvmsg

While commit 30a584d944fb fixes datagram interface in LLC, a use
after free bug has been introduced for SOCK_STREAM sockets that do
not make use of MSG_PEEK.

The flow is as follow ...

  if (!(flags & MSG_PEEK)) {
    ...
    sk_eat_skb(sk, skb, false);
    ...
  }
  ...
  if (used + offset < skb->len)
    continue;

... where sk_eat_skb() calls __kfree_skb(). Therefore, cache
original length and work on skb_len to check partial reads.

Fixes: 30a584d944fb ("[LLX]: SOCK_DGRAM interface fixes")
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 7b01b9f..c71b699 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -715,7 +715,7 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock,
 	unsigned long cpu_flags;
 	size_t copied = 0;
 	u32 peek_seq = 0;
-	u32 *seq;
+	u32 *seq, skb_len;
 	unsigned long used;
 	int target;	/* Read at least this many bytes */
 	long timeo;
@@ -812,6 +812,7 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock,
 		}
 		continue;
 	found_ok_skb:
+		skb_len = skb->len;
 		/* Ok so how much can we use? */
 		used = skb->len - offset;
 		if (len < used)
@@ -844,7 +845,7 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock,
 		}
 
 		/* Partial read */
-		if (used + offset < skb->len)
+		if (used + offset < skb_len)
 			continue;
 	} while (len > 0);
 
-- 
cgit v0.10.2


From fad8da3e085ddf5e661090033287f1a5d62858fc Mon Sep 17 00:00:00 2001
From: Yasushi Asano <yasushi.asano@jp.fujitsu.com>
Date: Tue, 31 Dec 2013 12:04:19 +0900
Subject: ipv6 addrconf: fix preferred lifetime state-changing behavior while
 valid_lft is infinity

Fixed a problem with setting the lifetime of an IPv6
address. When setting preferred_lft to a value not zero or
infinity, while valid_lft is infinity(0xffffffff) preferred
lifetime is set to forever and does not update. Therefore
preferred lifetime never becomes deprecated. valid lifetime
and preferred lifetime should be set independently, even if
valid lifetime is infinity, preferred lifetime must expire
correctly (meaning it must eventually become deprecated)

Signed-off-by: Yasushi Asano <yasushi.asano@jp.fujitsu.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index d5fa5b8..1a341f7 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3456,7 +3456,12 @@ restart:
 					 &inet6_addr_lst[i], addr_lst) {
 			unsigned long age;
 
-			if (ifp->flags & IFA_F_PERMANENT)
+			/* When setting preferred_lft to a value not zero or
+			 * infinity, while valid_lft is infinity
+			 * IFA_F_PERMANENT has a non-infinity life time.
+			 */
+			if ((ifp->flags & IFA_F_PERMANENT) &&
+			    (ifp->prefered_lft == INFINITY_LIFE_TIME))
 				continue;
 
 			spin_lock(&ifp->lock);
@@ -3481,7 +3486,8 @@ restart:
 					ifp->flags |= IFA_F_DEPRECATED;
 				}
 
-				if (time_before(ifp->tstamp + ifp->valid_lft * HZ, next))
+				if ((ifp->valid_lft != INFINITY_LIFE_TIME) &&
+				    (time_before(ifp->tstamp + ifp->valid_lft * HZ, next)))
 					next = ifp->tstamp + ifp->valid_lft * HZ;
 
 				spin_unlock(&ifp->lock);
@@ -3761,7 +3767,8 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
 	put_ifaddrmsg(nlh, ifa->prefix_len, ifa->flags, rt_scope(ifa->scope),
 		      ifa->idev->dev->ifindex);
 
-	if (!(ifa->flags&IFA_F_PERMANENT)) {
+	if (!((ifa->flags&IFA_F_PERMANENT) &&
+	      (ifa->prefered_lft == INFINITY_LIFE_TIME))) {
 		preferred = ifa->prefered_lft;
 		valid = ifa->valid_lft;
 		if (preferred != INFINITY_LIFE_TIME) {
-- 
cgit v0.10.2


From abb6013cca147ad940b0e9fee260d2d9e93b7018 Mon Sep 17 00:00:00 2001
From: Li RongQing <roy.qing.li@gmail.com>
Date: Thu, 2 Jan 2014 13:20:12 +0800
Subject: ipv6: fix the use of pcpu_tstats in ip6_tunnel

when read/write the 64bit data, the correct lock should be hold.

Fixes: 87b6d218f3adb ("tunnel: implement 64 bits statistics")

Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Li RongQing <roy.qing.li@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index d606232..7881965 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -103,16 +103,25 @@ struct ip6_tnl_net {
 
 static struct net_device_stats *ip6_get_stats(struct net_device *dev)
 {
-	struct pcpu_tstats sum = { 0 };
+	struct pcpu_tstats tmp, sum = { 0 };
 	int i;
 
 	for_each_possible_cpu(i) {
+		unsigned int start;
 		const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
 
-		sum.rx_packets += tstats->rx_packets;
-		sum.rx_bytes   += tstats->rx_bytes;
-		sum.tx_packets += tstats->tx_packets;
-		sum.tx_bytes   += tstats->tx_bytes;
+		do {
+			start = u64_stats_fetch_begin_bh(&tstats->syncp);
+			tmp.rx_packets = tstats->rx_packets;
+			tmp.rx_bytes = tstats->rx_bytes;
+			tmp.tx_packets = tstats->tx_packets;
+			tmp.tx_bytes =  tstats->tx_bytes;
+		} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
+
+		sum.rx_packets += tmp.rx_packets;
+		sum.rx_bytes   += tmp.rx_bytes;
+		sum.tx_packets += tmp.tx_packets;
+		sum.tx_bytes   += tmp.tx_bytes;
 	}
 	dev->stats.rx_packets = sum.rx_packets;
 	dev->stats.rx_bytes   = sum.rx_bytes;
@@ -824,8 +833,10 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol,
 		}
 
 		tstats = this_cpu_ptr(t->dev->tstats);
+		u64_stats_update_begin(&tstats->syncp);
 		tstats->rx_packets++;
 		tstats->rx_bytes += skb->len;
+		u64_stats_update_end(&tstats->syncp);
 
 		netif_rx(skb);
 
-- 
cgit v0.10.2


From 469bdcefdc47a69028029e792ff1e80680c867b9 Mon Sep 17 00:00:00 2001
From: Li RongQing <roy.qing.li@gmail.com>
Date: Thu, 2 Jan 2014 14:24:36 +0800
Subject: ipv6: fix the use of pcpu_tstats in ip6_vti.c

when read/write the 64bit data, the correct lock should be hold.
and we can use the generic vti6_get_stats to return stats, and
not define a new one in ip6_vti.c

Fixes: 87b6d218f3adb ("tunnel: implement 64 bits statistics")
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Li RongQing <roy.qing.li@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index ed94ba6..a4564b0 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -75,26 +75,6 @@ struct vti6_net {
 	struct ip6_tnl __rcu **tnls[2];
 };
 
-static struct net_device_stats *vti6_get_stats(struct net_device *dev)
-{
-	struct pcpu_tstats sum = { 0 };
-	int i;
-
-	for_each_possible_cpu(i) {
-		const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
-
-		sum.rx_packets += tstats->rx_packets;
-		sum.rx_bytes   += tstats->rx_bytes;
-		sum.tx_packets += tstats->tx_packets;
-		sum.tx_bytes   += tstats->tx_bytes;
-	}
-	dev->stats.rx_packets = sum.rx_packets;
-	dev->stats.rx_bytes   = sum.rx_bytes;
-	dev->stats.tx_packets = sum.tx_packets;
-	dev->stats.tx_bytes   = sum.tx_bytes;
-	return &dev->stats;
-}
-
 #define for_each_vti6_tunnel_rcu(start) \
 	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
 
@@ -331,8 +311,10 @@ static int vti6_rcv(struct sk_buff *skb)
 		}
 
 		tstats = this_cpu_ptr(t->dev->tstats);
+		u64_stats_update_begin(&tstats->syncp);
 		tstats->rx_packets++;
 		tstats->rx_bytes += skb->len;
+		u64_stats_update_end(&tstats->syncp);
 
 		skb->mark = 0;
 		secpath_reset(skb);
@@ -716,7 +698,7 @@ static const struct net_device_ops vti6_netdev_ops = {
 	.ndo_start_xmit = vti6_tnl_xmit,
 	.ndo_do_ioctl	= vti6_ioctl,
 	.ndo_change_mtu = vti6_change_mtu,
-	.ndo_get_stats	= vti6_get_stats,
+	.ndo_get_stats64 = ip_tunnel_get_stats64,
 };
 
 /**
-- 
cgit v0.10.2


From aca5f58f9ba803ec8c2e6bcf890db17589e8dfcc Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 2 Jan 2014 19:50:52 -0500
Subject: netpoll: Fix missing TXQ unlock and and OOPS.

The VLAN tag handling code in netpoll_send_skb_on_dev() has two problems.

1) It exits without unlocking the TXQ.

2) It then tries to queue a NULL skb to npinfo->txq.

Reported-by: Ahmed Tamrawi <atamrawi@iastate.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 8f97199..3030978 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -386,8 +386,14 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 					    !vlan_hw_offload_capable(netif_skb_features(skb),
 								     skb->vlan_proto)) {
 						skb = __vlan_put_tag(skb, skb->vlan_proto, vlan_tx_tag_get(skb));
-						if (unlikely(!skb))
-							break;
+						if (unlikely(!skb)) {
+							/* This is actually a packet drop, but we
+							 * don't want the code at the end of this
+							 * function to try and re-queue a NULL skb.
+							 */
+							status = NETDEV_TX_OK;
+							goto unlock_txq;
+						}
 						skb->vlan_tci = 0;
 					}
 
@@ -395,6 +401,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 					if (status == NETDEV_TX_OK)
 						txq_trans_update(txq);
 				}
+			unlock_txq:
 				__netif_tx_unlock(txq);
 
 				if (status == NETDEV_TX_OK)
-- 
cgit v0.10.2


From 41a34cec2e0df7798ea322ed1480bc3d3facdc8e Mon Sep 17 00:00:00 2001
From: Dave Young <dyoung@redhat.com>
Date: Fri, 3 Jan 2014 11:54:31 +0800
Subject: x86: ksysfs.c build fix

kbuild test robot report below error for randconfig:

  arch/x86/kernel/ksysfs.c: In function 'get_setup_data_paddr':
  arch/x86/kernel/ksysfs.c:81:3: error: implicit declaration of function 'ioremap_cache' [-Werror=implicit-function-declaration]
  arch/x86/kernel/ksysfs.c:86:3: error: implicit declaration of function 'iounmap' [-Werror=implicit-function-declaration]

Fix it by including <asm/io.h> in ksysfs.c

Signed-off-by: Dave Young <dyoung@redhat.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c
index eb53d15..c2bedae 100644
--- a/arch/x86/kernel/ksysfs.c
+++ b/arch/x86/kernel/ksysfs.c
@@ -17,6 +17,7 @@
 #include <linux/slab.h>
 #include <linux/mm.h>
 
+#include <asm/io.h>
 #include <asm/setup.h>
 
 static ssize_t version_show(struct kobject *kobj,
-- 
cgit v0.10.2


From 5c12af0c41e3417e1939095325920463b5f8e726 Mon Sep 17 00:00:00 2001
From: Dave Young <dyoung@redhat.com>
Date: Fri, 3 Jan 2014 11:56:49 +0800
Subject: x86/efi: parse_efi_setup() build fix

In case without CONFIG_EFI, there will be below build error:

   arch/x86/built-in.o: In function `setup_arch':
  (.init.text+0x9dc): undefined reference to `parse_efi_setup'

Thus fix it by adding blank inline function in asm/efi.h
Also remove an unused declaration for variable efi_data_len.

Signed-off-by: Dave Young <dyoung@redhat.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>

diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 4d1ba80..3b978c4 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -142,8 +142,6 @@ struct efi_setup_data {
 };
 
 extern u64 efi_setup;
-extern u32 efi_data_len;
-extern void parse_efi_setup(u64 phys_addr, u32 data_len);
 
 #ifdef CONFIG_EFI
 
@@ -153,7 +151,7 @@ static inline bool efi_is_native(void)
 }
 
 extern struct console early_efi_console;
-
+extern void parse_efi_setup(u64 phys_addr, u32 data_len);
 #else
 /*
  * IF EFI is not configured, have the EFI calls return -ENOSYS.
@@ -165,6 +163,7 @@ extern struct console early_efi_console;
 #define efi_call4(_f, _a1, _a2, _a3, _a4)		(-ENOSYS)
 #define efi_call5(_f, _a1, _a2, _a3, _a4, _a5)		(-ENOSYS)
 #define efi_call6(_f, _a1, _a2, _a3, _a4, _a5, _a6)	(-ENOSYS)
+static inline void parse_efi_setup(u64 phys_addr, u32 data_len) {}
 #endif /* CONFIG_EFI */
 
 #endif /* _ASM_X86_EFI_H */
-- 
cgit v0.10.2


From dd360393f4d948eb518372316e52101cf3b44212 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Mon, 23 Dec 2013 14:16:58 +0200
Subject: x86, cpu: Detect more TLB configuration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Intel Software Developer’s Manual covers few more TLB
configurations exposed as CPUID 2 descriptors:

61H Instruction TLB: 4 KByte pages, fully associative, 48 entries
63H Data TLB: 1 GByte pages, 4-way set associative, 4 entries
76H Instruction TLB: 2M/4M pages, fully associative, 8 entries
B5H Instruction TLB: 4KByte pages, 8-way set associative, 64 entries
B6H Instruction TLB: 4KByte pages, 8-way set associative, 128 entries
C1H Shared 2nd-Level TLB: 4 KByte/2MByte pages, 8-way associative, 1024 entries
C2H DTLB DTLB: 2 MByte/$MByte pages, 4-way associative, 16 entries

Let's detect them as well.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Link: http://lkml.kernel.org/r/1387801018-14499-1-git-send-email-kirill.shutemov@linux.intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 7b034a4..1dd6260 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -72,6 +72,7 @@ extern u16 __read_mostly tlb_lli_4m[NR_INFO];
 extern u16 __read_mostly tlb_lld_4k[NR_INFO];
 extern u16 __read_mostly tlb_lld_2m[NR_INFO];
 extern u16 __read_mostly tlb_lld_4m[NR_INFO];
+extern u16 __read_mostly tlb_lld_1g[NR_INFO];
 extern s8  __read_mostly tlb_flushall_shift;
 
 /*
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 6abc172..24b6fd1 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -472,6 +472,7 @@ u16 __read_mostly tlb_lli_4m[NR_INFO];
 u16 __read_mostly tlb_lld_4k[NR_INFO];
 u16 __read_mostly tlb_lld_2m[NR_INFO];
 u16 __read_mostly tlb_lld_4m[NR_INFO];
+u16 __read_mostly tlb_lld_1g[NR_INFO];
 
 /*
  * tlb_flushall_shift shows the balance point in replacing cr3 write
@@ -486,13 +487,13 @@ void cpu_detect_tlb(struct cpuinfo_x86 *c)
 	if (this_cpu->c_detect_tlb)
 		this_cpu->c_detect_tlb(c);
 
-	printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \
-		"Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d\n"	     \
+	printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n"
+		"Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %d\n"
 		"tlb_flushall_shift: %d\n",
 		tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES],
 		tlb_lli_4m[ENTRIES], tlb_lld_4k[ENTRIES],
 		tlb_lld_2m[ENTRIES], tlb_lld_4m[ENTRIES],
-		tlb_flushall_shift);
+		tlb_lld_1g[ENTRIES], tlb_flushall_shift);
 }
 
 void detect_ht(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index ea04b34..5eb7ea5 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -506,6 +506,7 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 #define TLB_DATA0_2M_4M	0x23
 
 #define STLB_4K		0x41
+#define STLB_4K_2M	0x42
 
 static const struct _tlb_table intel_tlb_table[] = {
 	{ 0x01, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages, 4-way set associative" },
@@ -526,13 +527,20 @@ static const struct _tlb_table intel_tlb_table[] = {
 	{ 0x5b, TLB_DATA_4K_4M,		64,	" TLB_DATA 4 KByte and 4 MByte pages" },
 	{ 0x5c, TLB_DATA_4K_4M,		128,	" TLB_DATA 4 KByte and 4 MByte pages" },
 	{ 0x5d, TLB_DATA_4K_4M,		256,	" TLB_DATA 4 KByte and 4 MByte pages" },
+	{ 0x61, TLB_INST_4K,		48,	" TLB_INST 4 KByte pages, full associative" },
+	{ 0x63, TLB_DATA_1G,		4,	" TLB_DATA 1 GByte pages, 4-way set associative" },
+	{ 0x76, TLB_INST_2M_4M,		8,	" TLB_INST 2-MByte or 4-MByte pages, fully associative" },
 	{ 0xb0, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 4-way set associative" },
 	{ 0xb1, TLB_INST_2M_4M,		4,	" TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" },
 	{ 0xb2, TLB_INST_4K,		64,	" TLB_INST 4KByte pages, 4-way set associative" },
 	{ 0xb3, TLB_DATA_4K,		128,	" TLB_DATA 4 KByte pages, 4-way set associative" },
 	{ 0xb4, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 4-way associative" },
+	{ 0xb5, TLB_INST_4K,		64,	" TLB_INST 4 KByte pages, 8-way set ssociative" },
+	{ 0xb6, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 8-way set ssociative" },
 	{ 0xba, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way associative" },
 	{ 0xc0, TLB_DATA_4K_4M,		8,	" TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" },
+	{ 0xc1, STLB_4K_2M,		1024,	" STLB 4 KByte and 2 MByte pages, 8-way associative" },
+	{ 0xc2, TLB_DATA_2M_4M,		16,	" DTLB 2 MByte/4MByte pages, 4-way associative" },
 	{ 0xca, STLB_4K,		512,	" STLB 4 KByte pages, 4-way associative" },
 	{ 0x00, 0, 0 }
 };
@@ -558,6 +566,20 @@ static void intel_tlb_lookup(const unsigned char desc)
 		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
 			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
 		break;
+	case STLB_4K_2M:
+		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
+		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
+		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
+		if (tlb_lld_2m[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lld_2m[ENTRIES] = intel_tlb_table[k].entries;
+		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		break;
 	case TLB_INST_ALL:
 		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
 			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
@@ -603,6 +625,10 @@ static void intel_tlb_lookup(const unsigned char desc)
 		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
 			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
 		break;
+	case TLB_DATA_1G:
+		if (tlb_lld_1g[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lld_1g[ENTRIES] = intel_tlb_table[k].entries;
+		break;
 	}
 }
 
-- 
cgit v0.10.2


From 940d9d34a5467c2e2574866eb009d4cb61e27299 Mon Sep 17 00:00:00 2001
From: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Date: Mon, 23 Dec 2013 15:34:29 -0200
Subject: cxgb4: allow large buffer size to have page size

Since commit 52367a763d8046190754ab43743e42638564a2d1
("cxgb4/cxgb4vf: Code cleanup to enable T4 Configuration File support"),
we have failures like this during cxgb4 probe:

cxgb4 0000:01:00.4: bad SGE FL page buffer sizes [65536, 65536]
cxgb4: probe of 0000:01:00.4 failed with error -22

This happens whenever software parameters are used, without a
configuration file. That happens when the hardware was already
initialized (after kexec, or after csiostor is loaded).

It happens that these values are acceptable, rendering fl_pg_order equal
to 0, which is the case of a hard init when the page size is equal or
larger than 65536.

Accepting fl_large_pg equal to fl_small_pg solves the issue, and
shouldn't cause any trouble besides a possible performance reduction
when smaller pages are used. And that can be fixed by a configuration
file.

Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index cc380c3..cc3511a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -2581,7 +2581,7 @@ static int t4_sge_init_soft(struct adapter *adap)
 	#undef READ_FL_BUF
 
 	if (fl_small_pg != PAGE_SIZE ||
-	    (fl_large_pg != 0 && (fl_large_pg <= fl_small_pg ||
+	    (fl_large_pg != 0 && (fl_large_pg < fl_small_pg ||
 				  (fl_large_pg & (fl_large_pg-1)) != 0))) {
 		dev_err(adap->pdev_dev, "bad SGE FL page buffer sizes [%d, %d]\n",
 			fl_small_pg, fl_large_pg);
-- 
cgit v0.10.2


From 7bda701e012373ca53c9d837b7b25131852e0238 Mon Sep 17 00:00:00 2001
From: "fan.du" <fan.du@windriver.com>
Date: Fri, 3 Jan 2014 10:18:58 +0800
Subject: {vxlan, inet6} Mark vxlan_dev flags with VXLAN_F_IPV6 properly

Even if user doesn't supply the physical netdev to attach vxlan dev
to, and at the same time user want to vxlan sit top of IPv6, mark
vxlan_dev flags with VXLAN_F_IPV6 to create IPv6 based socket.
Otherwise kernel crashes safely every time spitting below messages,

Steps to reproduce:
ip link add vxlan0 type vxlan id 42 group ff0e::110
ip link set vxlan0 up

[   62.656266] BUG: unable to handle kernel NULL pointer dereference[   62.656320] ip (3008) used greatest stack depth: 3912 bytes left
 at 0000000000000046
[   62.656423] IP: [<ffffffff816d822d>] ip6_route_output+0xbd/0xe0
[   62.656525] PGD 2c966067 PUD 2c9a2067 PMD 0
[   62.656674] Oops: 0000 [#1] SMP
[   62.656781] Modules linked in: vxlan netconsole deflate zlib_deflate af_key
[   62.657083] CPU: 1 PID: 2128 Comm: whoopsie Not tainted 3.12.0+ #182
[   62.657083] Hardware name: innotek GmbH VirtualBox, BIOS VirtualBox 12/01/2006
[   62.657083] task: ffff88002e2335d0 ti: ffff88002c94c000 task.ti: ffff88002c94c000
[   62.657083] RIP: 0010:[<ffffffff816d822d>]  [<ffffffff816d822d>] ip6_route_output+0xbd/0xe0
[   62.657083] RSP: 0000:ffff88002fd038f8  EFLAGS: 00210296
[   62.657083] RAX: 0000000000000000 RBX: ffff88002fd039e0 RCX: 0000000000000000
[   62.657083] RDX: ffff88002fd0eb68 RSI: ffff88002fd0d278 RDI: ffff88002fd0d278
[   62.657083] RBP: ffff88002fd03918 R08: 0000000002000000 R09: 0000000000000000
[   62.657083] R10: 00000000000001ff R11: 0000000000000000 R12: 0000000000000001
[   62.657083] R13: ffff88002d96b480 R14: ffffffff81c8e2c0 R15: 0000000000000001
[   62.657083] FS:  0000000000000000(0000) GS:ffff88002fd00000(0063) knlGS:00000000f693b740
[   62.657083] CS:  0010 DS: 002b ES: 002b CR0: 0000000080050033
[   62.657083] CR2: 0000000000000046 CR3: 000000002c9d2000 CR4: 00000000000006e0
[   62.657083] Stack:
[   62.657083]  ffff88002fd03a40 ffffffff81c8e2c0 ffff88002fd039e0 ffff88002d96b480
[   62.657083]  ffff88002fd03958 ffffffff816cac8b ffff880019277cc0 ffff8800192b5d00
[   62.657083]  ffff88002d5bc000 ffff880019277cc0 0000000000001821 0000000000000001
[   62.657083] Call Trace:
[   62.657083]  <IRQ>
[   62.657083]  [<ffffffff816cac8b>] ip6_dst_lookup_tail+0xdb/0xf0
[   62.657083]  [<ffffffff816caea0>] ip6_dst_lookup+0x10/0x20
[   62.657083]  [<ffffffffa0020c13>] vxlan_xmit_one+0x193/0x9c0 [vxlan]
[   62.657083]  [<ffffffff8137b3b7>] ? account+0xc7/0x1f0
[   62.657083]  [<ffffffffa0021513>] vxlan_xmit+0xd3/0x400 [vxlan]
[   62.657083]  [<ffffffff8161390d>] dev_hard_start_xmit+0x49d/0x5e0
[   62.657083]  [<ffffffff81613d29>] dev_queue_xmit+0x2d9/0x480
[   62.657083]  [<ffffffff817cb854>] ? _raw_write_unlock_bh+0x14/0x20
[   62.657083]  [<ffffffff81630565>] ? eth_header+0x35/0xe0
[   62.657083]  [<ffffffff8161bc5e>] neigh_resolve_output+0x11e/0x1e0
[   62.657083]  [<ffffffff816ce0e0>] ? ip6_fragment+0xad0/0xad0
[   62.657083]  [<ffffffff816cb465>] ip6_finish_output2+0x2f5/0x470
[   62.657083]  [<ffffffff816ce166>] ip6_finish_output+0x86/0xc0
[   62.657083]  [<ffffffff816ce218>] ip6_output+0x78/0xb0
[   62.657083]  [<ffffffff816eadd6>] mld_sendpack+0x256/0x2a0
[   62.657083]  [<ffffffff816ebd8c>] mld_ifc_timer_expire+0x17c/0x290
[   62.657083]  [<ffffffff816ebc10>] ? igmp6_timer_handler+0x80/0x80
[   62.657083]  [<ffffffff816ebc10>] ? igmp6_timer_handler+0x80/0x80
[   62.657083]  [<ffffffff81051065>] call_timer_fn+0x45/0x150
[   62.657083]  [<ffffffff816ebc10>] ? igmp6_timer_handler+0x80/0x80
[   62.657083]  [<ffffffff81052353>] run_timer_softirq+0x1f3/0x2a0
[   62.657083]  [<ffffffff8102dfd8>] ? lapic_next_event+0x18/0x20
[   62.657083]  [<ffffffff8109e36f>] ? clockevents_program_event+0x6f/0x110
[   62.657083]  [<ffffffff8104a2f6>] __do_softirq+0xd6/0x2b0
[   62.657083]  [<ffffffff8104a75e>] irq_exit+0x7e/0xa0
[   62.657083]  [<ffffffff8102ea15>] smp_apic_timer_interrupt+0x45/0x60
[   62.657083]  [<ffffffff817d3eca>] apic_timer_interrupt+0x6a/0x70
[   62.657083]  <EOI>
[   62.657083]  [<ffffffff817d4a35>] ? sysenter_dispatch+0x7/0x1a
[   62.657083] Code: 4d 8b 85 a8 02 00 00 4c 89 e9 ba 03 04 00 00 48 c7 c6 c0 be 8d 81 48 c7 c7 48 35 a3 81 31 c0 e8 db 68 0e 00 49 8b 85 a8 02 00 00 <0f> b6 40 46 c0 e8 05 0f b6 c0 c1 e0 03 41 09 c4 e9 77 ff ff ff
[   62.657083] RIP  [<ffffffff816d822d>] ip6_route_output+0xbd/0xe0
[   62.657083]  RSP <ffff88002fd038f8>
[   62.657083] CR2: 0000000000000046
[   62.657083] ---[ end trace ba8a9583d7cd1934 ]---
[   62.657083] Kernel panic - not syncing: Fatal exception in interrupt

Signed-off-by: Fan Du <fan.du@windriver.com>
Reported-by: Ryan Whelan <rcwhelan@gmail.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 249e01c..ed384fe 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2440,7 +2440,8 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
 		/* update header length based on lower device */
 		dev->hard_header_len = lowerdev->hard_header_len +
 				       (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
-	}
+	} else if (use_ipv6)
+		vxlan->flags |= VXLAN_F_IPV6;
 
 	if (data[IFLA_VXLAN_TOS])
 		vxlan->tos  = nla_get_u8(data[IFLA_VXLAN_TOS]);
-- 
cgit v0.10.2


From 0d68fc4f1210f8caea2bdd68f99dc6da35ee3740 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 3 Jan 2014 11:33:45 +0800
Subject: infiniband: make sure the src net is infiniband when create new link

When we create a new infiniband link with uninfiniband device, e.g. `ip link
add link em1 type ipoib pkey 0x8001`. We will get a NULL pointer dereference
cause other dev like Ethernet don't have struct ib_device.

The code path is:
rtnl_newlink
  |-- ipoib_new_child_link
        |-- __ipoib_vlan_add
              |-- ipoib_set_dev_features
                    |-- ib_query_device

Fix this bug by make sure the src net is infiniband when create new link.

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
index c29b5c8..cdc7df4 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
@@ -31,6 +31,7 @@
  */
 
 #include <linux/netdevice.h>
+#include <linux/if_arp.h>      /* For ARPHRD_xxx */
 #include <linux/module.h>
 #include <net/rtnetlink.h>
 #include "ipoib.h"
@@ -103,7 +104,7 @@ static int ipoib_new_child_link(struct net *src_net, struct net_device *dev,
 		return -EINVAL;
 
 	pdev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
-	if (!pdev)
+	if (!pdev || pdev->type != ARPHRD_INFINIBAND)
 		return -ENODEV;
 
 	ppriv = netdev_priv(pdev);
-- 
cgit v0.10.2


From a02bdd423d844f5beb3196922f07c85c2f7691b8 Mon Sep 17 00:00:00 2001
From: Shahed Shaikh <shahed.shaikh@qlogic.com>
Date: Fri, 3 Jan 2014 01:34:28 -0500
Subject: qlcnic: Fix bug in Tx completion path

o Driver is using common tx_clean_lock for all Tx queues. This patch
  adds per queue tx_clean_lock.
o Driver is not updating sw_consumer while processing Tx completion
  when interface is going down. Fixed in this patch.

Signed-off-by: Shahed Shaikh <shahed.shaikh@qlogic.com>
Signed-off-by: Manish Chopra <manish.chopra@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index 4dfef81..ff80cd8 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -579,6 +579,8 @@ struct qlcnic_host_tx_ring {
 	dma_addr_t phys_addr;
 	dma_addr_t hw_cons_phys_addr;
 	struct netdev_queue *txq;
+	/* Lock to protect Tx descriptors cleanup */
+	spinlock_t tx_clean_lock;
 } ____cacheline_internodealigned_in_smp;
 
 /*
@@ -1095,7 +1097,6 @@ struct qlcnic_adapter {
 	struct qlcnic_filter_hash rx_fhash;
 	struct list_head vf_mc_list;
 
-	spinlock_t tx_clean_lock;
 	spinlock_t mac_learn_lock;
 	/* spinlock for catching rcv filters for eswitch traffic */
 	spinlock_t rx_mac_learn_lock;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c
index e9c21e5..c4262c2 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c
@@ -134,6 +134,8 @@ void qlcnic_release_tx_buffers(struct qlcnic_adapter *adapter,
 	struct qlcnic_skb_frag *buffrag;
 	int i, j;
 
+	spin_lock(&tx_ring->tx_clean_lock);
+
 	cmd_buf = tx_ring->cmd_buf_arr;
 	for (i = 0; i < tx_ring->num_desc; i++) {
 		buffrag = cmd_buf->frag_array;
@@ -157,6 +159,8 @@ void qlcnic_release_tx_buffers(struct qlcnic_adapter *adapter,
 		}
 		cmd_buf++;
 	}
+
+	spin_unlock(&tx_ring->tx_clean_lock);
 }
 
 void qlcnic_free_sw_resources(struct qlcnic_adapter *adapter)
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
index 1362976..ad1531a 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
@@ -782,7 +782,7 @@ static int qlcnic_process_cmd_ring(struct qlcnic_adapter *adapter,
 	struct net_device *netdev = adapter->netdev;
 	struct qlcnic_skb_frag *frag;
 
-	if (!spin_trylock(&adapter->tx_clean_lock))
+	if (!spin_trylock(&tx_ring->tx_clean_lock))
 		return 1;
 
 	sw_consumer = tx_ring->sw_consumer;
@@ -811,8 +811,9 @@ static int qlcnic_process_cmd_ring(struct qlcnic_adapter *adapter,
 			break;
 	}
 
+	tx_ring->sw_consumer = sw_consumer;
+
 	if (count && netif_running(netdev)) {
-		tx_ring->sw_consumer = sw_consumer;
 		smp_mb();
 		if (netif_tx_queue_stopped(tx_ring->txq) &&
 		    netif_carrier_ok(netdev)) {
@@ -838,7 +839,8 @@ static int qlcnic_process_cmd_ring(struct qlcnic_adapter *adapter,
 	 */
 	hw_consumer = le32_to_cpu(*(tx_ring->hw_consumer));
 	done = (sw_consumer == hw_consumer);
-	spin_unlock(&adapter->tx_clean_lock);
+
+	spin_unlock(&tx_ring->tx_clean_lock);
 
 	return done;
 }
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 2c8cac0..b8a245a 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -1756,7 +1756,6 @@ void __qlcnic_down(struct qlcnic_adapter *adapter, struct net_device *netdev)
 	if (qlcnic_sriov_vf_check(adapter))
 		qlcnic_sriov_cleanup_async_list(&adapter->ahw->sriov->bc);
 	smp_mb();
-	spin_lock(&adapter->tx_clean_lock);
 	netif_carrier_off(netdev);
 	adapter->ahw->linkup = 0;
 	netif_tx_disable(netdev);
@@ -1777,7 +1776,6 @@ void __qlcnic_down(struct qlcnic_adapter *adapter, struct net_device *netdev)
 
 	for (ring = 0; ring < adapter->drv_tx_rings; ring++)
 		qlcnic_release_tx_buffers(adapter, &adapter->tx_ring[ring]);
-	spin_unlock(&adapter->tx_clean_lock);
 }
 
 /* Usage: During suspend and firmware recovery module */
@@ -2172,6 +2170,7 @@ int qlcnic_alloc_tx_rings(struct qlcnic_adapter *adapter,
 		}
 		memset(cmd_buf_arr, 0, TX_BUFF_RINGSIZE(tx_ring));
 		tx_ring->cmd_buf_arr = cmd_buf_arr;
+		spin_lock_init(&tx_ring->tx_clean_lock);
 	}
 
 	if (qlcnic_83xx_check(adapter) ||
@@ -2299,7 +2298,6 @@ qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	rwlock_init(&adapter->ahw->crb_lock);
 	mutex_init(&adapter->ahw->mem_lock);
 
-	spin_lock_init(&adapter->tx_clean_lock);
 	INIT_LIST_HEAD(&adapter->mac_list);
 
 	qlcnic_register_dcb(adapter);
-- 
cgit v0.10.2


From d31652a26bc9e752a99b6ac3b61353129934e451 Mon Sep 17 00:00:00 2001
From: Arron Wang <arron.wang@intel.com>
Date: Thu, 14 Nov 2013 17:03:41 +0800
Subject: NFC: Fix target mode p2p link establishment

With commit e29a9e2ae165620d, we set the active_target pointer from
nfc_dep_link_is_up() in order to support the case where the target
detection and the DEP link setting are done atomically by the driver.
That can only happen in initiator mode, so we need to check for that
otherwise we fail to bring a p2p link in target mode.

Signed-off-by: Arron Wang <arron.wang@intel.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>

diff --git a/net/nfc/core.c b/net/nfc/core.c
index 8725291..83b9927 100644
--- a/net/nfc/core.c
+++ b/net/nfc/core.c
@@ -384,7 +384,7 @@ int nfc_dep_link_is_up(struct nfc_dev *dev, u32 target_idx,
 {
 	dev->dep_link_up = true;
 
-	if (!dev->active_target) {
+	if (!dev->active_target && rf_mode == NFC_RF_INITIATOR) {
 		struct nfc_target *target;
 
 		target = nfc_find_target(dev, target_idx);
-- 
cgit v0.10.2


From d6e0a2dd12f4067a5bcefb8bbd8ddbeff800afbc Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sat, 4 Jan 2014 15:12:14 -0800
Subject: Linux 3.13-rc7


diff --git a/Makefile b/Makefile
index ab80be7..ae1a55a 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 13
 SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
 NAME = One Giant Leap for Frogkind
 
 # *DOCUMENTATION*
-- 
cgit v0.10.2


From bf70053c5d2000514ade1f60f47e1f426899af39 Mon Sep 17 00:00:00 2001
From: Yijing Wang <wangyijing@huawei.com>
Date: Wed, 11 Dec 2013 14:00:26 +0800
Subject: sparc/PCI: Use dev_is_pci() to identify PCI devices

Use dev_is_pci() instead of checking bus type directly.

Signed-off-by: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 070ed14..76663b0 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -854,7 +854,7 @@ int dma_supported(struct device *dev, u64 device_mask)
 		return 1;
 
 #ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type)
+	if (dev_is_pci(dev))
 		return pci64_dma_supported(to_pci_dev(dev), device_mask);
 #endif
 
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index 2096468..e7e215d 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -666,10 +666,9 @@ EXPORT_SYMBOL(dma_ops);
  */
 int dma_supported(struct device *dev, u64 mask)
 {
-#ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type)
+	if (dev_is_pci(dev))
 		return 1;
-#endif
+
 	return 0;
 }
 EXPORT_SYMBOL(dma_supported);
-- 
cgit v0.10.2


From ce2521bf7d366a13e2ab3f9e1ff2084b145f4605 Mon Sep 17 00:00:00 2001
From: Kirill Tkhai <tkhai@yandex.ru>
Date: Thu, 12 Dec 2013 18:09:50 +0400
Subject: sparc64: smp_callin: Enable irqs after preemption is disabled

Most of other architectures have below suggested order.
So lets do the same to fit generic idle loop scheme better.

Signed-off-by: Kirill Tkhai <tkhai@yandex.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index b66a533..b085311 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -123,11 +123,12 @@ void smp_callin(void)
 		rmb();
 
 	set_cpu_online(cpuid, true);
-	local_irq_enable();
 
 	/* idle thread is expected to have preempt disabled */
 	preempt_disable();
 
+	local_irq_enable();
+
 	cpu_startup_entry(CPUHP_ONLINE);
 }
 
-- 
cgit v0.10.2


From 16932237f2978a2265662f8de4af743b1f55a209 Mon Sep 17 00:00:00 2001
From: Dave Kleikamp <dave.kleikamp@oracle.com>
Date: Mon, 16 Dec 2013 15:01:00 -0600
Subject: Revert "sparc64: Fix __copy_{to,from}_user_inatomic defines."

This reverts commit 145e1c0023585e0e8f6df22316308ec61c5066b2.

This commit broke the behavior of __copy_from_user_inatomic when
it is only partially successful. Instead of returning the number
of bytes not copied, it now returns 1. This translates to the
wrong value being returned by iov_iter_copy_from_user_atomic.

xfstests generic/246 and LTP writev01 both fail on btrfs and nfs
because of this.

Signed-off-by: Dave Kleikamp <dave.kleikamp@oracle.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: sparclinux@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index e562d3c..ad7e178 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -262,8 +262,8 @@ extern unsigned long __must_check __clear_user(void __user *, unsigned long);
 extern __must_check long strlen_user(const char __user *str);
 extern __must_check long strnlen_user(const char __user *str, long n);
 
-#define __copy_to_user_inatomic ___copy_to_user
-#define __copy_from_user_inatomic ___copy_from_user
+#define __copy_to_user_inatomic __copy_to_user
+#define __copy_from_user_inatomic __copy_from_user
 
 struct pt_regs;
 extern unsigned long compute_effective_address(struct pt_regs *,
-- 
cgit v0.10.2


From d2eca20d77d9d42f3163a0a3d6ead75ee3635f99 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Thu, 2 Jan 2014 17:14:45 +0000
Subject: CRYPTO: Fix more AES build errors

Building a multi-arch kernel results in:

arch/arm/crypto/built-in.o: In function `aesbs_xts_decrypt':
sha1_glue.c:(.text+0x15c8): undefined reference to `bsaes_xts_decrypt'
arch/arm/crypto/built-in.o: In function `aesbs_xts_encrypt':
sha1_glue.c:(.text+0x1664): undefined reference to `bsaes_xts_encrypt'
arch/arm/crypto/built-in.o: In function `aesbs_ctr_encrypt':
sha1_glue.c:(.text+0x184c): undefined reference to `bsaes_ctr32_encrypt_blocks'
arch/arm/crypto/built-in.o: In function `aesbs_cbc_decrypt':
sha1_glue.c:(.text+0x19b4): undefined reference to `bsaes_cbc_encrypt'

This code is already runtime-conditional on NEON being supported, so
there's no point compiling it out depending on the minimum build
architecture.

Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

diff --git a/arch/arm/crypto/aesbs-core.S_shipped b/arch/arm/crypto/aesbs-core.S_shipped
index 64205d4..71e5fc7 100644
--- a/arch/arm/crypto/aesbs-core.S_shipped
+++ b/arch/arm/crypto/aesbs-core.S_shipped
@@ -58,7 +58,7 @@
 # define VFP_ABI_FRAME	0
 # define BSAES_ASM_EXTENDED_KEY
 # define XTS_CHAIN_TWEAK
-# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_ARCH__	7
 #endif
 
 #ifdef __thumb__
diff --git a/arch/arm/crypto/bsaes-armv7.pl b/arch/arm/crypto/bsaes-armv7.pl
index f3d96d9..be068db 100644
--- a/arch/arm/crypto/bsaes-armv7.pl
+++ b/arch/arm/crypto/bsaes-armv7.pl
@@ -701,7 +701,7 @@ $code.=<<___;
 # define VFP_ABI_FRAME	0
 # define BSAES_ASM_EXTENDED_KEY
 # define XTS_CHAIN_TWEAK
-# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_ARCH__	7
 #endif
 
 #ifdef __thumb__
-- 
cgit v0.10.2


From 29c350bf28da333e41e30497b649fe335712a2ab Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Fri, 3 Jan 2014 15:01:39 +0000
Subject: ARM: fix "bad mode in ... handler" message for undefined instructions

The array was missing the final entry for the undefined instruction
exception handler; this commit adds it.

Cc: <stable@vger.kernel.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 7940241..6eda3bf 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -36,7 +36,13 @@
 #include <asm/system_misc.h>
 #include <asm/opcodes.h>
 
-static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" };
+static const char *handler[]= {
+	"prefetch abort",
+	"data abort",
+	"address exception",
+	"interrupt",
+	"undefined instruction",
+};
 
 void *vectors_page;
 
-- 
cgit v0.10.2


From 0a5ccc86507f45b80831dac1049197c4d45be955 Mon Sep 17 00:00:00 2001
From: Rob Herring <rob.herring@calxeda.com>
Date: Fri, 3 Jan 2014 16:17:44 +0100
Subject: ARM: 7933/1: rename ioremap_cached to ioremap_cache

ioremap_cache is more aligned with other architectures.
There are only 2 users of this in the kernel: pxa2xx-flash and Xen.

This fixes Xen build failures on arm64:

drivers/tty/hvc/hvc_xen.c:233:2: error: implicit declaration of function 'ioremap_cached' [-Werror=implicit-function-declaration]
drivers/xen/grant-table.c:1174:3: error: implicit declaration of function 'ioremap_cached' [-Werror=implicit-function-declaration]
drivers/xen/xenbus/xenbus_probe.c:778:4: error: implicit declaration of function 'ioremap_cached' [-Werror=implicit-function-declaration]

Signed-off-by: Rob Herring <rob.herring@calxeda.com>
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 3c597c2..fbeb39c 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -329,7 +329,7 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
  */
 #define ioremap(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE)
 #define ioremap_nocache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_cached(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE_CACHED)
+#define ioremap_cache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE_CACHED)
 #define ioremap_wc(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE_WC)
 #define iounmap				__arm_iounmap
 
diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h
index 75579a9..3759cac 100644
--- a/arch/arm/include/asm/xen/page.h
+++ b/arch/arm/include/asm/xen/page.h
@@ -117,6 +117,6 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 	return __set_phys_to_machine(pfn, mfn);
 }
 
-#define xen_remap(cookie, size) ioremap_cached((cookie), (size));
+#define xen_remap(cookie, size) ioremap_cache((cookie), (size));
 
 #endif /* _ASM_ARM_XEN_PAGE_H */
diff --git a/drivers/mtd/maps/pxa2xx-flash.c b/drivers/mtd/maps/pxa2xx-flash.c
index d210d13..0f55589 100644
--- a/drivers/mtd/maps/pxa2xx-flash.c
+++ b/drivers/mtd/maps/pxa2xx-flash.c
@@ -73,7 +73,7 @@ static int pxa2xx_flash_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 	info->map.cached =
-		ioremap_cached(info->map.phys, info->map.size);
+		ioremap_cache(info->map.phys, info->map.size);
 	if (!info->map.cached)
 		printk(KERN_WARNING "Failed to ioremap cached %s\n",
 		       info->map.name);
-- 
cgit v0.10.2


From 50a2bc5429f07ec4d53df2d287b03bdbceb281bb Mon Sep 17 00:00:00 2001
From: Alexander Mezin <mezin.alexander@gmail.com>
Date: Sat, 4 Jan 2014 09:07:59 +0700
Subject: ACPI / AC: change notification handler type to ACPI_ALL_NOTIFY

With kernel 3.13rc5 there are no AC adapter notifications on my laptop.

Commit cc8ef5270734 "ACPI / AC: convert ACPI ac driver to platform bus"
changed the driver to listen to device notifications only. However, AML
code on my laptop notifies the driver with zero event.

This patch changes the driver to listen to all events again.

Fixes: cc8ef5270734 (ACPI / AC: convert ACPI ac driver to platform bus)
References: https://bugzilla.kernel.org/show_bug.cgi?id=67821
Signed-off-by: Alexander Mezin <mezin.alexander@gmail.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index 8711e37..3c2e4aa 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -207,7 +207,7 @@ static int acpi_ac_probe(struct platform_device *pdev)
 		goto end;
 
 	result = acpi_install_notify_handler(ACPI_HANDLE(&pdev->dev),
-			ACPI_DEVICE_NOTIFY, acpi_ac_notify_handler, ac);
+			ACPI_ALL_NOTIFY, acpi_ac_notify_handler, ac);
 	if (result) {
 		power_supply_unregister(&ac->charger);
 		goto end;
@@ -255,7 +255,7 @@ static int acpi_ac_remove(struct platform_device *pdev)
 		return -EINVAL;
 
 	acpi_remove_notify_handler(ACPI_HANDLE(&pdev->dev),
-			ACPI_DEVICE_NOTIFY, acpi_ac_notify_handler);
+			ACPI_ALL_NOTIFY, acpi_ac_notify_handler);
 
 	ac = platform_get_drvdata(pdev);
 	if (ac->charger.dev)
-- 
cgit v0.10.2


From df45c712d1f4ef37714245fb75de726f4ca2bf8d Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Thu, 19 Dec 2013 20:38:15 +0800
Subject: ACPI / TPM: fix memory leak when walking ACPI namespace

In function ppi_callback(), memory allocated by acpi_get_name() will get
leaked when current device isn't the desired TPM device, so fix the
memory leak.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: All applicable <stable@vger.kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

diff --git a/drivers/char/tpm/tpm_ppi.c b/drivers/char/tpm/tpm_ppi.c
index 8e562dc..e1f3337 100644
--- a/drivers/char/tpm/tpm_ppi.c
+++ b/drivers/char/tpm/tpm_ppi.c
@@ -27,15 +27,18 @@ static char *tpm_device_name = "TPM";
 static acpi_status ppi_callback(acpi_handle handle, u32 level, void *context,
 				void **return_value)
 {
-	acpi_status status;
+	acpi_status status = AE_OK;
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
-	status = acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
-	if (strstr(buffer.pointer, context) != NULL) {
-		*return_value = handle;
+
+	if (ACPI_SUCCESS(acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer))) {
+		if (strstr(buffer.pointer, context) != NULL) {
+			*return_value = handle;
+			status = AE_CTRL_TERMINATE;
+		}
 		kfree(buffer.pointer);
-		return AE_CTRL_TERMINATE;
 	}
-	return AE_OK;
+
+	return status;
 }
 
 static inline void ppi_assign_params(union acpi_object params[4],
-- 
cgit v0.10.2


From e848582cee23f7ab540ec49ab1c7d7f8bfefcd84 Mon Sep 17 00:00:00 2001
From: Dmitry Kravkov <dmitry@broadcom.com>
Date: Sun, 5 Jan 2014 18:33:50 +0200
Subject: bnx2x: limit number of interrupt vectors for 57711

Original straightforward division may lead to zeroing number of SB and
null-pointer dereference when device is short of MSIX vectors or lacks
MSIX capabilities.

Reported-by: Vladislav Zolotarov <vladz@cloudius-systems.com>
Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com>
Signed-off-by: Yuval Mintz <yuvalmin@broadcom.com>
Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index a1f66e2..cb30d1a3 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -2499,4 +2499,6 @@ void bnx2x_set_local_cmng(struct bnx2x *bp);
 #define MCPR_SCRATCH_BASE(bp) \
 	(CHIP_IS_E1x(bp) ? MCP_REG_MCPR_SCRATCH : MCP_A_REG_MCPR_SCRATCH)
 
+#define E1H_MAX_MF_SB_COUNT (HC_SB_MAX_SB_E1X/(E1HVN_MAX * PORT_MAX))
+
 #endif /* bnx2x.h */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 814d0ec..8b3107b 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -11447,9 +11447,9 @@ static int bnx2x_get_hwinfo(struct bnx2x *bp)
 		}
 	}
 
-	/* adjust igu_sb_cnt to MF for E1x */
-	if (CHIP_IS_E1x(bp) && IS_MF(bp))
-		bp->igu_sb_cnt /= E1HVN_MAX;
+	/* adjust igu_sb_cnt to MF for E1H */
+	if (CHIP_IS_E1H(bp) && IS_MF(bp))
+		bp->igu_sb_cnt = min_t(u8, bp->igu_sb_cnt, E1H_MAX_MF_SB_COUNT);
 
 	/* port info */
 	bnx2x_get_port_hwinfo(bp);
-- 
cgit v0.10.2


From 89e18ae6e6288deb1940cd16afe4e6983545defa Mon Sep 17 00:00:00 2001
From: Michal Kalderon <michals@broadcom.com>
Date: Sun, 5 Jan 2014 18:33:51 +0200
Subject: bnx2x: Correct number of MSI-X vectors for VFs

Number of VFs in PCIe configuration space is zero-based. Driver incorrectly
sets the number of VFs to be larger by one than what actually is feasible by
HW, which might cause later VFs to fail to allocate their MSI-X interrupts.

Signed-off-by: Michal Kalderon <michals@broadcom.com>
Signed-off-by: Yuval Mintz <yuvalmin@broadcom.com>
Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 2e46c28..ddd95b9 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -3202,13 +3202,16 @@ int bnx2x_enable_sriov(struct bnx2x *bp)
 		bnx2x_iov_static_resc(bp, vf);
 	}
 
-	/* prepare msix vectors in VF configuration space */
+	/* prepare msix vectors in VF configuration space - the value in the
+	 * PCI configuration space should be the index of the last entry,
+	 * namely one less than the actual size of the table
+	 */
 	for (vf_idx = first_vf; vf_idx < first_vf + req_vfs; vf_idx++) {
 		bnx2x_pretend_func(bp, HW_VF_HANDLE(bp, vf_idx));
 		REG_WR(bp, PCICFG_OFFSET + GRC_CONFIG_REG_VF_MSIX_CONTROL,
-		       num_vf_queues);
+		       num_vf_queues - 1);
 		DP(BNX2X_MSG_IOV, "set msix vec num in VF %d cfg space to %d\n",
-		   vf_idx, num_vf_queues);
+		   vf_idx, num_vf_queues - 1);
 	}
 	bnx2x_pretend_func(bp, BP_ABS_FUNC(bp));
 
-- 
cgit v0.10.2


From 5b622918cd6f4ff5b5200ea6b2e48ae2fa6ad09e Mon Sep 17 00:00:00 2001
From: Michal Kalderon <michals@broadcom.com>
Date: Sun, 5 Jan 2014 18:33:52 +0200
Subject: bnx2x: Clean before update RSS arrives

When a PF receives a VF message indicating a change in RSS properties
it should clean the flags' bit-fields; Otherwise, it's possible that
some random values will be considered as flags by the lower layers configuring
the RSS in FW.

Signed-off-by: Michal Kalderon <michals@broadcom.com>
Signed-off-by: Yuval Mintz <yuvalmin@broadcom.com>
Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 32c92ab..95feada 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -4382,8 +4382,11 @@ int bnx2x_config_rss(struct bnx2x *bp,
 	struct bnx2x_raw_obj *r = &o->raw;
 
 	/* Do nothing if only driver cleanup was requested */
-	if (test_bit(RAMROD_DRV_CLR_ONLY, &p->ramrod_flags))
+	if (test_bit(RAMROD_DRV_CLR_ONLY, &p->ramrod_flags)) {
+		DP(BNX2X_MSG_SP, "Not configuring RSS ramrod_flags=%lx\n",
+		   p->ramrod_flags);
 		return 0;
+	}
 
 	r->set_pending(r);
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index 3dc2537..26fcba2 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -1805,6 +1805,9 @@ static void bnx2x_vf_mbx_update_rss(struct bnx2x *bp, struct bnx2x_virtf *vf,
 	vf_op_params->rss_result_mask = rss_tlv->rss_result_mask;
 
 	/* flags handled individually for backward/forward compatability */
+	vf_op_params->rss_flags = 0;
+	vf_op_params->ramrod_flags = 0;
+
 	if (rss_tlv->rss_flags & VFPF_RSS_MODE_DISABLED)
 		__set_bit(BNX2X_RSS_MODE_DISABLED, &vf_op_params->rss_flags);
 	if (rss_tlv->rss_flags & VFPF_RSS_MODE_REGULAR)
-- 
cgit v0.10.2


From 9dfef3adaebb42163d691be73e05b12da440cbe5 Mon Sep 17 00:00:00 2001
From: Yuval Mintz <yuvalmin@broadcom.com>
Date: Sun, 5 Jan 2014 18:33:53 +0200
Subject: bnx2x: fix AFEX memory overflow

There are 2 different (related) flows in the slowpath configuration
that utilize the same pointer and cast it to different structs;
This is obviously incorrect as the intended allocated memory is that
of the smaller struct, possibly causing the flow utilizing the larger
struct to corrupt other slowpath configuration.

Since both flows are exclusive, set the allocated memory to be a union
of both structs.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Yuval Mintz <yuvalmin@broadcom.com>
Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index cb30d1a3..2d5fce4 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -1250,7 +1250,10 @@ struct bnx2x_slowpath {
 	 * Therefore, if they would have been defined in the same union,
 	 * data can get corrupted.
 	 */
-	struct afex_vif_list_ramrod_data func_afex_rdata;
+	union {
+		struct afex_vif_list_ramrod_data	viflist_data;
+		struct function_update_data		func_update;
+	} func_afex_rdata;
 
 	/* used by dmae command executer */
 	struct dmae_command		dmae[MAX_DMAE_C];
-- 
cgit v0.10.2


From e8379c79542c95b25890ed49be652b1634deca17 Mon Sep 17 00:00:00 2001
From: Yuval Mintz <yuvalmin@broadcom.com>
Date: Sun, 5 Jan 2014 18:33:54 +0200
Subject: bnx2x: fix VLAN configuration for VFs.

If the hypervisor configures a vlan for the VF via the PF, the expected
result is that only packets tagged by said vlan will be received by the VF
(and that vlan will be silently removed).
Due to an incorrect manipulation of vlan filters in the driver, the
VF can receive untagged traffic even if the hypervisor configured
some vlan for it.

This patch corrects the behaviour.

Signed-off-by: Yuval Mintz <yuvalmin@broadcom.com>
Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 95feada..18438a5 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -2038,6 +2038,7 @@ static int bnx2x_vlan_mac_del_all(struct bnx2x *bp,
 	struct bnx2x_vlan_mac_ramrod_params p;
 	struct bnx2x_exe_queue_obj *exeq = &o->exe_queue;
 	struct bnx2x_exeq_elem *exeq_pos, *exeq_pos_n;
+	unsigned long flags;
 	int read_lock;
 	int rc = 0;
 
@@ -2046,8 +2047,9 @@ static int bnx2x_vlan_mac_del_all(struct bnx2x *bp,
 	spin_lock_bh(&exeq->lock);
 
 	list_for_each_entry_safe(exeq_pos, exeq_pos_n, &exeq->exe_queue, link) {
-		if (exeq_pos->cmd_data.vlan_mac.vlan_mac_flags ==
-		    *vlan_mac_flags) {
+		flags = exeq_pos->cmd_data.vlan_mac.vlan_mac_flags;
+		if (BNX2X_VLAN_MAC_CMP_FLAGS(flags) ==
+		    BNX2X_VLAN_MAC_CMP_FLAGS(*vlan_mac_flags)) {
 			rc = exeq->remove(bp, exeq->owner, exeq_pos);
 			if (rc) {
 				BNX2X_ERR("Failed to remove command\n");
@@ -2080,7 +2082,9 @@ static int bnx2x_vlan_mac_del_all(struct bnx2x *bp,
 		return read_lock;
 
 	list_for_each_entry(pos, &o->head, link) {
-		if (pos->vlan_mac_flags == *vlan_mac_flags) {
+		flags = pos->vlan_mac_flags;
+		if (BNX2X_VLAN_MAC_CMP_FLAGS(flags) ==
+		    BNX2X_VLAN_MAC_CMP_FLAGS(*vlan_mac_flags)) {
 			p.user_req.vlan_mac_flags = pos->vlan_mac_flags;
 			memcpy(&p.user_req.u, &pos->u, sizeof(pos->u));
 			rc = bnx2x_config_vlan_mac(bp, &p);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
index 658f4e3..6a53c15 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
@@ -266,6 +266,13 @@ enum {
 	BNX2X_DONT_CONSUME_CAM_CREDIT,
 	BNX2X_DONT_CONSUME_CAM_CREDIT_DEST,
 };
+/* When looking for matching filters, some flags are not interesting */
+#define BNX2X_VLAN_MAC_CMP_MASK	(1 << BNX2X_UC_LIST_MAC | \
+				 1 << BNX2X_ETH_MAC | \
+				 1 << BNX2X_ISCSI_ETH_MAC | \
+				 1 << BNX2X_NETQ_ETH_MAC)
+#define BNX2X_VLAN_MAC_CMP_FLAGS(flags) \
+	((flags) & BNX2X_VLAN_MAC_CMP_MASK)
 
 struct bnx2x_vlan_mac_ramrod_params {
 	/* Object to run the command from */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index ddd95b9..e7845e5 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -1209,6 +1209,11 @@ static void bnx2x_vfop_rxmode(struct bnx2x *bp, struct bnx2x_virtf *vf)
 		/* next state */
 		vfop->state = BNX2X_VFOP_RXMODE_DONE;
 
+		/* record the accept flags in vfdb so hypervisor can modify them
+		 * if necessary
+		 */
+		bnx2x_vfq(vf, ramrod->cl_id - vf->igu_base_id, accept_flags) =
+			ramrod->rx_accept_flags;
 		vfop->rc = bnx2x_config_rx_mode(bp, ramrod);
 		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
 op_err:
@@ -1224,39 +1229,43 @@ op_pending:
 	return;
 }
 
+static void bnx2x_vf_prep_rx_mode(struct bnx2x *bp, u8 qid,
+				  struct bnx2x_rx_mode_ramrod_params *ramrod,
+				  struct bnx2x_virtf *vf,
+				  unsigned long accept_flags)
+{
+	struct bnx2x_vf_queue *vfq = vfq_get(vf, qid);
+
+	memset(ramrod, 0, sizeof(*ramrod));
+	ramrod->cid = vfq->cid;
+	ramrod->cl_id = vfq_cl_id(vf, vfq);
+	ramrod->rx_mode_obj = &bp->rx_mode_obj;
+	ramrod->func_id = FW_VF_HANDLE(vf->abs_vfid);
+	ramrod->rx_accept_flags = accept_flags;
+	ramrod->tx_accept_flags = accept_flags;
+	ramrod->pstate = &vf->filter_state;
+	ramrod->state = BNX2X_FILTER_RX_MODE_PENDING;
+
+	set_bit(BNX2X_FILTER_RX_MODE_PENDING, &vf->filter_state);
+	set_bit(RAMROD_RX, &ramrod->ramrod_flags);
+	set_bit(RAMROD_TX, &ramrod->ramrod_flags);
+
+	ramrod->rdata = bnx2x_vf_sp(bp, vf, rx_mode_rdata.e2);
+	ramrod->rdata_mapping = bnx2x_vf_sp_map(bp, vf, rx_mode_rdata.e2);
+}
+
 int bnx2x_vfop_rxmode_cmd(struct bnx2x *bp,
 			  struct bnx2x_virtf *vf,
 			  struct bnx2x_vfop_cmd *cmd,
 			  int qid, unsigned long accept_flags)
 {
-	struct bnx2x_vf_queue *vfq = vfq_get(vf, qid);
 	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
 
 	if (vfop) {
 		struct bnx2x_rx_mode_ramrod_params *ramrod =
 			&vf->op_params.rx_mode;
 
-		memset(ramrod, 0, sizeof(*ramrod));
-
-		/* Prepare ramrod parameters */
-		ramrod->cid = vfq->cid;
-		ramrod->cl_id = vfq_cl_id(vf, vfq);
-		ramrod->rx_mode_obj = &bp->rx_mode_obj;
-		ramrod->func_id = FW_VF_HANDLE(vf->abs_vfid);
-
-		ramrod->rx_accept_flags = accept_flags;
-		ramrod->tx_accept_flags = accept_flags;
-		ramrod->pstate = &vf->filter_state;
-		ramrod->state = BNX2X_FILTER_RX_MODE_PENDING;
-
-		set_bit(BNX2X_FILTER_RX_MODE_PENDING, &vf->filter_state);
-		set_bit(RAMROD_RX, &ramrod->ramrod_flags);
-		set_bit(RAMROD_TX, &ramrod->ramrod_flags);
-
-		ramrod->rdata =
-			bnx2x_vf_sp(bp, vf, rx_mode_rdata.e2);
-		ramrod->rdata_mapping =
-			bnx2x_vf_sp_map(bp, vf, rx_mode_rdata.e2);
+		bnx2x_vf_prep_rx_mode(bp, qid, ramrod, vf, accept_flags);
 
 		bnx2x_vfop_opset(BNX2X_VFOP_RXMODE_CONFIG,
 				 bnx2x_vfop_rxmode, cmd->done);
@@ -3439,10 +3448,18 @@ out:
 
 int bnx2x_set_vf_vlan(struct net_device *dev, int vfidx, u16 vlan, u8 qos)
 {
+	struct bnx2x_queue_state_params q_params = {NULL};
+	struct bnx2x_vlan_mac_ramrod_params ramrod_param;
+	struct bnx2x_queue_update_params *update_params;
+	struct pf_vf_bulletin_content *bulletin = NULL;
+	struct bnx2x_rx_mode_ramrod_params rx_ramrod;
 	struct bnx2x *bp = netdev_priv(dev);
-	int rc, q_logical_state;
+	struct bnx2x_vlan_mac_obj *vlan_obj;
+	unsigned long vlan_mac_flags = 0;
+	unsigned long ramrod_flags = 0;
 	struct bnx2x_virtf *vf = NULL;
-	struct pf_vf_bulletin_content *bulletin = NULL;
+	unsigned long accept_flags;
+	int rc;
 
 	/* sanity and init */
 	rc = bnx2x_vf_ndo_prep(bp, vfidx, &vf, &bulletin);
@@ -3460,104 +3477,118 @@ int bnx2x_set_vf_vlan(struct net_device *dev, int vfidx, u16 vlan, u8 qos)
 	/* update PF's copy of the VF's bulletin. No point in posting the vlan
 	 * to the VF since it doesn't have anything to do with it. But it useful
 	 * to store it here in case the VF is not up yet and we can only
-	 * configure the vlan later when it does.
+	 * configure the vlan later when it does. Treat vlan id 0 as remove the
+	 * Host tag.
 	 */
-	bulletin->valid_bitmap |= 1 << VLAN_VALID;
+	if (vlan > 0)
+		bulletin->valid_bitmap |= 1 << VLAN_VALID;
+	else
+		bulletin->valid_bitmap &= ~(1 << VLAN_VALID);
 	bulletin->vlan = vlan;
 
 	/* is vf initialized and queue set up? */
-	q_logical_state =
-		bnx2x_get_q_logical_state(bp, &bnx2x_leading_vfq(vf, sp_obj));
-	if (vf->state == VF_ENABLED &&
-	    q_logical_state == BNX2X_Q_LOGICAL_STATE_ACTIVE) {
-		/* configure the vlan in device on this vf's queue */
-		unsigned long ramrod_flags = 0;
-		unsigned long vlan_mac_flags = 0;
-		struct bnx2x_vlan_mac_obj *vlan_obj =
-			&bnx2x_leading_vfq(vf, vlan_obj);
-		struct bnx2x_vlan_mac_ramrod_params ramrod_param;
-		struct bnx2x_queue_state_params q_params = {NULL};
-		struct bnx2x_queue_update_params *update_params;
+	if (vf->state != VF_ENABLED ||
+	    bnx2x_get_q_logical_state(bp, &bnx2x_leading_vfq(vf, sp_obj)) !=
+	    BNX2X_Q_LOGICAL_STATE_ACTIVE)
+		return rc;
 
-		rc = validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, mac_obj));
-		if (rc)
-			return rc;
-		memset(&ramrod_param, 0, sizeof(ramrod_param));
+	/* configure the vlan in device on this vf's queue */
+	vlan_obj = &bnx2x_leading_vfq(vf, vlan_obj);
+	rc = validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, mac_obj));
+	if (rc)
+		return rc;
 
-		/* must lock vfpf channel to protect against vf flows */
-		bnx2x_lock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_VLAN);
+	/* must lock vfpf channel to protect against vf flows */
+	bnx2x_lock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_VLAN);
 
-		/* remove existing vlans */
-		__set_bit(RAMROD_COMP_WAIT, &ramrod_flags);
-		rc = vlan_obj->delete_all(bp, vlan_obj, &vlan_mac_flags,
-					  &ramrod_flags);
-		if (rc) {
-			BNX2X_ERR("failed to delete vlans\n");
-			rc = -EINVAL;
-			goto out;
-		}
+	/* remove existing vlans */
+	__set_bit(RAMROD_COMP_WAIT, &ramrod_flags);
+	rc = vlan_obj->delete_all(bp, vlan_obj, &vlan_mac_flags,
+				  &ramrod_flags);
+	if (rc) {
+		BNX2X_ERR("failed to delete vlans\n");
+		rc = -EINVAL;
+		goto out;
+	}
+
+	/* need to remove/add the VF's accept_any_vlan bit */
+	accept_flags = bnx2x_leading_vfq(vf, accept_flags);
+	if (vlan)
+		clear_bit(BNX2X_ACCEPT_ANY_VLAN, &accept_flags);
+	else
+		set_bit(BNX2X_ACCEPT_ANY_VLAN, &accept_flags);
+
+	bnx2x_vf_prep_rx_mode(bp, LEADING_IDX, &rx_ramrod, vf,
+			      accept_flags);
+	bnx2x_leading_vfq(vf, accept_flags) = accept_flags;
+	bnx2x_config_rx_mode(bp, &rx_ramrod);
+
+	/* configure the new vlan to device */
+	memset(&ramrod_param, 0, sizeof(ramrod_param));
+	__set_bit(RAMROD_COMP_WAIT, &ramrod_flags);
+	ramrod_param.vlan_mac_obj = vlan_obj;
+	ramrod_param.ramrod_flags = ramrod_flags;
+	set_bit(BNX2X_DONT_CONSUME_CAM_CREDIT,
+		&ramrod_param.user_req.vlan_mac_flags);
+	ramrod_param.user_req.u.vlan.vlan = vlan;
+	ramrod_param.user_req.cmd = BNX2X_VLAN_MAC_ADD;
+	rc = bnx2x_config_vlan_mac(bp, &ramrod_param);
+	if (rc) {
+		BNX2X_ERR("failed to configure vlan\n");
+		rc =  -EINVAL;
+		goto out;
+	}
 
-		/* send queue update ramrod to configure default vlan and silent
-		 * vlan removal
+	/* send queue update ramrod to configure default vlan and silent
+	 * vlan removal
+	 */
+	__set_bit(RAMROD_COMP_WAIT, &q_params.ramrod_flags);
+	q_params.cmd = BNX2X_Q_CMD_UPDATE;
+	q_params.q_obj = &bnx2x_leading_vfq(vf, sp_obj);
+	update_params = &q_params.params.update;
+	__set_bit(BNX2X_Q_UPDATE_DEF_VLAN_EN_CHNG,
+		  &update_params->update_flags);
+	__set_bit(BNX2X_Q_UPDATE_SILENT_VLAN_REM_CHNG,
+		  &update_params->update_flags);
+	if (vlan == 0) {
+		/* if vlan is 0 then we want to leave the VF traffic
+		 * untagged, and leave the incoming traffic untouched
+		 * (i.e. do not remove any vlan tags).
 		 */
-		__set_bit(RAMROD_COMP_WAIT, &q_params.ramrod_flags);
-		q_params.cmd = BNX2X_Q_CMD_UPDATE;
-		q_params.q_obj = &bnx2x_leading_vfq(vf, sp_obj);
-		update_params = &q_params.params.update;
-		__set_bit(BNX2X_Q_UPDATE_DEF_VLAN_EN_CHNG,
+		__clear_bit(BNX2X_Q_UPDATE_DEF_VLAN_EN,
+			    &update_params->update_flags);
+		__clear_bit(BNX2X_Q_UPDATE_SILENT_VLAN_REM,
+			    &update_params->update_flags);
+	} else {
+		/* configure default vlan to vf queue and set silent
+		 * vlan removal (the vf remains unaware of this vlan).
+		 */
+		__set_bit(BNX2X_Q_UPDATE_DEF_VLAN_EN,
 			  &update_params->update_flags);
-		__set_bit(BNX2X_Q_UPDATE_SILENT_VLAN_REM_CHNG,
+		__set_bit(BNX2X_Q_UPDATE_SILENT_VLAN_REM,
 			  &update_params->update_flags);
+		update_params->def_vlan = vlan;
+		update_params->silent_removal_value =
+			vlan & VLAN_VID_MASK;
+		update_params->silent_removal_mask = VLAN_VID_MASK;
+	}
 
-		if (vlan == 0) {
-			/* if vlan is 0 then we want to leave the VF traffic
-			 * untagged, and leave the incoming traffic untouched
-			 * (i.e. do not remove any vlan tags).
-			 */
-			__clear_bit(BNX2X_Q_UPDATE_DEF_VLAN_EN,
-				    &update_params->update_flags);
-			__clear_bit(BNX2X_Q_UPDATE_SILENT_VLAN_REM,
-				    &update_params->update_flags);
-		} else {
-			/* configure the new vlan to device */
-			__set_bit(RAMROD_COMP_WAIT, &ramrod_flags);
-			ramrod_param.vlan_mac_obj = vlan_obj;
-			ramrod_param.ramrod_flags = ramrod_flags;
-			ramrod_param.user_req.u.vlan.vlan = vlan;
-			ramrod_param.user_req.cmd = BNX2X_VLAN_MAC_ADD;
-			rc = bnx2x_config_vlan_mac(bp, &ramrod_param);
-			if (rc) {
-				BNX2X_ERR("failed to configure vlan\n");
-				rc =  -EINVAL;
-				goto out;
-			}
-
-			/* configure default vlan to vf queue and set silent
-			 * vlan removal (the vf remains unaware of this vlan).
-			 */
-			update_params = &q_params.params.update;
-			__set_bit(BNX2X_Q_UPDATE_DEF_VLAN_EN,
-				  &update_params->update_flags);
-			__set_bit(BNX2X_Q_UPDATE_SILENT_VLAN_REM,
-				  &update_params->update_flags);
-			update_params->def_vlan = vlan;
-		}
+	/* Update the Queue state */
+	rc = bnx2x_queue_state_change(bp, &q_params);
+	if (rc) {
+		BNX2X_ERR("Failed to configure default VLAN\n");
+		goto out;
+	}
 
-		/* Update the Queue state */
-		rc = bnx2x_queue_state_change(bp, &q_params);
-		if (rc) {
-			BNX2X_ERR("Failed to configure default VLAN\n");
-			goto out;
-		}
 
-		/* clear the flag indicating that this VF needs its vlan
-		 * (will only be set if the HV configured the Vlan before vf was
-		 * up and we were called because the VF came up later
-		 */
+	/* clear the flag indicating that this VF needs its vlan
+	 * (will only be set if the HV configured the Vlan before vf was
+	 * up and we were called because the VF came up later
+	 */
 out:
-		vf->cfg_flags &= ~VF_CFG_VLAN;
-		bnx2x_unlock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_VLAN);
-	}
+	vf->cfg_flags &= ~VF_CFG_VLAN;
+	bnx2x_unlock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_VLAN);
+
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index 1ff6a93..8c213fa52 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -74,6 +74,7 @@ struct bnx2x_vf_queue {
 	/* VLANs object */
 	struct bnx2x_vlan_mac_obj	vlan_obj;
 	atomic_t vlan_count;		/* 0 means vlan-0 is set  ~ untagged */
+	unsigned long accept_flags;	/* last accept flags configured */
 
 	/* Queue Slow-path State object */
 	struct bnx2x_queue_sp_obj	sp_obj;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index 26fcba2..0756d7d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -1598,6 +1598,8 @@ static void bnx2x_vfop_mbx_qfilters(struct bnx2x *bp, struct bnx2x_virtf *vf)
 
 		if (msg->flags & VFPF_SET_Q_FILTERS_RX_MASK_CHANGED) {
 			unsigned long accept = 0;
+			struct pf_vf_bulletin_content *bulletin =
+				BP_VF_BULLETIN(bp, vf->index);
 
 			/* covert VF-PF if mask to bnx2x accept flags */
 			if (msg->rx_mask & VFPF_RX_MASK_ACCEPT_MATCHED_UNICAST)
@@ -1617,9 +1619,11 @@ static void bnx2x_vfop_mbx_qfilters(struct bnx2x *bp, struct bnx2x_virtf *vf)
 				__set_bit(BNX2X_ACCEPT_BROADCAST, &accept);
 
 			/* A packet arriving the vf's mac should be accepted
-			 * with any vlan
+			 * with any vlan, unless a vlan has already been
+			 * configured.
 			 */
-			__set_bit(BNX2X_ACCEPT_ANY_VLAN, &accept);
+			if (!(bulletin->valid_bitmap & (1 << VLAN_VALID)))
+				__set_bit(BNX2X_ACCEPT_ANY_VLAN, &accept);
 
 			/* set rx-mode */
 			rc = bnx2x_vfop_rxmode_cmd(bp, vf, &cmd,
@@ -1710,6 +1714,21 @@ static void bnx2x_vf_mbx_set_q_filters(struct bnx2x *bp,
 			goto response;
 		}
 	}
+	/* if vlan was set by hypervisor we don't allow guest to config vlan */
+	if (bulletin->valid_bitmap & 1 << VLAN_VALID) {
+		int i;
+
+		/* search for vlan filters */
+		for (i = 0; i < filters->n_mac_vlan_filters; i++) {
+			if (filters->filters[i].flags &
+			    VFPF_Q_FILTER_VLAN_TAG_VALID) {
+				BNX2X_ERR("VF[%d] attempted to configure vlan but one was already set by Hypervisor. Aborting request\n",
+					  vf->abs_vfid);
+				vf->op_rc = -EPERM;
+				goto response;
+			}
+		}
+	}
 
 	/* verify vf_qid */
 	if (filters->vf_qid > vf_rxq_count(vf))
-- 
cgit v0.10.2


From 7d30622dbe64a7207af8a98f48d4a4ef00ab658a Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@freescale.com>
Date: Sun, 5 Jan 2014 22:08:25 -0200
Subject: fec: Revert "fec: Do not assume that PHY reset is active low"

In order to keep DT compatibility we need to revert this, otherwise the original
dts files will no longer work with this driver change.

This reverts commit 7a399e3a2e05bc580a78ea72371b3896827f72e1.

Signed-off-by: Fabio Estevam <fabio.estevam@freescale.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 45b8b22..50bb71c 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2049,8 +2049,6 @@ static void fec_reset_phy(struct platform_device *pdev)
 	int err, phy_reset;
 	int msec = 1;
 	struct device_node *np = pdev->dev.of_node;
-	enum of_gpio_flags flags;
-	bool port;
 
 	if (!np)
 		return;
@@ -2060,22 +2058,18 @@ static void fec_reset_phy(struct platform_device *pdev)
 	if (msec > 1000)
 		msec = 1;
 
-	phy_reset = of_get_named_gpio_flags(np, "phy-reset-gpios", 0, &flags);
+	phy_reset = of_get_named_gpio(np, "phy-reset-gpios", 0);
 	if (!gpio_is_valid(phy_reset))
 		return;
 
-	if (flags & OF_GPIO_ACTIVE_LOW)
-		port = GPIOF_OUT_INIT_LOW;
-	else
-		port = GPIOF_OUT_INIT_HIGH;
-
-	err = devm_gpio_request_one(&pdev->dev, phy_reset, port, "phy-reset");
+	err = devm_gpio_request_one(&pdev->dev, phy_reset,
+				    GPIOF_OUT_INIT_LOW, "phy-reset");
 	if (err) {
 		dev_err(&pdev->dev, "failed to get phy-reset-gpios: %d\n", err);
 		return;
 	}
 	msleep(msec);
-	gpio_set_value(phy_reset, !port);
+	gpio_set_value(phy_reset, 1);
 }
 #else /* CONFIG_OF */
 static void fec_reset_phy(struct platform_device *pdev)
-- 
cgit v0.10.2


From 965801e1eb624154fe5e9dc5d2ff0b7f1951a11c Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Mon, 6 Jan 2014 01:45:50 +0100
Subject: net: 6lowpan: fix lowpan_header_create non-compression memcpy call

In function lowpan_header_create(), we invoke the following code
construct:

  struct ipv6hdr *hdr;
  ...
  hdr = ipv6_hdr(skb);
  ...
  if (...)
    memcpy(hc06_ptr + 1, &hdr->flow_lbl[1], 2);
  else
    memcpy(hc06_ptr, &hdr, 4);

Where the else path of the condition, that is, non-compression
path, calls memcpy() with a pointer to struct ipv6hdr *hdr as
source, thus two levels of indirection. This cannot be correct,
and likely only one level of pointer was intended as source
buffer for memcpy() here.

Fixes: 44331fe2aa0d ("IEEE802.15.4: 6LoWPAN basic support")
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
Cc: Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
Cc: Werner Almesberger <werner@almesberger.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c
index 459e200..a2d2456 100644
--- a/net/ieee802154/6lowpan.c
+++ b/net/ieee802154/6lowpan.c
@@ -547,7 +547,7 @@ static int lowpan_header_create(struct sk_buff *skb,
 			hc06_ptr += 3;
 		} else {
 			/* compress nothing */
-			memcpy(hc06_ptr, &hdr, 4);
+			memcpy(hc06_ptr, hdr, 4);
 			/* replace the top byte with new ECN | DSCP format */
 			*hc06_ptr = tmp;
 			hc06_ptr += 4;
-- 
cgit v0.10.2


From f35f76ee76df008131bbe01a2297de0c55ee2297 Mon Sep 17 00:00:00 2001
From: Josh Boyer <jwboyer@redhat.com>
Date: Sun, 5 Jan 2014 10:24:01 -0500
Subject: xen-netback: Include header for vmalloc

Commit ac3d5ac27735 ("xen-netback: fix guest-receive-side array sizes")
added calls to vmalloc and vfree in the interface.c file without including
<linux/vmalloc.h>.  This causes build failures if the
-Werror=implicit-function-declaration flag is passed.

Signed-off-by: Josh Boyer <jwboyer@fedoraproject.org>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 34ca4e5..fff8cdd 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -34,6 +34,7 @@
 #include <linux/ethtool.h>
 #include <linux/rtnetlink.h>
 #include <linux/if_vlan.h>
+#include <linux/vmalloc.h>
 
 #include <xen/events.h>
 #include <asm/xen/hypercall.h>
-- 
cgit v0.10.2


From e9a1d0165bbda4398d4a5d71736cf6390fb42c6f Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@linux-m68k.org>
Date: Fri, 3 Jan 2014 16:43:51 +0100
Subject: metag/smp: Make boot_secondary() static

boot_secondary() is not used outside arch/metag/kernel/smp.c, hence make it
static.

Signed-off-by: Geert Uytterhoeven <geert+renesas@linux-m68k.org>
Signed-off-by: James Hogan <james.hogan@imgtec.com>

diff --git a/arch/metag/kernel/smp.c b/arch/metag/kernel/smp.c
index f74008b..f006d22 100644
--- a/arch/metag/kernel/smp.c
+++ b/arch/metag/kernel/smp.c
@@ -68,7 +68,7 @@ static DECLARE_COMPLETION(cpu_running);
 /*
  * "thread" is assumed to be a valid Meta hardware thread ID.
  */
-int boot_secondary(unsigned int thread, struct task_struct *idle)
+static int boot_secondary(unsigned int thread, struct task_struct *idle)
 {
 	u32 val;
 
-- 
cgit v0.10.2


From 058840c7a06bc7d6825caae7c7f9c4759b24aaa5 Mon Sep 17 00:00:00 2001
From: Ben Widawsky <benjamin.widawsky@intel.com>
Date: Tue, 24 Dec 2013 15:18:54 -0800
Subject: drm/i915/bdw: Flush system agent on gen8 also

gem_gtt_cpu_tlb seems to indicate that it is needed.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=72869

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index c79dd2b..d3c3b5b 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -906,14 +906,12 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 		WARN_ON(readq(&gtt_entries[i-1])
 			!= gen8_pte_encode(addr, level, true));
 
-#if 0 /* TODO: Still needed on GEN8? */
 	/* This next bit makes the above posting read even more important. We
 	 * want to flush the TLBs only after we're certain all the PTE updates
 	 * have finished.
 	 */
 	I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
 	POSTING_READ(GFX_FLSH_CNTL_GEN6);
-#endif
 }
 
 /*
-- 
cgit v0.10.2


From be505f643925e257087247b996cd8ece787c12af Mon Sep 17 00:00:00 2001
From: Alexander van Heukelum <heukelum@fastmail.fm>
Date: Sat, 28 Dec 2013 21:00:39 +0100
Subject: Revert "drm/i915: assume all GM45 Acer laptops use inverted backlight
 PWM"

My Acer 8510TZ stops displaying anything when X starts with Linus' current
tree. I bisected it down to commit ee1452d74584.

This patch reverts commit ee1452d74584.

After the revert, everything works as before.

Signed-off-by: Alexander van Heukelum <heukelum@fastmail.fm>
Reported-by: Dylan Borg <borgdylan@hotmail.com> (for a Acer Extensa 5635Z)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 54e82a8..769b864 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -10541,11 +10541,20 @@ static struct intel_quirk intel_quirks[] = {
 	/* Sony Vaio Y cannot use SSC on LVDS */
 	{ 0x0046, 0x104d, 0x9076, quirk_ssc_force_disable },
 
-	/*
-	 * All GM45 Acer (and its brands eMachines and Packard Bell) laptops
-	 * seem to use inverted backlight PWM.
-	 */
-	{ 0x2a42, 0x1025, PCI_ANY_ID, quirk_invert_brightness },
+	/* Acer Aspire 5734Z must invert backlight brightness */
+	{ 0x2a42, 0x1025, 0x0459, quirk_invert_brightness },
+
+	/* Acer/eMachines G725 */
+	{ 0x2a42, 0x1025, 0x0210, quirk_invert_brightness },
+
+	/* Acer/eMachines e725 */
+	{ 0x2a42, 0x1025, 0x0212, quirk_invert_brightness },
+
+	/* Acer/Packard Bell NCL20 */
+	{ 0x2a42, 0x1025, 0x034b, quirk_invert_brightness },
+
+	/* Acer Aspire 4736Z */
+	{ 0x2a42, 0x1025, 0x0260, quirk_invert_brightness },
 
 	/* Dell XPS13 HD Sandy Bridge */
 	{ 0x0116, 0x1028, 0x052e, quirk_no_pcm_pwm_enable },
-- 
cgit v0.10.2


From 2690d97ade05c5325cbf7c72b94b90d265659886 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Tue, 31 Dec 2013 16:28:39 +0100
Subject: netfilter: nf_nat: fix access to uninitialized buffer in IRC NAT
 helper

Commit 5901b6be885e attempted to introduce IPv6 support into
IRC NAT helper. By doing so, the following code seemed to be removed
by accident:

  ip = ntohl(exp->master->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip);
  sprintf(buffer, "%u %u", ip, port);
  pr_debug("nf_nat_irc: inserting '%s' == %pI4, port %u\n", buffer, &ip, port);

This leads to the fact that buffer[] was left uninitialized and
contained some stack value. When we call nf_nat_mangle_tcp_packet(),
we call strlen(buffer) on excatly this uninitialized buffer. If we
are unlucky and the skb has enough tailroom, we overwrite resp. leak
contents with values that sit on our stack into the packet and send
that out to the receiver.

Since the rather informal DCC spec [1] does not seem to specify
IPv6 support right now, we log such occurences so that admins can
act accordingly, and drop the packet. I've looked into XChat source,
and IPv6 is not supported there: addresses are in u32 and print
via %u format string.

Therefore, restore old behaviour as in IPv4, use snprintf(). The
IRC helper does not support IPv6 by now. By this, we can safely use
strlen(buffer) in nf_nat_mangle_tcp_packet() and prevent a buffer
overflow. Also simplify some code as we now have ct variable anyway.

  [1] http://www.irchelp.org/irchelp/rfc/ctcpspec.html

Fixes: 5901b6be885e ("netfilter: nf_nat: support IPv6 in IRC NAT helper")
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Harald Welte <laforge@gnumonks.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c
index f02b360..1fb2258 100644
--- a/net/netfilter/nf_nat_irc.c
+++ b/net/netfilter/nf_nat_irc.c
@@ -34,10 +34,14 @@ static unsigned int help(struct sk_buff *skb,
 			 struct nf_conntrack_expect *exp)
 {
 	char buffer[sizeof("4294967296 65635")];
+	struct nf_conn *ct = exp->master;
+	union nf_inet_addr newaddr;
 	u_int16_t port;
 	unsigned int ret;
 
 	/* Reply comes from server. */
+	newaddr = ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3;
+
 	exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port;
 	exp->dir = IP_CT_DIR_REPLY;
 	exp->expectfn = nf_nat_follow_master;
@@ -57,17 +61,35 @@ static unsigned int help(struct sk_buff *skb,
 	}
 
 	if (port == 0) {
-		nf_ct_helper_log(skb, exp->master, "all ports in use");
+		nf_ct_helper_log(skb, ct, "all ports in use");
 		return NF_DROP;
 	}
 
-	ret = nf_nat_mangle_tcp_packet(skb, exp->master, ctinfo,
-				       protoff, matchoff, matchlen, buffer,
-				       strlen(buffer));
+	/* strlen("\1DCC CHAT chat AAAAAAAA P\1\n")=27
+	 * strlen("\1DCC SCHAT chat AAAAAAAA P\1\n")=28
+	 * strlen("\1DCC SEND F AAAAAAAA P S\1\n")=26
+	 * strlen("\1DCC MOVE F AAAAAAAA P S\1\n")=26
+	 * strlen("\1DCC TSEND F AAAAAAAA P S\1\n")=27
+	 *
+	 * AAAAAAAAA: bound addr (1.0.0.0==16777216, min 8 digits,
+	 *                        255.255.255.255==4294967296, 10 digits)
+	 * P:         bound port (min 1 d, max 5d (65635))
+	 * F:         filename   (min 1 d )
+	 * S:         size       (min 1 d )
+	 * 0x01, \n:  terminators
+	 */
+	/* AAA = "us", ie. where server normally talks to. */
+	snprintf(buffer, sizeof(buffer), "%u %u", ntohl(newaddr.ip), port);
+	pr_debug("nf_nat_irc: inserting '%s' == %pI4, port %u\n",
+		 buffer, &newaddr.ip, port);
+
+	ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff, matchoff,
+				       matchlen, buffer, strlen(buffer));
 	if (ret != NF_ACCEPT) {
-		nf_ct_helper_log(skb, exp->master, "cannot mangle packet");
+		nf_ct_helper_log(skb, ct, "cannot mangle packet");
 		nf_ct_unexpect_related(exp);
 	}
+
 	return ret;
 }
 
-- 
cgit v0.10.2


From f2661adc0c134d890d84c32d7cb54a2b4d1f0a5f Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Sat, 4 Jan 2014 14:10:43 +0100
Subject: netfilter: only warn once on wrong seqadj usage

Avoid potentially spamming the kernel log with WARN splash messages
when catching wrong usage of seqadj, by simply using WARN_ONCE.

This is a followup to commit db12cf274353 (netfilter: WARN about
wrong usage of sequence number adjustments)

Suggested-by: Flavio Leitner <fbl@redhat.com>
Suggested-by: Daniel Borkmann <dborkman@redhat.com>
Suggested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

diff --git a/net/netfilter/nf_conntrack_seqadj.c b/net/netfilter/nf_conntrack_seqadj.c
index b2d38da..f6e2ae9 100644
--- a/net/netfilter/nf_conntrack_seqadj.c
+++ b/net/netfilter/nf_conntrack_seqadj.c
@@ -37,7 +37,7 @@ int nf_ct_seqadj_set(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
 		return 0;
 
 	if (unlikely(!seqadj)) {
-		WARN(1, "Wrong seqadj usage, missing nfct_seqadj_ext_add()\n");
+		WARN_ONCE(1, "Missing nfct_seqadj_ext_add() setup call\n");
 		return 0;
 	}
 
-- 
cgit v0.10.2


From da1388d655292a11b5e9c011532e9ca83f77e1d3 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara.volam@emulex.com>
Date: Mon, 6 Jan 2014 13:02:23 +0530
Subject: be2net: disable RSS when number of RXQs is reduced to 1 via
 set-channels

When *only* the default RXQ is used, the RSS policy must be disabled so
that all IP and no-IP traffic is placed into the default RXQ. If not,
IP traffic is dropped.

Also, issue the RSS_CONFIG cmd only if FW advertises RSS capability for
the interface.
Signed-off-by: Vasundhara Volam <vasundhara.volam@emulex.com>
Signed-off-by: Sathya Perla <sathya.perla@emulex.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index e0e8bc1..b84902e 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -2017,6 +2017,9 @@ int be_cmd_rss_config(struct be_adapter *adapter, u8 *rsstable,
 			0x3ea83c02, 0x4a110304};
 	int status;
 
+	if (!(be_if_cap_flags(adapter) & BE_IF_FLAGS_RSS))
+		return 0;
+
 	if (mutex_lock_interruptible(&adapter->mbox_lock))
 		return -1;
 
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 0fde69d..6b774a5 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -2744,13 +2744,16 @@ static int be_rx_qs_create(struct be_adapter *adapter)
 		if (!BEx_chip(adapter))
 			adapter->rss_flags |= RSS_ENABLE_UDP_IPV4 |
 						RSS_ENABLE_UDP_IPV6;
+	} else {
+		/* Disable RSS, if only default RX Q is created */
+		adapter->rss_flags = RSS_ENABLE_NONE;
+	}
 
-		rc = be_cmd_rss_config(adapter, rsstable, adapter->rss_flags,
-				       128);
-		if (rc) {
-			adapter->rss_flags = 0;
-			return rc;
-		}
+	rc = be_cmd_rss_config(adapter, rsstable, adapter->rss_flags,
+			       128);
+	if (rc) {
+		adapter->rss_flags = RSS_ENABLE_NONE;
+		return rc;
 	}
 
 	/* First time posting */
-- 
cgit v0.10.2


From 5eeff6354faffb3f140d690eec1cede78de53b06 Mon Sep 17 00:00:00 2001
From: Suresh Reddy <suresh.reddy@emulex.com>
Date: Mon, 6 Jan 2014 13:02:24 +0530
Subject: be2net: increase the timeout value for loopback-test FW cmd

The loopback test FW cmd may need upto 15 seconds to complete on
certain PHYs. This patch also fixes the name of the completion variable
used to synchronize FW cmd completions as it not used by the flashing
cmd alone anymore.

Signed-off-by: Suresh Reddy <suresh.reddy@emulex.com>
Signed-off-by: Sathya Perla <sathya.perla@emulex.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 5878df6..2e031f2 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -480,7 +480,7 @@ struct be_adapter {
 	struct list_head entry;
 
 	u32 flash_status;
-	struct completion flash_compl;
+	struct completion et_cmd_compl;
 
 	struct be_resources res;	/* resources available for the func */
 	u16 num_vfs;			/* Number of VFs provisioned by PF */
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index b84902e..94c35c8 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -141,11 +141,17 @@ static int be_mcc_compl_process(struct be_adapter *adapter,
 		subsystem = resp_hdr->subsystem;
 	}
 
+	if (opcode == OPCODE_LOWLEVEL_LOOPBACK_TEST &&
+	    subsystem == CMD_SUBSYSTEM_LOWLEVEL) {
+		complete(&adapter->et_cmd_compl);
+		return 0;
+	}
+
 	if (((opcode == OPCODE_COMMON_WRITE_FLASHROM) ||
 	     (opcode == OPCODE_COMMON_WRITE_OBJECT)) &&
 	    (subsystem == CMD_SUBSYSTEM_COMMON)) {
 		adapter->flash_status = compl_status;
-		complete(&adapter->flash_compl);
+		complete(&adapter->et_cmd_compl);
 	}
 
 	if (compl_status == MCC_STATUS_SUCCESS) {
@@ -2163,7 +2169,7 @@ int lancer_cmd_write_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
 	be_mcc_notify(adapter);
 	spin_unlock_bh(&adapter->mcc_lock);
 
-	if (!wait_for_completion_timeout(&adapter->flash_compl,
+	if (!wait_for_completion_timeout(&adapter->et_cmd_compl,
 					 msecs_to_jiffies(60000)))
 		status = -1;
 	else
@@ -2258,8 +2264,8 @@ int be_cmd_write_flashrom(struct be_adapter *adapter, struct be_dma_mem *cmd,
 	be_mcc_notify(adapter);
 	spin_unlock_bh(&adapter->mcc_lock);
 
-	if (!wait_for_completion_timeout(&adapter->flash_compl,
-			msecs_to_jiffies(40000)))
+	if (!wait_for_completion_timeout(&adapter->et_cmd_compl,
+					 msecs_to_jiffies(40000)))
 		status = -1;
 	else
 		status = adapter->flash_status;
@@ -2370,6 +2376,7 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_loopback_test *req;
+	struct be_cmd_resp_loopback_test *resp;
 	int status;
 
 	spin_lock_bh(&adapter->mcc_lock);
@@ -2384,8 +2391,8 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
 
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_LOWLEVEL,
 			OPCODE_LOWLEVEL_LOOPBACK_TEST, sizeof(*req), wrb, NULL);
-	req->hdr.timeout = cpu_to_le32(4);
 
+	req->hdr.timeout = cpu_to_le32(15);
 	req->pattern = cpu_to_le64(pattern);
 	req->src_port = cpu_to_le32(port_num);
 	req->dest_port = cpu_to_le32(port_num);
@@ -2393,12 +2400,15 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
 	req->num_pkts = cpu_to_le32(num_pkts);
 	req->loopback_type = cpu_to_le32(loopback_type);
 
-	status = be_mcc_notify_wait(adapter);
-	if (!status) {
-		struct be_cmd_resp_loopback_test *resp = embedded_payload(wrb);
-		status = le32_to_cpu(resp->status);
-	}
+	be_mcc_notify(adapter);
+
+	spin_unlock_bh(&adapter->mcc_lock);
 
+	wait_for_completion(&adapter->et_cmd_compl);
+	resp = embedded_payload(wrb);
+	status = le32_to_cpu(resp->status);
+
+	return status;
 err:
 	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 6b774a5..fa44bba 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -4208,7 +4208,7 @@ static int be_ctrl_init(struct be_adapter *adapter)
 	spin_lock_init(&adapter->mcc_lock);
 	spin_lock_init(&adapter->mcc_cq_lock);
 
-	init_completion(&adapter->flash_compl);
+	init_completion(&adapter->et_cmd_compl);
 	pci_save_state(adapter->pdev);
 	return 0;
 
-- 
cgit v0.10.2


From e3dc867c1758fc4ae6fc6b63ea6bbcd454479f08 Mon Sep 17 00:00:00 2001
From: Suresh Reddy <suresh.reddy@emulex.com>
Date: Mon, 6 Jan 2014 13:02:25 +0530
Subject: be2net: fix max_evt_qs calculation for BE3 in SR-IOV config

The driver wrongly assumes 16 EQs/vectors are available for each BE3 PF.
When SR-IOV is enabled, a BE3 PF can support only a max of 8 EQs.

Signed-off-by: Suresh Reddy <suresh.reddy@emulex.com>
Signed-off-by: Sathya Perla <sathya.perla@emulex.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 2e031f2..4ccaf9a 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -104,6 +104,7 @@ static inline char *nic_name(struct pci_dev *pdev)
 #define BE3_MAX_RSS_QS		16
 #define BE3_MAX_TX_QS		16
 #define BE3_MAX_EVT_QS		16
+#define BE3_SRIOV_MAX_EVT_QS	8
 
 #define MAX_RX_QS		32
 #define MAX_EVT_QS		32
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index fa44bba..bf40fda 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -3127,11 +3127,11 @@ static void BEx_get_resources(struct be_adapter *adapter,
 {
 	struct pci_dev *pdev = adapter->pdev;
 	bool use_sriov = false;
+	int max_vfs;
 
-	if (BE3_chip(adapter) && sriov_want(adapter)) {
-		int max_vfs;
+	max_vfs = pci_sriov_get_totalvfs(pdev);
 
-		max_vfs = pci_sriov_get_totalvfs(pdev);
+	if (BE3_chip(adapter) && sriov_want(adapter)) {
 		res->max_vfs = max_vfs > 0 ? min(MAX_VFS, max_vfs) : 0;
 		use_sriov = res->max_vfs;
 	}
@@ -3162,7 +3162,11 @@ static void BEx_get_resources(struct be_adapter *adapter,
 					   BE3_MAX_RSS_QS : BE2_MAX_RSS_QS;
 	res->max_rx_qs = res->max_rss_qs + 1;
 
-	res->max_evt_qs = be_physfn(adapter) ? BE3_MAX_EVT_QS : 1;
+	if (be_physfn(adapter))
+		res->max_evt_qs = (max_vfs > 0) ?
+					BE3_SRIOV_MAX_EVT_QS : BE3_MAX_EVT_QS;
+	else
+		res->max_evt_qs = 1;
 
 	res->if_cap_flags = BE_IF_CAP_FLAGS_WANT;
 	if (!(adapter->function_caps & BE_FUNCTION_CAPS_RSS))
-- 
cgit v0.10.2


From d0abafac8c9162f39c4f6b2f8141b772a09b3770 Mon Sep 17 00:00:00 2001
From: Eric Whitney <enwlinux@gmail.com>
Date: Mon, 6 Jan 2014 14:00:23 -0500
Subject: ext4: fix bigalloc regression

Commit f5a44db5d2 introduced a regression on filesystems created with
the bigalloc feature (cluster size > blocksize).  It causes xfstests
generic/006 and /013 to fail with an unexpected JBD2 failure and
transaction abort that leaves the test file system in a read only state.
Other xfstests run on bigalloc file systems are likely to fail as well.

The cause is the accidental use of a cluster mask where a cluster
offset was needed in ext4_ext_map_blocks().

Signed-off-by: Eric Whitney <enwlinux@gmail.com>

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 4410cc3..3384dc4 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4218,7 +4218,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	 */
 	map->m_flags &= ~EXT4_MAP_FROM_CLUSTER;
 	newex.ee_block = cpu_to_le32(map->m_lblk);
-	cluster_offset = EXT4_LBLK_CMASK(sbi, map->m_lblk);
+	cluster_offset = EXT4_LBLK_COFF(sbi, map->m_lblk);
 
 	/*
 	 * If we are doing bigalloc, check to see if the extent returned
-- 
cgit v0.10.2


From 22d3b76ed7d2a02bca513b113f2613b9b6e61d58 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Sun, 5 Jan 2014 20:31:39 -0800
Subject: isdn: Drop big endian cpp checks from telespci and hfc_pci drivers

With arm:allmodconfig, building the Teles PCI driver fails with

telespci.c:294:2: error: #error "not running on big endian machines now"

Similar, building the driver for HFC PCI-Bus cards fails with

hfc_pci.c:1647:2: error: #error "not running on big endian machines now"

Remove the big endian cpp check from both drivers to fix the build errors.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/isdn/hisax/hfc_pci.c b/drivers/isdn/hisax/hfc_pci.c
index 497bd02..4a48255 100644
--- a/drivers/isdn/hisax/hfc_pci.c
+++ b/drivers/isdn/hisax/hfc_pci.c
@@ -1643,10 +1643,6 @@ setup_hfcpci(struct IsdnCard *card)
 	int i;
 	struct pci_dev *tmp_hfcpci = NULL;
 
-#ifdef __BIG_ENDIAN
-#error "not running on big endian machines now"
-#endif
-
 	strcpy(tmp, hfcpci_revision);
 	printk(KERN_INFO "HiSax: HFC-PCI driver Rev. %s\n", HiSax_getrev(tmp));
 
diff --git a/drivers/isdn/hisax/telespci.c b/drivers/isdn/hisax/telespci.c
index f6ab63a..33eeb46 100644
--- a/drivers/isdn/hisax/telespci.c
+++ b/drivers/isdn/hisax/telespci.c
@@ -290,10 +290,6 @@ int setup_telespci(struct IsdnCard *card)
 	struct IsdnCardState *cs = card->cs;
 	char tmp[64];
 
-#ifdef __BIG_ENDIAN
-#error "not running on big endian machines now"
-#endif
-
 	strcpy(tmp, telespci_revision);
 	printk(KERN_INFO "HiSax: Teles/PCI driver Rev. %s\n", HiSax_getrev(tmp));
 	if (cs->typ != ISDN_CTYPE_TELESPCI)
-- 
cgit v0.10.2


From 6cbd7ee10e2842a3d1f9b60abede1c8f3d1f1130 Mon Sep 17 00:00:00 2001
From: Dirk Brandewie <dirk.j.brandewie@intel.com>
Date: Mon, 6 Jan 2014 10:59:16 -0800
Subject: intel_pstate: Add X86_FEATURE_APERFMPERF to cpu match parameters.

KVM environments do not support APERF/MPERF MSRs. intel_pstate cannot
operate without these registers.

The previous validity checks in intel_pstate_msrs_not_valid() are
insufficent in nested KVMs.

References: https://bugzilla.redhat.com/show_bug.cgi?id=1046317
Signed-off-by: Dirk Brandewie <dirk.j.brandewie@intel.com>
Cc: All applicable <stable@vger.kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index f9d561e..d51f17ed 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -581,7 +581,8 @@ static void intel_pstate_timer_func(unsigned long __data)
 }
 
 #define ICPU(model, policy) \
-	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&policy }
+	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF,\
+			(unsigned long)&policy }
 
 static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	ICPU(0x2a, core_params),
-- 
cgit v0.10.2


From a90b40385735af0d3031f98e97b439e8944a31b3 Mon Sep 17 00:00:00 2001
From: Lan Tianyu <tianyu.lan@intel.com>
Date: Mon, 6 Jan 2014 22:50:37 +0800
Subject: ACPI / Battery: Add a _BIX quirk for NEC LZ750/LS

The AML method _BIX of NEC LZ750/LS returns a broken package which
skips the first member "Revision" (ACPI 5.0, Table 10-234).

Add a quirk for this machine to skip member "Revision" during parsing
the package returned by _BIX.

Reference: https://bugzilla.kernel.org/show_bug.cgi?id=67351
Reported-and-tested-by: Francisco Castro <fcr@adinet.com.uy>
Cc: 3.8+ <stable@vger.kernel.org> " 3.8+
Signed-off-by: Lan Tianyu <tianyu.lan@intel.com>
Reviewed-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index fbf1ace..5876a49 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -62,6 +62,7 @@ MODULE_AUTHOR("Alexey Starikovskiy <astarikovskiy@suse.de>");
 MODULE_DESCRIPTION("ACPI Battery Driver");
 MODULE_LICENSE("GPL");
 
+static int battery_bix_broken_package;
 static unsigned int cache_time = 1000;
 module_param(cache_time, uint, 0644);
 MODULE_PARM_DESC(cache_time, "cache time in milliseconds");
@@ -416,7 +417,12 @@ static int acpi_battery_get_info(struct acpi_battery *battery)
 		ACPI_EXCEPTION((AE_INFO, status, "Evaluating %s", name));
 		return -ENODEV;
 	}
-	if (test_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags))
+
+	if (battery_bix_broken_package)
+		result = extract_package(battery, buffer.pointer,
+				extended_info_offsets + 1,
+				ARRAY_SIZE(extended_info_offsets) - 1);
+	else if (test_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags))
 		result = extract_package(battery, buffer.pointer,
 				extended_info_offsets,
 				ARRAY_SIZE(extended_info_offsets));
@@ -754,6 +760,17 @@ static int battery_notify(struct notifier_block *nb,
 	return 0;
 }
 
+static struct dmi_system_id bat_dmi_table[] = {
+	{
+		.ident = "NEC LZ750/LS",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "PC-LZ750LS"),
+		},
+	},
+	{},
+};
+
 static int acpi_battery_add(struct acpi_device *device)
 {
 	int result = 0;
@@ -846,6 +863,9 @@ static void __init acpi_battery_init_async(void *unused, async_cookie_t cookie)
 {
 	if (acpi_disabled)
 		return;
+
+	if (dmi_check_system(bat_dmi_table))
+		battery_bix_broken_package = 1;
 	acpi_bus_register_driver(&acpi_battery_driver);
 }
 
-- 
cgit v0.10.2


From e5e97ee956d8c5ed2fc5877d29dee17a6a59de8e Mon Sep 17 00:00:00 2001
From: Dan Williams <dcbw@redhat.com>
Date: Mon, 6 Jan 2014 10:07:29 -0600
Subject: hso: fix handling of modem port SERIAL_STATE notifications

The existing serial state notification handling expected older Option
devices, having a hardcoded assumption that the Modem port was always
USB interface #2.  That isn't true for devices from the past few years.

hso_serial_state_notification is a local cache of a USB Communications
Interface Class SERIAL_STATE notification from the device, and the
USB CDC specification (section 6.3, table 67 "Class-Specific Notifications")
defines wIndex as the USB interface the event applies to.  For hso
devices this will always be the Modem port, as the Modem port is the
only port which is set up to receive them by the driver.

So instead of always expecting USB interface #2, instead validate the
notification with the actual USB interface number of the Modem port.

Signed-off-by: Dan Williams <dcbw@redhat.com>
Tested-by: H. Nikolaus Schaller <hns@goldelico.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index 86292e6..1a48234 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -185,7 +185,6 @@ enum rx_ctrl_state{
 #define BM_REQUEST_TYPE (0xa1)
 #define B_NOTIFICATION  (0x20)
 #define W_VALUE         (0x0)
-#define W_INDEX         (0x2)
 #define W_LENGTH        (0x2)
 
 #define B_OVERRUN       (0x1<<6)
@@ -1487,6 +1486,7 @@ static void tiocmget_intr_callback(struct urb *urb)
 	struct uart_icount *icount;
 	struct hso_serial_state_notification *serial_state_notification;
 	struct usb_device *usb;
+	int if_num;
 
 	/* Sanity checks */
 	if (!serial)
@@ -1495,15 +1495,24 @@ static void tiocmget_intr_callback(struct urb *urb)
 		handle_usb_error(status, __func__, serial->parent);
 		return;
 	}
+
+	/* tiocmget is only supported on HSO_PORT_MODEM */
 	tiocmget = serial->tiocmget;
 	if (!tiocmget)
 		return;
+	BUG_ON((serial->parent->port_spec & HSO_PORT_MASK) != HSO_PORT_MODEM);
+
 	usb = serial->parent->usb;
+	if_num = serial->parent->interface->altsetting->desc.bInterfaceNumber;
+
+	/* wIndex should be the USB interface number of the port to which the
+	 * notification applies, which should always be the Modem port.
+	 */
 	serial_state_notification = &tiocmget->serial_state_notification;
 	if (serial_state_notification->bmRequestType != BM_REQUEST_TYPE ||
 	    serial_state_notification->bNotification != B_NOTIFICATION ||
 	    le16_to_cpu(serial_state_notification->wValue) != W_VALUE ||
-	    le16_to_cpu(serial_state_notification->wIndex) != W_INDEX ||
+	    le16_to_cpu(serial_state_notification->wIndex) != if_num ||
 	    le16_to_cpu(serial_state_notification->wLength) != W_LENGTH) {
 		dev_warn(&usb->dev,
 			 "hso received invalid serial state notification\n");
-- 
cgit v0.10.2


From 88ad31491e21f5dec347911d9804c673af414a09 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Mon, 6 Jan 2014 17:53:14 +0100
Subject: ipv6: don't install anycast address for /128 addresses on routers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It does not make sense to create an anycast address for an /128-prefix.
Suppress it.

As 32019e651c6fce ("ipv6: Do not leave router anycast address for /127
prefixes.") shows we also may not leave them, because we could accidentally
remove an anycast address the user has allocated or got added via another
prefix.

Cc: François-Xavier Le Bail <fx.lebail@yahoo.com>
Cc: Thomas Haller <thaller@redhat.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 1a341f7..f62c72b 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1671,7 +1671,7 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr)
 static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
 {
 	struct in6_addr addr;
-	if (ifp->prefix_len == 127) /* RFC 6164 */
+	if (ifp->prefix_len >= 127) /* RFC 6164 */
 		return;
 	ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
 	if (ipv6_addr_any(&addr))
@@ -1682,7 +1682,7 @@ static void addrconf_join_anycast(struct inet6_ifaddr *ifp)
 static void addrconf_leave_anycast(struct inet6_ifaddr *ifp)
 {
 	struct in6_addr addr;
-	if (ifp->prefix_len == 127) /* RFC 6164 */
+	if (ifp->prefix_len >= 127) /* RFC 6164 */
 		return;
 	ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len);
 	if (ipv6_addr_any(&addr))
-- 
cgit v0.10.2


From fe0d692bbc645786bce1a98439e548ae619269f5 Mon Sep 17 00:00:00 2001
From: Curt Brune <curt@cumulusnetworks.com>
Date: Mon, 6 Jan 2014 11:00:32 -0800
Subject: bridge: use spin_lock_bh() in br_multicast_set_hash_max

br_multicast_set_hash_max() is called from process context in
net/bridge/br_sysfs_br.c by the sysfs store_hash_max() function.

br_multicast_set_hash_max() calls spin_lock(&br->multicast_lock),
which can deadlock the CPU if a softirq that also tries to take the
same lock interrupts br_multicast_set_hash_max() while the lock is
held .  This can happen quite easily when any of the bridge multicast
timers expire, which try to take the same lock.

The fix here is to use spin_lock_bh(), preventing other softirqs from
executing on this CPU.

Steps to reproduce:

1. Create a bridge with several interfaces (I used 4).
2. Set the "multicast query interval" to a low number, like 2.
3. Enable the bridge as a multicast querier.
4. Repeatedly set the bridge hash_max parameter via sysfs.

  # brctl addbr br0
  # brctl addif br0 eth1 eth2 eth3 eth4
  # brctl setmcqi br0 2
  # brctl setmcquerier br0 1

  # while true ; do echo 4096 > /sys/class/net/br0/bridge/hash_max; done

Signed-off-by: Curt Brune <curt@cumulusnetworks.com>
Signed-off-by: Scott Feldman <sfeldma@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 4c214b2..ef66365 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1998,7 +1998,7 @@ int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val)
 	u32 old;
 	struct net_bridge_mdb_htable *mdb;
 
-	spin_lock(&br->multicast_lock);
+	spin_lock_bh(&br->multicast_lock);
 	if (!netif_running(br->dev))
 		goto unlock;
 
@@ -2030,7 +2030,7 @@ rollback:
 	}
 
 unlock:
-	spin_unlock(&br->multicast_lock);
+	spin_unlock_bh(&br->multicast_lock);
 
 	return err;
 }
-- 
cgit v0.10.2


From 61b365a505d625734be9ac54066fe4700672abc9 Mon Sep 17 00:00:00 2001
From: Ben Skeggs <bskeggs@redhat.com>
Date: Wed, 27 Nov 2013 09:46:56 +1000
Subject: drm/nouveau: populate master subdev pointer only when fully
 constructed

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>

diff --git a/drivers/gpu/drm/nouveau/core/core/subdev.c b/drivers/gpu/drm/nouveau/core/core/subdev.c
index 48f0637..2ea5568 100644
--- a/drivers/gpu/drm/nouveau/core/core/subdev.c
+++ b/drivers/gpu/drm/nouveau/core/core/subdev.c
@@ -104,11 +104,8 @@ nouveau_subdev_create_(struct nouveau_object *parent,
 
 	if (parent) {
 		struct nouveau_device *device = nv_device(parent);
-		int subidx = nv_hclass(subdev) & 0xff;
-
 		subdev->debug = nouveau_dbgopt(device->dbgopt, subname);
 		subdev->mmio  = nv_subdev(device)->mmio;
-		device->subdev[subidx] = *pobject;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/nouveau/core/engine/device/base.c b/drivers/gpu/drm/nouveau/core/engine/device/base.c
index 9135b25a..dd01c6c 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/base.c
@@ -268,6 +268,8 @@ nouveau_devobj_ctor(struct nouveau_object *parent,
 		if (ret)
 			return ret;
 
+		device->subdev[i] = devobj->subdev[i];
+
 		/* note: can't init *any* subdevs until devinit has been run
 		 * due to not knowing exactly what the vbios init tables will
 		 * mess with.  devinit also can't be run until all of its
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/fb.h b/drivers/gpu/drm/nouveau/core/include/subdev/fb.h
index 8541aa3..d89dbdf 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/fb.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/fb.h
@@ -75,6 +75,11 @@ struct nouveau_fb {
 static inline struct nouveau_fb *
 nouveau_fb(void *obj)
 {
+	/* fbram uses this before device subdev pointer is valid */
+	if (nv_iclass(obj, NV_SUBDEV_CLASS) &&
+	    nv_subidx(obj) == NVDEV_SUBDEV_FB)
+		return obj;
+
 	return (void *)nv_device(obj)->subdev[NVDEV_SUBDEV_FB];
 }
 
-- 
cgit v0.10.2


From 854cc0e4cb71d215b1104605f2dbf73578de8a94 Mon Sep 17 00:00:00 2001
From: Kelly Doran <kel.p.doran@gmail.com>
Date: Fri, 20 Dec 2013 11:07:26 -0600
Subject: drm/nvc0/gr: fix mthd data submission

If the initial data element is 0, it will never be written, even
though the value from the previous method may be there.

Signed-off-by: Kelly Doran <kel.p.doran@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>

diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c
index 434bb4b..5c8a63d 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/nvc0.c
@@ -334,7 +334,7 @@ nvc0_graph_mthd(struct nvc0_graph_priv *priv, struct nvc0_graph_mthd *mthds)
 	while ((mthd = &mthds[i++]) && (init = mthd->init)) {
 		u32  addr = 0x80000000 | mthd->oclass;
 		for (data = 0; init->count; init++) {
-			if (data != init->data) {
+			if (init == mthd->init || data != init->data) {
 				nv_wr32(priv, 0x40448c, init->data);
 				data = init->data;
 			}
-- 
cgit v0.10.2


From 6e9cbb40d2be7e0693d6b1b0e2790277a366c471 Mon Sep 17 00:00:00 2001
From: Sid Boyce <sboyce@blueyonder.co.uk>
Date: Mon, 6 Jan 2014 09:12:05 +1000
Subject: drm/nvce/mc: fix msi rearm on GF114

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>

diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c b/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c
index 8d06eef..dbc5e33 100644
--- a/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/device/nvc0.c
@@ -161,7 +161,7 @@ nvc0_identify(struct nouveau_device *device)
 		device->oclass[NVDEV_SUBDEV_THERM  ] = &nva3_therm_oclass;
 		device->oclass[NVDEV_SUBDEV_MXM    ] = &nv50_mxm_oclass;
 		device->oclass[NVDEV_SUBDEV_DEVINIT] = &nvc0_devinit_oclass;
-		device->oclass[NVDEV_SUBDEV_MC     ] =  nvc3_mc_oclass;
+		device->oclass[NVDEV_SUBDEV_MC     ] =  nvc0_mc_oclass;
 		device->oclass[NVDEV_SUBDEV_BUS    ] =  nvc0_bus_oclass;
 		device->oclass[NVDEV_SUBDEV_TIMER  ] = &nv04_timer_oclass;
 		device->oclass[NVDEV_SUBDEV_FB     ] =  nvc0_fb_oclass;
-- 
cgit v0.10.2


From 6d60792ec059d9f2139828f9f017679abb81aa73 Mon Sep 17 00:00:00 2001
From: Ilia Mirkin <imirkin@alum.mit.edu>
Date: Sun, 5 Jan 2014 20:07:02 -0500
Subject: drm/nouveau/bios: make jump conditional
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This fixes a hang in VBIOS scripts of the form "condition; jump".
The jump used to always be executed, while now it will only be
executed if the condition is true.

See https://bugs.freedesktop.org/show_bug.cgi?id=72943

Reported-by: Darcy Brás da Silva <dardevelin@cidadecool.com>
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: stable@vger.kernel.org

diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
index 420908c..9f5b81e 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
@@ -1294,7 +1294,11 @@ init_jump(struct nvbios_init *init)
 	u16 offset = nv_ro16(bios, init->offset + 1);
 
 	trace("JUMP\t0x%04x\n", offset);
-	init->offset = offset;
+
+	if (init_exec(init))
+		init->offset = offset;
+	else
+		init->offset += 3;
 }
 
 /**
-- 
cgit v0.10.2


From c1ccaa646cce2538b00fdca6d7eea0c38ebfd179 Mon Sep 17 00:00:00 2001
From: Bob Gleitsmann <rjgleits@bellsouth.net>
Date: Mon, 6 Jan 2014 08:59:07 +1000
Subject: drm/nouveau: return offset of allocated notifier

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>

diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index 6828d81..900fae0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -447,6 +447,8 @@ nouveau_abi16_ioctl_notifierobj_alloc(ABI16_IOCTL_ARGS)
 	if (ret)
 		goto done;
 
+	info->offset = ntfy->node->offset;
+
 done:
 	if (ret)
 		nouveau_abi16_ntfy_fini(chan, ntfy);
-- 
cgit v0.10.2


From 663b55b9b39fa9c848cca273ca4e12bf29b32c71 Mon Sep 17 00:00:00 2001
From: Paul Gortmaker <paul.gortmaker@windriver.com>
Date: Mon, 6 Jan 2014 19:20:26 -0500
Subject: x86: Delete non-required instances of include <linux/init.h>

None of these files are actually using any __init type directives
and hence don't need to include <linux/init.h>.  Most are just a
left over from __devinit and __cpuinit removal, or simply due to
code getting copied from one driver to the next.

[ hpa: undid incorrect removal from arch/x86/kernel/head_32.S ]

Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Link: http://lkml.kernel.org/r/1389054026-12947-1-git-send-email-paul.gortmaker@windriver.com
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index c696a86..6e4ce2d 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -118,7 +118,6 @@ extern void mce_register_decode_chain(struct notifier_block *nb);
 extern void mce_unregister_decode_chain(struct notifier_block *nb);
 
 #include <linux/percpu.h>
-#include <linux/init.h>
 #include <linux/atomic.h>
 
 extern int mce_p5_enabled;
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index 3142a94..3e6b492 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -1,7 +1,6 @@
 #ifndef _ASM_X86_MPSPEC_H
 #define _ASM_X86_MPSPEC_H
 
-#include <linux/init.h>
 
 #include <asm/mpspec_def.h>
 #include <asm/x86_init.h>
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 7b034a4..8ade617 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -27,7 +27,6 @@ struct mm_struct;
 #include <linux/cache.h>
 #include <linux/threads.h>
 #include <linux/math64.h>
-#include <linux/init.h>
 #include <linux/err.h>
 #include <linux/irqflags.h>
 
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 942a086..14fd6fd 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -60,7 +60,6 @@ struct pt_regs {
 
 #endif /* !__i386__ */
 
-#include <linux/init.h>
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt_types.h>
 #endif
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 4137890..8cd27e0 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -2,7 +2,6 @@
 #define _ASM_X86_SMP_H
 #ifndef __ASSEMBLY__
 #include <linux/cpumask.h>
-#include <linux/init.h>
 #include <asm/percpu.h>
 
 /*
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index 34baa0e..a6f3e77 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -1,6 +1,5 @@
 #ifndef _ASM_X86_TIMER_H
 #define _ASM_X86_TIMER_H
-#include <linux/init.h>
 #include <linux/pm.h>
 #include <linux/percpu.h>
 #include <linux/interrupt.h>
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 00c77cf..5d5b9eb 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -14,7 +14,6 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/ctype.h>
-#include <linux/init.h>
 #include <linux/hardirq.h>
 #include <linux/module.h>
 #include <asm/smp.h>
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index e145f28..191ce75 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -15,7 +15,6 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/ctype.h>
-#include <linux/init.h>
 #include <linux/errno.h>
 #include <asm/fixmap.h>
 #include <asm/mpspec.h>
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 7434d85..6207156 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -1,6 +1,5 @@
 #include <linux/cpumask.h>
 #include <linux/interrupt.h>
-#include <linux/init.h>
 
 #include <linux/mm.h>
 #include <linux/delay.h>
diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c
index 77c95c0..00146f9 100644
--- a/arch/x86/kernel/apic/summit_32.c
+++ b/arch/x86/kernel/apic/summit_32.c
@@ -29,7 +29,6 @@
 #define pr_fmt(fmt) "summit: %s: " fmt, __func__
 
 #include <linux/mm.h>
-#include <linux/init.h>
 #include <asm/io.h>
 #include <asm/bios_ebda.h>
 
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 140e29d..cac85ee 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -3,7 +3,6 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/ctype.h>
-#include <linux/init.h>
 #include <linux/dmar.h>
 #include <linux/cpu.h>
 
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 562a76d..de231e3 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -3,7 +3,6 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/ctype.h>
-#include <linux/init.h>
 #include <linux/dmar.h>
 
 #include <asm/smp.h>
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index bca023b..39bc78d 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1,5 +1,4 @@
 #include <linux/export.h>
-#include <linux/init.h>
 #include <linux/bitops.h>
 #include <linux/elf.h>
 #include <linux/mm.h>
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 8d5652d..8779eda 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -1,6 +1,5 @@
 #include <linux/bitops.h>
 #include <linux/kernel.h>
-#include <linux/init.h>
 
 #include <asm/processor.h>
 #include <asm/e820.h>
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index d0969c7..aaf152e 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -1,4 +1,3 @@
-#include <linux/init.h>
 #include <linux/bitops.h>
 #include <linux/delay.h>
 #include <linux/pci.h>
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index dc1ec0d..53f5d3c 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -1,4 +1,3 @@
-#include <linux/init.h>
 #include <linux/kernel.h>
 
 #include <linux/string.h>
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 4cfe045..fb6156f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -6,7 +6,6 @@
  */
 
 #include <linux/gfp.h>
-#include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/percpu.h>
 #include <linux/sched.h>
diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c
index 1c044b1..a304298 100644
--- a/arch/x86/kernel/cpu/mcheck/p5.c
+++ b/arch/x86/kernel/cpu/mcheck/p5.c
@@ -5,7 +5,6 @@
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
-#include <linux/init.h>
 #include <linux/smp.h>
 
 #include <asm/processor.h>
diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c
index e9a701a..7dc5564 100644
--- a/arch/x86/kernel/cpu/mcheck/winchip.c
+++ b/arch/x86/kernel/cpu/mcheck/winchip.c
@@ -5,7 +5,6 @@
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
-#include <linux/init.h>
 
 #include <asm/processor.h>
 #include <asm/mce.h>
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index aa0430d..3fa0e5a 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -1,6 +1,5 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
-#include <linux/init.h>
 #include <asm/processor.h>
 #include <asm/msr.h>
 #include "cpu.h"
diff --git a/arch/x86/kernel/cpu/umc.c b/arch/x86/kernel/cpu/umc.c
index 75c5ad5..ef9c2a0 100644
--- a/arch/x86/kernel/cpu/umc.c
+++ b/arch/x86/kernel/cpu/umc.c
@@ -1,5 +1,4 @@
 #include <linux/kernel.h>
-#include <linux/init.h>
 #include <asm/processor.h>
 #include "cpu.h"
 
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 18677a9..a57902e 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -7,7 +7,6 @@
  *
  */
 
-#include <linux/init.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/smp.h>
diff --git a/arch/x86/kernel/doublefault.c b/arch/x86/kernel/doublefault.c
index 5d3fe8d..f6dfd93 100644
--- a/arch/x86/kernel/doublefault.c
+++ b/arch/x86/kernel/doublefault.c
@@ -1,6 +1,5 @@
 #include <linux/mm.h>
 #include <linux/sched.h>
-#include <linux/init.h>
 #include <linux/init_task.h>
 #include <linux/fs.h>
 
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index f66ff16..a67b47c 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -38,7 +38,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sched.h>
-#include <linux/init.h>
 #include <linux/smp.h>
 
 #include <asm/hw_breakpoint.h>
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 836f832..7ec1d5f 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -39,7 +39,6 @@
 #include <linux/sched.h>
 #include <linux/delay.h>
 #include <linux/kgdb.h>
-#include <linux/init.h>
 #include <linux/smp.h>
 #include <linux/nmi.h>
 #include <linux/hw_breakpoint.h>
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 5b19e4d..1667b1d 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -9,7 +9,6 @@
 #include <linux/mm.h>
 #include <linux/kexec.h>
 #include <linux/delay.h>
-#include <linux/init.h>
 #include <linux/numa.h>
 #include <linux/ftrace.h>
 #include <linux/suspend.h>
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index 871be4a..da15918 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -3,7 +3,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/scatterlist.h>
 #include <linux/string.h>
-#include <linux/init.h>
 #include <linux/gfp.h>
 #include <linux/pci.h>
 #include <linux/mm.h>
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 6f1236c..0de43e9 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -24,7 +24,6 @@
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/reboot.h>
-#include <linux/init.h>
 #include <linux/mc146818rtc.h>
 #include <linux/module.h>
 #include <linux/kallsyms.h>
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index adfdf56..2648848 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -16,7 +16,6 @@
  */
 #include <linux/spinlock.h>
 #include <linux/kernel.h>
-#include <linux/init.h>
 #include <linux/smp.h>
 #include <linux/nmi.h>
 #include <asm/tsc.h>
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index 7c3bee6..39d6a3d 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -16,7 +16,6 @@
 #include <linux/timex.h>
 #include <linux/preempt.h>
 #include <linux/delay.h>
-#include <linux/init.h>
 
 #include <asm/processor.h>
 #include <asm/delay.h>
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index e5d5e2c..637ab34 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -11,7 +11,6 @@
 #include <linux/rculist.h>
 #include <linux/spinlock.h>
 #include <linux/hash.h>
-#include <linux/init.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/uaccess.h>
diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c
index d0b1773..461bc82 100644
--- a/arch/x86/mm/pageattr-test.c
+++ b/arch/x86/mm/pageattr-test.c
@@ -8,7 +8,6 @@
 #include <linux/kthread.h>
 #include <linux/random.h>
 #include <linux/kernel.h>
-#include <linux/init.h>
 #include <linux/mm.h>
 
 #include <asm/cacheflush.h>
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index b046e07..bca9e85 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -5,7 +5,6 @@
 #include <linux/delay.h>
 #include <linux/dmi.h>
 #include <linux/pci.h>
-#include <linux/init.h>
 #include <linux/vgaarb.h>
 #include <asm/pci_x86.h>
 
diff --git a/arch/x86/platform/intel-mid/early_printk_intel_mid.c b/arch/x86/platform/intel-mid/early_printk_intel_mid.c
index 4f702f5..e0bd082 100644
--- a/arch/x86/platform/intel-mid/early_printk_intel_mid.c
+++ b/arch/x86/platform/intel-mid/early_printk_intel_mid.c
@@ -22,7 +22,6 @@
 #include <linux/console.h>
 #include <linux/kernel.h>
 #include <linux/delay.h>
-#include <linux/init.h>
 #include <linux/io.h>
 
 #include <asm/fixmap.h>
diff --git a/arch/x86/platform/iris/iris.c b/arch/x86/platform/iris/iris.c
index e6cb80f..4d171e8 100644
--- a/arch/x86/platform/iris/iris.c
+++ b/arch/x86/platform/iris/iris.c
@@ -27,7 +27,6 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/delay.h>
-#include <linux/init.h>
 #include <linux/pm.h>
 #include <asm/io.h>
 
diff --git a/arch/x86/realmode/rm/reboot.S b/arch/x86/realmode/rm/reboot.S
index f932ea6..d66c607 100644
--- a/arch/x86/realmode/rm/reboot.S
+++ b/arch/x86/realmode/rm/reboot.S
@@ -1,5 +1,4 @@
 #include <linux/linkage.h>
-#include <linux/init.h>
 #include <asm/segment.h>
 #include <asm/page_types.h>
 #include <asm/processor-flags.h>
diff --git a/arch/x86/realmode/rm/trampoline_32.S b/arch/x86/realmode/rm/trampoline_32.S
index c1b2791..48ddd76 100644
--- a/arch/x86/realmode/rm/trampoline_32.S
+++ b/arch/x86/realmode/rm/trampoline_32.S
@@ -20,7 +20,6 @@
  */
 
 #include <linux/linkage.h>
-#include <linux/init.h>
 #include <asm/segment.h>
 #include <asm/page_types.h>
 #include "realmode.h"
diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S
index bb360dc..dac7b20 100644
--- a/arch/x86/realmode/rm/trampoline_64.S
+++ b/arch/x86/realmode/rm/trampoline_64.S
@@ -25,7 +25,6 @@
  */
 
 #include <linux/linkage.h>
-#include <linux/init.h>
 #include <asm/pgtable_types.h>
 #include <asm/page_types.h>
 #include <asm/msr.h>
diff --git a/arch/x86/um/vdso/vdso.S b/arch/x86/um/vdso/vdso.S
index 1cb468a..4b4bd4c 100644
--- a/arch/x86/um/vdso/vdso.S
+++ b/arch/x86/um/vdso/vdso.S
@@ -1,4 +1,3 @@
-#include <linux/init.h>
 
 __INITDATA
 
diff --git a/arch/x86/vdso/vdso.S b/arch/x86/vdso/vdso.S
index 01f5e3b..1e13eb8 100644
--- a/arch/x86/vdso/vdso.S
+++ b/arch/x86/vdso/vdso.S
@@ -1,6 +1,5 @@
 #include <asm/page_types.h>
 #include <linux/linkage.h>
-#include <linux/init.h>
 
 __PAGE_ALIGNED_DATA
 
diff --git a/arch/x86/vdso/vdsox32.S b/arch/x86/vdso/vdsox32.S
index d6b9a7f..295f1c7 100644
--- a/arch/x86/vdso/vdsox32.S
+++ b/arch/x86/vdso/vdsox32.S
@@ -1,6 +1,5 @@
 #include <asm/page_types.h>
 #include <linux/linkage.h>
-#include <linux/init.h>
 
 __PAGE_ALIGNED_DATA
 
-- 
cgit v0.10.2


From 47f956477dc6173f8882e8ea0fa9e8edb8a7d942 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Tue, 7 Jan 2014 09:24:31 +0100
Subject: MAINTAINERS: Updates for drm/i915

Jani for co-maintainer!

Jani has been a really active bug-scrubber in the past few months.
I've asked him whether he wants to do this in a more official capacity
and he agreed. I've already chatted with Dave and Jesse and they
support this.

Note that everyone can't now just relax because "Jani will do all the
bug scrubbing" - au contraire expect more nagging and poking now that
we have more bandwidth.

Longer-term the plan is to share more of the maintainer duties, but we
need to fix up the infrastructure a bit first (like moving the git
repo to a common location).

While at it also add the newly set-up patchwork instance.

Cc: Dave Airlie <airlied@gmail.com>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

diff --git a/MAINTAINERS b/MAINTAINERS
index 6c20792..31a0462 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2828,8 +2828,10 @@ F:	include/uapi/drm/
 
 INTEL DRM DRIVERS (excluding Poulsbo, Moorestown and derivative chipsets)
 M:	Daniel Vetter <daniel.vetter@ffwll.ch>
+M:	Jani Nikula <jani.nikula@linux.intel.com>
 L:	intel-gfx@lists.freedesktop.org
 L:	dri-devel@lists.freedesktop.org
+Q:	http://patchwork.freedesktop.org/project/intel-gfx/
 T:	git git://people.freedesktop.org/~danvet/drm-intel
 S:	Supported
 F:	drivers/gpu/drm/i915/
-- 
cgit v0.10.2


From 6bcac805bacb3b637911244d95368512ae389abc Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Tue, 7 Jan 2014 17:53:54 +0000
Subject: Revert "ARM: 7908/1: mm: Fix the arm_dma_limit calculation"

This reverts commit 787b0d5c1ca7ff24feb6f92e4c7f4410ee7d81a8 since
it is no longer required after 7909/1 was applied, and it causes
build regressions when ARM_PATCH_PHYS_VIRT is disabled and DMA_ZONE
is enabled.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 1f7b19a..3e8f106e 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -229,7 +229,7 @@ void __init setup_dma_zone(const struct machine_desc *mdesc)
 #ifdef CONFIG_ZONE_DMA
 	if (mdesc->dma_zone_size) {
 		arm_dma_zone_size = mdesc->dma_zone_size;
-		arm_dma_limit = __pv_phys_offset + arm_dma_zone_size - 1;
+		arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1;
 	} else
 		arm_dma_limit = 0xffffffff;
 	arm_dma_pfn_limit = arm_dma_limit >> PAGE_SHIFT;
-- 
cgit v0.10.2


From 657e5d19657542631461e72fdc375b1e83e72070 Mon Sep 17 00:00:00 2001
From: Li RongQing <roy.qing.li@gmail.com>
Date: Tue, 7 Jan 2014 15:39:43 +0800
Subject: ipv6: pcpu_tstats.syncp should be initialised in ip6_vti.c

initialise pcpu_tstats.syncp to kill the calltrace
[   11.973950] Call Trace:
[   11.973950]  [<819bbaff>] dump_stack+0x48/0x60
[   11.973950]  [<819bbaff>] dump_stack+0x48/0x60
[   11.973950]  [<81078dcf>] __lock_acquire.isra.22+0x1bf/0xc10
[   11.973950]  [<81078dcf>] __lock_acquire.isra.22+0x1bf/0xc10
[   11.973950]  [<81079fa7>] lock_acquire+0x77/0xa0
[   11.973950]  [<81079fa7>] lock_acquire+0x77/0xa0
[   11.973950]  [<817ca7ab>] ? dev_get_stats+0xcb/0x130
[   11.973950]  [<817ca7ab>] ? dev_get_stats+0xcb/0x130
[   11.973950]  [<8183862d>] ip_tunnel_get_stats64+0x6d/0x230
[   11.973950]  [<8183862d>] ip_tunnel_get_stats64+0x6d/0x230
[   11.973950]  [<817ca7ab>] ? dev_get_stats+0xcb/0x130
[   11.973950]  [<817ca7ab>] ? dev_get_stats+0xcb/0x130
[   11.973950]  [<811cf8c1>] ? __nla_reserve+0x21/0xd0
[   11.973950]  [<811cf8c1>] ? __nla_reserve+0x21/0xd0
[   11.973950]  [<817ca7ab>] dev_get_stats+0xcb/0x130
[   11.973950]  [<817ca7ab>] dev_get_stats+0xcb/0x130
[   11.973950]  [<817d5409>] rtnl_fill_ifinfo+0x569/0xe20
[   11.973950]  [<817d5409>] rtnl_fill_ifinfo+0x569/0xe20
[   11.973950]  [<810352e0>] ? kvm_clock_read+0x20/0x30
[   11.973950]  [<810352e0>] ? kvm_clock_read+0x20/0x30
[   11.973950]  [<81008e38>] ? sched_clock+0x8/0x10
[   11.973950]  [<81008e38>] ? sched_clock+0x8/0x10
[   11.973950]  [<8106ba45>] ? sched_clock_local+0x25/0x170
[   11.973950]  [<8106ba45>] ? sched_clock_local+0x25/0x170
[   11.973950]  [<810da6bd>] ? __kmalloc+0x3d/0x90
[   11.973950]  [<810da6bd>] ? __kmalloc+0x3d/0x90
[   11.973950]  [<817b8c10>] ? __kmalloc_reserve.isra.41+0x20/0x70
[   11.973950]  [<817b8c10>] ? __kmalloc_reserve.isra.41+0x20/0x70
[   11.973950]  [<810da81a>] ? slob_alloc_node+0x2a/0x60
[   11.973950]  [<810da81a>] ? slob_alloc_node+0x2a/0x60
[   11.973950]  [<817b919a>] ? __alloc_skb+0x6a/0x2b0
[   11.973950]  [<817b919a>] ? __alloc_skb+0x6a/0x2b0
[   11.973950]  [<817d8795>] rtmsg_ifinfo+0x65/0xe0
[   11.973950]  [<817d8795>] rtmsg_ifinfo+0x65/0xe0
[   11.973950]  [<817cbd31>] register_netdevice+0x531/0x5a0
[   11.973950]  [<817cbd31>] register_netdevice+0x531/0x5a0
[   11.973950]  [<81892b87>] ? ip6_tnl_get_cap+0x27/0x90
[   11.973950]  [<81892b87>] ? ip6_tnl_get_cap+0x27/0x90
[   11.973950]  [<817cbdb6>] register_netdev+0x16/0x30
[   11.973950]  [<817cbdb6>] register_netdev+0x16/0x30
[   11.973950]  [<81f574a6>] vti6_init_net+0x1c4/0x1d4
[   11.973950]  [<81f574a6>] vti6_init_net+0x1c4/0x1d4
[   11.973950]  [<81f573af>] ? vti6_init_net+0xcd/0x1d4
[   11.973950]  [<81f573af>] ? vti6_init_net+0xcd/0x1d4
[   11.973950]  [<817c16df>] ops_init.constprop.11+0x17f/0x1c0
[   11.973950]  [<817c16df>] ops_init.constprop.11+0x17f/0x1c0
[   11.973950]  [<817c1779>] register_pernet_operations.isra.9+0x59/0x90
[   11.973950]  [<817c1779>] register_pernet_operations.isra.9+0x59/0x90
[   11.973950]  [<817c18d1>] register_pernet_device+0x21/0x60
[   11.973950]  [<817c18d1>] register_pernet_device+0x21/0x60
[   11.973950]  [<81f574b6>] ? vti6_init_net+0x1d4/0x1d4
[   11.973950]  [<81f574b6>] ? vti6_init_net+0x1d4/0x1d4
[   11.973950]  [<81f574c7>] vti6_tunnel_init+0x11/0x68
[   11.973950]  [<81f574c7>] vti6_tunnel_init+0x11/0x68
[   11.973950]  [<81f572a1>] ? mip6_init+0x73/0xb4
[   11.973950]  [<81f572a1>] ? mip6_init+0x73/0xb4
[   11.973950]  [<81f0cba4>] do_one_initcall+0xbb/0x15b
[   11.973950]  [<81f0cba4>] do_one_initcall+0xbb/0x15b
[   11.973950]  [<811a00d8>] ? sha_transform+0x528/0x1150
[   11.973950]  [<811a00d8>] ? sha_transform+0x528/0x1150
[   11.973950]  [<81f0c544>] ? repair_env_string+0x12/0x51
[   11.973950]  [<81f0c544>] ? repair_env_string+0x12/0x51
[   11.973950]  [<8105c30d>] ? parse_args+0x2ad/0x440
[   11.973950]  [<8105c30d>] ? parse_args+0x2ad/0x440
[   11.973950]  [<810546be>] ? __usermodehelper_set_disable_depth+0x3e/0x50
[   11.973950]  [<810546be>] ? __usermodehelper_set_disable_depth+0x3e/0x50
[   11.973950]  [<81f0cd27>] kernel_init_freeable+0xe3/0x182
[   11.973950]  [<81f0cd27>] kernel_init_freeable+0xe3/0x182
[   11.973950]  [<81f0c532>] ? do_early_param+0x7a/0x7a
[   11.973950]  [<81f0c532>] ? do_early_param+0x7a/0x7a
[   11.973950]  [<819b5b1b>] kernel_init+0xb/0x100
[   11.973950]  [<819b5b1b>] kernel_init+0xb/0x100
[   11.973950]  [<819cebf7>] ret_from_kernel_thread+0x1b/0x28
[   11.973950]  [<819cebf7>] ret_from_kernel_thread+0x1b/0x28
[   11.973950]  [<819b5b10>] ? rest_init+0xc0/0xc0
[   11.973950]  [<819b5b10>] ? rest_init+0xc0/0xc0

Before 469bdcefdc ("ipv6: fix the use of pcpu_tstats in ip6_vti.c"),
the pcpu_tstats.syncp is not used to pretect the 64bit elements of
pcpu_tstats, so not appear this calltrace.

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Li RongQing <roy.qing.li@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index a4564b0..7b42d5e 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -732,12 +732,18 @@ static void vti6_dev_setup(struct net_device *dev)
 static inline int vti6_dev_init_gen(struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
+	int i;
 
 	t->dev = dev;
 	t->net = dev_net(dev);
 	dev->tstats = alloc_percpu(struct pcpu_tstats);
 	if (!dev->tstats)
 		return -ENOMEM;
+	for_each_possible_cpu(i) {
+		struct pcpu_tstats *stats;
+		stats = per_cpu_ptr(dev->tstats, i);
+		u64_stats_init(&stats->syncp);
+	}
 	return 0;
 }
 
-- 
cgit v0.10.2


From 732256b9335f8456623bb772d86c2a24e3cafca2 Mon Sep 17 00:00:00 2001
From: Erik Hugne <erik.hugne@ericsson.com>
Date: Tue, 7 Jan 2014 15:51:36 -0500
Subject: tipc: correctly unlink packets from deferred packet queue

When we pull a received packet from a link's 'deferred packets' queue
for processing, its 'next' pointer is not cleared, and still refers to
the next packet in that queue, if any. This is incorrect, but caused
no harm before commit 40ba3cdf542a469aaa9083fa041656e59b109b90 ("tipc:
message reassembly using fragment chain") was introduced. After that
commit, it may sometimes lead to the following oops:

general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC
Modules linked in: tipc
CPU: 4 PID: 0 Comm: swapper/4 Tainted: G        W 3.13.0-rc2+ #6
Hardware name: Bochs Bochs, BIOS Bochs 01/01/2007
task: ffff880017af4880 ti: ffff880017aee000 task.ti: ffff880017aee000
RIP: 0010:[<ffffffff81710694>]  [<ffffffff81710694>] skb_try_coalesce+0x44/0x3d0
RSP: 0018:ffff880016603a78  EFLAGS: 00010212
RAX: 6b6b6b6bd6d6d6d6 RBX: ffff880013106ac0 RCX: ffff880016603ad0
RDX: ffff880016603ad7 RSI: ffff88001223ed00 RDI: ffff880013106ac0
RBP: ffff880016603ab8 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000000 R12: ffff88001223ed00
R13: ffff880016603ad0 R14: 000000000000058c R15: ffff880012297650
FS:  0000000000000000(0000) GS:ffff880016600000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 000000000805b000 CR3: 0000000011f5d000 CR4: 00000000000006e0
Stack:
 ffff880016603a88 ffffffff810a38ed ffff880016603aa8 ffff88001223ed00
 0000000000000001 ffff880012297648 ffff880016603b68 ffff880012297650
 ffff880016603b08 ffffffffa0006c51 ffff880016603b08 00ffffffa00005fc
Call Trace:
 <IRQ>
 [<ffffffff810a38ed>] ? trace_hardirqs_on+0xd/0x10
 [<ffffffffa0006c51>] tipc_link_recv_fragment+0xd1/0x1b0 [tipc]
 [<ffffffffa0007214>] tipc_recv_msg+0x4e4/0x920 [tipc]
 [<ffffffffa00016f0>] ? tipc_l2_rcv_msg+0x40/0x250 [tipc]
 [<ffffffffa000177c>] tipc_l2_rcv_msg+0xcc/0x250 [tipc]
 [<ffffffffa00016f0>] ? tipc_l2_rcv_msg+0x40/0x250 [tipc]
 [<ffffffff8171e65b>] __netif_receive_skb_core+0x80b/0xd00
 [<ffffffff8171df94>] ? __netif_receive_skb_core+0x144/0xd00
 [<ffffffff8171eb76>] __netif_receive_skb+0x26/0x70
 [<ffffffff8171ed6d>] netif_receive_skb+0x2d/0x200
 [<ffffffff8171fe70>] napi_gro_receive+0xb0/0x130
 [<ffffffff815647c2>] e1000_clean_rx_irq+0x2c2/0x530
 [<ffffffff81565986>] e1000_clean+0x266/0x9c0
 [<ffffffff81985f7b>] ? notifier_call_chain+0x2b/0x160
 [<ffffffff8171f971>] net_rx_action+0x141/0x310
 [<ffffffff81051c1b>] __do_softirq+0xeb/0x480
 [<ffffffff819817bb>] ? _raw_spin_unlock+0x2b/0x40
 [<ffffffff810b8c42>] ? handle_fasteoi_irq+0x72/0x100
 [<ffffffff81052346>] irq_exit+0x96/0xc0
 [<ffffffff8198cbc3>] do_IRQ+0x63/0xe0
 [<ffffffff81981def>] common_interrupt+0x6f/0x6f
 <EOI>

This happens when the last fragment of a message has passed through the
the receiving link's 'deferred packets' queue, and at least one other
packet was added to that queue while it was there. After the fragment
chain with the complete message has been successfully delivered to the
receiving socket, it is released. Since 'next' pointer of the last
fragment in the released chain now is non-NULL, we get the crash shown
above.

We fix this by clearing the 'next' pointer of all received packets,
including those being pulled from the 'deferred' queue, before they
undergo any further processing.

Fixes: 40ba3cdf542a4 ("tipc: message reassembly using fragment chain")
Signed-off-by: Erik Hugne <erik.hugne@ericsson.com>
Reported-by: Ying Xue <ying.xue@windriver.com>
Reviewed-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/tipc/link.c b/net/tipc/link.c
index 69cd9bf..13b9877 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1498,6 +1498,7 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr)
 		int type;
 
 		head = head->next;
+		buf->next = NULL;
 
 		/* Ensure bearer is still enabled */
 		if (unlikely(!b_ptr->active))
-- 
cgit v0.10.2


From 5d2f4767c4eacab351b8450b0de4d3261fe1a957 Mon Sep 17 00:00:00 2001
From: Ilia Mirkin <imirkin@alum.mit.edu>
Date: Tue, 7 Jan 2014 12:33:59 -0500
Subject: drm/nouveau/bios: fix offset calculation for BMPv1 bioses

The only BIOS on record that needs the 14 offset has a bios major
version 2 but BMP version 1.01. Another bunch of BIOSes that need the 18
offset have BMP version 2.01 or 5.01 or higher. So instead of looking at the
bios major version, look at the BMP version. BIOSes with BMP version 0
do not contain a detectable script, so always return 0 for them.

See https://bugs.freedesktop.org/show_bug.cgi?id=68835

Reported-by: Mauro Molinari <mauromol@tiscali.it>
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>

diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
index 9f5b81e..df1b1b4 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/init.c
@@ -365,13 +365,13 @@ static u16
 init_script(struct nouveau_bios *bios, int index)
 {
 	struct nvbios_init init = { .bios = bios };
-	u16 data;
+	u16 bmp_ver = bmp_version(bios), data;
 
-	if (bmp_version(bios) && bmp_version(bios) < 0x0510) {
-		if (index > 1)
+	if (bmp_ver && bmp_ver < 0x0510) {
+		if (index > 1 || bmp_ver < 0x0100)
 			return 0x0000;
 
-		data = bios->bmp_offset + (bios->version.major < 2 ? 14 : 18);
+		data = bios->bmp_offset + (bmp_ver < 0x0200 ? 14 : 18);
 		return nv_ro16(bios, data + (index * 2));
 	}
 
-- 
cgit v0.10.2


From bbc6319676944aa43527656b996766b85558e7e0 Mon Sep 17 00:00:00 2001
From: Christian Engelmayer <cengelma@gmx.at>
Date: Sun, 29 Dec 2013 23:08:54 +0100
Subject: drm/nouveau/nouveau: fix memory leak in nouveau_crtc_page_flip()

Fix a memory leak in the nouveau_crtc_page_flip() error handling path.

Signed-off-by: Christian Engelmayer <cengelma@gmx.at>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>

diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 29c3efd..25ea82f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -610,7 +610,7 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 	ret = nouveau_fence_sync(fence, chan);
 	nouveau_fence_unref(&fence);
 	if (ret)
-		return ret;
+		goto fail_free;
 
 	if (new_bo != old_bo) {
 		ret = nouveau_bo_pin(new_bo, TTM_PL_FLAG_VRAM);
-- 
cgit v0.10.2


From 0882dae983707455e97479e5e904e37673517ebc Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Wed, 8 Jan 2014 11:12:27 -0200
Subject: drm/i915: fix DDI PLLs HW state readout code

Properly zero the refcounts and crtc->ddi_pll_set so the previous HW
state doesn't affect the result of reading the current HW state.

This fixes WARNs about WRPLL refcount if we have an HDMI monitor on
HSW and then suspend/resume.

Cc: stable@vger.kernel.org
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=64379
Tested-by: Qingshuai Tian <qingshuai.tian@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 526c8de..b69dc3e 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1057,12 +1057,18 @@ void intel_ddi_setup_hw_pll_state(struct drm_device *dev)
 	enum pipe pipe;
 	struct intel_crtc *intel_crtc;
 
+	dev_priv->ddi_plls.spll_refcount = 0;
+	dev_priv->ddi_plls.wrpll1_refcount = 0;
+	dev_priv->ddi_plls.wrpll2_refcount = 0;
+
 	for_each_pipe(pipe) {
 		intel_crtc =
 			to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
 
-		if (!intel_crtc->active)
+		if (!intel_crtc->active) {
+			intel_crtc->ddi_pll_sel = PORT_CLK_SEL_NONE;
 			continue;
+		}
 
 		intel_crtc->ddi_pll_sel = intel_ddi_get_crtc_pll(dev_priv,
 								 pipe);
-- 
cgit v0.10.2


From 778037e1ccb75609846deca9e419449c1dc137fa Mon Sep 17 00:00:00 2001
From: James Hogan <james.hogan@imgtec.com>
Date: Mon, 16 Dec 2013 10:41:38 +0000
Subject: clk: clk-divider: fix divisor > 255 bug

Commit 6d9252bd9a4bb (clk: Add support for power of two type dividers)
merged in v3.6 added the _get_val function to convert a divisor value to
a register field value depending on the flags. However it used the type
u8 for the div field, causing divisors larger than 255 to be masked
and the resultant clock rate to be too high.

E.g. in my case an 11bit divider was supposed to divide 24.576 MHz down
to 32.768KHz. The divisor was correctly calculated as 750 (0x2ee). This
was masked to 238 (0xee) resulting in a frequency of 103.26KHz.

Signed-off-by: James Hogan <james.hogan@imgtec.com>
Cc: Rajendra Nayak <rnayak@ti.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: stable@vger.kernel.org
Signed-off-by: Mike Turquette <mturquette@linaro.org>

diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c
index 8d3009e..5543b7d 100644
--- a/drivers/clk/clk-divider.c
+++ b/drivers/clk/clk-divider.c
@@ -87,7 +87,7 @@ static unsigned int _get_table_val(const struct clk_div_table *table,
 	return 0;
 }
 
-static unsigned int _get_val(struct clk_divider *divider, u8 div)
+static unsigned int _get_val(struct clk_divider *divider, unsigned int div)
 {
 	if (divider->flags & CLK_DIVIDER_ONE_BASED)
 		return div;
-- 
cgit v0.10.2


From f8dae00684d678afa13041ef170cecfd1297ed40 Mon Sep 17 00:00:00 2001
From: John David Anglin <dave.anglin@bell.net>
Date: Sun, 5 Jan 2014 21:25:00 -0500
Subject: parisc: Ensure full cache coherency for kmap/kunmap

Helge Deller noted a few weeks ago problems with the AIO support on
parisc. This change is the result of numerous iterations on how best to
deal with this problem.

The solution adopted here is to provide full cache coherency in a
uniform manner on all parisc systems. This involves calling
flush_dcache_page() on kmap operations and flush_kernel_dcache_page() on
kunmap operations. As a result, the copy_user_page() and
clear_user_page() functions can be removed and the overall code is
simpler.

The change ensures that both userspace and kernel aliases to a mapped
page are invalidated and flushed. This is necessary for the correct
operation of PA8800 and PA8900 based systems which do not support
inequivalent aliases.

With this change, I have observed no cache related issues on c8000 and
rp3440. It is now possible for example to do kernel builds with "-j64"
on four way systems.

On systems using XFS file systems, the patch recently posted by Mikulas
Patocka to "fix crash using XFS on loopback" is needed to avoid a hang
caused by an uninitialized lock passed to flush_dcache_page() in the
page struct.

Signed-off-by: John David Anglin <dave.anglin@bell.net>
Cc: stable@vger.kernel.org # v3.9+
Signed-off-by: Helge Deller <deller@gmx.de>

diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index f0e2784..2f9b751 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -125,42 +125,38 @@ flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vma
 void mark_rodata_ro(void);
 #endif
 
-#ifdef CONFIG_PA8X00
-/* Only pa8800, pa8900 needs this */
-
 #include <asm/kmap_types.h>
 
 #define ARCH_HAS_KMAP
 
-void kunmap_parisc(void *addr);
-
 static inline void *kmap(struct page *page)
 {
 	might_sleep();
+	flush_dcache_page(page);
 	return page_address(page);
 }
 
 static inline void kunmap(struct page *page)
 {
-	kunmap_parisc(page_address(page));
+	flush_kernel_dcache_page_addr(page_address(page));
 }
 
 static inline void *kmap_atomic(struct page *page)
 {
 	pagefault_disable();
+	flush_dcache_page(page);
 	return page_address(page);
 }
 
 static inline void __kunmap_atomic(void *addr)
 {
-	kunmap_parisc(addr);
+	flush_kernel_dcache_page_addr(addr);
 	pagefault_enable();
 }
 
 #define kmap_atomic_prot(page, prot)	kmap_atomic(page)
 #define kmap_atomic_pfn(pfn)	kmap_atomic(pfn_to_page(pfn))
 #define kmap_atomic_to_page(ptr)	virt_to_page(ptr)
-#endif
 
 #endif /* _PARISC_CACHEFLUSH_H */
 
diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h
index b7adb2a..c53fc63 100644
--- a/arch/parisc/include/asm/page.h
+++ b/arch/parisc/include/asm/page.h
@@ -28,9 +28,8 @@ struct page;
 
 void clear_page_asm(void *page);
 void copy_page_asm(void *to, void *from);
-void clear_user_page(void *vto, unsigned long vaddr, struct page *pg);
-void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
-			   struct page *pg);
+#define clear_user_page(vto, vaddr, page) clear_page_asm(vto)
+#define copy_user_page(vto, vfrom, vaddr, page) copy_page_asm(vto, vfrom)
 
 /* #define CONFIG_PARISC_TMPALIAS */
 
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index c035673..a725455 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -388,41 +388,6 @@ void flush_kernel_dcache_page_addr(void *addr)
 }
 EXPORT_SYMBOL(flush_kernel_dcache_page_addr);
 
-void clear_user_page(void *vto, unsigned long vaddr, struct page *page)
-{
-	clear_page_asm(vto);
-	if (!parisc_requires_coherency())
-		flush_kernel_dcache_page_asm(vto);
-}
-EXPORT_SYMBOL(clear_user_page);
-
-void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
-	struct page *pg)
-{
-	/* Copy using kernel mapping.  No coherency is needed
-	   (all in kmap/kunmap) on machines that don't support
-	   non-equivalent aliasing.  However, the `from' page
-	   needs to be flushed before it can be accessed through
-	   the kernel mapping. */
-	preempt_disable();
-	flush_dcache_page_asm(__pa(vfrom), vaddr);
-	preempt_enable();
-	copy_page_asm(vto, vfrom);
-	if (!parisc_requires_coherency())
-		flush_kernel_dcache_page_asm(vto);
-}
-EXPORT_SYMBOL(copy_user_page);
-
-#ifdef CONFIG_PA8X00
-
-void kunmap_parisc(void *addr)
-{
-	if (parisc_requires_coherency())
-		flush_kernel_dcache_page_addr(addr);
-}
-EXPORT_SYMBOL(kunmap_parisc);
-#endif
-
 void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
 {
 	unsigned long flags;
-- 
cgit v0.10.2


From 46184415368a6095d5da33991c5e011f1084353d Mon Sep 17 00:00:00 2001
From: "David E. Box" <david.e.box@linux.intel.com>
Date: Wed, 8 Jan 2014 13:27:51 -0800
Subject: arch: x86: New MailBox support driver for Intel SOC's

Current Intel SOC cores use a MailBox Interface (MBI) to provide access to
configuration registers on devices (called units) connected to the system
fabric. This is a support driver that implements access to this interface on
those platforms that can enumerate the device using PCI. Initial support is for
BayTrail, for which port definitons are provided. This is a requirement for
implementing platform specific features (e.g. RAPL driver requires this to
perform platform specific power management using the registers in PUNIT).
Dependant modules should select IOSF_MBI in their respective Kconfig
configuraiton. Serialized access is handled by all exported routines with
spinlocks.

The API includes 3 functions for access to unit registers:

int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr)
int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr)
int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask)

port:	indicating the unit being accessed
opcode:	the read or write port specific opcode
offset:	the register offset within the port
mdr:	the register data to be read, written, or modified
mask:	bit locations in mdr to change

Returns nonzero on error

Note: GPU code handles access to the GFX unit. Therefore access to that unit
with this driver is disallowed to avoid conflicts.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Link: http://lkml.kernel.org/r/1389216471-734-1-git-send-email-david.e.box@linux.intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Cc: Matthew Garrett <mjg59@srcf.ucam.org>

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0952ecd..ca5959a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2393,6 +2393,14 @@ config X86_DMA_REMAP
 	bool
 	depends on STA2X11
 
+config IOSF_MBI
+	bool
+	depends on PCI
+	---help---
+	  To be selected by modules requiring access to the Intel OnChip System
+	  Fabric (IOSF) Sideband MailBox Interface (MBI). For MBI platforms
+	  enumerable by PCI.
+
 source "net/Kconfig"
 
 source "drivers/Kconfig"
diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h
new file mode 100644
index 0000000..8e71c79
--- /dev/null
+++ b/arch/x86/include/asm/iosf_mbi.h
@@ -0,0 +1,90 @@
+/*
+ * iosf_mbi.h: Intel OnChip System Fabric MailBox access support
+ */
+
+#ifndef IOSF_MBI_SYMS_H
+#define IOSF_MBI_SYMS_H
+
+#define MBI_MCR_OFFSET		0xD0
+#define MBI_MDR_OFFSET		0xD4
+#define MBI_MCRX_OFFSET		0xD8
+
+#define MBI_RD_MASK		0xFEFFFFFF
+#define MBI_WR_MASK		0X01000000
+
+#define MBI_MASK_HI		0xFFFFFF00
+#define MBI_MASK_LO		0x000000FF
+#define MBI_ENABLE		0xF0
+
+/* Baytrail available units */
+#define BT_MBI_UNIT_AUNIT	0x00
+#define BT_MBI_UNIT_SMC		0x01
+#define BT_MBI_UNIT_CPU		0x02
+#define BT_MBI_UNIT_BUNIT	0x03
+#define BT_MBI_UNIT_PMC		0x04
+#define BT_MBI_UNIT_GFX		0x06
+#define BT_MBI_UNIT_SMI		0x0C
+#define BT_MBI_UNIT_USB		0x43
+#define BT_MBI_UNIT_SATA	0xA3
+#define BT_MBI_UNIT_PCIE	0xA6
+
+/* Baytrail read/write opcodes */
+#define BT_MBI_AUNIT_READ	0x10
+#define BT_MBI_AUNIT_WRITE	0x11
+#define BT_MBI_SMC_READ		0x10
+#define BT_MBI_SMC_WRITE	0x11
+#define BT_MBI_CPU_READ		0x10
+#define BT_MBI_CPU_WRITE	0x11
+#define BT_MBI_BUNIT_READ	0x10
+#define BT_MBI_BUNIT_WRITE	0x11
+#define BT_MBI_PMC_READ		0x06
+#define BT_MBI_PMC_WRITE	0x07
+#define BT_MBI_GFX_READ		0x00
+#define BT_MBI_GFX_WRITE	0x01
+#define BT_MBI_SMIO_READ	0x06
+#define BT_MBI_SMIO_WRITE	0x07
+#define BT_MBI_USB_READ		0x06
+#define BT_MBI_USB_WRITE	0x07
+#define BT_MBI_SATA_READ	0x00
+#define BT_MBI_SATA_WRITE	0x01
+#define BT_MBI_PCIE_READ	0x00
+#define BT_MBI_PCIE_WRITE	0x01
+
+/**
+ * iosf_mbi_read() - MailBox Interface read command
+ * @port:	port indicating subunit being accessed
+ * @opcode:	port specific read or write opcode
+ * @offset:	register address offset
+ * @mdr:	register data to be read
+ *
+ * Locking is handled by spinlock - cannot sleep.
+ * Return: Nonzero on error
+ */
+int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr);
+
+/**
+ * iosf_mbi_write() - MailBox unmasked write command
+ * @port:	port indicating subunit being accessed
+ * @opcode:	port specific read or write opcode
+ * @offset:	register address offset
+ * @mdr:	register data to be written
+ *
+ * Locking is handled by spinlock - cannot sleep.
+ * Return: Nonzero on error
+ */
+int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr);
+
+/**
+ * iosf_mbi_modify() - MailBox masked write command
+ * @port:	port indicating subunit being accessed
+ * @opcode:	port specific read or write opcode
+ * @offset:	register address offset
+ * @mdr:	register data being modified
+ * @mask:	mask indicating bits in mdr to be modified
+ *
+ * Locking is handled by spinlock - cannot sleep.
+ * Return: Nonzero on error
+ */
+int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask);
+
+#endif /* IOSF_MBI_SYMS_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 9b0a34e..dbe9bd6 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -111,6 +111,7 @@ obj-$(CONFIG_EFI)			+= sysfb_efi.o
 
 obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o
 obj-$(CONFIG_TRACING)			+= tracepoint.o
+obj-$(CONFIG_IOSF_MBI)			+= iosf_mbi.o
 
 ###
 # 64 bit specific files
diff --git a/arch/x86/kernel/iosf_mbi.c b/arch/x86/kernel/iosf_mbi.c
new file mode 100644
index 0000000..c3aae66
--- /dev/null
+++ b/arch/x86/kernel/iosf_mbi.c
@@ -0,0 +1,226 @@
+/*
+ * IOSF-SB MailBox Interface Driver
+ * Copyright (c) 2013, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ *
+ * The IOSF-SB is a fabric bus available on Atom based SOC's that uses a
+ * mailbox interface (MBI) to communicate with mutiple devices. This
+ * driver implements access to this interface for those platforms that can
+ * enumerate the device using PCI.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+
+#include <asm/iosf_mbi.h>
+
+static DEFINE_SPINLOCK(iosf_mbi_lock);
+
+static inline u32 iosf_mbi_form_mcr(u8 op, u8 port, u8 offset)
+{
+	return (op << 24) | (port << 16) | (offset << 8) | MBI_ENABLE;
+}
+
+static struct pci_dev *mbi_pdev;	/* one mbi device */
+
+static int iosf_mbi_pci_read_mdr(u32 mcrx, u32 mcr, u32 *mdr)
+{
+	int result;
+
+	if (!mbi_pdev)
+		return -ENODEV;
+
+	if (mcrx) {
+		result = pci_write_config_dword(mbi_pdev, MBI_MCRX_OFFSET,
+						mcrx);
+		if (result < 0)
+			goto fail_read;
+	}
+
+	result = pci_write_config_dword(mbi_pdev, MBI_MCR_OFFSET, mcr);
+	if (result < 0)
+		goto fail_read;
+
+	result = pci_read_config_dword(mbi_pdev, MBI_MDR_OFFSET, mdr);
+	if (result < 0)
+		goto fail_read;
+
+	return 0;
+
+fail_read:
+	dev_err(&mbi_pdev->dev, "PCI config access failed with %d\n", result);
+	return result;
+}
+
+static int iosf_mbi_pci_write_mdr(u32 mcrx, u32 mcr, u32 mdr)
+{
+	int result;
+
+	if (!mbi_pdev)
+		return -ENODEV;
+
+	result = pci_write_config_dword(mbi_pdev, MBI_MDR_OFFSET, mdr);
+	if (result < 0)
+		goto fail_write;
+
+	if (mcrx) {
+		result = pci_write_config_dword(mbi_pdev, MBI_MCRX_OFFSET,
+						mcrx);
+		if (result < 0)
+			goto fail_write;
+	}
+
+	result = pci_write_config_dword(mbi_pdev, MBI_MCR_OFFSET, mcr);
+	if (result < 0)
+		goto fail_write;
+
+	return 0;
+
+fail_write:
+	dev_err(&mbi_pdev->dev, "PCI config access failed with %d\n", result);
+	return result;
+}
+
+int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr)
+{
+	u32 mcr, mcrx;
+	unsigned long flags;
+	int ret;
+
+	/*Access to the GFX unit is handled by GPU code */
+	if (port == BT_MBI_UNIT_GFX) {
+		WARN_ON(1);
+		return -EPERM;
+	}
+
+	mcr = iosf_mbi_form_mcr(opcode, port, offset & MBI_MASK_LO);
+	mcrx = offset & MBI_MASK_HI;
+
+	spin_lock_irqsave(&iosf_mbi_lock, flags);
+	ret = iosf_mbi_pci_read_mdr(mcrx, mcr, mdr);
+	spin_unlock_irqrestore(&iosf_mbi_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL(iosf_mbi_read);
+
+int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr)
+{
+	u32 mcr, mcrx;
+	unsigned long flags;
+	int ret;
+
+	/*Access to the GFX unit is handled by GPU code */
+	if (port == BT_MBI_UNIT_GFX) {
+		WARN_ON(1);
+		return -EPERM;
+	}
+
+	mcr = iosf_mbi_form_mcr(opcode, port, offset & MBI_MASK_LO);
+	mcrx = offset & MBI_MASK_HI;
+
+	spin_lock_irqsave(&iosf_mbi_lock, flags);
+	ret = iosf_mbi_pci_write_mdr(mcrx, mcr, mdr);
+	spin_unlock_irqrestore(&iosf_mbi_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL(iosf_mbi_write);
+
+int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask)
+{
+	u32 mcr, mcrx;
+	u32 value;
+	unsigned long flags;
+	int ret;
+
+	/*Access to the GFX unit is handled by GPU code */
+	if (port == BT_MBI_UNIT_GFX) {
+		WARN_ON(1);
+		return -EPERM;
+	}
+
+	mcr = iosf_mbi_form_mcr(opcode, port, offset & MBI_MASK_LO);
+	mcrx = offset & MBI_MASK_HI;
+
+	spin_lock_irqsave(&iosf_mbi_lock, flags);
+
+	/* Read current mdr value */
+	ret = iosf_mbi_pci_read_mdr(mcrx, mcr & MBI_RD_MASK, &value);
+	if (ret < 0) {
+		spin_unlock_irqrestore(&iosf_mbi_lock, flags);
+		return ret;
+	}
+
+	/* Apply mask */
+	value &= ~mask;
+	mdr &= mask;
+	value |= mdr;
+
+	/* Write back */
+	ret = iosf_mbi_pci_write_mdr(mcrx, mcr | MBI_WR_MASK, value);
+
+	spin_unlock_irqrestore(&iosf_mbi_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL(iosf_mbi_modify);
+
+static int iosf_mbi_probe(struct pci_dev *pdev,
+			  const struct pci_device_id *unused)
+{
+	int ret;
+
+	ret = pci_enable_device(pdev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "error: could not enable device\n");
+		return ret;
+	}
+
+	mbi_pdev = pci_dev_get(pdev);
+	return 0;
+}
+
+static DEFINE_PCI_DEVICE_TABLE(iosf_mbi_pci_ids) = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x0F00) },
+	{ 0, },
+};
+MODULE_DEVICE_TABLE(pci, iosf_mbi_pci_ids);
+
+static struct pci_driver iosf_mbi_pci_driver = {
+	.name		= "iosf_mbi_pci",
+	.probe		= iosf_mbi_probe,
+	.id_table	= iosf_mbi_pci_ids,
+};
+
+static int __init iosf_mbi_init(void)
+{
+	return pci_register_driver(&iosf_mbi_pci_driver);
+}
+
+static void __exit iosf_mbi_exit(void)
+{
+	pci_unregister_driver(&iosf_mbi_pci_driver);
+	if (mbi_pdev) {
+		pci_dev_put(mbi_pdev);
+		mbi_pdev = NULL;
+	}
+}
+
+module_init(iosf_mbi_init);
+module_exit(iosf_mbi_exit);
+
+MODULE_AUTHOR("David E. Box <david.e.box@linux.intel.com>");
+MODULE_DESCRIPTION("IOSF Mailbox Interface accessor");
+MODULE_LICENSE("GPL v2");
-- 
cgit v0.10.2


From ba0dc81ed5d9549daa233d7322b4c2809e28fca8 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Thu, 9 Jan 2014 15:30:26 +0800
Subject: Revert "intel_idle: mark states tables with __initdata tag"

This reverts commit 9d046ccb98085f1d437585f84748c783a04ba240.

Commit 9d046ccb98085 marks all state tables with __initdata, but
the state table may be accessed when doing CPU online, which then
causing system crash as below:

[  204.188841] BUG: unable to handle kernel paging request at ffffffff8227cce8
[  204.196844] IP: [<ffffffff814aa1c0>] intel_idle_cpu_init+0x40/0x130
[  204.203996] PGD 1e11067 PUD 1e12063 PMD 455859063 PTE 800000000227c062
[  204.211638] Oops: 0000 [#1] SMP DEBUG_PAGEALLOC
[  204.216975] Modules linked in: x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel aes_x86_64 lrw gf128mul glue_helper ablk_helper cryptd gpio_ich microcode joydev sb_edac edac_core ipmi_si lpc_ich ipmi_msghandler lp tpm_tis parport wmi mac_hid acpi_pad hid_generic ixgbe isci usbhid dca hid libsas ptp ahci libahci scsi_transport_sas megaraid_sas pps_core mdio
[  204.262815] CPU: 11 PID: 1489 Comm: bash Not tainted 3.13.0-rc7+ #48
[  204.269993] Hardware name: Intel Corporation BRICKLAND/BRICKLAND, BIOS BRIVTIN1.86B.0047.L09.1312061514 12/06/2013
[  204.281646] task: ffff8804303a24a0 ti: ffff880440fac000 task.ti: ffff880440fac000
[  204.290311] RIP: 0010:[<ffffffff814aa1c0>]  [<ffffffff814aa1c0>] intel_idle_cpu_init+0x40/0x130
[  204.300184] RSP: 0018:ffff880440fadd28  EFLAGS: 00010286
[  204.306192] RAX: ffffffff8227cca0 RBX: ffffe8fff1a03400 RCX: 0000000000000007
[  204.314244] RDX: ffff88045f400000 RSI: 0000000000000009 RDI: 0000000000001120
[  204.322296] RBP: ffff880440fadd38 R08: 0000000000000000 R09: 0000000000000001
[  204.330411] R10: 0000000000000001 R11: 0000000000000000 R12: 000000000000001e
[  204.338482] R13: 00000000ffffffdb R14: 0000000000000001 R15: 0000000000000000
[  204.346743] FS:  00007f64f7b0c740(0000) GS:ffff88045ce00000(0000) knlGS:0000000000000000
[  204.355919] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  204.362449] CR2: ffffffff8227cce8 CR3: 0000000444ab0000 CR4: 00000000001407e0
[  204.370520] Stack:
[  204.372853]  000000000000001e ffffffff81f10240 ffff880440fadd50 ffffffff814aa307
[  204.381519]  ffffffff81ea80e0 ffff880440fadda0 ffffffff8185a230 0000000000000000
[  204.390196]  000000000000001e 0000000000000002 0000000000000002 0000000000000000
[  204.398856] Call Trace:
[  204.401683]  [<ffffffff814aa307>] cpu_hotplug_notify+0x57/0x70
[  204.408638]  [<ffffffff8185a230>] notifier_call_chain+0x100/0x150
[  204.415553]  [<ffffffff810a7dae>] __raw_notifier_call_chain+0xe/0x10
[  204.422772]  [<ffffffff81072163>] cpu_notify+0x23/0x50
[  204.428616]  [<ffffffff810723b2>] _cpu_up+0x132/0x1a0
[  204.434361]  [<ffffffff8107249d>] cpu_up+0x7d/0xa0
[  204.439819]  [<ffffffff81836c9c>] cpu_subsys_online+0x3c/0x90
[  204.446345]  [<ffffffff81554625>] device_online+0x45/0xa0
[  204.452471]  [<ffffffff815546ce>] online_store+0x4e/0x80
[  204.458511]  [<ffffffff815519a8>] dev_attr_store+0x18/0x30
[  204.464744]  [<ffffffff812a68f1>] sysfs_write_file+0x151/0x1c0
[  204.471681]  [<ffffffff81217ef1>] vfs_write+0xe1/0x160
[  204.477524]  [<ffffffff8121889c>] SyS_write+0x4c/0x90
[  204.483270]  [<ffffffff8185f2ed>] system_call_fastpath+0x1a/0x1f
[  204.490081] Code: 41 54 41 89 fc 8b 3d 48 25 85 01 53 48 8b 1d 30 25 85 01 48 03 1c c5 40 90 fb 81 48 8b 05 19 25 85 01 c7 43 0c 01 00 00 00 66 90 <48> 83 78 48 00 74 4f 41 83 c0 01 41 39 f0 7e 10 48 c7 c7 38 79
[  204.515723] RIP  [<ffffffff814aa1c0>] intel_idle_cpu_init+0x40/0x130
[  204.522996]  RSP <ffff880440fadd28>
[  204.526976] CR2: ffffffff8227cce8
[  204.530766] ---[ end trace 336f56cc3d1cfc8c ]---

Fixes: 9d046ccb98085 (intel_idle: mark states tables with __initdata tag)
Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index f80b700..6f456f0 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -123,7 +123,7 @@ static struct cpuidle_state *cpuidle_state_table;
  * which is also the index into the MWAIT hint array.
  * Thus C0 is a dummy.
  */
-static struct cpuidle_state nehalem_cstates[] __initdata = {
+static struct cpuidle_state nehalem_cstates[] = {
 	{
 		.name = "C1-NHM",
 		.desc = "MWAIT 0x00",
@@ -156,7 +156,7 @@ static struct cpuidle_state nehalem_cstates[] __initdata = {
 		.enter = NULL }
 };
 
-static struct cpuidle_state snb_cstates[] __initdata = {
+static struct cpuidle_state snb_cstates[] = {
 	{
 		.name = "C1-SNB",
 		.desc = "MWAIT 0x00",
@@ -196,7 +196,7 @@ static struct cpuidle_state snb_cstates[] __initdata = {
 		.enter = NULL }
 };
 
-static struct cpuidle_state ivb_cstates[] __initdata = {
+static struct cpuidle_state ivb_cstates[] = {
 	{
 		.name = "C1-IVB",
 		.desc = "MWAIT 0x00",
@@ -236,7 +236,7 @@ static struct cpuidle_state ivb_cstates[] __initdata = {
 		.enter = NULL }
 };
 
-static struct cpuidle_state hsw_cstates[] __initdata = {
+static struct cpuidle_state hsw_cstates[] = {
 	{
 		.name = "C1-HSW",
 		.desc = "MWAIT 0x00",
@@ -297,7 +297,7 @@ static struct cpuidle_state hsw_cstates[] __initdata = {
 		.enter = NULL }
 };
 
-static struct cpuidle_state atom_cstates[] __initdata = {
+static struct cpuidle_state atom_cstates[] = {
 	{
 		.name = "C1E-ATM",
 		.desc = "MWAIT 0x00",
-- 
cgit v0.10.2


From 1739f09e33d8f66bf48ddbc3eca615574da6c4f6 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Wed, 13 Nov 2013 15:20:04 -0500
Subject: ftrace/x86: Load ftrace_ops in parameter not the variable holding it

Function tracing callbacks expect to have the ftrace_ops that registered it
passed to them, not the address of the variable that holds the ftrace_ops
that registered it.

Use a mov instead of a lea to store the ftrace_ops into the parameter
of the function tracing callback.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Link: http://lkml.kernel.org/r/20131113152004.459787f9@gandalf.local.home
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: <stable@vger.kernel.org> # v3.8+

diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 51e2988..a2a4f46 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1082,7 +1082,7 @@ ENTRY(ftrace_caller)
 	pushl $0	/* Pass NULL as regs pointer */
 	movl 4*4(%esp), %eax
 	movl 0x4(%ebp), %edx
-	leal function_trace_op, %ecx
+	movl function_trace_op, %ecx
 	subl $MCOUNT_INSN_SIZE, %eax
 
 .globl ftrace_call
@@ -1140,7 +1140,7 @@ ENTRY(ftrace_regs_caller)
 	movl 12*4(%esp), %eax	/* Load ip (1st parameter) */
 	subl $MCOUNT_INSN_SIZE, %eax	/* Adjust ip */
 	movl 0x4(%ebp), %edx	/* Load parent ip (2nd parameter) */
-	leal function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
+	movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
 	pushl %esp		/* Save pt_regs as 4th parameter */
 
 GLOBAL(ftrace_regs_call)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index e21b078..1e96c36 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -88,7 +88,7 @@ END(function_hook)
 	MCOUNT_SAVE_FRAME \skip
 
 	/* Load the ftrace_ops into the 3rd parameter */
-	leaq function_trace_op, %rdx
+	movq function_trace_op(%rip), %rdx
 
 	/* Load ip into the first parameter */
 	movq RIP(%rsp), %rdi
-- 
cgit v0.10.2


From 88390996c95b879ba365888199b45ace3f5ca80b Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Thu, 9 Jan 2014 15:30:27 +0800
Subject: intel_idle: close avn_cstates array with correct marker

Close avn_cstates array with correct marker to avoid overflow
in function intel_idle_cpu_init().

[rjw: The problem was introduced when commit 22e580d07f65 was merged
 on top of eba682a5aeb6 (intel_idle: shrink states tables).]

Fixes: 22e580d07f65 (intel_idle: Fixed C6 state on Avoton/Rangeley processors)
Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 6f456f0..797ed29 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -329,7 +329,7 @@ static struct cpuidle_state atom_cstates[] = {
 	{
 		.enter = NULL }
 };
-static struct cpuidle_state avn_cstates[] __initdata = {
+static struct cpuidle_state avn_cstates[] = {
 	{
 		.name = "C1-AVN",
 		.desc = "MWAIT 0x00",
@@ -344,6 +344,8 @@ static struct cpuidle_state avn_cstates[] __initdata = {
 		.exit_latency = 15,
 		.target_residency = 45,
 		.enter = &intel_idle },
+	{
+		.enter = NULL }
 };
 
 /**
-- 
cgit v0.10.2


From 9a2620c877454bb4b5c19f73d4d1d7b375da3632 Mon Sep 17 00:00:00 2001
From: Yuval Mintz <yuvalmin@broadcom.com>
Date: Tue, 7 Jan 2014 12:07:41 +0200
Subject: bnx2x: prevent WARN during driver unload

Starting with commit 80c33dd "net: add might_sleep() call to napi_disable"
bnx2x fails the might_sleep tests causing a stack trace to appear whenever
the driver is unloaded, as local_bh_disable() is being called before
napi_disable().

This changes the locking schematics related to CONFIG_NET_RX_BUSY_POLL,
preventing the need for calling local_bh_disable() and thus eliminating
the issue.

Signed-off-by: Yuval Mintz <yuvalmin@broadcom.com>
Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com>
Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 2d5fce4..ec61190 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -520,10 +520,12 @@ struct bnx2x_fastpath {
 #define BNX2X_FP_STATE_IDLE		      0
 #define BNX2X_FP_STATE_NAPI		(1 << 0)    /* NAPI owns this FP */
 #define BNX2X_FP_STATE_POLL		(1 << 1)    /* poll owns this FP */
-#define BNX2X_FP_STATE_NAPI_YIELD	(1 << 2)    /* NAPI yielded this FP */
-#define BNX2X_FP_STATE_POLL_YIELD	(1 << 3)    /* poll yielded this FP */
+#define BNX2X_FP_STATE_DISABLED		(1 << 2)
+#define BNX2X_FP_STATE_NAPI_YIELD	(1 << 3)    /* NAPI yielded this FP */
+#define BNX2X_FP_STATE_POLL_YIELD	(1 << 4)    /* poll yielded this FP */
+#define BNX2X_FP_OWNED	(BNX2X_FP_STATE_NAPI | BNX2X_FP_STATE_POLL)
 #define BNX2X_FP_YIELD	(BNX2X_FP_STATE_NAPI_YIELD | BNX2X_FP_STATE_POLL_YIELD)
-#define BNX2X_FP_LOCKED	(BNX2X_FP_STATE_NAPI | BNX2X_FP_STATE_POLL)
+#define BNX2X_FP_LOCKED	(BNX2X_FP_OWNED | BNX2X_FP_STATE_DISABLED)
 #define BNX2X_FP_USER_PEND (BNX2X_FP_STATE_POLL | BNX2X_FP_STATE_POLL_YIELD)
 	/* protect state */
 	spinlock_t lock;
@@ -613,7 +615,7 @@ static inline bool bnx2x_fp_lock_napi(struct bnx2x_fastpath *fp)
 {
 	bool rc = true;
 
-	spin_lock(&fp->lock);
+	spin_lock_bh(&fp->lock);
 	if (fp->state & BNX2X_FP_LOCKED) {
 		WARN_ON(fp->state & BNX2X_FP_STATE_NAPI);
 		fp->state |= BNX2X_FP_STATE_NAPI_YIELD;
@@ -622,7 +624,7 @@ static inline bool bnx2x_fp_lock_napi(struct bnx2x_fastpath *fp)
 		/* we don't care if someone yielded */
 		fp->state = BNX2X_FP_STATE_NAPI;
 	}
-	spin_unlock(&fp->lock);
+	spin_unlock_bh(&fp->lock);
 	return rc;
 }
 
@@ -631,14 +633,16 @@ static inline bool bnx2x_fp_unlock_napi(struct bnx2x_fastpath *fp)
 {
 	bool rc = false;
 
-	spin_lock(&fp->lock);
+	spin_lock_bh(&fp->lock);
 	WARN_ON(fp->state &
 		(BNX2X_FP_STATE_POLL | BNX2X_FP_STATE_NAPI_YIELD));
 
 	if (fp->state & BNX2X_FP_STATE_POLL_YIELD)
 		rc = true;
-	fp->state = BNX2X_FP_STATE_IDLE;
-	spin_unlock(&fp->lock);
+
+	/* state ==> idle, unless currently disabled */
+	fp->state &= BNX2X_FP_STATE_DISABLED;
+	spin_unlock_bh(&fp->lock);
 	return rc;
 }
 
@@ -669,7 +673,9 @@ static inline bool bnx2x_fp_unlock_poll(struct bnx2x_fastpath *fp)
 
 	if (fp->state & BNX2X_FP_STATE_POLL_YIELD)
 		rc = true;
-	fp->state = BNX2X_FP_STATE_IDLE;
+
+	/* state ==> idle, unless currently disabled */
+	fp->state &= BNX2X_FP_STATE_DISABLED;
 	spin_unlock_bh(&fp->lock);
 	return rc;
 }
@@ -677,9 +683,23 @@ static inline bool bnx2x_fp_unlock_poll(struct bnx2x_fastpath *fp)
 /* true if a socket is polling, even if it did not get the lock */
 static inline bool bnx2x_fp_ll_polling(struct bnx2x_fastpath *fp)
 {
-	WARN_ON(!(fp->state & BNX2X_FP_LOCKED));
+	WARN_ON(!(fp->state & BNX2X_FP_OWNED));
 	return fp->state & BNX2X_FP_USER_PEND;
 }
+
+/* false if fp is currently owned */
+static inline bool bnx2x_fp_ll_disable(struct bnx2x_fastpath *fp)
+{
+	int rc = true;
+
+	spin_lock_bh(&fp->lock);
+	if (fp->state & BNX2X_FP_OWNED)
+		rc = false;
+	fp->state |= BNX2X_FP_STATE_DISABLED;
+	spin_unlock_bh(&fp->lock);
+
+	return rc;
+}
 #else
 static inline void bnx2x_fp_init_lock(struct bnx2x_fastpath *fp)
 {
@@ -709,6 +729,10 @@ static inline bool bnx2x_fp_ll_polling(struct bnx2x_fastpath *fp)
 {
 	return false;
 }
+static inline bool bnx2x_fp_ll_disable(struct bnx2x_fastpath *fp)
+{
+	return true;
+}
 #endif /* CONFIG_NET_RX_BUSY_POLL */
 
 /* Use 2500 as a mini-jumbo MTU for FCoE */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index ec96130..c6745d7 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1790,26 +1790,22 @@ static void bnx2x_napi_disable_cnic(struct bnx2x *bp)
 {
 	int i;
 
-	local_bh_disable();
 	for_each_rx_queue_cnic(bp, i) {
 		napi_disable(&bnx2x_fp(bp, i, napi));
-		while (!bnx2x_fp_lock_napi(&bp->fp[i]))
-			mdelay(1);
+		while (!bnx2x_fp_ll_disable(&bp->fp[i]))
+			usleep_range(1000, 2000);
 	}
-	local_bh_enable();
 }
 
 static void bnx2x_napi_disable(struct bnx2x *bp)
 {
 	int i;
 
-	local_bh_disable();
 	for_each_eth_queue(bp, i) {
 		napi_disable(&bnx2x_fp(bp, i, napi));
-		while (!bnx2x_fp_lock_napi(&bp->fp[i]))
-			mdelay(1);
+		while (!bnx2x_fp_ll_disable(&bp->fp[i]))
+			usleep_range(1000, 2000);
 	}
-	local_bh_enable();
 }
 
 void bnx2x_netif_start(struct bnx2x *bp)
-- 
cgit v0.10.2


From 07edd741c838e376933b445bbf2692f83b6774e6 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Wed, 8 Jan 2014 15:43:22 +0100
Subject: ipv6: add link-local, sit and loopback address with
 INFINITY_LIFE_TIME
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the past the IFA_PERMANENT flag indicated, that the valid and preferred
lifetime where ignored. Since change fad8da3e085ddf ("ipv6 addrconf: fix
preferred lifetime state-changing behavior while valid_lft is infinity")
we honour at least the preferred lifetime on those addresses. As such
the valid lifetime gets recalculated and updated to 0.

If loopback address is added manually this problem does not occur.
Also if NetworkManager manages IPv6, those addresses will get added via
inet6_rtm_newaddr and thus will have a correct lifetime, too.

Reported-by: François-Xavier Le Bail <fx.lebail@yahoo.com>
Reported-by: Damien Wyart <damien.wyart@gmail.com>
Fixes: fad8da3e085ddf ("ipv6 addrconf: fix preferred lifetime state-changing behavior while valid_lft is infinity")
Cc: Yasushi Asano <yasushi.asano@jp.fujitsu.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f62c72b..abe46a4 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2509,7 +2509,8 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
 	struct inet6_ifaddr *ifp;
 
 	ifp = ipv6_add_addr(idev, addr, NULL, plen,
-			    scope, IFA_F_PERMANENT, 0, 0);
+			    scope, IFA_F_PERMANENT,
+			    INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
 	if (!IS_ERR(ifp)) {
 		spin_lock_bh(&ifp->lock);
 		ifp->flags &= ~IFA_F_TENTATIVE;
@@ -2637,7 +2638,8 @@ static void addrconf_add_linklocal(struct inet6_dev *idev, const struct in6_addr
 #endif
 
 
-	ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags, 0, 0);
+	ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags,
+			    INFINITY_LIFE_TIME, INFINITY_LIFE_TIME);
 	if (!IS_ERR(ifp)) {
 		addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev, 0, 0);
 		addrconf_dad_start(ifp);
-- 
cgit v0.10.2


From 7ad228b11ec26a820291c9f5a1168d6176580dc1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Tue, 7 Jan 2014 16:15:36 +0200
Subject: drm/i915: Don't grab crtc mutexes in intel_modeset_gem_init()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When the pipe A force quirk is applied the code will attempt to grab
a crtc mutex during intel_modeset_setup_hw_state(). If we're already
holding all crtc mutexes this will obviously deadlock every time.

So instead of using drm_modeset_lock_all() just grab the
mode_config.mutex. This is enough to avoid the unlocked mutex warnings
from certain lower level functions.

The regression was introduced in:

 commit 027476642811f8559cbe00ef6cc54db230e48a20
 Author: Ville Syrjälä <ville.syrjala@linux.intel.com>
 Date:   Mon Dec 2 11:08:06 2013 +0200

    drm/i915: Take modeset locks around intel_modeset_setup_hw_state()

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: stable@vger.kernel.org
[danvet: Add cc: stable since the offending commit has that, too.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 769b864..2bde35d 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -11053,10 +11053,10 @@ void intel_modeset_gem_init(struct drm_device *dev)
 
 	intel_setup_overlay(dev);
 
-	drm_modeset_lock_all(dev);
+	mutex_lock(&dev->mode_config.mutex);
 	drm_mode_config_reset(dev);
 	intel_modeset_setup_hw_state(dev, false);
-	drm_modeset_unlock_all(dev);
+	mutex_unlock(&dev->mode_config.mutex);
 }
 
 void intel_modeset_cleanup(struct drm_device *dev)
-- 
cgit v0.10.2


From 881f0fcef9993992c24f5b649a3fb67fd4208f8f Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@codeaurora.org>
Date: Mon, 30 Dec 2013 12:14:12 -0800
Subject: EDAC: Don't try to cancel workqueue when it's never setup

We only setup a workqueue for edac devices that use the polling
method. We still try to cancel the workqueue if an edac_device
uses the irq method though. This causes a warning from debug
objects when we remove an edac device:

WARNING: CPU: 0 PID: 56 at lib/debugobjects.c:260 debug_print_object+0x98/0xc0()
ODEBUG: assert_init not available (active state 0) object type: timer_list hint: stub_timer+0x0/0x28
Modules linked in: krait_edac(-)
CPU: 0 PID: 56 Comm: rmmod Not tainted 3.12.0-rc2-00035-g15292a0 #69
(unwind_backtrace+0x0/0x144)
(show_stack+0x20/0x24)
(dump_stack+0x74/0xb4)
(warn_slowpath_common+0x78/0x9c)
(warn_slowpath_fmt+0x40/0x48)
(debug_print_object+0x98/0xc0)
(debug_object_assert_init+0xdc/0xec)
(del_timer+0x24/0x7c)
(try_to_grab_pending+0xc0/0x1b0)
(cancel_delayed_work+0x2c/0xa0)
(edac_device_workq_teardown+0x1c/0x38)
(edac_device_del_device+0xb8/0xe4)
(krait_edac_remove+0x50/0x70 [krait_edac])
(platform_drv_remove+0x24/0x28)
(__device_release_driver+0x68/0xc0)
(driver_detach+0xc4/0xc8)
(bus_remove_driver+0xac/0x114)
(driver_unregister+0x38/0x58)
(platform_driver_unregister+0x1c/0x20)
(krait_edac_driver_exit+0x14/0x1c [krait_edac])
(SyS_delete_module+0x178/0x2b4)

Fix it by skipping the workqueue teardown for such devices.

Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Link: http://lkml.kernel.org/r/1388434457-4194-2-git-send-email-sboyd@codeaurora.org
Signed-off-by: Borislav Petkov <bp@suse.de>

diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c
index 1026743..592af5f 100644
--- a/drivers/edac/edac_device.c
+++ b/drivers/edac/edac_device.c
@@ -437,6 +437,9 @@ void edac_device_workq_teardown(struct edac_device_ctl_info *edac_dev)
 {
 	int status;
 
+	if (!edac_dev->edac_check)
+		return;
+
 	status = cancel_delayed_work(&edac_dev->work);
 	if (status == 0) {
 		/* workq instance might be running, wait for it */
-- 
cgit v0.10.2


From 95e92fd40c967c363ad66b2fd1ce4dcd68132e54 Mon Sep 17 00:00:00 2001
From: Michal Schmidt <mschmidt@redhat.com>
Date: Thu, 9 Jan 2014 14:36:27 +0100
Subject: bnx2x: fix DMA unmapping of TSO split BDs

bnx2x triggers warnings with CONFIG_DMA_API_DEBUG=y:

  WARNING: CPU: 0 PID: 2253 at lib/dma-debug.c:887 check_unmap+0xf8/0x920()
  bnx2x 0000:28:00.0: DMA-API: device driver frees DMA memory with
  different size [device address=0x00000000da2b389e] [map size=1490 bytes]
  [unmap size=66 bytes]

The reason is that bnx2x splits a TSO BD into two BDs (headers + data)
using one DMA mapping for both, but it uses only the length of the first
BD when unmapping.

This patch fixes the bug by unmapping the whole length of the two BDs.

Signed-off-by: Michal Schmidt <mschmidt@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Dmitry Kravkov <dmitry@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index c6745d7..5504120 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -160,6 +160,7 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata,
 	struct sk_buff *skb = tx_buf->skb;
 	u16 bd_idx = TX_BD(tx_buf->first_bd), new_cons;
 	int nbd;
+	u16 split_bd_len = 0;
 
 	/* prefetch skb end pointer to speedup dev_kfree_skb() */
 	prefetch(&skb->end);
@@ -167,10 +168,7 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata,
 	DP(NETIF_MSG_TX_DONE, "fp[%d]: pkt_idx %d  buff @(%p)->skb %p\n",
 	   txdata->txq_index, idx, tx_buf, skb);
 
-	/* unmap first bd */
 	tx_start_bd = &txdata->tx_desc_ring[bd_idx].start_bd;
-	dma_unmap_single(&bp->pdev->dev, BD_UNMAP_ADDR(tx_start_bd),
-			 BD_UNMAP_LEN(tx_start_bd), DMA_TO_DEVICE);
 
 	nbd = le16_to_cpu(tx_start_bd->nbd) - 1;
 #ifdef BNX2X_STOP_ON_ERROR
@@ -188,12 +186,19 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata,
 	--nbd;
 	bd_idx = TX_BD(NEXT_TX_IDX(bd_idx));
 
-	/* ...and the TSO split header bd since they have no mapping */
+	/* TSO headers+data bds share a common mapping. See bnx2x_tx_split() */
 	if (tx_buf->flags & BNX2X_TSO_SPLIT_BD) {
+		tx_data_bd = &txdata->tx_desc_ring[bd_idx].reg_bd;
+		split_bd_len = BD_UNMAP_LEN(tx_data_bd);
 		--nbd;
 		bd_idx = TX_BD(NEXT_TX_IDX(bd_idx));
 	}
 
+	/* unmap first bd */
+	dma_unmap_single(&bp->pdev->dev, BD_UNMAP_ADDR(tx_start_bd),
+			 BD_UNMAP_LEN(tx_start_bd) + split_bd_len,
+			 DMA_TO_DEVICE);
+
 	/* now free frags */
 	while (nbd > 0) {
 
-- 
cgit v0.10.2


From b13ba1b83f524732523db1079e56478b32c85c96 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 10 Jan 2014 16:18:25 +0800
Subject: macvlan: forbid L2 fowarding offload for macvtap

L2 fowarding offload will bypass the rx handler of real device. This will make
the packet could not be forwarded to macvtap device. Another problem is the
dev_hard_start_xmit() called for macvtap does not have any synchronization.

Fix this by forbidding L2 forwarding for macvtap.

Cc: John Fastabend <john.r.fastabend@intel.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: John Fastabend <john.r.fastabend@intel.com.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 60406b0..5360f73 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -338,6 +338,8 @@ static const struct header_ops macvlan_hard_header_ops = {
 	.cache_update	= eth_header_cache_update,
 };
 
+static struct rtnl_link_ops macvlan_link_ops;
+
 static int macvlan_open(struct net_device *dev)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
@@ -353,7 +355,8 @@ static int macvlan_open(struct net_device *dev)
 		goto hash_add;
 	}
 
-	if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD) {
+	if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD &&
+	    dev->rtnl_link_ops == &macvlan_link_ops) {
 		vlan->fwd_priv =
 		      lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev);
 
-- 
cgit v0.10.2


From f663dd9aaf9ed124f25f0f8452edf238f087ad50 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 10 Jan 2014 16:18:26 +0800
Subject: net: core: explicitly select a txq before doing l2 forwarding

Currently, the tx queue were selected implicitly in ndo_dfwd_start_xmit(). The
will cause several issues:

- NETIF_F_LLTX were removed for macvlan, so txq lock were done for macvlan
  instead of lower device which misses the necessary txq synchronization for
  lower device such as txq stopping or frozen required by dev watchdog or
  control path.
- dev_hard_start_xmit() was called with NULL txq which bypasses the net device
  watchdog.
- dev_hard_start_xmit() does not check txq everywhere which will lead a crash
  when tso is disabled for lower device.

Fix this by explicitly introducing a new param for .ndo_select_queue() for just
selecting queues in the case of l2 forwarding offload. netdev_pick_tx() was also
extended to accept this parameter and dev_queue_xmit_accel() was used to do l2
forwarding transmission.

With this fixes, NETIF_F_LLTX could be preserved for macvlan and there's no need
to check txq against NULL in dev_hard_start_xmit(). Also there's no need to keep
a dedicated ndo_dfwd_start_xmit() and we can just reuse the code of
dev_queue_xmit() to do the transmission.

In the future, it was also required for macvtap l2 forwarding support since it
provides a necessary synchronization method.

Cc: John Fastabend <john.r.fastabend@intel.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: e1000-devel@lists.sourceforge.net
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 398e299..4b8c58b 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3732,7 +3732,8 @@ static inline int bond_slave_override(struct bonding *bond,
 }
 
 
-static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb,
+			     void *accel_priv)
 {
 	/*
 	 * This helper function exists to help dev_pick_tx get the correct
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 5504120..bf81156 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1833,7 +1833,8 @@ void bnx2x_netif_stop(struct bnx2x *bp, int disable_hw)
 		bnx2x_napi_disable_cnic(bp);
 }
 
-u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb)
+u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
+		       void *accel_priv)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index da8fcaa..41f3ca5a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -524,7 +524,8 @@ int bnx2x_set_vf_mac(struct net_device *dev, int queue, u8 *mac);
 int bnx2x_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos);
 
 /* select_queue callback */
-u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb);
+u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
+		       void *accel_priv);
 
 static inline void bnx2x_update_rx_prod(struct bnx2x *bp,
 					struct bnx2x_fastpath *fp,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index cc06854..5bcc870 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -6827,12 +6827,20 @@ static inline int ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size)
 	return __ixgbe_maybe_stop_tx(tx_ring, size);
 }
 
-#ifdef IXGBE_FCOE
-static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
+			      void *accel_priv)
 {
+	struct ixgbe_fwd_adapter *fwd_adapter = accel_priv;
+#ifdef IXGBE_FCOE
 	struct ixgbe_adapter *adapter;
 	struct ixgbe_ring_feature *f;
 	int txq;
+#endif
+
+	if (fwd_adapter)
+		return skb->queue_mapping + fwd_adapter->tx_base_queue;
+
+#ifdef IXGBE_FCOE
 
 	/*
 	 * only execute the code below if protocol is FCoE
@@ -6858,9 +6866,11 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb)
 		txq -= f->indices;
 
 	return txq + f->offset;
+#else
+	return __netdev_pick_tx(dev, skb);
+#endif
 }
 
-#endif
 netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
 			  struct ixgbe_adapter *adapter,
 			  struct ixgbe_ring *tx_ring)
@@ -7629,27 +7639,11 @@ static void ixgbe_fwd_del(struct net_device *pdev, void *priv)
 	kfree(fwd_adapter);
 }
 
-static netdev_tx_t ixgbe_fwd_xmit(struct sk_buff *skb,
-				  struct net_device *dev,
-				  void *priv)
-{
-	struct ixgbe_fwd_adapter *fwd_adapter = priv;
-	unsigned int queue;
-	struct ixgbe_ring *tx_ring;
-
-	queue = skb->queue_mapping + fwd_adapter->tx_base_queue;
-	tx_ring = fwd_adapter->real_adapter->tx_ring[queue];
-
-	return __ixgbe_xmit_frame(skb, dev, tx_ring);
-}
-
 static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_open		= ixgbe_open,
 	.ndo_stop		= ixgbe_close,
 	.ndo_start_xmit		= ixgbe_xmit_frame,
-#ifdef IXGBE_FCOE
 	.ndo_select_queue	= ixgbe_select_queue,
-#endif
 	.ndo_set_rx_mode	= ixgbe_set_rx_mode,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= ixgbe_set_mac,
@@ -7689,7 +7683,6 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_bridge_getlink	= ixgbe_ndo_bridge_getlink,
 	.ndo_dfwd_add_station	= ixgbe_fwd_add,
 	.ndo_dfwd_del_station	= ixgbe_fwd_del,
-	.ndo_dfwd_start_xmit	= ixgbe_fwd_xmit,
 };
 
 /**
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 6a6c1f7..ec94a20 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -619,7 +619,8 @@ ltq_etop_set_multicast_list(struct net_device *dev)
 }
 
 static u16
-ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb)
+ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb,
+		      void *accel_priv)
 {
 	/* we are currently only using the first queue */
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index f54ebd5..a7fcd59 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -592,7 +592,8 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc, struct sk_buff *sk
 	}
 }
 
-u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb)
+u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
+			 void *accel_priv)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	u16 rings_p_up = priv->num_tx_rings_p_up;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index f3758de..d5758ad 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -714,7 +714,8 @@ int mlx4_en_set_cq_moder(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq);
 int mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq);
 
 void mlx4_en_tx_irq(struct mlx4_cq *mcq);
-u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb);
+u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
+			 void *accel_priv);
 netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c
index 628b736..0e9fb33 100644
--- a/drivers/net/ethernet/tile/tilegx.c
+++ b/drivers/net/ethernet/tile/tilegx.c
@@ -2080,7 +2080,8 @@ static int tile_net_tx(struct sk_buff *skb, struct net_device *dev)
 }
 
 /* Return subqueue id on this core (one per core). */
-static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb,
+				 void *accel_priv)
 {
 	return smp_processor_id();
 }
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 5360f73..bc8faae 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -299,7 +299,7 @@ netdev_tx_t macvlan_start_xmit(struct sk_buff *skb,
 
 	if (vlan->fwd_priv) {
 		skb->dev = vlan->lowerdev;
-		ret = dev_hard_start_xmit(skb, skb->dev, NULL, vlan->fwd_priv);
+		ret = dev_queue_xmit_accel(skb, vlan->fwd_priv);
 	} else {
 		ret = macvlan_queue_xmit(skb, dev);
 	}
@@ -365,10 +365,8 @@ static int macvlan_open(struct net_device *dev)
 		 */
 		if (IS_ERR_OR_NULL(vlan->fwd_priv)) {
 			vlan->fwd_priv = NULL;
-		} else {
-			dev->features &= ~NETIF_F_LLTX;
+		} else
 			return 0;
-		}
 	}
 
 	err = -EBUSY;
@@ -702,8 +700,7 @@ static netdev_features_t macvlan_fix_features(struct net_device *dev,
 	features = netdev_increment_features(vlan->lowerdev->features,
 					     features,
 					     mask);
-	if (!vlan->fwd_priv)
-		features |= NETIF_F_LLTX;
+	features |= NETIF_F_LLTX;
 
 	return features;
 }
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 736050d..b75ae5b 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1647,7 +1647,8 @@ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
-static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb,
+			     void *accel_priv)
 {
 	/*
 	 * This helper function exists to help dev_pick_tx get the correct
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 7c8343a..ecec802 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -348,7 +348,8 @@ unlock:
  * different rxq no. here. If we could not get rxhash, then we would
  * hope the rxq no. may help here.
  */
-static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
+			    void *accel_priv)
 {
 	struct tun_struct *tun = netdev_priv(dev);
 	struct tun_flow_entry *e;
diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c
index 78e8a66..8bb8988 100644
--- a/drivers/net/wireless/mwifiex/main.c
+++ b/drivers/net/wireless/mwifiex/main.c
@@ -746,7 +746,8 @@ static struct net_device_stats *mwifiex_get_stats(struct net_device *dev)
 }
 
 static u16
-mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb)
+mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb,
+				void *accel_priv)
 {
 	skb->priority = cfg80211_classify8021d(skb);
 	return mwifiex_1d_to_wmm_queue[skb->priority];
diff --git a/drivers/staging/bcm/Bcmnet.c b/drivers/staging/bcm/Bcmnet.c
index 53fee2f..8dfdd27 100644
--- a/drivers/staging/bcm/Bcmnet.c
+++ b/drivers/staging/bcm/Bcmnet.c
@@ -39,7 +39,8 @@ static INT bcm_close(struct net_device *dev)
 	return 0;
 }
 
-static u16 bcm_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 bcm_select_queue(struct net_device *dev, struct sk_buff *skb,
+			    void *accel_priv)
 {
 	return ClassifyPacket(netdev_priv(dev), skb);
 }
diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c
index 235d2b1..eedffed 100644
--- a/drivers/staging/netlogic/xlr_net.c
+++ b/drivers/staging/netlogic/xlr_net.c
@@ -306,7 +306,8 @@ static netdev_tx_t xlr_net_start_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 }
 
-static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb)
+static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb,
+				void *accel_priv)
 {
 	return (u16)smp_processor_id();
 }
diff --git a/drivers/staging/rtl8188eu/os_dep/os_intfs.c b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
index 17659bb..dd69e34 100644
--- a/drivers/staging/rtl8188eu/os_dep/os_intfs.c
+++ b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
@@ -652,7 +652,8 @@ static unsigned int rtw_classify8021d(struct sk_buff *skb)
 	return dscp >> 5;
 }
 
-static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb,
+			    void *accel_priv)
 {
 	struct adapter	*padapter = rtw_netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5faaadb..ce2a1f5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -769,7 +769,8 @@ struct netdev_phys_port_id {
  *        (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX)
  *	Required can not be NULL.
  *
- * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb);
+ * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
+ *                         void *accel_priv);
  *	Called to decide which queue to when device supports multiple
  *	transmit queues.
  *
@@ -990,7 +991,8 @@ struct net_device_ops {
 	netdev_tx_t		(*ndo_start_xmit) (struct sk_buff *skb,
 						   struct net_device *dev);
 	u16			(*ndo_select_queue)(struct net_device *dev,
-						    struct sk_buff *skb);
+						    struct sk_buff *skb,
+						    void *accel_priv);
 	void			(*ndo_change_rx_flags)(struct net_device *dev,
 						       int flags);
 	void			(*ndo_set_rx_mode)(struct net_device *dev);
@@ -1529,7 +1531,8 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
 }
 
 struct netdev_queue *netdev_pick_tx(struct net_device *dev,
-				    struct sk_buff *skb);
+				    struct sk_buff *skb,
+				    void *accel_priv);
 u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb);
 
 /*
@@ -1819,6 +1822,7 @@ int dev_close(struct net_device *dev);
 void dev_disable_lro(struct net_device *dev);
 int dev_loopback_xmit(struct sk_buff *newskb);
 int dev_queue_xmit(struct sk_buff *skb);
+int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv);
 int register_netdevice(struct net_device *dev);
 void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
 void unregister_netdevice_many(struct list_head *head);
@@ -2426,7 +2430,7 @@ int dev_change_carrier(struct net_device *, bool new_carrier);
 int dev_get_phys_port_id(struct net_device *dev,
 			 struct netdev_phys_port_id *ppid);
 int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
-			struct netdev_queue *txq, void *accel_priv);
+			struct netdev_queue *txq);
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 
 extern int		netdev_budget;
diff --git a/net/core/dev.c b/net/core/dev.c
index 4fc1722..0ce469e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2539,7 +2539,7 @@ static inline int skb_needs_linearize(struct sk_buff *skb,
 }
 
 int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
-			struct netdev_queue *txq, void *accel_priv)
+			struct netdev_queue *txq)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	int rc = NETDEV_TX_OK;
@@ -2605,13 +2605,10 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			dev_queue_xmit_nit(skb, dev);
 
 		skb_len = skb->len;
-		if (accel_priv)
-			rc = ops->ndo_dfwd_start_xmit(skb, dev, accel_priv);
-		else
 			rc = ops->ndo_start_xmit(skb, dev);
 
 		trace_net_dev_xmit(skb, rc, dev, skb_len);
-		if (rc == NETDEV_TX_OK && txq)
+		if (rc == NETDEV_TX_OK)
 			txq_trans_update(txq);
 		return rc;
 	}
@@ -2627,10 +2624,7 @@ gso:
 			dev_queue_xmit_nit(nskb, dev);
 
 		skb_len = nskb->len;
-		if (accel_priv)
-			rc = ops->ndo_dfwd_start_xmit(nskb, dev, accel_priv);
-		else
-			rc = ops->ndo_start_xmit(nskb, dev);
+		rc = ops->ndo_start_xmit(nskb, dev);
 		trace_net_dev_xmit(nskb, rc, dev, skb_len);
 		if (unlikely(rc != NETDEV_TX_OK)) {
 			if (rc & ~NETDEV_TX_MASK)
@@ -2811,7 +2805,7 @@ EXPORT_SYMBOL(dev_loopback_xmit);
  *      the BH enable code must have IRQs enabled so that it will not deadlock.
  *          --BLG
  */
-int dev_queue_xmit(struct sk_buff *skb)
+int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
 {
 	struct net_device *dev = skb->dev;
 	struct netdev_queue *txq;
@@ -2827,7 +2821,7 @@ int dev_queue_xmit(struct sk_buff *skb)
 
 	skb_update_prio(skb);
 
-	txq = netdev_pick_tx(dev, skb);
+	txq = netdev_pick_tx(dev, skb, accel_priv);
 	q = rcu_dereference_bh(txq->qdisc);
 
 #ifdef CONFIG_NET_CLS_ACT
@@ -2863,7 +2857,7 @@ int dev_queue_xmit(struct sk_buff *skb)
 
 			if (!netif_xmit_stopped(txq)) {
 				__this_cpu_inc(xmit_recursion);
-				rc = dev_hard_start_xmit(skb, dev, txq, NULL);
+				rc = dev_hard_start_xmit(skb, dev, txq);
 				__this_cpu_dec(xmit_recursion);
 				if (dev_xmit_complete(rc)) {
 					HARD_TX_UNLOCK(dev, txq);
@@ -2892,8 +2886,19 @@ out:
 	rcu_read_unlock_bh();
 	return rc;
 }
+
+int dev_queue_xmit(struct sk_buff *skb)
+{
+	return __dev_queue_xmit(skb, NULL);
+}
 EXPORT_SYMBOL(dev_queue_xmit);
 
+int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv)
+{
+	return __dev_queue_xmit(skb, accel_priv);
+}
+EXPORT_SYMBOL(dev_queue_xmit_accel);
+
 
 /*=======================================================================
 			Receiver routines
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index d6ef173..2fc5bea 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -395,17 +395,21 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
 EXPORT_SYMBOL(__netdev_pick_tx);
 
 struct netdev_queue *netdev_pick_tx(struct net_device *dev,
-				    struct sk_buff *skb)
+				    struct sk_buff *skb,
+				    void *accel_priv)
 {
 	int queue_index = 0;
 
 	if (dev->real_num_tx_queues != 1) {
 		const struct net_device_ops *ops = dev->netdev_ops;
 		if (ops->ndo_select_queue)
-			queue_index = ops->ndo_select_queue(dev, skb);
+			queue_index = ops->ndo_select_queue(dev, skb,
+							    accel_priv);
 		else
 			queue_index = __netdev_pick_tx(dev, skb);
-		queue_index = dev_cap_txqueue(dev, queue_index);
+
+		if (!accel_priv)
+			queue_index = dev_cap_txqueue(dev, queue_index);
 	}
 
 	skb_set_queue_mapping(skb, queue_index);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 3030978..19fe9c7 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -375,7 +375,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 	if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) {
 		struct netdev_queue *txq;
 
-		txq = netdev_pick_tx(dev, skb);
+		txq = netdev_pick_tx(dev, skb, NULL);
 
 		/* try until next clock tick */
 		for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 36c3a4c..a075791 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1061,7 +1061,8 @@ static void ieee80211_uninit(struct net_device *dev)
 }
 
 static u16 ieee80211_netdev_select_queue(struct net_device *dev,
-					 struct sk_buff *skb)
+					 struct sk_buff *skb,
+					 void *accel_priv)
 {
 	return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb);
 }
@@ -1078,7 +1079,8 @@ static const struct net_device_ops ieee80211_dataif_ops = {
 };
 
 static u16 ieee80211_monitor_select_queue(struct net_device *dev,
-					  struct sk_buff *skb)
+					  struct sk_buff *skb,
+					  void *accel_priv)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = sdata->local;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 922a094..7fc899a 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -126,7 +126,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 
 	HARD_TX_LOCK(dev, txq, smp_processor_id());
 	if (!netif_xmit_frozen_or_stopped(txq))
-		ret = dev_hard_start_xmit(skb, dev, txq, NULL);
+		ret = dev_hard_start_xmit(skb, dev, txq);
 
 	HARD_TX_UNLOCK(dev, txq);
 
-- 
cgit v0.10.2


From 1ac6762a0b8f5f2dc35ea869a08da25c68d7a8ba Mon Sep 17 00:00:00 2001
From: Manish Chopra <manish.chopra@qlogic.com>
Date: Thu, 9 Jan 2014 12:41:04 -0500
Subject: qlcnic: Fix bug in TX statistics

o Driver was not updating TX stats so it was not populating
  statistics in `ifconfig` command output.

Signed-off-by: Manish Chopra <manish.chopra@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index ff80cd8..f2a7c71 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -1711,6 +1711,7 @@ int qlcnic_83xx_init_mailbox_work(struct qlcnic_adapter *);
 void qlcnic_83xx_detach_mailbox_work(struct qlcnic_adapter *);
 void qlcnic_83xx_reinit_mbx_work(struct qlcnic_mailbox *mbx);
 void qlcnic_83xx_free_mailbox(struct qlcnic_mailbox *mbx);
+void qlcnic_update_stats(struct qlcnic_adapter *);
 
 /* Adapter hardware abstraction */
 struct qlcnic_hardware_ops {
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index e3be276..7b36340 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -1267,7 +1267,7 @@ static u64 *qlcnic_fill_stats(u64 *data, void *stats, int type)
 	return data;
 }
 
-static void qlcnic_update_stats(struct qlcnic_adapter *adapter)
+void qlcnic_update_stats(struct qlcnic_adapter *adapter)
 {
 	struct qlcnic_host_tx_ring *tx_ring;
 	int ring;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index b8a245a..550791b 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -2780,6 +2780,9 @@ static struct net_device_stats *qlcnic_get_stats(struct net_device *netdev)
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	struct net_device_stats *stats = &netdev->stats;
 
+	if (test_bit(__QLCNIC_DEV_UP, &adapter->state))
+		qlcnic_update_stats(adapter);
+
 	stats->rx_packets = adapter->stats.rx_pkts + adapter->stats.lro_pkts;
 	stats->tx_packets = adapter->stats.xmitfinished;
 	stats->rx_bytes = adapter->stats.rxbytes + adapter->stats.lrobytes;
-- 
cgit v0.10.2


From d6e9c89a8d3cf0a5184badbcd50169179af27721 Mon Sep 17 00:00:00 2001
From: Shahed Shaikh <shahed.shaikh@qlogic.com>
Date: Thu, 9 Jan 2014 12:41:05 -0500
Subject: qlcnic: Fix ethtool statistics length calculation

o Consider number of Tx queues while calculating the length of
  Tx statistics as part of ethtool stats.
o Calculate statistics lenght properly for 82xx and 83xx adapter

Signed-off-by: Shahed Shaikh <shahed.shaikh@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index 7b36340..6b08194 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -167,27 +167,35 @@ static const char qlcnic_gstrings_test[][ETH_GSTRING_LEN] = {
 
 #define QLCNIC_TEST_LEN	ARRAY_SIZE(qlcnic_gstrings_test)
 
-static inline int qlcnic_82xx_statistics(void)
+static inline int qlcnic_82xx_statistics(struct qlcnic_adapter *adapter)
 {
-	return ARRAY_SIZE(qlcnic_device_gstrings_stats) +
-	       ARRAY_SIZE(qlcnic_83xx_mac_stats_strings);
+	return ARRAY_SIZE(qlcnic_gstrings_stats) +
+	       ARRAY_SIZE(qlcnic_83xx_mac_stats_strings) +
+	       QLCNIC_TX_STATS_LEN * adapter->drv_tx_rings;
 }
 
-static inline int qlcnic_83xx_statistics(void)
+static inline int qlcnic_83xx_statistics(struct qlcnic_adapter *adapter)
 {
-	return ARRAY_SIZE(qlcnic_83xx_tx_stats_strings) +
+	return ARRAY_SIZE(qlcnic_gstrings_stats) +
+	       ARRAY_SIZE(qlcnic_83xx_tx_stats_strings) +
 	       ARRAY_SIZE(qlcnic_83xx_mac_stats_strings) +
-	       ARRAY_SIZE(qlcnic_83xx_rx_stats_strings);
+	       ARRAY_SIZE(qlcnic_83xx_rx_stats_strings) +
+	       QLCNIC_TX_STATS_LEN * adapter->drv_tx_rings;
 }
 
 static int qlcnic_dev_statistics_len(struct qlcnic_adapter *adapter)
 {
-	if (qlcnic_82xx_check(adapter))
-		return qlcnic_82xx_statistics();
-	else if (qlcnic_83xx_check(adapter))
-		return qlcnic_83xx_statistics();
-	else
-		return -1;
+	int len = -1;
+
+	if (qlcnic_82xx_check(adapter)) {
+		len = qlcnic_82xx_statistics(adapter);
+		if (adapter->flags & QLCNIC_ESWITCH_ENABLED)
+			len += ARRAY_SIZE(qlcnic_device_gstrings_stats);
+	} else if (qlcnic_83xx_check(adapter)) {
+		len = qlcnic_83xx_statistics(adapter);
+	}
+
+	return len;
 }
 
 #define	QLCNIC_TX_INTR_NOT_CONFIGURED	0X78563412
@@ -920,18 +928,13 @@ static int qlcnic_eeprom_test(struct net_device *dev)
 
 static int qlcnic_get_sset_count(struct net_device *dev, int sset)
 {
-	int len;
 
 	struct qlcnic_adapter *adapter = netdev_priv(dev);
 	switch (sset) {
 	case ETH_SS_TEST:
 		return QLCNIC_TEST_LEN;
 	case ETH_SS_STATS:
-		len = qlcnic_dev_statistics_len(adapter) + QLCNIC_STATS_LEN;
-		if ((adapter->flags & QLCNIC_ESWITCH_ENABLED) ||
-		    qlcnic_83xx_check(adapter))
-			return len;
-		return qlcnic_82xx_statistics();
+		return qlcnic_dev_statistics_len(adapter);
 	default:
 		return -EOPNOTSUPP;
 	}
-- 
cgit v0.10.2


From bba719b5004234e55737e7074b81b337210c511d Mon Sep 17 00:00:00 2001
From: Jie Liu <jeff.liu@oracle.com>
Date: Wed, 1 Jan 2014 19:28:03 +0800
Subject: xfs: fix off-by-one error in xfs_attr3_rmt_verify

With CRC check is enabled, if trying to set an attributes value just
equal to the maximum size of XATTR_SIZE_MAX would cause the v3 remote
attr write verification procedure failure, which would yield the back
trace like below:

<snip>
XFS (sda7): Internal error xfs_attr3_rmt_write_verify at line 191 of file fs/xfs/xfs_attr_remote.c
<snip>
Call Trace:
[<ffffffff816f0042>] dump_stack+0x45/0x56
[<ffffffffa0d99c8b>] xfs_error_report+0x3b/0x40 [xfs]
[<ffffffffa0d96edd>] ? _xfs_buf_ioapply+0x6d/0x390 [xfs]
[<ffffffffa0d99ce5>] xfs_corruption_error+0x55/0x80 [xfs]
[<ffffffffa0dbef6b>] xfs_attr3_rmt_write_verify+0x14b/0x1a0 [xfs]
[<ffffffffa0d96edd>] ? _xfs_buf_ioapply+0x6d/0x390 [xfs]
[<ffffffffa0d97315>] ? xfs_bdstrat_cb+0x55/0xb0 [xfs]
[<ffffffffa0d96edd>] _xfs_buf_ioapply+0x6d/0x390 [xfs]
[<ffffffff81184cda>] ? vm_map_ram+0x31a/0x460
[<ffffffff81097230>] ? wake_up_state+0x20/0x20
[<ffffffffa0d97315>] ? xfs_bdstrat_cb+0x55/0xb0 [xfs]
[<ffffffffa0d9726b>] xfs_buf_iorequest+0x6b/0xc0 [xfs]
[<ffffffffa0d97315>] xfs_bdstrat_cb+0x55/0xb0 [xfs]
[<ffffffffa0d97906>] xfs_bwrite+0x46/0x80 [xfs]
[<ffffffffa0dbfa94>] xfs_attr_rmtval_set+0x334/0x490 [xfs]
[<ffffffffa0db84aa>] xfs_attr_leaf_addname+0x24a/0x410 [xfs]
[<ffffffffa0db8893>] xfs_attr_set_int+0x223/0x470 [xfs]
[<ffffffffa0db8b76>] xfs_attr_set+0x96/0xb0 [xfs]
[<ffffffffa0db13b2>] xfs_xattr_set+0x42/0x70 [xfs]
[<ffffffff811df9b2>] generic_setxattr+0x62/0x80
[<ffffffff811e0213>] __vfs_setxattr_noperm+0x63/0x1b0
[<ffffffff81307afe>] ? evm_inode_setxattr+0xe/0x10
[<ffffffff811e0415>] vfs_setxattr+0xb5/0xc0
[<ffffffff811e054e>] setxattr+0x12e/0x1c0
[<ffffffff811c6e82>] ? final_putname+0x22/0x50
[<ffffffff811c708b>] ? putname+0x2b/0x40
[<ffffffff811cc4bf>] ? user_path_at_empty+0x5f/0x90
[<ffffffff811bdfd9>] ? __sb_start_write+0x49/0xe0
[<ffffffff81168589>] ? vm_mmap_pgoff+0x99/0xc0
[<ffffffff811e07df>] SyS_setxattr+0x8f/0xe0
[<ffffffff81700c2d>] system_call_fastpath+0x1a/0x1f

Tests:
    setfattr -n user.longxattr -v `perl -e 'print "A"x65536'` testfile

This patch fix it to check the remote EA size is greater than the
XATTR_SIZE_MAX rather than more than or equal to it, because it's
valid if the specified EA value size is equal to the limitation as
per VFS setxattr interface.

Signed-off-by: Jie Liu <jeff.liu@oracle.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

(cherry picked from commit 85dd0707f0cad26d60f2dc574d17a5ab948d10f7)

diff --git a/fs/xfs/xfs_attr_remote.c b/fs/xfs/xfs_attr_remote.c
index 739e0a52..5549d69 100644
--- a/fs/xfs/xfs_attr_remote.c
+++ b/fs/xfs/xfs_attr_remote.c
@@ -110,7 +110,7 @@ xfs_attr3_rmt_verify(
 	if (be32_to_cpu(rmt->rm_bytes) > fsbsize - sizeof(*rmt))
 		return false;
 	if (be32_to_cpu(rmt->rm_offset) +
-				be32_to_cpu(rmt->rm_bytes) >= XATTR_SIZE_MAX)
+				be32_to_cpu(rmt->rm_bytes) > XATTR_SIZE_MAX)
 		return false;
 	if (rmt->rm_owner == 0)
 		return false;
-- 
cgit v0.10.2


From 1f4a63bf019524c96e79f088cd717b96ef00a249 Mon Sep 17 00:00:00 2001
From: Chuansheng Liu <chuansheng.liu@intel.com>
Date: Tue, 7 Jan 2014 16:53:34 +0800
Subject: xfs: Calling destroy_work_on_stack() to pair with INIT_WORK_ONSTACK()

In case CONFIG_DEBUG_OBJECTS_WORK is defined, it is needed to
call destroy_work_on_stack() which frees the debug object to pair
with INIT_WORK_ONSTACK().

Signed-off-by: Liu, Chuansheng <chuansheng.liu@intel.com>
Reviewed-by: Ben Myers <bpm@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>

(cherry picked from commit 6f96b3063cdd473c68664a190524ed966ac0cd92)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 1394106..82e0dab 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -287,6 +287,7 @@ xfs_bmapi_allocate(
 	INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker);
 	queue_work(xfs_alloc_wq, &args->work);
 	wait_for_completion(&done);
+	destroy_work_on_stack(&args->work);
 	return args->result;
 }
 
-- 
cgit v0.10.2


From 09f2344d0896eb458a639b922224c7a202c11599 Mon Sep 17 00:00:00 2001
From: Jesse Barnes <jbarnes@virtuousgeek.org>
Date: Fri, 10 Jan 2014 13:13:09 -0800
Subject: drm/i915/bdw: make sure south port interrupts are enabled properly v2

We were apparently relying on the defaults on BDW, which resulted in no
hotplug or AUX interrupts.  So be sure to call the ibx_irq_preinstall to
enable all interrupts.

v2: use preinstall instead of redundant SDIER write

References: https://bugs.freedesktop.org/show_bug.cgi?id=72834
References: https://bugs.freedesktop.org/show_bug.cgi?id=72833
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 5d1dedc..f13d5ed 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2713,6 +2713,8 @@ static void gen8_irq_preinstall(struct drm_device *dev)
 #undef GEN8_IRQ_INIT_NDX
 
 	POSTING_READ(GEN8_PCU_IIR);
+
+	ibx_irq_preinstall(dev);
 }
 
 static void ibx_hpd_irq_setup(struct drm_device *dev)
-- 
cgit v0.10.2


From e70988d1aaf73221355e06125c9937bd4b27761c Mon Sep 17 00:00:00 2001
From: Milo Kim <milo.kim@ti.com>
Date: Mon, 2 Dec 2013 17:21:44 -0800
Subject: leds: lp5521/5523: Remove duplicate mutex
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It can be a problem when a pattern is loaded via the firmware interface.
LP55xx common driver has already locked the mutex in 'lp55xx_firmware_loaded()'.
So it should be deleted.

On the other hand, locks are required in store_engine_load()
on updating program memory.

Reported-by: Pali Rohár <pali.rohar@gmail.com>
Reported-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Milo Kim <milo.kim@ti.com>
Signed-off-by: Bryan Wu <cooloney@gmail.com>
Cc: <stable@vger.kernel.org>

diff --git a/drivers/leds/leds-lp5521.c b/drivers/leds/leds-lp5521.c
index 0518835..a97263e 100644
--- a/drivers/leds/leds-lp5521.c
+++ b/drivers/leds/leds-lp5521.c
@@ -244,18 +244,12 @@ static int lp5521_update_program_memory(struct lp55xx_chip *chip,
 	if (i % 2)
 		goto err;
 
-	mutex_lock(&chip->lock);
-
 	for (i = 0; i < LP5521_PROGRAM_LENGTH; i++) {
 		ret = lp55xx_write(chip, addr[idx] + i, pattern[i]);
-		if (ret) {
-			mutex_unlock(&chip->lock);
+		if (ret)
 			return -EINVAL;
-		}
 	}
 
-	mutex_unlock(&chip->lock);
-
 	return size;
 
 err:
@@ -427,15 +421,17 @@ static ssize_t store_engine_load(struct device *dev,
 {
 	struct lp55xx_led *led = i2c_get_clientdata(to_i2c_client(dev));
 	struct lp55xx_chip *chip = led->chip;
+	int ret;
 
 	mutex_lock(&chip->lock);
 
 	chip->engine_idx = nr;
 	lp5521_load_engine(chip);
+	ret = lp5521_update_program_memory(chip, buf, len);
 
 	mutex_unlock(&chip->lock);
 
-	return lp5521_update_program_memory(chip, buf, len);
+	return ret;
 }
 store_load(1)
 store_load(2)
diff --git a/drivers/leds/leds-lp5523.c b/drivers/leds/leds-lp5523.c
index 6b553d9..fd9ab5f 100644
--- a/drivers/leds/leds-lp5523.c
+++ b/drivers/leds/leds-lp5523.c
@@ -337,18 +337,12 @@ static int lp5523_update_program_memory(struct lp55xx_chip *chip,
 	if (i % 2)
 		goto err;
 
-	mutex_lock(&chip->lock);
-
 	for (i = 0; i < LP5523_PROGRAM_LENGTH; i++) {
 		ret = lp55xx_write(chip, LP5523_REG_PROG_MEM + i, pattern[i]);
-		if (ret) {
-			mutex_unlock(&chip->lock);
+		if (ret)
 			return -EINVAL;
-		}
 	}
 
-	mutex_unlock(&chip->lock);
-
 	return size;
 
 err:
@@ -548,15 +542,17 @@ static ssize_t store_engine_load(struct device *dev,
 {
 	struct lp55xx_led *led = i2c_get_clientdata(to_i2c_client(dev));
 	struct lp55xx_chip *chip = led->chip;
+	int ret;
 
 	mutex_lock(&chip->lock);
 
 	chip->engine_idx = nr;
 	lp5523_load_engine_and_select_page(chip);
+	ret = lp5523_update_program_memory(chip, buf, len);
 
 	mutex_unlock(&chip->lock);
 
-	return lp5523_update_program_memory(chip, buf, len);
+	return ret;
 }
 store_load(1)
 store_load(2)
-- 
cgit v0.10.2


From e44ef891e9e68b6ce7d3fd3bac73b7d5433050ae Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Wed, 8 Jan 2014 18:24:21 +0100
Subject: ARM: 7934/1: DT/kernel: fix arch_match_cpu_phys_id to avoid erroneous
 match

The MPIDR contains specific bitfields(MPIDR.Aff{2..0}) which uniquely
identify a CPU, in addition to some non-identifying information and
reserved bits. The ARM cpu binding defines the 'reg' property to only
contain the affinity bits, and any cpu nodes with other bits set in
their 'reg' entry are skipped.

As such it is not necessary to mask the phys_id with MPIDR_HWID_BITMASK,
and doing so could lead to matching erroneous CPU nodes in the device
tree. This patch removes the masking of the physical identifier.

Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 739c3df..34d5fd5 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -171,7 +171,7 @@ void __init arm_dt_init_cpu_maps(void)
 
 bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
 {
-	return (phys_id & MPIDR_HWID_BITMASK) == cpu_logical_map(cpu);
+	return phys_id == cpu_logical_map(cpu);
 }
 
 static const void * __init arch_get_next_mach(const char *const **match)
-- 
cgit v0.10.2


From 261521f142fb426b58ed460d2476049dc8fa4fb9 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@codeaurora.org>
Date: Fri, 10 Jan 2014 00:57:06 +0100
Subject: ARM: 7937/1: perf_event: Silence sparse warning

arch/arm/kernel/perf_event_cpu.c:274:25: warning: incorrect type in assignment (different modifiers)
arch/arm/kernel/perf_event_cpu.c:274:25: expected int ( *init_fn )( ... )
arch/arm/kernel/perf_event_cpu.c:274:25: got void const *const data

Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index d85055c..20d553c 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -254,7 +254,7 @@ static int probe_current_pmu(struct arm_pmu *pmu)
 static int cpu_pmu_device_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id;
-	int (*init_fn)(struct arm_pmu *);
+	const int (*init_fn)(struct arm_pmu *);
 	struct device_node *node = pdev->dev.of_node;
 	struct arm_pmu *pmu;
 	int ret = -ENODEV;
-- 
cgit v0.10.2


From d6cd989477e2fee29ccda257614ef7b2621d0601 Mon Sep 17 00:00:00 2001
From: Taras Kondratiuk <taras.kondratiuk@linaro.org>
Date: Fri, 10 Jan 2014 01:36:00 +0100
Subject: ARM: 7939/1: traps: fix opcode endianness when read from user memory

Currently code has an inverted logic: opcode from user memory
is swapped to a proper endianness only in case of read error.
While normally opcode should be swapped only if it was read
correctly from user memory.

Reviewed-by: Victor Kamensky <victor.kamensky@linaro.org>
Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Signed-off-by: Taras Kondratiuk <taras.kondratiuk@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 6eda3bf..4636d56 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -431,9 +431,10 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 			instr2 = __mem_to_opcode_thumb16(instr2);
 			instr = __opcode_thumb32_compose(instr, instr2);
 		}
-	} else if (get_user(instr, (u32 __user *)pc)) {
+	} else {
+		if (get_user(instr, (u32 __user *)pc))
+			goto die_sig;
 		instr = __mem_to_opcode_arm(instr);
-		goto die_sig;
 	}
 
 	if (call_undef_hook(regs, instr) == 0)
-- 
cgit v0.10.2


From 26bef1318adc1b3a530ecc807ef99346db2aa8b0 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sat, 11 Jan 2014 19:15:52 -0800
Subject: x86, fpu, amd: Clear exceptions in AMD FXSAVE workaround

Before we do an EMMS in the AMD FXSAVE information leak workaround we
need to clear any pending exceptions, otherwise we trap with a
floating-point exception inside this code.

Reported-by: halfdog <me@halfdog.net>
Tested-by: Borislav Petkov <bp@suse.de>
Link: http://lkml.kernel.org/r/CA%2B55aFxQnY_PCG_n4=0w-VG=YLXL-yr7oMxyy0WU2gCBAf3ydg@mail.gmail.com
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index c49a613..cea1c76 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -293,12 +293,13 @@ static inline int restore_fpu_checking(struct task_struct *tsk)
 	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
 	   is pending.  Clear the x87 state here by setting it to fixed
 	   values. "m" is a random variable that should be in L1 */
-	alternative_input(
-		ASM_NOP8 ASM_NOP2,
-		"emms\n\t"		/* clear stack tags */
-		"fildl %P[addr]",	/* set F?P to defined value */
-		X86_FEATURE_FXSAVE_LEAK,
-		[addr] "m" (tsk->thread.fpu.has_fpu));
+	if (unlikely(static_cpu_has(X86_FEATURE_FXSAVE_LEAK))) {
+		asm volatile(
+			"fnclex\n\t"
+			"emms\n\t"
+			"fildl %P[addr]"	/* set F?P to defined value */
+			: : [addr] "m" (tsk->thread.fpu.has_fpu));
+	}
 
 	return fpu_restore_checking(&tsk->thread.fpu);
 }
-- 
cgit v0.10.2


From 9722c2dac708e9468cc0dc30218ef76946ffbc9d Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Mon, 6 Jan 2014 11:39:12 +0000
Subject: sched: Calculate effective load even if local weight is 0

Thomas Hellstrom bisected a regression where erratic 3D performance is
experienced on virtual machines as measured by glxgears. It identified
commit 58d081b5 ("sched/numa: Avoid overloading CPUs on a preferred NUMA
node") as the problem which had modified the behaviour of effective_load.

Effective load calculates the difference to the system-wide load if a
scheduling entity was moved to another CPU. The task group is not heavier
as a result of the move but overall system load can increase/decrease as a
result of the change. Commit 58d081b5 ("sched/numa: Avoid overloading CPUs
on a preferred NUMA node") changed effective_load to make it suitable for
calculating if a particular NUMA node was compute overloaded. To reduce
the cost of the function, it assumed that a current sched entity weight
of 0 was uninteresting but that is not the case.

wake_affine() uses a weight of 0 for sync wakeups on the grounds that it
is assuming the waking task will sleep and not contribute to load in the
near future. In this case, we still want to calculate the effective load
of the sched entity hierarchy. As effective_load is no longer used by
task_numa_compare since commit fb13c7ee (sched/numa: Use a system-wide
search to find swap/migration candidates), this patch simply restores the
historical behaviour.

Reported-and-tested-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
[ Wrote changelog]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140106113912.GC6178@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c7395d9..e64b079 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3923,7 +3923,7 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
 {
 	struct sched_entity *se = tg->se[cpu];
 
-	if (!tg->parent || !wl)	/* the trivial, non-cgroup case */
+	if (!tg->parent)	/* the trivial, non-cgroup case */
 		return wl;
 
 	for_each_sched_entity(se) {
-- 
cgit v0.10.2


From 0c3351d451ae2fa438d5d1ed719fc43354fbffbb Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Thu, 2 Jan 2014 15:11:13 -0800
Subject: seqlock: Use raw_ prefix instead of _no_lockdep
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Linus disliked the _no_lockdep() naming, so instead
use the more-consistent raw_* prefix to the non-lockdep
enabled seqcount methods.

This also adds raw_ methods for the write operations
as well, which will be utilized in a following patch.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Krzysztof Hałasa <khalasa@piap.pl>
Cc: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Cc: Willy Tarreau <w@1wt.eu>
Link: http://lkml.kernel.org/r/1388704274-5278-1-git-send-email-john.stultz@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 2ada505..eb5d7a5 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -178,7 +178,7 @@ notrace static int __always_inline do_realtime(struct timespec *ts)
 
 	ts->tv_nsec = 0;
 	do {
-		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
+		seq = raw_read_seqcount_begin(&gtod->seq);
 		mode = gtod->clock.vclock_mode;
 		ts->tv_sec = gtod->wall_time_sec;
 		ns = gtod->wall_time_snsec;
@@ -198,7 +198,7 @@ notrace static int do_monotonic(struct timespec *ts)
 
 	ts->tv_nsec = 0;
 	do {
-		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
+		seq = raw_read_seqcount_begin(&gtod->seq);
 		mode = gtod->clock.vclock_mode;
 		ts->tv_sec = gtod->monotonic_time_sec;
 		ns = gtod->monotonic_time_snsec;
@@ -214,7 +214,7 @@ notrace static int do_realtime_coarse(struct timespec *ts)
 {
 	unsigned long seq;
 	do {
-		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
+		seq = raw_read_seqcount_begin(&gtod->seq);
 		ts->tv_sec = gtod->wall_time_coarse.tv_sec;
 		ts->tv_nsec = gtod->wall_time_coarse.tv_nsec;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
@@ -225,7 +225,7 @@ notrace static int do_monotonic_coarse(struct timespec *ts)
 {
 	unsigned long seq;
 	do {
-		seq = read_seqcount_begin_no_lockdep(&gtod->seq);
+		seq = raw_read_seqcount_begin(&gtod->seq);
 		ts->tv_sec = gtod->monotonic_time_coarse.tv_sec;
 		ts->tv_nsec = gtod->monotonic_time_coarse.tv_nsec;
 	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index cf87a24..535f158 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -117,15 +117,15 @@ repeat:
 }
 
 /**
- * read_seqcount_begin_no_lockdep - start seq-read critical section w/o lockdep
+ * raw_read_seqcount_begin - start seq-read critical section w/o lockdep
  * @s: pointer to seqcount_t
  * Returns: count to be passed to read_seqcount_retry
  *
- * read_seqcount_begin_no_lockdep opens a read critical section of the given
+ * raw_read_seqcount_begin opens a read critical section of the given
  * seqcount, but without any lockdep checking. Validity of the critical
  * section is tested by checking read_seqcount_retry function.
  */
-static inline unsigned read_seqcount_begin_no_lockdep(const seqcount_t *s)
+static inline unsigned raw_read_seqcount_begin(const seqcount_t *s)
 {
 	unsigned ret = __read_seqcount_begin(s);
 	smp_rmb();
@@ -144,7 +144,7 @@ static inline unsigned read_seqcount_begin_no_lockdep(const seqcount_t *s)
 static inline unsigned read_seqcount_begin(const seqcount_t *s)
 {
 	seqcount_lockdep_reader_access(s);
-	return read_seqcount_begin_no_lockdep(s);
+	return raw_read_seqcount_begin(s);
 }
 
 /**
@@ -206,14 +206,26 @@ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
 }
 
 
+
+static inline void raw_write_seqcount_begin(seqcount_t *s)
+{
+	s->sequence++;
+	smp_wmb();
+}
+
+static inline void raw_write_seqcount_end(seqcount_t *s)
+{
+	smp_wmb();
+	s->sequence++;
+}
+
 /*
  * Sequence counter only version assumes that callers are using their
  * own mutexing.
  */
 static inline void write_seqcount_begin_nested(seqcount_t *s, int subclass)
 {
-	s->sequence++;
-	smp_wmb();
+	raw_write_seqcount_begin(s);
 	seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_);
 }
 
@@ -225,8 +237,7 @@ static inline void write_seqcount_begin(seqcount_t *s)
 static inline void write_seqcount_end(seqcount_t *s)
 {
 	seqcount_release(&s->dep_map, 1, _RET_IP_);
-	smp_wmb();
-	s->sequence++;
+	raw_write_seqcount_end(s);
 }
 
 /**
-- 
cgit v0.10.2


From 7a06c41cbec33c6dbe7eec575c61986122617408 Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Thu, 2 Jan 2014 15:11:14 -0800
Subject: sched_clock: Disable seqlock lockdep usage in sched_clock()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Unfortunately the seqlock lockdep enablement can't be used
in sched_clock(), since the lockdep infrastructure eventually
calls into sched_clock(), which causes a deadlock.

Thus, this patch changes all generic sched_clock() usage
to use the raw_* methods.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Reported-by: Krzysztof Hałasa <khalasa@piap.pl>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Cc: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Cc: Willy Tarreau <w@1wt.eu>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1388704274-5278-2-git-send-email-john.stultz@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 68b7993..0abb364 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -74,7 +74,7 @@ unsigned long long notrace sched_clock(void)
 		return cd.epoch_ns;
 
 	do {
-		seq = read_seqcount_begin(&cd.seq);
+		seq = raw_read_seqcount_begin(&cd.seq);
 		epoch_cyc = cd.epoch_cyc;
 		epoch_ns = cd.epoch_ns;
 	} while (read_seqcount_retry(&cd.seq, seq));
@@ -99,10 +99,10 @@ static void notrace update_sched_clock(void)
 			  cd.mult, cd.shift);
 
 	raw_local_irq_save(flags);
-	write_seqcount_begin(&cd.seq);
+	raw_write_seqcount_begin(&cd.seq);
 	cd.epoch_ns = ns;
 	cd.epoch_cyc = cyc;
-	write_seqcount_end(&cd.seq);
+	raw_write_seqcount_end(&cd.seq);
 	raw_local_irq_restore(flags);
 }
 
-- 
cgit v0.10.2


From f3ae75de98c4bac145a87d830c156c96f9414022 Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Wed, 8 Jan 2014 11:15:52 +0100
Subject: perf/x86: Fix active_entry initialization

This patch fixes a problem with the initialization of the
struct perf_event active_entry field. It is defined inside
an anonymous union and was initialized in perf_event_alloc()
using INIT_LIST_HEAD(). However at that time, we do not know
whether the event is going to use active_entry or hlist_entry (SW).
Or at last, we don't want to make that determination there.
The problem is that hlist and list_head are not initialized
the same way. One is okay with NULL (from kzmalloc), the other
needs to pointers to point to self.

This patch resolves this problem by dropping the union.
This will avoid problems later on, if someone starts using
active_entry or hlist_entry without verifying that they
actually overlap. This also solves the initialization
problem.

Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: ak@linux.intel.com
Cc: acme@redhat.com
Cc: jolsa@redhat.com
Cc: zheng.z.yan@intel.com
Cc: bp@alien8.de
Cc: vincent.weaver@maine.edu
Cc: maria.n.dimakopoulou@gmail.com
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1389176153-3128-2-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 8f4a70f..e56b07f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -319,10 +319,8 @@ struct perf_event {
 	 */
 	struct list_head		migrate_entry;
 
-	union {
-		struct hlist_node	hlist_entry;
-		struct list_head	active_entry;
-	};
+	struct hlist_node		hlist_entry;
+	struct list_head		active_entry;
 	int				nr_siblings;
 	int				group_flags;
 	struct perf_event		*group_leader;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 89d34f9..c3b6c27 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6670,6 +6670,8 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	INIT_LIST_HEAD(&event->sibling_list);
 	INIT_LIST_HEAD(&event->rb_entry);
 	INIT_LIST_HEAD(&event->active_entry);
+	INIT_HLIST_NODE(&event->hlist_entry);
+
 
 	init_waitqueue_head(&event->waitq);
 	init_irq_work(&event->pending, perf_pending_event);
-- 
cgit v0.10.2


From f228c5b882602697a1adb50d61ff688b0df1eced Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Wed, 8 Jan 2014 11:15:53 +0100
Subject: perf/x86/intel: Add Intel RAPL PP1 energy counter support

This patch adds support for the Intel RAPL energy counter
PP1 (Power Plane 1).

On client processors, it usually corresponds to the
energy consumption of the builtin graphic card. That
is why the sysfs event is called energy-gpu.

New event:
 - name: power/energy-gpu/
 - code: event=0x4
 - unit: 2^-32 Joules

On processors without graphics, this should count 0.
The patch only enables this event on client processors.

Reviewed-by: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com>
Signed-off-by: Stephane Eranian <eranian@google.com>
Cc: ak@linux.intel.com
Cc: acme@redhat.com
Cc: jolsa@redhat.com
Cc: zheng.z.yan@intel.com
Cc: bp@alien8.de
Cc: vincent.weaver@maine.edu
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1389176153-3128-3-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 0e3754e..5ad35ad 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -27,6 +27,10 @@
  *	  event: rapl_energy_dram
  *    perf code: 0x3
  *
+ * dram counter: consumption of the builtin-gpu domain (client only)
+ *	  event: rapl_energy_gpu
+ *    perf code: 0x4
+ *
  * We manage those counters as free running (read-only). They may be
  * use simultaneously by other tools, such as turbostat.
  *
@@ -55,10 +59,13 @@
 #define INTEL_RAPL_PKG		0x2	/* pseudo-encoding */
 #define RAPL_IDX_RAM_NRG_STAT	2	/* DRAM */
 #define INTEL_RAPL_RAM		0x3	/* pseudo-encoding */
+#define RAPL_IDX_PP1_NRG_STAT	3	/* DRAM */
+#define INTEL_RAPL_PP1		0x4	/* pseudo-encoding */
 
 /* Clients have PP0, PKG */
 #define RAPL_IDX_CLN	(1<<RAPL_IDX_PP0_NRG_STAT|\
-			 1<<RAPL_IDX_PKG_NRG_STAT)
+			 1<<RAPL_IDX_PKG_NRG_STAT|\
+			 1<<RAPL_IDX_PP1_NRG_STAT)
 
 /* Servers have PP0, PKG, RAM */
 #define RAPL_IDX_SRV	(1<<RAPL_IDX_PP0_NRG_STAT|\
@@ -315,6 +322,10 @@ static int rapl_pmu_event_init(struct perf_event *event)
 		bit = RAPL_IDX_RAM_NRG_STAT;
 		msr = MSR_DRAM_ENERGY_STATUS;
 		break;
+	case INTEL_RAPL_PP1:
+		bit = RAPL_IDX_PP1_NRG_STAT;
+		msr = MSR_PP1_ENERGY_STATUS;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -367,19 +378,22 @@ static struct attribute_group rapl_pmu_attr_group = {
 };
 
 EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
-EVENT_ATTR_STR(energy-pkg  , rapl_pkg, "event=0x02");
-EVENT_ATTR_STR(energy-ram  , rapl_ram, "event=0x03");
+EVENT_ATTR_STR(energy-pkg  ,   rapl_pkg, "event=0x02");
+EVENT_ATTR_STR(energy-ram  ,   rapl_ram, "event=0x03");
+EVENT_ATTR_STR(energy-gpu  ,   rapl_gpu, "event=0x04");
 
 EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules");
-EVENT_ATTR_STR(energy-pkg.unit  , rapl_pkg_unit, "Joules");
-EVENT_ATTR_STR(energy-ram.unit  , rapl_ram_unit, "Joules");
+EVENT_ATTR_STR(energy-pkg.unit  ,   rapl_pkg_unit, "Joules");
+EVENT_ATTR_STR(energy-ram.unit  ,   rapl_ram_unit, "Joules");
+EVENT_ATTR_STR(energy-gpu.unit  ,   rapl_gpu_unit, "Joules");
 
 /*
  * we compute in 0.23 nJ increments regardless of MSR
  */
 EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10");
-EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10");
-EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10");
+EVENT_ATTR_STR(energy-pkg.scale,     rapl_pkg_scale, "2.3283064365386962890625e-10");
+EVENT_ATTR_STR(energy-ram.scale,     rapl_ram_scale, "2.3283064365386962890625e-10");
+EVENT_ATTR_STR(energy-gpu.scale,     rapl_gpu_scale, "2.3283064365386962890625e-10");
 
 static struct attribute *rapl_events_srv_attr[] = {
 	EVENT_PTR(rapl_cores),
@@ -399,12 +413,15 @@ static struct attribute *rapl_events_srv_attr[] = {
 static struct attribute *rapl_events_cln_attr[] = {
 	EVENT_PTR(rapl_cores),
 	EVENT_PTR(rapl_pkg),
+	EVENT_PTR(rapl_gpu),
 
 	EVENT_PTR(rapl_cores_unit),
 	EVENT_PTR(rapl_pkg_unit),
+	EVENT_PTR(rapl_gpu_unit),
 
 	EVENT_PTR(rapl_cores_scale),
 	EVENT_PTR(rapl_pkg_scale),
+	EVENT_PTR(rapl_gpu_scale),
 	NULL,
 };
 
-- 
cgit v0.10.2


From a21b0b354d4ac39be691f51c53562e2c24443d9e Mon Sep 17 00:00:00 2001
From: Yann Droneaud <ydroneaud@opteya.com>
Date: Sun, 5 Jan 2014 21:36:33 +0100
Subject: perf: Introduce a flag to enable close-on-exec in perf_event_open()

Unlike recent modern userspace API such as:

  epoll_create1 (EPOLL_CLOEXEC), eventfd (EFD_CLOEXEC),
  fanotify_init (FAN_CLOEXEC), inotify_init1 (IN_CLOEXEC),
  signalfd (SFD_CLOEXEC), timerfd_create (TFD_CLOEXEC),
  or the venerable general purpose open (O_CLOEXEC),

perf_event_open() syscall lack a flag to atomically set FD_CLOEXEC
(eg. close-on-exec) flag on file descriptor it returns to userspace.

The present patch adds a PERF_FLAG_FD_CLOEXEC flag to allow
perf_event_open() syscall to atomically set close-on-exec.

Having this flag will enable userspace to remove the file descriptor
from the list of file descriptors being inherited across exec,
without the need to call fcntl(fd, F_SETFD, FD_CLOEXEC) and the
associated race condition between the current thread and another
thread calling fork(2) then execve(2).

Links:

 - Secure File Descriptor Handling (Ulrich Drepper, 2008)
   http://udrepper.livejournal.com/20407.html

 - Excuse me son, but your code is leaking !!! (Dan Walsh, March 2012)
   http://danwalsh.livejournal.com/53603.html

 - Notes in DMA buffer sharing: leak and security hole
   http://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/tree/Documentation/dma-buf-sharing.txt?id=v3.13-rc3#n428

Signed-off-by: Yann Droneaud <ydroneaud@opteya.com>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/8c03f54e1598b1727c19706f3af03f98685d9fe6.1388952061.git.ydroneaud@opteya.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index e1802d6..ca018b4 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -724,6 +724,7 @@ enum perf_callchain_context {
 #define PERF_FLAG_FD_NO_GROUP		(1U << 0)
 #define PERF_FLAG_FD_OUTPUT		(1U << 1)
 #define PERF_FLAG_PID_CGROUP		(1U << 2) /* pid=cgroup id, per-cpu mode only */
+#define PERF_FLAG_FD_CLOEXEC		(1U << 3) /* O_CLOEXEC */
 
 union perf_mem_data_src {
 	__u64 val;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c3b6c27..5c87264 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -119,7 +119,8 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
 
 #define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
 		       PERF_FLAG_FD_OUTPUT  |\
-		       PERF_FLAG_PID_CGROUP)
+		       PERF_FLAG_PID_CGROUP |\
+		       PERF_FLAG_FD_CLOEXEC)
 
 /*
  * branch priv levels that need permission checks
@@ -6982,6 +6983,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	int event_fd;
 	int move_group = 0;
 	int err;
+	int f_flags = O_RDWR;
 
 	/* for future expandability... */
 	if (flags & ~PERF_FLAG_ALL)
@@ -7010,7 +7012,10 @@ SYSCALL_DEFINE5(perf_event_open,
 	if ((flags & PERF_FLAG_PID_CGROUP) && (pid == -1 || cpu == -1))
 		return -EINVAL;
 
-	event_fd = get_unused_fd();
+	if (flags & PERF_FLAG_FD_CLOEXEC)
+		f_flags |= O_CLOEXEC;
+
+	event_fd = get_unused_fd_flags(f_flags);
 	if (event_fd < 0)
 		return event_fd;
 
@@ -7132,7 +7137,8 @@ SYSCALL_DEFINE5(perf_event_open,
 			goto err_context;
 	}
 
-	event_file = anon_inode_getfile("[perf_event]", &perf_fops, event, O_RDWR);
+	event_file = anon_inode_getfile("[perf_event]", &perf_fops, event,
+					f_flags);
 	if (IS_ERR(event_file)) {
 		err = PTR_ERR(event_file);
 		goto err_context;
-- 
cgit v0.10.2


From 518d00b7498c5894be94545848d55e5b9c55749e Mon Sep 17 00:00:00 2001
From: Ming Lei <tom.leiming@gmail.com>
Date: Thu, 26 Dec 2013 21:31:37 +0800
Subject: block: null_blk: fix queue leak inside removing device

When queue_mode is NULL_Q_MQ and null_blk is being removed,
blk_cleanup_queue() isn't called to cleanup queue, so the queue
allocated won't be freed.

This patch calls blk_cleanup_queue() for MQ to drain all pending
requests first and release the reference counter of queue kobject, then
blk_mq_free_queue() will be called in queue kobject's release handler
when queue kobject's reference counter drops to zero.

Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index a2e69d2..83a598e 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -425,10 +425,7 @@ static void null_del_dev(struct nullb *nullb)
 	list_del_init(&nullb->list);
 
 	del_gendisk(nullb->disk);
-	if (queue_mode == NULL_Q_MQ)
-		blk_mq_free_queue(nullb->q);
-	else
-		blk_cleanup_queue(nullb->q);
+	blk_cleanup_queue(nullb->q);
 	put_disk(nullb->disk);
 	kfree(nullb);
 }
@@ -578,10 +575,7 @@ static int null_add_dev(void)
 	disk = nullb->disk = alloc_disk_node(1, home_node);
 	if (!disk) {
 queue_fail:
-		if (queue_mode == NULL_Q_MQ)
-			blk_mq_free_queue(nullb->q);
-		else
-			blk_cleanup_queue(nullb->q);
+		blk_cleanup_queue(nullb->q);
 		cleanup_queues(nullb);
 err:
 		kfree(nullb);
-- 
cgit v0.10.2


From 2e4f5382d12a441b5cccfdde00308df15c2ce300 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 6 Nov 2013 14:57:36 +0100
Subject: locking/doc: Rename LOCK/UNLOCK to ACQUIRE/RELEASE

The LOCK and UNLOCK barriers as described in our barrier document are
generally known as ACQUIRE and RELEASE barriers in other literature.

Since we plan to introduce the acquire and release nomenclature in
generic kernel primitives we should amend the document to avoid
confusion as to what an acquire/release means.

Reviewed-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Michael Ellerman <michael@ellerman.id.au>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Victor Kaplansky <VICTORK@il.ibm.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Link: http://lkml.kernel.org/r/20131217092435.GC21999@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index cb753c8..102dc19 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -381,39 +381,44 @@ Memory barriers come in four basic varieties:
 
 And a couple of implicit varieties:
 
- (5) LOCK operations.
+ (5) ACQUIRE operations.
 
      This acts as a one-way permeable barrier.  It guarantees that all memory
-     operations after the LOCK operation will appear to happen after the LOCK
-     operation with respect to the other components of the system.
+     operations after the ACQUIRE operation will appear to happen after the
+     ACQUIRE operation with respect to the other components of the system.
+     ACQUIRE operations include LOCK operations and smp_load_acquire()
+     operations.
 
-     Memory operations that occur before a LOCK operation may appear to happen
-     after it completes.
+     Memory operations that occur before an ACQUIRE operation may appear to
+     happen after it completes.
 
-     A LOCK operation should almost always be paired with an UNLOCK operation.
+     An ACQUIRE operation should almost always be paired with a RELEASE
+     operation.
 
 
- (6) UNLOCK operations.
+ (6) RELEASE operations.
 
      This also acts as a one-way permeable barrier.  It guarantees that all
-     memory operations before the UNLOCK operation will appear to happen before
-     the UNLOCK operation with respect to the other components of the system.
+     memory operations before the RELEASE operation will appear to happen
+     before the RELEASE operation with respect to the other components of the
+     system. RELEASE operations include UNLOCK operations and
+     smp_store_release() operations.
 
-     Memory operations that occur after an UNLOCK operation may appear to
+     Memory operations that occur after a RELEASE operation may appear to
      happen before it completes.
 
-     The use of LOCK and UNLOCK operations generally precludes the need for
-     other sorts of memory barrier (but note the exceptions mentioned in the
-     subsection "MMIO write barrier").  In addition, an UNLOCK+LOCK pair
-     is -not- guaranteed to act as a full memory barrier.  However,
-     after a LOCK on a given lock variable, all memory accesses preceding any
-     prior UNLOCK on that same variable are guaranteed to be visible.
-     In other words, within a given lock variable's critical section,
-     all accesses of all previous critical sections for that lock variable
-     are guaranteed to have completed.
+     The use of ACQUIRE and RELEASE operations generally precludes the need
+     for other sorts of memory barrier (but note the exceptions mentioned in
+     the subsection "MMIO write barrier").  In addition, a RELEASE+ACQUIRE
+     pair is -not- guaranteed to act as a full memory barrier.  However, after
+     an ACQUIRE on a given variable, all memory accesses preceding any prior
+     RELEASE on that same variable are guaranteed to be visible.  In other
+     words, within a given variable's critical section, all accesses of all
+     previous critical sections for that variable are guaranteed to have
+     completed.
 
-     This means that LOCK acts as a minimal "acquire" operation and
-     UNLOCK acts as a minimal "release" operation.
+     This means that ACQUIRE acts as a minimal "acquire" operation and
+     RELEASE acts as a minimal "release" operation.
 
 
 Memory barriers are only required where there's a possibility of interaction
@@ -1585,7 +1590,7 @@ There are some more advanced barrier functions:
 	clear_bit( ... );
 
      This prevents memory operations before the clear leaking to after it.  See
-     the subsection on "Locking Functions" with reference to UNLOCK operation
+     the subsection on "Locking Functions" with reference to RELEASE operation
      implications.
 
      See Documentation/atomic_ops.txt for more information.  See the "Atomic
@@ -1619,8 +1624,8 @@ provide more substantial guarantees, but these may not be relied upon outside
 of arch specific code.
 
 
-LOCKING FUNCTIONS
------------------
+ACQUIRING FUNCTIONS
+-------------------
 
 The Linux kernel has a number of locking constructs:
 
@@ -1631,106 +1636,106 @@ The Linux kernel has a number of locking constructs:
  (*) R/W semaphores
  (*) RCU
 
-In all cases there are variants on "LOCK" operations and "UNLOCK" operations
+In all cases there are variants on "ACQUIRE" operations and "RELEASE" operations
 for each construct.  These operations all imply certain barriers:
 
- (1) LOCK operation implication:
+ (1) ACQUIRE operation implication:
 
-     Memory operations issued after the LOCK will be completed after the LOCK
-     operation has completed.
+     Memory operations issued after the ACQUIRE will be completed after the
+     ACQUIRE operation has completed.
 
-     Memory operations issued before the LOCK may be completed after the
-     LOCK operation has completed.  An smp_mb__before_spinlock(), combined
-     with a following LOCK, orders prior loads against subsequent stores
-     and stores and prior stores against subsequent stores.  Note that
-     this is weaker than smp_mb()!  The smp_mb__before_spinlock()
-     primitive is free on many architectures.
+     Memory operations issued before the ACQUIRE may be completed after the
+     ACQUIRE operation has completed.  An smp_mb__before_spinlock(), combined
+     with a following ACQUIRE, orders prior loads against subsequent stores and
+     stores and prior stores against subsequent stores.  Note that this is
+     weaker than smp_mb()!  The smp_mb__before_spinlock() primitive is free on
+     many architectures.
 
- (2) UNLOCK operation implication:
+ (2) RELEASE operation implication:
 
-     Memory operations issued before the UNLOCK will be completed before the
-     UNLOCK operation has completed.
+     Memory operations issued before the RELEASE will be completed before the
+     RELEASE operation has completed.
 
-     Memory operations issued after the UNLOCK may be completed before the
-     UNLOCK operation has completed.
+     Memory operations issued after the RELEASE may be completed before the
+     RELEASE operation has completed.
 
- (3) LOCK vs LOCK implication:
+ (3) ACQUIRE vs ACQUIRE implication:
 
-     All LOCK operations issued before another LOCK operation will be completed
-     before that LOCK operation.
+     All ACQUIRE operations issued before another ACQUIRE operation will be
+     completed before that ACQUIRE operation.
 
- (4) LOCK vs UNLOCK implication:
+ (4) ACQUIRE vs RELEASE implication:
 
-     All LOCK operations issued before an UNLOCK operation will be completed
-     before the UNLOCK operation.
+     All ACQUIRE operations issued before a RELEASE operation will be
+     completed before the RELEASE operation.
 
- (5) Failed conditional LOCK implication:
+ (5) Failed conditional ACQUIRE implication:
 
-     Certain variants of the LOCK operation may fail, either due to being
-     unable to get the lock immediately, or due to receiving an unblocked
+     Certain locking variants of the ACQUIRE operation may fail, either due to
+     being unable to get the lock immediately, or due to receiving an unblocked
      signal whilst asleep waiting for the lock to become available.  Failed
      locks do not imply any sort of barrier.
 
-[!] Note: one of the consequences of LOCKs and UNLOCKs being only one-way
-    barriers is that the effects of instructions outside of a critical section
-    may seep into the inside of the critical section.
+[!] Note: one of the consequences of lock ACQUIREs and RELEASEs being only
+one-way barriers is that the effects of instructions outside of a critical
+section may seep into the inside of the critical section.
 
-A LOCK followed by an UNLOCK may not be assumed to be full memory barrier
-because it is possible for an access preceding the LOCK to happen after the
-LOCK, and an access following the UNLOCK to happen before the UNLOCK, and the
-two accesses can themselves then cross:
+An ACQUIRE followed by a RELEASE may not be assumed to be full memory barrier
+because it is possible for an access preceding the ACQUIRE to happen after the
+ACQUIRE, and an access following the RELEASE to happen before the RELEASE, and
+the two accesses can themselves then cross:
 
 	*A = a;
-	LOCK M
-	UNLOCK M
+	ACQUIRE M
+	RELEASE M
 	*B = b;
 
 may occur as:
 
-	LOCK M, STORE *B, STORE *A, UNLOCK M
+	ACQUIRE M, STORE *B, STORE *A, RELEASE M
 
-This same reordering can of course occur if the LOCK and UNLOCK are
-to the same lock variable, but only from the perspective of another
-CPU not holding that lock.
+This same reordering can of course occur if the lock's ACQUIRE and RELEASE are
+to the same lock variable, but only from the perspective of another CPU not
+holding that lock.
 
-In short, an UNLOCK followed by a LOCK may -not- be assumed to be a full
-memory barrier because it is possible for a preceding UNLOCK to pass a
-later LOCK from the viewpoint of the CPU, but not from the viewpoint
+In short, a RELEASE followed by an ACQUIRE may -not- be assumed to be a full
+memory barrier because it is possible for a preceding RELEASE to pass a
+later ACQUIRE from the viewpoint of the CPU, but not from the viewpoint
 of the compiler.  Note that deadlocks cannot be introduced by this
-interchange because if such a deadlock threatened, the UNLOCK would
+interchange because if such a deadlock threatened, the RELEASE would
 simply complete.
 
-If it is necessary for an UNLOCK-LOCK pair to produce a full barrier,
-the LOCK can be followed by an smp_mb__after_unlock_lock() invocation.
-This will produce a full barrier if either (a) the UNLOCK and the LOCK
-are executed by the same CPU or task, or (b) the UNLOCK and LOCK act
-on the same lock variable.  The smp_mb__after_unlock_lock() primitive
-is free on many architectures.  Without smp_mb__after_unlock_lock(),
-the critical sections corresponding to the UNLOCK and the LOCK can cross:
+If it is necessary for a RELEASE-ACQUIRE pair to produce a full barrier, the
+ACQUIRE can be followed by an smp_mb__after_unlock_lock() invocation.  This
+will produce a full barrier if either (a) the RELEASE and the ACQUIRE are
+executed by the same CPU or task, or (b) the RELEASE and ACQUIRE act on the
+same variable.  The smp_mb__after_unlock_lock() primitive is free on many
+architectures.  Without smp_mb__after_unlock_lock(), the critical sections
+corresponding to the RELEASE and the ACQUIRE can cross:
 
 	*A = a;
-	UNLOCK M
-	LOCK N
+	RELEASE M
+	ACQUIRE N
 	*B = b;
 
 could occur as:
 
-	LOCK N, STORE *B, STORE *A, UNLOCK M
+	ACQUIRE N, STORE *B, STORE *A, RELEASE M
 
 With smp_mb__after_unlock_lock(), they cannot, so that:
 
 	*A = a;
-	UNLOCK M
-	LOCK N
+	RELEASE M
+	ACQUIRE N
 	smp_mb__after_unlock_lock();
 	*B = b;
 
 will always occur as either of the following:
 
-	STORE *A, UNLOCK, LOCK, STORE *B
-	STORE *A, LOCK, UNLOCK, STORE *B
+	STORE *A, RELEASE, ACQUIRE, STORE *B
+	STORE *A, ACQUIRE, RELEASE, STORE *B
 
-If the UNLOCK and LOCK were instead both operating on the same lock
+If the RELEASE and ACQUIRE were instead both operating on the same lock
 variable, only the first of these two alternatives can occur.
 
 Locks and semaphores may not provide any guarantee of ordering on UP compiled
@@ -1745,33 +1750,33 @@ As an example, consider the following:
 
 	*A = a;
 	*B = b;
-	LOCK
+	ACQUIRE
 	*C = c;
 	*D = d;
-	UNLOCK
+	RELEASE
 	*E = e;
 	*F = f;
 
 The following sequence of events is acceptable:
 
-	LOCK, {*F,*A}, *E, {*C,*D}, *B, UNLOCK
+	ACQUIRE, {*F,*A}, *E, {*C,*D}, *B, RELEASE
 
 	[+] Note that {*F,*A} indicates a combined access.
 
 But none of the following are:
 
-	{*F,*A}, *B,	LOCK, *C, *D,	UNLOCK, *E
-	*A, *B, *C,	LOCK, *D,	UNLOCK, *E, *F
-	*A, *B,		LOCK, *C,	UNLOCK, *D, *E, *F
-	*B,		LOCK, *C, *D,	UNLOCK, {*F,*A}, *E
+	{*F,*A}, *B,	ACQUIRE, *C, *D,	RELEASE, *E
+	*A, *B, *C,	ACQUIRE, *D,		RELEASE, *E, *F
+	*A, *B,		ACQUIRE, *C,		RELEASE, *D, *E, *F
+	*B,		ACQUIRE, *C, *D,	RELEASE, {*F,*A}, *E
 
 
 
 INTERRUPT DISABLING FUNCTIONS
 -----------------------------
 
-Functions that disable interrupts (LOCK equivalent) and enable interrupts
-(UNLOCK equivalent) will act as compiler barriers only.  So if memory or I/O
+Functions that disable interrupts (ACQUIRE equivalent) and enable interrupts
+(RELEASE equivalent) will act as compiler barriers only.  So if memory or I/O
 barriers are required in such a situation, they must be provided from some
 other means.
 
@@ -1910,17 +1915,17 @@ Other functions that imply barriers:
  (*) schedule() and similar imply full memory barriers.
 
 
-=================================
-INTER-CPU LOCKING BARRIER EFFECTS
-=================================
+===================================
+INTER-CPU ACQUIRING BARRIER EFFECTS
+===================================
 
 On SMP systems locking primitives give a more substantial form of barrier: one
 that does affect memory access ordering on other CPUs, within the context of
 conflict on any particular lock.
 
 
-LOCKS VS MEMORY ACCESSES
-------------------------
+ACQUIRES VS MEMORY ACCESSES
+---------------------------
 
 Consider the following: the system has a pair of spinlocks (M) and (Q), and
 three CPUs; then should the following sequence of events occur:
@@ -1928,24 +1933,24 @@ three CPUs; then should the following sequence of events occur:
 	CPU 1				CPU 2
 	===============================	===============================
 	ACCESS_ONCE(*A) = a;		ACCESS_ONCE(*E) = e;
-	LOCK M				LOCK Q
+	ACQUIRE M			ACQUIRE Q
 	ACCESS_ONCE(*B) = b;		ACCESS_ONCE(*F) = f;
 	ACCESS_ONCE(*C) = c;		ACCESS_ONCE(*G) = g;
-	UNLOCK M			UNLOCK Q
+	RELEASE M			RELEASE Q
 	ACCESS_ONCE(*D) = d;		ACCESS_ONCE(*H) = h;
 
 Then there is no guarantee as to what order CPU 3 will see the accesses to *A
 through *H occur in, other than the constraints imposed by the separate locks
 on the separate CPUs. It might, for example, see:
 
-	*E, LOCK M, LOCK Q, *G, *C, *F, *A, *B, UNLOCK Q, *D, *H, UNLOCK M
+	*E, ACQUIRE M, ACQUIRE Q, *G, *C, *F, *A, *B, RELEASE Q, *D, *H, RELEASE M
 
 But it won't see any of:
 
-	*B, *C or *D preceding LOCK M
-	*A, *B or *C following UNLOCK M
-	*F, *G or *H preceding LOCK Q
-	*E, *F or *G following UNLOCK Q
+	*B, *C or *D preceding ACQUIRE M
+	*A, *B or *C following RELEASE M
+	*F, *G or *H preceding ACQUIRE Q
+	*E, *F or *G following RELEASE Q
 
 
 However, if the following occurs:
@@ -1953,29 +1958,29 @@ However, if the following occurs:
 	CPU 1				CPU 2
 	===============================	===============================
 	ACCESS_ONCE(*A) = a;
-	LOCK M		     [1]
+	ACQUIRE M		     [1]
 	ACCESS_ONCE(*B) = b;
 	ACCESS_ONCE(*C) = c;
-	UNLOCK M	     [1]
+	RELEASE M	     [1]
 	ACCESS_ONCE(*D) = d;		ACCESS_ONCE(*E) = e;
-					LOCK M		     [2]
+					ACQUIRE M		     [2]
 					smp_mb__after_unlock_lock();
 					ACCESS_ONCE(*F) = f;
 					ACCESS_ONCE(*G) = g;
-					UNLOCK M	     [2]
+					RELEASE M	     [2]
 					ACCESS_ONCE(*H) = h;
 
 CPU 3 might see:
 
-	*E, LOCK M [1], *C, *B, *A, UNLOCK M [1],
-		LOCK M [2], *H, *F, *G, UNLOCK M [2], *D
+	*E, ACQUIRE M [1], *C, *B, *A, RELEASE M [1],
+		ACQUIRE M [2], *H, *F, *G, RELEASE M [2], *D
 
 But assuming CPU 1 gets the lock first, CPU 3 won't see any of:
 
-	*B, *C, *D, *F, *G or *H preceding LOCK M [1]
-	*A, *B or *C following UNLOCK M [1]
-	*F, *G or *H preceding LOCK M [2]
-	*A, *B, *C, *E, *F or *G following UNLOCK M [2]
+	*B, *C, *D, *F, *G or *H preceding ACQUIRE M [1]
+	*A, *B or *C following RELEASE M [1]
+	*F, *G or *H preceding ACQUIRE M [2]
+	*A, *B, *C, *E, *F or *G following RELEASE M [2]
 
 Note that the smp_mb__after_unlock_lock() is critically important
 here: Without it CPU 3 might see some of the above orderings.
@@ -1983,8 +1988,8 @@ Without smp_mb__after_unlock_lock(), the accesses are not guaranteed
 to be seen in order unless CPU 3 holds lock M.
 
 
-LOCKS VS I/O ACCESSES
----------------------
+ACQUIRES VS I/O ACCESSES
+------------------------
 
 Under certain circumstances (especially involving NUMA), I/O accesses within
 two spinlocked sections on two different CPUs may be seen as interleaved by the
@@ -2202,13 +2207,13 @@ explicit lock operations, described later).  These include:
 	/* when succeeds (returns 1) */
 	atomic_add_unless();		atomic_long_add_unless();
 
-These are used for such things as implementing LOCK-class and UNLOCK-class
+These are used for such things as implementing ACQUIRE-class and RELEASE-class
 operations and adjusting reference counters towards object destruction, and as
 such the implicit memory barrier effects are necessary.
 
 
 The following operations are potential problems as they do _not_ imply memory
-barriers, but might be used for implementing such things as UNLOCK-class
+barriers, but might be used for implementing such things as RELEASE-class
 operations:
 
 	atomic_set();
@@ -2250,7 +2255,7 @@ The following operations are special locking primitives:
 	clear_bit_unlock();
 	__clear_bit_unlock();
 
-These implement LOCK-class and UNLOCK-class operations. These should be used in
+These implement ACQUIRE-class and RELEASE-class operations. These should be used in
 preference to other operations when implementing locking primitives, because
 their implementations can be optimised on many architectures.
 
-- 
cgit v0.10.2


From 1de7da377bd880ff23917f78924d0e908329d978 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 8 Nov 2013 12:01:59 +0100
Subject: arch: Move smp_mb__{before,after}_atomic_{inc,dec}.h into
 asm/atomic.h

Move the barriers functions that depend on the atomic implementation
into the atomic implementation.

Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Vineet Gupta <vgupta@synopsys.com> [for arch/arc bits]
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/20131213150640.786183683@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 83f03ca..03e494f 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -190,6 +190,11 @@ static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
 
 #endif /* !CONFIG_ARC_HAS_LLSC */
 
+#define smp_mb__before_atomic_dec()	barrier()
+#define smp_mb__after_atomic_dec()	barrier()
+#define smp_mb__before_atomic_inc()	barrier()
+#define smp_mb__after_atomic_inc()	barrier()
+
 /**
  * __atomic_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t
diff --git a/arch/arc/include/asm/barrier.h b/arch/arc/include/asm/barrier.h
index f6cb7c4..c32245c 100644
--- a/arch/arc/include/asm/barrier.h
+++ b/arch/arc/include/asm/barrier.h
@@ -30,11 +30,6 @@
 #define smp_wmb()       barrier()
 #endif
 
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
 #define smp_read_barrier_depends()      do { } while (0)
 
 #endif
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index 8a64ff2..7aae4cb 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -160,8 +160,12 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 #define atomic_sub_and_test(i, v) (atomic_sub_return(i, (v)) == 0)
 #define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0)
 
-
 #define atomic_inc_return(v) (atomic_add_return(1, v))
 #define atomic_dec_return(v) (atomic_sub_return(1, v))
 
+#define smp_mb__before_atomic_dec()	barrier()
+#define smp_mb__after_atomic_dec()	barrier()
+#define smp_mb__before_atomic_inc()	barrier()
+#define smp_mb__after_atomic_inc()	barrier()
+
 #endif
diff --git a/arch/hexagon/include/asm/barrier.h b/arch/hexagon/include/asm/barrier.h
index 1041a8e..4e863da 100644
--- a/arch/hexagon/include/asm/barrier.h
+++ b/arch/hexagon/include/asm/barrier.h
@@ -29,10 +29,6 @@
 #define smp_read_barrier_depends()	barrier()
 #define smp_wmb()			barrier()
 #define smp_mb()			barrier()
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
 
 /*  Set a value and use a memory barrier.  Used by the scheduler somewhere.  */
 #define set_mb(var, value) \
-- 
cgit v0.10.2


From 93ea02bb84354370e51de803a9405f171f3edf88 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 6 Nov 2013 14:57:36 +0100
Subject: arch: Clean up asm/barrier.h implementations using
 asm-generic/barrier.h

We're going to be adding a few new barrier primitives, and in order to
avoid endless duplication make more agressive use of
asm-generic/barrier.h.

Change the asm-generic/barrier.h such that it allows partial barrier
definitions and fills out the rest with defaults.

There are a few architectures (m32r, m68k) that could probably
do away with their barrier.h file entirely but are kept for now due to
their unconventional nop() implementation.

Suggested-by: Geert Uytterhoeven <geert@linux-m68k.org>
Reviewed-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Michael Ellerman <michael@ellerman.id.au>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Victor Kaplansky <VICTORK@il.ibm.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/20131213150640.846368594@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/alpha/include/asm/barrier.h b/arch/alpha/include/asm/barrier.h
index ce8860a..3832bdb 100644
--- a/arch/alpha/include/asm/barrier.h
+++ b/arch/alpha/include/asm/barrier.h
@@ -3,33 +3,18 @@
 
 #include <asm/compiler.h>
 
-#define mb() \
-__asm__ __volatile__("mb": : :"memory")
+#define mb()	__asm__ __volatile__("mb": : :"memory")
+#define rmb()	__asm__ __volatile__("mb": : :"memory")
+#define wmb()	__asm__ __volatile__("wmb": : :"memory")
 
-#define rmb() \
-__asm__ __volatile__("mb": : :"memory")
-
-#define wmb() \
-__asm__ __volatile__("wmb": : :"memory")
-
-#define read_barrier_depends() \
-__asm__ __volatile__("mb": : :"memory")
+#define read_barrier_depends() __asm__ __volatile__("mb": : :"memory")
 
 #ifdef CONFIG_SMP
 #define __ASM_SMP_MB	"\tmb\n"
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define smp_read_barrier_depends()	read_barrier_depends()
 #else
 #define __ASM_SMP_MB
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
 #endif
 
-#define set_mb(var, value) \
-do { var = value; mb(); } while (0)
+#include <asm-generic/barrier.h>
 
 #endif		/* __BARRIER_H */
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index 5943f7f..e07c786 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -47,3 +47,4 @@ generic-y += user.h
 generic-y += vga.h
 generic-y += xor.h
 generic-y += preempt.h
+generic-y += barrier.h
diff --git a/arch/avr32/include/asm/barrier.h b/arch/avr32/include/asm/barrier.h
index 0961275..7151007 100644
--- a/arch/avr32/include/asm/barrier.h
+++ b/arch/avr32/include/asm/barrier.h
@@ -8,22 +8,15 @@
 #ifndef __ASM_AVR32_BARRIER_H
 #define __ASM_AVR32_BARRIER_H
 
-#define nop()			asm volatile("nop")
-
-#define mb()			asm volatile("" : : : "memory")
-#define rmb()			mb()
-#define wmb()			asm volatile("sync 0" : : : "memory")
-#define read_barrier_depends()  do { } while(0)
-#define set_mb(var, value)      do { var = value; mb(); } while(0)
+/*
+ * Weirdest thing ever.. no full barrier, but it has a write barrier!
+ */
+#define wmb()	asm volatile("sync 0" : : : "memory")
 
 #ifdef CONFIG_SMP
 # error "The AVR32 port does not support SMP"
-#else
-# define smp_mb()		barrier()
-# define smp_rmb()		barrier()
-# define smp_wmb()		barrier()
-# define smp_read_barrier_depends() do { } while(0)
 #endif
 
+#include <asm-generic/barrier.h>
 
 #endif /* __ASM_AVR32_BARRIER_H */
diff --git a/arch/blackfin/include/asm/barrier.h b/arch/blackfin/include/asm/barrier.h
index ebb1895..19283a1 100644
--- a/arch/blackfin/include/asm/barrier.h
+++ b/arch/blackfin/include/asm/barrier.h
@@ -23,26 +23,10 @@
 # define rmb()	do { barrier(); smp_check_barrier(); } while (0)
 # define wmb()	do { barrier(); smp_mark_barrier(); } while (0)
 # define read_barrier_depends()	do { barrier(); smp_check_barrier(); } while (0)
-#else
-# define mb()	barrier()
-# define rmb()	barrier()
-# define wmb()	barrier()
-# define read_barrier_depends()	do { } while (0)
 #endif
 
-#else /* !CONFIG_SMP */
-
-#define mb()	barrier()
-#define rmb()	barrier()
-#define wmb()	barrier()
-#define read_barrier_depends()	do { } while (0)
-
 #endif /* !CONFIG_SMP */
 
-#define smp_mb()  mb()
-#define smp_rmb() rmb()
-#define smp_wmb() wmb()
-#define set_mb(var, value) do { var = value; mb(); } while (0)
-#define smp_read_barrier_depends()	read_barrier_depends()
+#include <asm-generic/barrier.h>
 
 #endif /* _BLACKFIN_BARRIER_H */
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index b06caf6..35ec2e5 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -12,3 +12,4 @@ generic-y += trace_clock.h
 generic-y += vga.h
 generic-y += xor.h
 generic-y += preempt.h
+generic-y += barrier.h
diff --git a/arch/cris/include/asm/barrier.h b/arch/cris/include/asm/barrier.h
deleted file mode 100644
index 198ad7f..0000000
--- a/arch/cris/include/asm/barrier.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef __ASM_CRIS_BARRIER_H
-#define __ASM_CRIS_BARRIER_H
-
-#define nop() __asm__ __volatile__ ("nop");
-
-#define barrier() __asm__ __volatile__("": : :"memory")
-#define mb() barrier()
-#define rmb() mb()
-#define wmb() mb()
-#define read_barrier_depends() do { } while(0)
-#define set_mb(var, value)  do { var = value; mb(); } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb()        mb()
-#define smp_rmb()       rmb()
-#define smp_wmb()       wmb()
-#define smp_read_barrier_depends()     read_barrier_depends()
-#else
-#define smp_mb()        barrier()
-#define smp_rmb()       barrier()
-#define smp_wmb()       barrier()
-#define smp_read_barrier_depends()     do { } while(0)
-#endif
-
-#endif /* __ASM_CRIS_BARRIER_H */
diff --git a/arch/frv/include/asm/barrier.h b/arch/frv/include/asm/barrier.h
index 06776ad..abbef47 100644
--- a/arch/frv/include/asm/barrier.h
+++ b/arch/frv/include/asm/barrier.h
@@ -17,13 +17,7 @@
 #define mb()			asm volatile ("membar" : : :"memory")
 #define rmb()			asm volatile ("membar" : : :"memory")
 #define wmb()			asm volatile ("membar" : : :"memory")
-#define read_barrier_depends()	do { } while (0)
 
-#define smp_mb()			barrier()
-#define smp_rmb()			barrier()
-#define smp_wmb()			barrier()
-#define smp_read_barrier_depends()	do {} while(0)
-#define set_mb(var, value) \
-	do { var = (value); barrier(); } while (0)
+#include <asm-generic/barrier.h>
 
 #endif /* _ASM_BARRIER_H */
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index 67c3450..a614ec9 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -54,3 +54,4 @@ generic-y += ucontext.h
 generic-y += unaligned.h
 generic-y += xor.h
 generic-y += preempt.h
+generic-y += barrier.h
diff --git a/arch/m32r/include/asm/barrier.h b/arch/m32r/include/asm/barrier.h
index 6976621..1a40265 100644
--- a/arch/m32r/include/asm/barrier.h
+++ b/arch/m32r/include/asm/barrier.h
@@ -11,84 +11,6 @@
 
 #define nop()  __asm__ __volatile__ ("nop" : : )
 
-/*
- * Memory barrier.
- *
- * mb() prevents loads and stores being reordered across this point.
- * rmb() prevents loads being reordered across this point.
- * wmb() prevents stores being reordered across this point.
- */
-#define mb()   barrier()
-#define rmb()  mb()
-#define wmb()  mb()
-
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *      CPU 0                           CPU 1
- *
- *      b = 2;
- *      memory_barrier();
- *      p = &b;                         q = p;
- *                                      read_barrier_depends();
- *                                      d = *q;
- * </programlisting>
- *
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *      CPU 0                           CPU 1
- *
- *      a = 2;
- *      memory_barrier();
- *      b = 3;                          y = b;
- *                                      read_barrier_depends();
- *                                      x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- **/
-
-#define read_barrier_depends()	do { } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define smp_read_barrier_depends()	read_barrier_depends()
-#define set_mb(var, value) do { (void) xchg(&var, value); } while (0)
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
-#endif
+#include <asm-generic/barrier.h>
 
 #endif /* _ASM_M32R_BARRIER_H */
diff --git a/arch/m68k/include/asm/barrier.h b/arch/m68k/include/asm/barrier.h
index 445ce22..15c5f77 100644
--- a/arch/m68k/include/asm/barrier.h
+++ b/arch/m68k/include/asm/barrier.h
@@ -1,20 +1,8 @@
 #ifndef _M68K_BARRIER_H
 #define _M68K_BARRIER_H
 
-/*
- * Force strict CPU ordering.
- * Not really required on m68k...
- */
 #define nop()		do { asm volatile ("nop"); barrier(); } while (0)
-#define mb()		barrier()
-#define rmb()		barrier()
-#define wmb()		barrier()
-#define read_barrier_depends()	((void)0)
-#define set_mb(var, value)	({ (var) = (value); wmb(); })
 
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	((void)0)
+#include <asm-generic/barrier.h>
 
 #endif /* _M68K_BARRIER_H */
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index ce0bbf8..f77fb66 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -4,3 +4,4 @@ generic-y += exec.h
 generic-y += trace_clock.h
 generic-y += syscalls.h
 generic-y += preempt.h
+generic-y += barrier.h
diff --git a/arch/microblaze/include/asm/barrier.h b/arch/microblaze/include/asm/barrier.h
deleted file mode 100644
index df5be3e8..0000000
--- a/arch/microblaze/include/asm/barrier.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * Copyright (C) 2006 Atmark Techno, Inc.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#ifndef _ASM_MICROBLAZE_BARRIER_H
-#define _ASM_MICROBLAZE_BARRIER_H
-
-#define nop()                  asm volatile ("nop")
-
-#define smp_read_barrier_depends()	do {} while (0)
-#define read_barrier_depends()		do {} while (0)
-
-#define mb()			barrier()
-#define rmb()			mb()
-#define wmb()			mb()
-#define set_mb(var, value)	do { var = value; mb(); } while (0)
-#define set_wmb(var, value)	do { var = value; wmb(); } while (0)
-
-#define smp_mb()		mb()
-#define smp_rmb()		rmb()
-#define smp_wmb()		wmb()
-
-#endif /* _ASM_MICROBLAZE_BARRIER_H */
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index 74742dc..367ef39 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -3,3 +3,4 @@ generic-y += clkdev.h
 generic-y += exec.h
 generic-y += trace_clock.h
 generic-y += preempt.h
+generic-y += barrier.h
diff --git a/arch/mn10300/include/asm/barrier.h b/arch/mn10300/include/asm/barrier.h
deleted file mode 100644
index 2bd97a5..0000000
--- a/arch/mn10300/include/asm/barrier.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/* MN10300 memory barrier definitions
- *
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-#ifndef _ASM_BARRIER_H
-#define _ASM_BARRIER_H
-
-#define nop()	asm volatile ("nop")
-
-#define mb()	asm volatile ("": : :"memory")
-#define rmb()	mb()
-#define wmb()	asm volatile ("": : :"memory")
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define set_mb(var, value)  do { xchg(&var, value); } while (0)
-#else  /* CONFIG_SMP */
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define set_mb(var, value)  do { var = value;  mb(); } while (0)
-#endif /* CONFIG_SMP */
-
-#define set_wmb(var, value) do { var = value; wmb(); } while (0)
-
-#define read_barrier_depends()		do {} while (0)
-#define smp_read_barrier_depends()	do {} while (0)
-
-#endif /* _ASM_BARRIER_H */
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index a603b9e..8df06d0 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -5,3 +5,4 @@ generic-y += word-at-a-time.h auxvec.h user.h cputime.h emergency-restart.h \
 	  poll.h xor.h clkdev.h exec.h
 generic-y += trace_clock.h
 generic-y += preempt.h
+generic-y += barrier.h
diff --git a/arch/parisc/include/asm/barrier.h b/arch/parisc/include/asm/barrier.h
deleted file mode 100644
index e77d834..0000000
--- a/arch/parisc/include/asm/barrier.h
+++ /dev/null
@@ -1,35 +0,0 @@
-#ifndef __PARISC_BARRIER_H
-#define __PARISC_BARRIER_H
-
-/*
-** This is simply the barrier() macro from linux/kernel.h but when serial.c
-** uses tqueue.h uses smp_mb() defined using barrier(), linux/kernel.h
-** hasn't yet been included yet so it fails, thus repeating the macro here.
-**
-** PA-RISC architecture allows for weakly ordered memory accesses although
-** none of the processors use it. There is a strong ordered bit that is
-** set in the O-bit of the page directory entry. Operating systems that
-** can not tolerate out of order accesses should set this bit when mapping
-** pages. The O-bit of the PSW should also be set to 1 (I don't believe any
-** of the processor implemented the PSW O-bit). The PCX-W ERS states that
-** the TLB O-bit is not implemented so the page directory does not need to
-** have the O-bit set when mapping pages (section 3.1). This section also
-** states that the PSW Y, Z, G, and O bits are not implemented.
-** So it looks like nothing needs to be done for parisc-linux (yet).
-** (thanks to chada for the above comment -ggg)
-**
-** The __asm__ op below simple prevents gcc/ld from reordering
-** instructions across the mb() "call".
-*/
-#define mb()		__asm__ __volatile__("":::"memory")	/* barrier() */
-#define rmb()		mb()
-#define wmb()		mb()
-#define smp_mb()	mb()
-#define smp_rmb()	mb()
-#define smp_wmb()	mb()
-#define smp_read_barrier_depends()	do { } while(0)
-#define read_barrier_depends()		do { } while(0)
-
-#define set_mb(var, value)		do { var = value; mb(); } while (0)
-
-#endif /* __PARISC_BARRIER_H */
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index f3414ad..ee2993b 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -5,3 +5,4 @@ generic-y += clkdev.h
 generic-y += trace_clock.h
 generic-y += xor.h
 generic-y += preempt.h
+generic-y += barrier.h
diff --git a/arch/score/include/asm/barrier.h b/arch/score/include/asm/barrier.h
deleted file mode 100644
index 0eacb64..0000000
--- a/arch/score/include/asm/barrier.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef _ASM_SCORE_BARRIER_H
-#define _ASM_SCORE_BARRIER_H
-
-#define mb()		barrier()
-#define rmb()		barrier()
-#define wmb()		barrier()
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-
-#define read_barrier_depends()		do {} while (0)
-#define smp_read_barrier_depends()	do {} while (0)
-
-#define set_mb(var, value) 		do {var = value; wmb(); } while (0)
-
-#endif /* _ASM_SCORE_BARRIER_H */
diff --git a/arch/sh/include/asm/barrier.h b/arch/sh/include/asm/barrier.h
index 72c103d..4371530 100644
--- a/arch/sh/include/asm/barrier.h
+++ b/arch/sh/include/asm/barrier.h
@@ -26,29 +26,14 @@
 #if defined(CONFIG_CPU_SH4A) || defined(CONFIG_CPU_SH5)
 #define mb()		__asm__ __volatile__ ("synco": : :"memory")
 #define rmb()		mb()
-#define wmb()		__asm__ __volatile__ ("synco": : :"memory")
+#define wmb()		mb()
 #define ctrl_barrier()	__icbi(PAGE_OFFSET)
-#define read_barrier_depends()	do { } while(0)
 #else
-#define mb()		__asm__ __volatile__ ("": : :"memory")
-#define rmb()		mb()
-#define wmb()		__asm__ __volatile__ ("": : :"memory")
 #define ctrl_barrier()	__asm__ __volatile__ ("nop;nop;nop;nop;nop;nop;nop;nop")
-#define read_barrier_depends()	do { } while(0)
-#endif
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define smp_read_barrier_depends()	read_barrier_depends()
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while(0)
 #endif
 
 #define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
 
+#include <asm-generic/barrier.h>
+
 #endif /* __ASM_SH_BARRIER_H */
diff --git a/arch/sparc/include/asm/barrier_32.h b/arch/sparc/include/asm/barrier_32.h
index c1b7665..ae69eda 100644
--- a/arch/sparc/include/asm/barrier_32.h
+++ b/arch/sparc/include/asm/barrier_32.h
@@ -1,15 +1,7 @@
 #ifndef __SPARC_BARRIER_H
 #define __SPARC_BARRIER_H
 
-/* XXX Change this if we ever use a PSO mode kernel. */
-#define mb()	__asm__ __volatile__ ("" : : : "memory")
-#define rmb()	mb()
-#define wmb()	mb()
-#define read_barrier_depends()	do { } while(0)
-#define set_mb(__var, __value)  do { __var = __value; mb(); } while(0)
-#define smp_mb()	__asm__ __volatile__("":::"memory")
-#define smp_rmb()	__asm__ __volatile__("":::"memory")
-#define smp_wmb()	__asm__ __volatile__("":::"memory")
-#define smp_read_barrier_depends()	do { } while(0)
+#include <asm/processor.h> /* for nop() */
+#include <asm-generic/barrier.h>
 
 #endif /* !(__SPARC_BARRIER_H) */
diff --git a/arch/tile/include/asm/barrier.h b/arch/tile/include/asm/barrier.h
index a9a73da..b5a05d0 100644
--- a/arch/tile/include/asm/barrier.h
+++ b/arch/tile/include/asm/barrier.h
@@ -22,59 +22,6 @@
 #include <arch/spr_def.h>
 #include <asm/timex.h>
 
-/*
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	b = 2;
- *	memory_barrier();
- *	p = &b;				q = p;
- *					read_barrier_depends();
- *					d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	a = 2;
- *	memory_barrier();
- *	b = 3;				y = b;
- *					read_barrier_depends();
- *					x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- */
-#define read_barrier_depends()	do { } while (0)
-
 #define __sync()	__insn_mf()
 
 #include <hv/syscall_public.h>
@@ -125,20 +72,7 @@ mb_incoherent(void)
 #define mb()		fast_mb()
 #define iob()		fast_iob()
 
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define smp_read_barrier_depends()	read_barrier_depends()
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
-#endif
-
-#define set_mb(var, value) \
-	do { var = value; mb(); } while (0)
+#include <asm-generic/barrier.h>
 
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_TILE_BARRIER_H */
diff --git a/arch/unicore32/include/asm/barrier.h b/arch/unicore32/include/asm/barrier.h
index a6620e5..83d6a52 100644
--- a/arch/unicore32/include/asm/barrier.h
+++ b/arch/unicore32/include/asm/barrier.h
@@ -14,15 +14,6 @@
 #define dsb() __asm__ __volatile__ ("" : : : "memory")
 #define dmb() __asm__ __volatile__ ("" : : : "memory")
 
-#define mb()				barrier()
-#define rmb()				barrier()
-#define wmb()				barrier()
-#define smp_mb()			barrier()
-#define smp_rmb()			barrier()
-#define smp_wmb()			barrier()
-#define read_barrier_depends()		do { } while (0)
-#define smp_read_barrier_depends()	do { } while (0)
-
-#define set_mb(var, value)		do { var = value; smp_mb(); } while (0)
+#include <asm-generic/barrier.h>
 
 #endif /* __UNICORE_BARRIER_H__ */
diff --git a/arch/xtensa/include/asm/barrier.h b/arch/xtensa/include/asm/barrier.h
index ef02167..e1ee6b5 100644
--- a/arch/xtensa/include/asm/barrier.h
+++ b/arch/xtensa/include/asm/barrier.h
@@ -9,21 +9,14 @@
 #ifndef _XTENSA_SYSTEM_H
 #define _XTENSA_SYSTEM_H
 
-#define smp_read_barrier_depends() do { } while(0)
-#define read_barrier_depends() do { } while(0)
-
 #define mb()  ({ __asm__ __volatile__("memw" : : : "memory"); })
 #define rmb() barrier()
 #define wmb() mb()
 
 #ifdef CONFIG_SMP
 #error smp_* not defined
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
 #endif
 
-#define set_mb(var, value)	do { var = value; mb(); } while (0)
+#include <asm-generic/barrier.h>
 
 #endif /* _XTENSA_SYSTEM_H */
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 639d7a4..d12a90f 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -1,4 +1,5 @@
-/* Generic barrier definitions, based on MN10300 definitions.
+/*
+ * Generic barrier definitions, originally based on MN10300 definitions.
  *
  * It should be possible to use these on really simple architectures,
  * but it serves more as a starting point for new ports.
@@ -16,35 +17,50 @@
 
 #ifndef __ASSEMBLY__
 
-#define nop() asm volatile ("nop")
+#include <linux/compiler.h>
+
+#ifndef nop
+#define nop()	asm volatile ("nop")
+#endif
 
 /*
- * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
- * to devices.
+ * Force strict CPU ordering. And yes, this is required on UP too when we're
+ * talking to devices.
  *
- * This implementation only contains a compiler barrier.
+ * Fall back to compiler barriers if nothing better is provided.
  */
 
-#define mb()	asm volatile ("": : :"memory")
+#ifndef mb
+#define mb()	barrier()
+#endif
+
+#ifndef rmb
 #define rmb()	mb()
-#define wmb()	asm volatile ("": : :"memory")
+#endif
+
+#ifndef wmb
+#define wmb()	mb()
+#endif
+
+#ifndef read_barrier_depends
+#define read_barrier_depends()		do { } while (0)
+#endif
 
 #ifdef CONFIG_SMP
 #define smp_mb()	mb()
 #define smp_rmb()	rmb()
 #define smp_wmb()	wmb()
+#define smp_read_barrier_depends()	read_barrier_depends()
 #else
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
+#define smp_read_barrier_depends()	do { } while (0)
 #endif
 
-#define set_mb(var, value)  do { var = value;  mb(); } while (0)
-#define set_wmb(var, value) do { var = value; wmb(); } while (0)
-
-#define read_barrier_depends()		do {} while (0)
-#define smp_read_barrier_depends()	do {} while (0)
+#ifndef set_mb
+#define set_mb(var, value)  do { (var) = (value); mb(); } while (0)
+#endif
 
 #endif /* !__ASSEMBLY__ */
 #endif /* __ASM_GENERIC_BARRIER_H */
-- 
cgit v0.10.2


From 47933ad41a86a4a9b50bed7c9b9bd2ba242aac63 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 6 Nov 2013 14:57:36 +0100
Subject: arch: Introduce smp_load_acquire(), smp_store_release()

A number of situations currently require the heavyweight smp_mb(),
even though there is no need to order prior stores against later
loads.  Many architectures have much cheaper ways to handle these
situations, but the Linux kernel currently has no portable way
to make use of them.

This commit therefore supplies smp_load_acquire() and
smp_store_release() to remedy this situation.  The new
smp_load_acquire() primitive orders the specified load against
any subsequent reads or writes, while the new smp_store_release()
primitive orders the specifed store against any prior reads or
writes.  These primitives allow array-based circular FIFOs to be
implemented without an smp_mb(), and also allow a theoretical
hole in rcu_assign_pointer() to be closed at no additional
expense on most architectures.

In addition, the RCU experience transitioning from explicit
smp_read_barrier_depends() and smp_wmb() to rcu_dereference()
and rcu_assign_pointer(), respectively resulted in substantial
improvements in readability.  It therefore seems likely that
replacing other explicit barriers with smp_load_acquire() and
smp_store_release() will provide similar benefits.  It appears
that roughly half of the explicit barriers in core kernel code
might be so replaced.

[Changelog by PaulMck]

Reviewed-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Michael Ellerman <michael@ellerman.id.au>
Cc: Michael Neuling <mikey@neuling.org>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Victor Kaplansky <VICTORK@il.ibm.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Link: http://lkml.kernel.org/r/20131213150640.908486364@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index 60f15e2..2f59f74 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -59,6 +59,21 @@
 #define smp_wmb()	dmb(ishst)
 #endif
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
 #define read_barrier_depends()		do { } while(0)
 #define smp_read_barrier_depends()	do { } while(0)
 
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index d4a6333..78e20ba 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -35,10 +35,60 @@
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
 #else
+
 #define smp_mb()	asm volatile("dmb ish" : : : "memory")
 #define smp_rmb()	asm volatile("dmb ishld" : : : "memory")
 #define smp_wmb()	asm volatile("dmb ishst" : : : "memory")
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	switch (sizeof(*p)) {						\
+	case 4:								\
+		asm volatile ("stlr %w1, %0"				\
+				: "=Q" (*p) : "r" (v) : "memory");	\
+		break;							\
+	case 8:								\
+		asm volatile ("stlr %1, %0"				\
+				: "=Q" (*p) : "r" (v) : "memory");	\
+		break;							\
+	}								\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1;						\
+	compiletime_assert_atomic_type(*p);				\
+	switch (sizeof(*p)) {						\
+	case 4:								\
+		asm volatile ("ldar %w0, %1"				\
+			: "=r" (___p1) : "Q" (*p) : "memory");		\
+		break;							\
+	case 8:								\
+		asm volatile ("ldar %0, %1"				\
+			: "=r" (___p1) : "Q" (*p) : "memory");		\
+		break;							\
+	}								\
+	___p1;								\
+})
+
 #endif
 
 #define read_barrier_depends()		do { } while(0)
diff --git a/arch/ia64/include/asm/barrier.h b/arch/ia64/include/asm/barrier.h
index 60576e0..d0a69aa 100644
--- a/arch/ia64/include/asm/barrier.h
+++ b/arch/ia64/include/asm/barrier.h
@@ -45,14 +45,37 @@
 # define smp_rmb()	rmb()
 # define smp_wmb()	wmb()
 # define smp_read_barrier_depends()	read_barrier_depends()
+
 #else
+
 # define smp_mb()	barrier()
 # define smp_rmb()	barrier()
 # define smp_wmb()	barrier()
 # define smp_read_barrier_depends()	do { } while(0)
+
 #endif
 
 /*
+ * IA64 GCC turns volatile stores into st.rel and volatile loads into ld.acq no
+ * need for asm trickery!
+ */
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	___p1;								\
+})
+
+/*
  * XXX check on this ---I suspect what Linus really wants here is
  * acquire vs release semantics but we can't discuss this stuff with
  * Linus just yet.  Grrr...
diff --git a/arch/metag/include/asm/barrier.h b/arch/metag/include/asm/barrier.h
index c90bfc6..5d6b4b4 100644
--- a/arch/metag/include/asm/barrier.h
+++ b/arch/metag/include/asm/barrier.h
@@ -82,4 +82,19 @@ static inline void fence(void)
 #define smp_read_barrier_depends()     do { } while (0)
 #define set_mb(var, value) do { var = value; smp_mb(); } while (0)
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
 #endif /* _ASM_METAG_BARRIER_H */
diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h
index f26d8e1..e1aa4e4 100644
--- a/arch/mips/include/asm/barrier.h
+++ b/arch/mips/include/asm/barrier.h
@@ -180,4 +180,19 @@
 #define nudge_writes() mb()
 #endif
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
 #endif /* __ASM_BARRIER_H */
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index ae78225..f89da80 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -45,11 +45,15 @@
 #    define SMPWMB      eieio
 #endif
 
+#define __lwsync()	__asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory")
+
 #define smp_mb()	mb()
-#define smp_rmb()	__asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory")
+#define smp_rmb()	__lwsync()
 #define smp_wmb()	__asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory")
 #define smp_read_barrier_depends()	read_barrier_depends()
 #else
+#define __lwsync()	barrier()
+
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
@@ -65,4 +69,19 @@
 #define data_barrier(x)	\
 	asm volatile("twi 0,%0,0; isync" : : "r" (x) : "memory");
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	__lwsync();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	__lwsync();							\
+	___p1;								\
+})
+
 #endif /* _ASM_POWERPC_BARRIER_H */
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index 16760ee..578680f 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -32,4 +32,19 @@
 
 #define set_mb(var, value)		do { var = value; mb(); } while (0)
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	___p1;								\
+})
+
 #endif /* __ASM_BARRIER_H */
diff --git a/arch/sparc/include/asm/barrier_64.h b/arch/sparc/include/asm/barrier_64.h
index 95d4598..b5aad96 100644
--- a/arch/sparc/include/asm/barrier_64.h
+++ b/arch/sparc/include/asm/barrier_64.h
@@ -53,4 +53,19 @@ do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
 
 #define smp_read_barrier_depends()	do { } while(0)
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	___p1;								\
+})
+
 #endif /* !(__SPARC64_BARRIER_H) */
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index c6cd358..04a4890 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -92,12 +92,53 @@
 #endif
 #define smp_read_barrier_depends()	read_barrier_depends()
 #define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
-#else
+#else /* !SMP */
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
 #define smp_read_barrier_depends()	do { } while (0)
 #define set_mb(var, value) do { var = value; barrier(); } while (0)
+#endif /* SMP */
+
+#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+
+/*
+ * For either of these options x86 doesn't have a strong TSO memory
+ * model and we should fall back to full barriers.
+ */
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
+#else /* regular x86 TSO memory ordering */
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	___p1;								\
+})
+
 #endif
 
 /*
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index d12a90f..6f692f8 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -62,5 +62,20 @@
 #define set_mb(var, value)  do { (var) = (value); mb(); } while (0)
 #endif
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
 #endif /* !__ASSEMBLY__ */
 #endif /* __ASM_GENERIC_BARRIER_H */
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 92669cd..fe7a686 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -298,6 +298,11 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
 # define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
 #endif
 
+/* Is this type a native word size -- useful for atomic operations */
+#ifndef __native_word
+# define __native_word(t) (sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
+#endif
+
 /* Compile time object size, -1 for unknown */
 #ifndef __compiletime_object_size
 # define __compiletime_object_size(obj) -1
@@ -337,6 +342,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
 #define compiletime_assert(condition, msg) \
 	_compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
 
+#define compiletime_assert_atomic_type(t)				\
+	compiletime_assert(__native_word(t),				\
+		"Need native word sized stores/loads for atomicity.")
+
 /*
  * Prevent the compiler from merging or refetching accesses.  The compiler
  * is also forbidden from reordering successive instances of ACCESS_ONCE(),
-- 
cgit v0.10.2


From eecc1e426d681351a6026a7d3e7d225f38955b6c Mon Sep 17 00:00:00 2001
From: Hugh Dickins <hughd@google.com>
Date: Sun, 12 Jan 2014 01:25:21 -0800
Subject: thp: fix copy_page_rep GPF by testing is_huge_zero_pmd once only

We see General Protection Fault on RSI in copy_page_rep: that RSI is
what you get from a NULL struct page pointer.

  RIP: 0010:[<ffffffff81154955>]  [<ffffffff81154955>] copy_page_rep+0x5/0x10
  RSP: 0000:ffff880136e15c00  EFLAGS: 00010286
  RAX: ffff880000000000 RBX: ffff880136e14000 RCX: 0000000000000200
  RDX: 6db6db6db6db6db7 RSI: db73880000000000 RDI: ffff880dd0c00000
  RBP: ffff880136e15c18 R08: 0000000000000200 R09: 000000000005987c
  R10: 000000000005987c R11: 0000000000000200 R12: 0000000000000001
  R13: ffffea00305aa000 R14: 0000000000000000 R15: 0000000000000000
  FS:  00007f195752f700(0000) GS:ffff880c7fc20000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000000093010000 CR3: 00000001458e1000 CR4: 00000000000027e0
  Call Trace:
    copy_user_huge_page+0x93/0xab
    do_huge_pmd_wp_page+0x710/0x815
    handle_mm_fault+0x15d8/0x1d70
    __do_page_fault+0x14d/0x840
    do_page_fault+0x2f/0x90
    page_fault+0x22/0x30

do_huge_pmd_wp_page() tests is_huge_zero_pmd(orig_pmd) four times: but
since shrink_huge_zero_page() can free the huge_zero_page, and we have
no hold of our own on it here (except where the fourth test holds
page_table_lock and has checked pmd_same), it's possible for it to
answer yes the first time, but no to the second or third test.  Change
all those last three to tests for NULL page.

(Note: this is not the same issue as trinity's DEBUG_PAGEALLOC BUG
in copy_page_rep with RSI: ffff88009c422000, reported by Sasha Levin
in https://lkml.org/lkml/2013/3/29/103.  I believe that one is due
to the source page being split, and a tail page freed, while copy
is in progress; and not a problem without DEBUG_PAGEALLOC, since
the pmd_same check will prevent a miscopy from being made visible.)

Fixes: 97ae17497e99 ("thp: implement refcounting for huge zero page")
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: stable@vger.kernel.org # v3.10 v3.11 v3.12
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9c0b172..95d1acb 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1154,7 +1154,7 @@ alloc:
 		new_page = NULL;
 
 	if (unlikely(!new_page)) {
-		if (is_huge_zero_pmd(orig_pmd)) {
+		if (!page) {
 			ret = do_huge_pmd_wp_zero_page_fallback(mm, vma,
 					address, pmd, orig_pmd, haddr);
 		} else {
@@ -1181,7 +1181,7 @@ alloc:
 
 	count_vm_event(THP_FAULT_ALLOC);
 
-	if (is_huge_zero_pmd(orig_pmd))
+	if (!page)
 		clear_huge_page(new_page, haddr, HPAGE_PMD_NR);
 	else
 		copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR);
@@ -1207,7 +1207,7 @@ alloc:
 		page_add_new_anon_rmap(new_page, vma, haddr);
 		set_pmd_at(mm, haddr, pmd, entry);
 		update_mmu_cache_pmd(vma, address, pmd);
-		if (is_huge_zero_pmd(orig_pmd)) {
+		if (!page) {
 			add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
 			put_huge_zero_page();
 		} else {
-- 
cgit v0.10.2


From 3dc91d4338d698ce77832985f9cb183d8eeaf6be Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 9 Jan 2014 21:46:34 -0500
Subject: SELinux: Fix possible NULL pointer dereference in
 selinux_inode_permission()

While running stress tests on adding and deleting ftrace instances I hit
this bug:

  BUG: unable to handle kernel NULL pointer dereference at 0000000000000020
  IP: selinux_inode_permission+0x85/0x160
  PGD 63681067 PUD 7ddbe067 PMD 0
  Oops: 0000 [#1] PREEMPT
  CPU: 0 PID: 5634 Comm: ftrace-test-mki Not tainted 3.13.0-rc4-test-00033-gd2a6dde-dirty #20
  Hardware name:                  /DG965MQ, BIOS MQ96510J.86A.0372.2006.0605.1717 06/05/2006
  task: ffff880078375800 ti: ffff88007ddb0000 task.ti: ffff88007ddb0000
  RIP: 0010:[<ffffffff812d8bc5>]  [<ffffffff812d8bc5>] selinux_inode_permission+0x85/0x160
  RSP: 0018:ffff88007ddb1c48  EFLAGS: 00010246
  RAX: 0000000000000000 RBX: 0000000000800000 RCX: ffff88006dd43840
  RDX: 0000000000000001 RSI: 0000000000000081 RDI: ffff88006ee46000
  RBP: ffff88007ddb1c88 R08: 0000000000000000 R09: ffff88007ddb1c54
  R10: 6e6576652f6f6f66 R11: 0000000000000003 R12: 0000000000000000
  R13: 0000000000000081 R14: ffff88006ee46000 R15: 0000000000000000
  FS:  00007f217b5b6700(0000) GS:ffffffff81e21000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033^M
  CR2: 0000000000000020 CR3: 000000006a0fe000 CR4: 00000000000007f0
  Call Trace:
    security_inode_permission+0x1c/0x30
    __inode_permission+0x41/0xa0
    inode_permission+0x18/0x50
    link_path_walk+0x66/0x920
    path_openat+0xa6/0x6c0
    do_filp_open+0x43/0xa0
    do_sys_open+0x146/0x240
    SyS_open+0x1e/0x20
    system_call_fastpath+0x16/0x1b
  Code: 84 a1 00 00 00 81 e3 00 20 00 00 89 d8 83 c8 02 40 f6 c6 04 0f 45 d8 40 f6 c6 08 74 71 80 cf 02 49 8b 46 38 4c 8d 4d cc 45 31 c0 <0f> b7 50 20 8b 70 1c 48 8b 41 70 89 d9 8b 78 04 e8 36 cf ff ff
  RIP  selinux_inode_permission+0x85/0x160
  CR2: 0000000000000020

Investigating, I found that the inode->i_security was NULL, and the
dereference of it caused the oops.

in selinux_inode_permission():

	isec = inode->i_security;

	rc = avc_has_perm_noaudit(sid, isec->sid, isec->sclass, perms, 0, &avd);

Note, the crash came from stressing the deletion and reading of debugfs
files.  I was not able to recreate this via normal files.  But I'm not
sure they are safe.  It may just be that the race window is much harder
to hit.

What seems to have happened (and what I have traced), is the file is
being opened at the same time the file or directory is being deleted.
As the dentry and inode locks are not held during the path walk, nor is
the inodes ref counts being incremented, there is nothing saving these
structures from being discarded except for an rcu_read_lock().

The rcu_read_lock() protects against freeing of the inode, but it does
not protect freeing of the inode_security_struct.  Now if the freeing of
the i_security happens with a call_rcu(), and the i_security field of
the inode is not changed (it gets freed as the inode gets freed) then
there will be no issue here.  (Linus Torvalds suggested not setting the
field to NULL such that we do not need to check if it is NULL in the
permission check).

Note, this is a hack, but it fixes the problem at hand.  A real fix is
to restructure the destroy_inode() to call all the destructor handlers
from the RCU callback.  But that is a major job to do, and requires a
lot of work.  For now, we just band-aid this bug with this fix (it
works), and work on a more maintainable solution in the future.

Link: http://lkml.kernel.org/r/20140109101932.0508dec7@gandalf.local.home
Link: http://lkml.kernel.org/r/20140109182756.17abaaa8@gandalf.local.home

Cc: stable@vger.kernel.org
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 6625699..57b0b49 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -234,6 +234,14 @@ static int inode_alloc_security(struct inode *inode)
 	return 0;
 }
 
+static void inode_free_rcu(struct rcu_head *head)
+{
+	struct inode_security_struct *isec;
+
+	isec = container_of(head, struct inode_security_struct, rcu);
+	kmem_cache_free(sel_inode_cache, isec);
+}
+
 static void inode_free_security(struct inode *inode)
 {
 	struct inode_security_struct *isec = inode->i_security;
@@ -244,8 +252,16 @@ static void inode_free_security(struct inode *inode)
 		list_del_init(&isec->list);
 	spin_unlock(&sbsec->isec_lock);
 
-	inode->i_security = NULL;
-	kmem_cache_free(sel_inode_cache, isec);
+	/*
+	 * The inode may still be referenced in a path walk and
+	 * a call to selinux_inode_permission() can be made
+	 * after inode_free_security() is called. Ideally, the VFS
+	 * wouldn't do this, but fixing that is a much harder
+	 * job. For now, simply free the i_security via RCU, and
+	 * leave the current inode->i_security pointer intact.
+	 * The inode will be freed after the RCU grace period too.
+	 */
+	call_rcu(&isec->rcu, inode_free_rcu);
 }
 
 static int file_alloc_security(struct file *file)
diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
index b1dfe10..078e553 100644
--- a/security/selinux/include/objsec.h
+++ b/security/selinux/include/objsec.h
@@ -38,7 +38,10 @@ struct task_security_struct {
 
 struct inode_security_struct {
 	struct inode *inode;	/* back pointer to inode object */
-	struct list_head list;	/* list of inode_security_struct */
+	union {
+		struct list_head list;	/* list of inode_security_struct */
+		struct rcu_head rcu;	/* for freeing the inode_security_struct */
+	};
 	u32 task_sid;		/* SID of creating task */
 	u32 sid;		/* SID of this object */
 	u16 sclass;		/* security class of this object */
-- 
cgit v0.10.2


From 7e22e91102c6b9df7c4ae2168910e19d2bb14cd6 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 12 Jan 2014 17:04:18 +0700
Subject: Linux 3.13-rc8


diff --git a/Makefile b/Makefile
index ae1a55a..eeec740 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 13
 SUBLEVEL = 0
-EXTRAVERSION = -rc7
+EXTRAVERSION = -rc8
 NAME = One Giant Leap for Frogkind
 
 # *DOCUMENTATION*
-- 
cgit v0.10.2


From 9345005f4eed805308193658d12e4e7e9c261e74 Mon Sep 17 00:00:00 2001
From: Prarit Bhargava <prarit@redhat.com>
Date: Sun, 5 Jan 2014 11:10:52 -0500
Subject: x86/irq: Fix do_IRQ() interrupt warning for cpu hotplug retriggered
 irqs

During heavy CPU-hotplug operations the following spurious kernel warnings
can trigger:

  do_IRQ: No ... irq handler for vector (irq -1)

  [ See: https://bugzilla.kernel.org/show_bug.cgi?id=64831 ]

When downing a cpu it is possible that there are unhandled irqs
left in the APIC IRR register.  The following code path shows
how the problem can occur:

 1. CPU 5 is to go down.

 2. cpu_disable() on CPU 5 executes with interrupt flag cleared
    by local_irq_save() via stop_machine().

 3. IRQ 12 asserts on CPU 5, setting IRR but not ISR because
    interrupt flag is cleared (CPU unabled to handle the irq)

 4. IRQs are migrated off of CPU 5, and the vectors' irqs are set
    to -1. 5. stop_machine() finishes cpu_disable()

 6. cpu_die() for CPU 5 executes in normal context.

 7. CPU 5 attempts to handle IRQ 12 because the IRR is set for
    IRQ 12.  The code attempts to find the vector's IRQ and cannot
    because it has been set to -1. 8. do_IRQ() warning displays
    warning about CPU 5 IRQ 12.

I added a debug printk to output which CPU & vector was
retriggered and discovered that that we are getting bogus
events.  I see a 100% correlation between this debug printk in
fixup_irqs() and the do_IRQ() warning.

This patchset resolves this by adding definitions for
VECTOR_UNDEFINED(-1) and VECTOR_RETRIGGERED(-2) and modifying
the code to use them.

Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=64831
Signed-off-by: Prarit Bhargava <prarit@redhat.com>
Reviewed-by: Rui Wang <rui.y.wang@intel.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Seiji Aguchi <seiji.aguchi@hds.com>
Cc: Yang Zhang <yang.z.zhang@Intel.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: janet.morgan@Intel.com
Cc: tony.luck@Intel.com
Cc: ruiv.wang@gmail.com
Link: http://lkml.kernel.org/r/1388938252-16627-1-git-send-email-prarit@redhat.com
[ Cleaned up the code a bit. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index cba45d9..67d69b8 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -191,6 +191,9 @@ extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void);
 #define trace_interrupt interrupt
 #endif
 
+#define VECTOR_UNDEFINED	-1
+#define VECTOR_RETRIGGERED	-2
+
 typedef int vector_irq_t[NR_VECTORS];
 DECLARE_PER_CPU(vector_irq_t, vector_irq);
 extern void setup_vector_irq(int cpu);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index e63a5bd..6df0b66 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1142,9 +1142,10 @@ next:
 		if (test_bit(vector, used_vectors))
 			goto next;
 
-		for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask)
-			if (per_cpu(vector_irq, new_cpu)[vector] != -1)
+		for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) {
+			if (per_cpu(vector_irq, new_cpu)[vector] > VECTOR_UNDEFINED)
 				goto next;
+		}
 		/* Found one! */
 		current_vector = vector;
 		current_offset = offset;
@@ -1183,7 +1184,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg)
 
 	vector = cfg->vector;
 	for_each_cpu_and(cpu, cfg->domain, cpu_online_mask)
-		per_cpu(vector_irq, cpu)[vector] = -1;
+		per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
 
 	cfg->vector = 0;
 	cpumask_clear(cfg->domain);
@@ -1191,11 +1192,10 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg)
 	if (likely(!cfg->move_in_progress))
 		return;
 	for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) {
-		for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
-								vector++) {
+		for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
 			if (per_cpu(vector_irq, cpu)[vector] != irq)
 				continue;
-			per_cpu(vector_irq, cpu)[vector] = -1;
+			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
 			break;
 		}
 	}
@@ -1228,12 +1228,12 @@ void __setup_vector_irq(int cpu)
 	/* Mark the free vectors */
 	for (vector = 0; vector < NR_VECTORS; ++vector) {
 		irq = per_cpu(vector_irq, cpu)[vector];
-		if (irq < 0)
+		if (irq <= VECTOR_UNDEFINED)
 			continue;
 
 		cfg = irq_cfg(irq);
 		if (!cpumask_test_cpu(cpu, cfg->domain))
-			per_cpu(vector_irq, cpu)[vector] = -1;
+			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
 	}
 	raw_spin_unlock(&vector_lock);
 }
@@ -2208,7 +2208,7 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
 		struct irq_cfg *cfg;
 		irq = __this_cpu_read(vector_irq[vector]);
 
-		if (irq == -1)
+		if (irq <= VECTOR_UNDEFINED)
 			continue;
 
 		desc = irq_to_desc(irq);
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 22d0687..884d875 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -193,9 +193,13 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 	if (!handle_irq(irq, regs)) {
 		ack_APIC_irq();
 
-		if (printk_ratelimit())
-			pr_emerg("%s: %d.%d No irq handler for vector (irq %d)\n",
-				__func__, smp_processor_id(), vector, irq);
+		if (irq != VECTOR_RETRIGGERED) {
+			pr_emerg_ratelimited("%s: %d.%d No irq handler for vector (irq %d)\n",
+					     __func__, smp_processor_id(),
+					     vector, irq);
+		} else {
+			__this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED);
+		}
 	}
 
 	irq_exit();
@@ -344,7 +348,7 @@ void fixup_irqs(void)
 	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
 		unsigned int irr;
 
-		if (__this_cpu_read(vector_irq[vector]) < 0)
+		if (__this_cpu_read(vector_irq[vector]) <= VECTOR_UNDEFINED)
 			continue;
 
 		irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
@@ -355,11 +359,14 @@ void fixup_irqs(void)
 			data = irq_desc_get_irq_data(desc);
 			chip = irq_data_get_irq_chip(data);
 			raw_spin_lock(&desc->lock);
-			if (chip->irq_retrigger)
+			if (chip->irq_retrigger) {
 				chip->irq_retrigger(data);
+				__this_cpu_write(vector_irq[vector], VECTOR_RETRIGGERED);
+			}
 			raw_spin_unlock(&desc->lock);
 		}
-		__this_cpu_write(vector_irq[vector], -1);
+		if (__this_cpu_read(vector_irq[vector]) != VECTOR_RETRIGGERED)
+			__this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED);
 	}
 }
 #endif
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index a2a1fbc..7f50156 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -52,7 +52,7 @@ static struct irqaction irq2 = {
 };
 
 DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
-	[0 ... NR_VECTORS - 1] = -1,
+	[0 ... NR_VECTORS - 1] = VECTOR_UNDEFINED,
 };
 
 int vector_used_by_percpu_irq(unsigned int vector)
@@ -60,7 +60,7 @@ int vector_used_by_percpu_irq(unsigned int vector)
 	int cpu;
 
 	for_each_online_cpu(cpu) {
-		if (per_cpu(vector_irq, cpu)[vector] != -1)
+		if (per_cpu(vector_irq, cpu)[vector] > VECTOR_UNDEFINED)
 			return 1;
 	}
 
-- 
cgit v0.10.2


From b25f3e1c358434bf850220e04f28eebfc45eb634 Mon Sep 17 00:00:00 2001
From: Taras Kondratiuk <taras.kondratiuk@linaro.org>
Date: Fri, 10 Jan 2014 01:27:08 +0100
Subject: ARM: 7938/1: OMAP4/highbank: Flush L2 cache before disabling

Kexec disables outer cache before jumping to reboot code, but it doesn't
flush it explicitly. Flush is done implicitly inside of l2x0_disable().
But some SoC's override default .disable handler and don't flush cache.
This may lead to a corrupted memory during Kexec reboot on these
platforms.

This patch adds cache flush inside of OMAP4 and Highbank outer_cache.disable()
handlers to make it consistent with default l2x0_disable().

Acked-by: Rob Herring <rob.herring@calxeda.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Taras Kondratiuk <taras.kondratiuk@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
index b3d7e56..ae17150 100644
--- a/arch/arm/mach-highbank/highbank.c
+++ b/arch/arm/mach-highbank/highbank.c
@@ -50,6 +50,7 @@ static void __init highbank_scu_map_io(void)
 
 static void highbank_l2x0_disable(void)
 {
+	outer_flush_all();
 	/* Disable PL310 L2 Cache controller */
 	highbank_smc1(0x102, 0x0);
 }
diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c
index 5791143..3f44b16 100644
--- a/arch/arm/mach-omap2/omap4-common.c
+++ b/arch/arm/mach-omap2/omap4-common.c
@@ -163,6 +163,7 @@ void __iomem *omap4_get_l2cache_base(void)
 
 static void omap4_l2x0_disable(void)
 {
+	outer_flush_all();
 	/* Disable PL310 L2 Cache controller */
 	omap_smc1(0x102, 0x0);
 }
-- 
cgit v0.10.2


From 4f75d8412792777a314ac5c1393a9ed43d695fd1 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Mon, 23 Dec 2013 18:05:02 +0100
Subject: x86, mce: Fix mce_start_timer semantics

So mce_start_timer() has a 'cpu' argument which is supposed to mean to
start a timer on that cpu. However, the code currently starts a timer on
the *current* cpu the function runs on and causes the sanity-check in
mce_timer_fn to fire:

	WARNING: CPU: 0 PID: 0 at arch/x86/kernel/cpu/mcheck/mce.c:1286 mce_timer_fn

because it is running on the wrong cpu.

This was triggered by Prarit Bhargava <prarit@redhat.com> by offlining
all the cpus in succession.

Then, we were fiddling with the CMCI storm settings when starting the
timer whereas there's no need for that - if there's storm happening
on this newly restarted cpu, we're going to be in normal CMCI mode
initially and then when the CMCI interrupt starts firing, we're going to
go to the polling mode with the timer real soon.

Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Prarit Bhargava <prarit@redhat.com>
Cc: Tony Luck <tony.luck@intel.com>
Reviewed-by: Chen, Gong <gong.chen@linux.intel.com>
Link: http://lkml.kernel.org/r/1387722156-5511-1-git-send-email-prarit@redhat.com

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index a389c1d..4d5419b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1638,15 +1638,15 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
 
 static void mce_start_timer(unsigned int cpu, struct timer_list *t)
 {
-	unsigned long iv = mce_adjust_timer(check_interval * HZ);
-
-	__this_cpu_write(mce_next_interval, iv);
+	unsigned long iv = check_interval * HZ;
 
 	if (mca_cfg.ignore_ce || !iv)
 		return;
 
+	per_cpu(mce_next_interval, cpu) = iv;
+
 	t->expires = round_jiffies(jiffies + iv);
-	add_timer_on(t, smp_processor_id());
+	add_timer_on(t, cpu);
 }
 
 static void __mcheck_cpu_init_timer(void)
-- 
cgit v0.10.2


From 106553aa4ead528b1bab37fb3cc47004a4451acc Mon Sep 17 00:00:00 2001
From: Richard Weinberger <richard@nod.at>
Date: Sun, 12 Jan 2014 15:52:21 +0100
Subject: um, x86: Fix vDSO build

Commit 663b55b9b39 ("x86: Delete non-required instances of include <linux/init.h>")
broke the UML build.

  arch/x86/um/vdso/vdso.S: Assembler messages:
  arch/x86/um/vdso/vdso.S:2: Error: no such instruction: `__initdata'
  arch/x86/um/vdso/vdso.S:9: Error: no such instruction: `__finit'

UML's vDSO needs linux/init.h.

Reported-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Richard Weinberger <richard@nod.at>
Cc: user-mode-linux-devel@lists.sourceforge.net
Cc: paul.gortmaker@windriver.com
Link: http://lkml.kernel.org/r/1389538341-31383-1-git-send-email-richard@nod.at
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/um/vdso/vdso.S b/arch/x86/um/vdso/vdso.S
index 4b4bd4c..1cb468a 100644
--- a/arch/x86/um/vdso/vdso.S
+++ b/arch/x86/um/vdso/vdso.S
@@ -1,3 +1,4 @@
+#include <linux/init.h>
 
 __INITDATA
 
-- 
cgit v0.10.2


From 10348f5976830e5d8f74e8abb04a9a057a5e8478 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Mon, 13 Jan 2014 09:49:17 +1100
Subject: powerpc: Check return value of instance-to-package OF call

On PA-Semi firmware, the instance-to-package callback doesn't seem
to be implemented. We didn't check for error, however, thus
subsequently passed the -1 value returned into stdout_node to
thins like prom_getprop etc...

Thus caused the firmware to load values around 0 (physical) internally
as node structures. It somewhat "worked" as long as we had a NULL in the
right place (address 8) at the beginning of the kernel, we didn't "see"
the bug. But commit 5c0484e25ec03243d4c2f2d4416d4a13efc77f6a
"powerpc: Endian safe trampoline" changed the kernel entry point causing
that old bug to now cause a crash early during boot.

This fixes booting on PA-Semi board by properly checking the return
value from instance-to-package.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Tested-by: Olof Johansson <olof@lixom.net>
---

diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index cb64a6e..078145a 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1986,19 +1986,23 @@ static void __init prom_init_stdout(void)
 	/* Get the full OF pathname of the stdout device */
 	memset(path, 0, 256);
 	call_prom("instance-to-path", 3, 1, prom.stdout, path, 255);
-	stdout_node = call_prom("instance-to-package", 1, 1, prom.stdout);
-	val = cpu_to_be32(stdout_node);
-	prom_setprop(prom.chosen, "/chosen", "linux,stdout-package",
-		     &val, sizeof(val));
 	prom_printf("OF stdout device is: %s\n", of_stdout_device);
 	prom_setprop(prom.chosen, "/chosen", "linux,stdout-path",
 		     path, strlen(path) + 1);
 
-	/* If it's a display, note it */
-	memset(type, 0, sizeof(type));
-	prom_getprop(stdout_node, "device_type", type, sizeof(type));
-	if (strcmp(type, "display") == 0)
-		prom_setprop(stdout_node, path, "linux,boot-display", NULL, 0);
+	/* instance-to-package fails on PA-Semi */
+	stdout_node = call_prom("instance-to-package", 1, 1, prom.stdout);
+	if (stdout_node != PROM_ERROR) {
+		val = cpu_to_be32(stdout_node);
+		prom_setprop(prom.chosen, "/chosen", "linux,stdout-package",
+			     &val, sizeof(val));
+
+		/* If it's a display, note it */
+		memset(type, 0, sizeof(type));
+		prom_getprop(stdout_node, "device_type", type, sizeof(type));
+		if (strcmp(type, "display") == 0)
+			prom_setprop(stdout_node, path, "linux,boot-display", NULL, 0);
+	}
 }
 
 static int __init prom_find_machine_type(void)
-- 
cgit v0.10.2


From a0b7b242261c8c1097925663bf44d51c1e357e58 Mon Sep 17 00:00:00 2001
From: Michael Schmitz <schmitzmic@gmail.com>
Date: Sat, 11 Jan 2014 13:58:55 +1300
Subject: m68k/irq - Use polled IRQ flag for MFP timer cascaded interrupts

Some Atari hardware has no capacity to raise interrupts (e.g.
network or USB adapter hardware attached via ROM port). The driver
interrupt routine is called from a timer interrupt (timer D) in
these cases, using chained device specific pseudo interrupts
(IRQ_MFP_TIMER1 ff.)

These interrupts will more often than not, return IRQ_NONE as
there is not always work for the device handler when called.
Too many unhandled interrupts will result in the interrupt
being disabled by the stuck interrupt watchdog.

As preferred option to flag interrupts as needing exclusion
from the watchdog mechanism, tglx added the IRQ_IS_POLLED flag
for use in such a case. Currently, two interrupts need to use
this flag. Add more users as needed.

Signed-off-by: Michael Schmitz <schmitz@debian.org>
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/atari/ataints.c b/arch/m68k/atari/ataints.c
index 20cde4e..3e73a63 100644
--- a/arch/m68k/atari/ataints.c
+++ b/arch/m68k/atari/ataints.c
@@ -333,6 +333,9 @@ void __init atari_init_IRQ(void)
 	m68k_setup_irq_controller(&atari_mfptimer_chip, handle_simple_irq,
 				  IRQ_MFP_TIMER1, 8);
 
+	irq_set_status_flags(IRQ_MFP_TIMER1, IRQ_IS_POLLED);
+	irq_set_status_flags(IRQ_MFP_TIMER2, IRQ_IS_POLLED);
+
 	/* prepare timer D data for use as poll interrupt */
 	/* set Timer D data Register - needs to be > 0 */
 	st_mfp.tim_dt_d = 254;	/* < 100 Hz */
-- 
cgit v0.10.2


From 0d00c7b20c7716ce08399570ea48813ecf001aa8 Mon Sep 17 00:00:00 2001
From: Jason Low <jason.low2@hp.com>
Date: Sun, 12 Jan 2014 15:31:22 -0800
Subject: futexes: Clean up various details

- Remove unnecessary head variables.
- Delete unused parameter in queue_unlock().

Reviewed-by: Darren Hart <dvhart@linux.intel.com>
Reviewed-by: Peter Zijlstra <peterz@infradead.org>
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Jason Low <jason.low2@hp.com>
Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Jeff Mahoney <jeffm@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Scott Norton <scott.norton@hp.com>
Cc: Tom Vaden <tom.vaden@hp.com>
Cc: Aswin Chandramouleeswaran <aswin@hp.com>
Cc: Waiman Long <Waiman.Long@hp.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1389569486-25487-2-git-send-email-davidlohr@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/futex.c b/kernel/futex.c
index f6ff019..085f5fa 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -598,13 +598,10 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 {
 	struct futex_pi_state *pi_state = NULL;
 	struct futex_q *this, *next;
-	struct plist_head *head;
 	struct task_struct *p;
 	pid_t pid = uval & FUTEX_TID_MASK;
 
-	head = &hb->chain;
-
-	plist_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, &hb->chain, list) {
 		if (match_futex(&this->key, key)) {
 			/*
 			 * Another waiter already exists - bump up
@@ -986,7 +983,6 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 {
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
-	struct plist_head *head;
 	union futex_key key = FUTEX_KEY_INIT;
 	int ret;
 
@@ -999,9 +995,8 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 
 	hb = hash_futex(&key);
 	spin_lock(&hb->lock);
-	head = &hb->chain;
 
-	plist_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, &hb->chain, list) {
 		if (match_futex (&this->key, &key)) {
 			if (this->pi_state || this->rt_waiter) {
 				ret = -EINVAL;
@@ -1034,7 +1029,6 @@ futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
 {
 	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
 	struct futex_hash_bucket *hb1, *hb2;
-	struct plist_head *head;
 	struct futex_q *this, *next;
 	int ret, op_ret;
 
@@ -1082,9 +1076,7 @@ retry_private:
 		goto retry;
 	}
 
-	head = &hb1->chain;
-
-	plist_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, &hb1->chain, list) {
 		if (match_futex (&this->key, &key1)) {
 			if (this->pi_state || this->rt_waiter) {
 				ret = -EINVAL;
@@ -1097,10 +1089,8 @@ retry_private:
 	}
 
 	if (op_ret > 0) {
-		head = &hb2->chain;
-
 		op_ret = 0;
-		plist_for_each_entry_safe(this, next, head, list) {
+		plist_for_each_entry_safe(this, next, &hb2->chain, list) {
 			if (match_futex (&this->key, &key2)) {
 				if (this->pi_state || this->rt_waiter) {
 					ret = -EINVAL;
@@ -1270,7 +1260,6 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	int drop_count = 0, task_count = 0, ret;
 	struct futex_pi_state *pi_state = NULL;
 	struct futex_hash_bucket *hb1, *hb2;
-	struct plist_head *head1;
 	struct futex_q *this, *next;
 	u32 curval2;
 
@@ -1393,8 +1382,7 @@ retry_private:
 		}
 	}
 
-	head1 = &hb1->chain;
-	plist_for_each_entry_safe(this, next, head1, list) {
+	plist_for_each_entry_safe(this, next, &hb1->chain, list) {
 		if (task_count - nr_wake >= nr_requeue)
 			break;
 
@@ -1494,7 +1482,7 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 }
 
 static inline void
-queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
+queue_unlock(struct futex_hash_bucket *hb)
 	__releases(&hb->lock)
 {
 	spin_unlock(&hb->lock);
@@ -1867,7 +1855,7 @@ retry_private:
 	ret = get_futex_value_locked(&uval, uaddr);
 
 	if (ret) {
-		queue_unlock(q, *hb);
+		queue_unlock(*hb);
 
 		ret = get_user(uval, uaddr);
 		if (ret)
@@ -1881,7 +1869,7 @@ retry_private:
 	}
 
 	if (uval != val) {
-		queue_unlock(q, *hb);
+		queue_unlock(*hb);
 		ret = -EWOULDBLOCK;
 	}
 
@@ -2029,7 +2017,7 @@ retry_private:
 			 * Task is exiting and we just wait for the
 			 * exit to complete.
 			 */
-			queue_unlock(&q, hb);
+			queue_unlock(hb);
 			put_futex_key(&q.key);
 			cond_resched();
 			goto retry;
@@ -2081,7 +2069,7 @@ retry_private:
 	goto out_put_key;
 
 out_unlock_put_key:
-	queue_unlock(&q, hb);
+	queue_unlock(hb);
 
 out_put_key:
 	put_futex_key(&q.key);
@@ -2091,7 +2079,7 @@ out:
 	return ret != -EINTR ? ret : -ERESTARTNOINTR;
 
 uaddr_faulted:
-	queue_unlock(&q, hb);
+	queue_unlock(hb);
 
 	ret = fault_in_user_writeable(uaddr);
 	if (ret)
@@ -2113,7 +2101,6 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 {
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
-	struct plist_head *head;
 	union futex_key key = FUTEX_KEY_INIT;
 	u32 uval, vpid = task_pid_vnr(current);
 	int ret;
@@ -2153,9 +2140,7 @@ retry:
 	 * Ok, other tasks may need to be woken up - check waiters
 	 * and do the wakeup if necessary:
 	 */
-	head = &hb->chain;
-
-	plist_for_each_entry_safe(this, next, head, list) {
+	plist_for_each_entry_safe(this, next, &hb->chain, list) {
 		if (!match_futex (&this->key, &key))
 			continue;
 		ret = wake_futex_pi(uaddr, uval, this);
-- 
cgit v0.10.2


From a52b89ebb6d4499be38780db8d176c5d3a6fbc17 Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <davidlohr@hp.com>
Date: Sun, 12 Jan 2014 15:31:23 -0800
Subject: futexes: Increase hash table size for better performance
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, the futex global hash table suffers from its fixed,
smallish (for today's standards) size of 256 entries, as well as
its lack of NUMA awareness. Large systems, using many futexes,
can be prone to high amounts of collisions; where these futexes
hash to the same bucket and lead to extra contention on the same
hb->lock. Furthermore, cacheline bouncing is a reality when we
have multiple hb->locks residing on the same cacheline and
different futexes hash to adjacent buckets.

This patch keeps the current static size of 16 entries for small
systems, or otherwise, 256 * ncpus (or larger as we need to
round the number to a power of 2). Note that this number of CPUs
accounts for all CPUs that can ever be available in the system,
taking into consideration things like hotpluging. While we do
impose extra overhead at bootup by making the hash table larger,
this is a one time thing, and does not shadow the benefits of
this patch.

Furthermore, as suggested by tglx, by cache aligning the hash
buckets we can avoid access across cacheline boundaries and also
avoid massive cache line bouncing if multiple cpus are hammering
away at different hash buckets which happen to reside in the
same cache line.

Also, similar to other core kernel components (pid, dcache,
tcp), by using alloc_large_system_hash() we benefit from its
NUMA awareness and thus the table is distributed among the nodes
instead of in a single one.

For a custom microbenchmark that pounds on the uaddr hashing --
making the wait path fail at futex_wait_setup() returning
-EWOULDBLOCK for large amounts of futexes, we can see the
following benefits on a 80-core, 8-socket 1Tb server:

 +---------+--------------------+------------------------+-----------------------+-------------------------------+
 | threads | baseline (ops/sec) | aligned-only (ops/sec) | large table (ops/sec) | large table+aligned (ops/sec) |
 +---------+--------------------+------------------------+-----------------------+-------------------------------+
 |     512 |              32426 | 50531  (+55.8%)        | 255274  (+687.2%)     | 292553  (+802.2%)             |
 |     256 |              65360 | 99588  (+52.3%)        | 443563  (+578.6%)     | 508088  (+677.3%)             |
 |     128 |             125635 | 200075 (+59.2%)        | 742613  (+491.1%)     | 835452  (+564.9%)             |
 |      80 |             193559 | 323425 (+67.1%)        | 1028147 (+431.1%)     | 1130304 (+483.9%)             |
 |      64 |             247667 | 443740 (+79.1%)        | 997300  (+302.6%)     | 1145494 (+362.5%)             |
 |      32 |             628412 | 721401 (+14.7%)        | 965996  (+53.7%)      | 1122115 (+78.5%)              |
 +---------+--------------------+------------------------+-----------------------+-------------------------------+

Reviewed-by: Darren Hart <dvhart@linux.intel.com>
Reviewed-by: Peter Zijlstra <peterz@infradead.org>
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Waiman Long <Waiman.Long@hp.com>
Reviewed-and-tested-by: Jason Low <jason.low2@hp.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Jeff Mahoney <jeffm@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Scott Norton <scott.norton@hp.com>
Cc: Tom Vaden <tom.vaden@hp.com>
Cc: Aswin Chandramouleeswaran <aswin@hp.com>
Link: http://lkml.kernel.org/r/1389569486-25487-3-git-send-email-davidlohr@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/futex.c b/kernel/futex.c
index 085f5fa..577481d 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -63,6 +63,7 @@
 #include <linux/sched/rt.h>
 #include <linux/hugetlb.h>
 #include <linux/freezer.h>
+#include <linux/bootmem.h>
 
 #include <asm/futex.h>
 
@@ -70,8 +71,6 @@
 
 int __read_mostly futex_cmpxchg_enabled;
 
-#define FUTEX_HASHBITS (CONFIG_BASE_SMALL ? 4 : 8)
-
 /*
  * Futex flags used to encode options to functions and preserve them across
  * restarts.
@@ -149,9 +148,11 @@ static const struct futex_q futex_q_init = {
 struct futex_hash_bucket {
 	spinlock_t lock;
 	struct plist_head chain;
-};
+} ____cacheline_aligned_in_smp;
 
-static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS];
+static unsigned long __read_mostly futex_hashsize;
+
+static struct futex_hash_bucket *futex_queues;
 
 /*
  * We hash on the keys returned from get_futex_key (see below).
@@ -161,7 +162,7 @@ static struct futex_hash_bucket *hash_futex(union futex_key *key)
 	u32 hash = jhash2((u32*)&key->both.word,
 			  (sizeof(key->both.word)+sizeof(key->both.ptr))/4,
 			  key->both.offset);
-	return &futex_queues[hash & ((1 << FUTEX_HASHBITS)-1)];
+	return &futex_queues[hash & (futex_hashsize - 1)];
 }
 
 /*
@@ -2719,7 +2720,18 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
 static int __init futex_init(void)
 {
 	u32 curval;
-	int i;
+	unsigned long i;
+
+#if CONFIG_BASE_SMALL
+	futex_hashsize = 16;
+#else
+	futex_hashsize = roundup_pow_of_two(256 * num_possible_cpus());
+#endif
+
+	futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues),
+					       futex_hashsize, 0,
+					       futex_hashsize < 256 ? HASH_SMALL : 0,
+					       NULL, NULL, futex_hashsize, futex_hashsize);
 
 	/*
 	 * This will fail and we want it. Some arch implementations do
@@ -2734,7 +2746,7 @@ static int __init futex_init(void)
 	if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
 		futex_cmpxchg_enabled = 1;
 
-	for (i = 0; i < ARRAY_SIZE(futex_queues); i++) {
+	for (i = 0; i < futex_hashsize; i++) {
 		plist_head_init(&futex_queues[i].chain);
 		spin_lock_init(&futex_queues[i].lock);
 	}
-- 
cgit v0.10.2


From 99b60ce69734dfeda58c6184a326b9475ce1dba3 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 12 Jan 2014 15:31:24 -0800
Subject: futexes: Document multiprocessor ordering guarantees

That's essential, if you want to hack on futexes.

Reviewed-by: Darren Hart <dvhart@linux.intel.com>
Reviewed-by: Peter Zijlstra <peterz@infradead.org>
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Jeff Mahoney <jeffm@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Scott Norton <scott.norton@hp.com>
Cc: Tom Vaden <tom.vaden@hp.com>
Cc: Aswin Chandramouleeswaran <aswin@hp.com>
Cc: Waiman Long <Waiman.Long@hp.com>
Cc: Jason Low <jason.low2@hp.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1389569486-25487-4-git-send-email-davidlohr@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/futex.c b/kernel/futex.c
index 577481d..fcc6850 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -69,6 +69,63 @@
 
 #include "locking/rtmutex_common.h"
 
+/*
+ * Basic futex operation and ordering guarantees:
+ *
+ * The waiter reads the futex value in user space and calls
+ * futex_wait(). This function computes the hash bucket and acquires
+ * the hash bucket lock. After that it reads the futex user space value
+ * again and verifies that the data has not changed. If it has not
+ * changed it enqueues itself into the hash bucket, releases the hash
+ * bucket lock and schedules.
+ *
+ * The waker side modifies the user space value of the futex and calls
+ * futex_wake(). This functions computes the hash bucket and acquires
+ * the hash bucket lock. Then it looks for waiters on that futex in the
+ * hash bucket and wakes them.
+ *
+ * Note that the spin_lock serializes waiters and wakers, so that the
+ * following scenario is avoided:
+ *
+ * CPU 0                               CPU 1
+ * val = *futex;
+ * sys_futex(WAIT, futex, val);
+ *   futex_wait(futex, val);
+ *   uval = *futex;
+ *                                     *futex = newval;
+ *                                     sys_futex(WAKE, futex);
+ *                                       futex_wake(futex);
+ *                                       if (queue_empty())
+ *                                         return;
+ *   if (uval == val)
+ *      lock(hash_bucket(futex));
+ *      queue();
+ *     unlock(hash_bucket(futex));
+ *     schedule();
+ *
+ * This would cause the waiter on CPU 0 to wait forever because it
+ * missed the transition of the user space value from val to newval
+ * and the waker did not find the waiter in the hash bucket queue.
+ * The spinlock serializes that:
+ *
+ * CPU 0                               CPU 1
+ * val = *futex;
+ * sys_futex(WAIT, futex, val);
+ *   futex_wait(futex, val);
+ *   lock(hash_bucket(futex));
+ *   uval = *futex;
+ *                                     *futex = newval;
+ *                                     sys_futex(WAKE, futex);
+ *                                       futex_wake(futex);
+ *                                       lock(hash_bucket(futex));
+ *   if (uval == val)
+ *      queue();
+ *     unlock(hash_bucket(futex));
+ *     schedule();                       if (!queue_empty())
+ *                                         wake_waiters(futex);
+ *                                       unlock(hash_bucket(futex));
+ */
+
 int __read_mostly futex_cmpxchg_enabled;
 
 /*
-- 
cgit v0.10.2


From b0c29f79ecea0b6fbcefc999e70f2843ae8306db Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <davidlohr@hp.com>
Date: Sun, 12 Jan 2014 15:31:25 -0800
Subject: futexes: Avoid taking the hb->lock if there's nothing to wake up

In futex_wake() there is clearly no point in taking the hb->lock
if we know beforehand that there are no tasks to be woken. While
the hash bucket's plist head is a cheap way of knowing this, we
cannot rely 100% on it as there is a racy window between the
futex_wait call and when the task is actually added to the
plist. To this end, we couple it with the spinlock check as
tasks trying to enter the critical region are most likely
potential waiters that will be added to the plist, thus
preventing tasks sleeping forever if wakers don't acknowledge
all possible waiters.

Furthermore, the futex ordering guarantees are preserved,
ensuring that waiters either observe the changed user space
value before blocking or is woken by a concurrent waker. For
wakers, this is done by relying on the barriers in
get_futex_key_refs() -- for archs that do not have implicit mb
in atomic_inc(), we explicitly add them through a new
futex_get_mm function. For waiters we rely on the fact that
spin_lock calls already update the head counter, so spinners
are visible even if the lock hasn't been acquired yet.

For more details please refer to the updated comments in the
code and related discussion:

  https://lkml.org/lkml/2013/11/26/556

Special thanks to tglx for careful review and feedback.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Darren Hart <dvhart@linux.intel.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Jeff Mahoney <jeffm@suse.com>
Cc: Scott Norton <scott.norton@hp.com>
Cc: Tom Vaden <tom.vaden@hp.com>
Cc: Aswin Chandramouleeswaran <aswin@hp.com>
Cc: Waiman Long <Waiman.Long@hp.com>
Cc: Jason Low <jason.low2@hp.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1389569486-25487-5-git-send-email-davidlohr@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/futex.c b/kernel/futex.c
index fcc6850..30971b5 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -75,17 +75,20 @@
  * The waiter reads the futex value in user space and calls
  * futex_wait(). This function computes the hash bucket and acquires
  * the hash bucket lock. After that it reads the futex user space value
- * again and verifies that the data has not changed. If it has not
- * changed it enqueues itself into the hash bucket, releases the hash
- * bucket lock and schedules.
+ * again and verifies that the data has not changed. If it has not changed
+ * it enqueues itself into the hash bucket, releases the hash bucket lock
+ * and schedules.
  *
  * The waker side modifies the user space value of the futex and calls
- * futex_wake(). This functions computes the hash bucket and acquires
- * the hash bucket lock. Then it looks for waiters on that futex in the
- * hash bucket and wakes them.
+ * futex_wake(). This function computes the hash bucket and acquires the
+ * hash bucket lock. Then it looks for waiters on that futex in the hash
+ * bucket and wakes them.
  *
- * Note that the spin_lock serializes waiters and wakers, so that the
- * following scenario is avoided:
+ * In futex wake up scenarios where no tasks are blocked on a futex, taking
+ * the hb spinlock can be avoided and simply return. In order for this
+ * optimization to work, ordering guarantees must exist so that the waiter
+ * being added to the list is acknowledged when the list is concurrently being
+ * checked by the waker, avoiding scenarios like the following:
  *
  * CPU 0                               CPU 1
  * val = *futex;
@@ -106,24 +109,52 @@
  * This would cause the waiter on CPU 0 to wait forever because it
  * missed the transition of the user space value from val to newval
  * and the waker did not find the waiter in the hash bucket queue.
- * The spinlock serializes that:
  *
- * CPU 0                               CPU 1
+ * The correct serialization ensures that a waiter either observes
+ * the changed user space value before blocking or is woken by a
+ * concurrent waker:
+ *
+ * CPU 0                                 CPU 1
  * val = *futex;
  * sys_futex(WAIT, futex, val);
  *   futex_wait(futex, val);
- *   lock(hash_bucket(futex));
- *   uval = *futex;
- *                                     *futex = newval;
- *                                     sys_futex(WAKE, futex);
- *                                       futex_wake(futex);
- *                                       lock(hash_bucket(futex));
+ *
+ *   waiters++;
+ *   mb(); (A) <-- paired with -.
+ *                              |
+ *   lock(hash_bucket(futex));  |
+ *                              |
+ *   uval = *futex;             |
+ *                              |        *futex = newval;
+ *                              |        sys_futex(WAKE, futex);
+ *                              |          futex_wake(futex);
+ *                              |
+ *                              `------->  mb(); (B)
  *   if (uval == val)
- *      queue();
+ *     queue();
  *     unlock(hash_bucket(futex));
- *     schedule();                       if (!queue_empty())
- *                                         wake_waiters(futex);
- *                                       unlock(hash_bucket(futex));
+ *     schedule();                         if (waiters)
+ *                                           lock(hash_bucket(futex));
+ *                                           wake_waiters(futex);
+ *                                           unlock(hash_bucket(futex));
+ *
+ * Where (A) orders the waiters increment and the futex value read -- this
+ * is guaranteed by the head counter in the hb spinlock; and where (B)
+ * orders the write to futex and the waiters read -- this is done by the
+ * barriers in get_futex_key_refs(), through either ihold or atomic_inc,
+ * depending on the futex type.
+ *
+ * This yields the following case (where X:=waiters, Y:=futex):
+ *
+ *	X = Y = 0
+ *
+ *	w[X]=1		w[Y]=1
+ *	MB		MB
+ *	r[Y]=y		r[X]=x
+ *
+ * Which guarantees that x==0 && y==0 is impossible; which translates back into
+ * the guarantee that we cannot both miss the futex variable change and the
+ * enqueue.
  */
 
 int __read_mostly futex_cmpxchg_enabled;
@@ -211,6 +242,36 @@ static unsigned long __read_mostly futex_hashsize;
 
 static struct futex_hash_bucket *futex_queues;
 
+static inline void futex_get_mm(union futex_key *key)
+{
+	atomic_inc(&key->private.mm->mm_count);
+	/*
+	 * Ensure futex_get_mm() implies a full barrier such that
+	 * get_futex_key() implies a full barrier. This is relied upon
+	 * as full barrier (B), see the ordering comment above.
+	 */
+	smp_mb__after_atomic_inc();
+}
+
+static inline bool hb_waiters_pending(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+	/*
+	 * Tasks trying to enter the critical region are most likely
+	 * potential waiters that will be added to the plist. Ensure
+	 * that wakers won't miss to-be-slept tasks in the window between
+	 * the wait call and the actual plist_add.
+	 */
+	if (spin_is_locked(&hb->lock))
+		return true;
+	smp_rmb(); /* Make sure we check the lock state first */
+
+	return !plist_head_empty(&hb->chain);
+#else
+	return true;
+#endif
+}
+
 /*
  * We hash on the keys returned from get_futex_key (see below).
  */
@@ -245,10 +306,10 @@ static void get_futex_key_refs(union futex_key *key)
 
 	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
 	case FUT_OFF_INODE:
-		ihold(key->shared.inode);
+		ihold(key->shared.inode); /* implies MB (B) */
 		break;
 	case FUT_OFF_MMSHARED:
-		atomic_inc(&key->private.mm->mm_count);
+		futex_get_mm(key); /* implies MB (B) */
 		break;
 	}
 }
@@ -322,7 +383,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
 	if (!fshared) {
 		key->private.mm = mm;
 		key->private.address = address;
-		get_futex_key_refs(key);
+		get_futex_key_refs(key);  /* implies MB (B) */
 		return 0;
 	}
 
@@ -429,7 +490,7 @@ again:
 		key->shared.pgoff = basepage_index(page);
 	}
 
-	get_futex_key_refs(key);
+	get_futex_key_refs(key); /* implies MB (B) */
 
 out:
 	unlock_page(page_head);
@@ -1052,6 +1113,11 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 		goto out;
 
 	hb = hash_futex(&key);
+
+	/* Make sure we really have tasks to wakeup */
+	if (!hb_waiters_pending(hb))
+		goto out_put_key;
+
 	spin_lock(&hb->lock);
 
 	plist_for_each_entry_safe(this, next, &hb->chain, list) {
@@ -1072,6 +1138,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 	}
 
 	spin_unlock(&hb->lock);
+out_put_key:
 	put_futex_key(&key);
 out:
 	return ret;
@@ -1535,7 +1602,7 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 	hb = hash_futex(&q->key);
 	q->lock_ptr = &hb->lock;
 
-	spin_lock(&hb->lock);
+	spin_lock(&hb->lock); /* implies MB (A) */
 	return hb;
 }
 
-- 
cgit v0.10.2


From d50dde5a10f305253cbc3855307f608f8a3c5f73 Mon Sep 17 00:00:00 2001
From: Dario Faggioli <raistlin@linux.it>
Date: Thu, 7 Nov 2013 14:43:36 +0100
Subject: sched: Add new scheduler syscalls to support an extended scheduling
 parameters ABI

Add the syscalls needed for supporting scheduling algorithms
with extended scheduling parameters (e.g., SCHED_DEADLINE).

In general, it makes possible to specify a periodic/sporadic task,
that executes for a given amount of runtime at each instance, and is
scheduled according to the urgency of their own timing constraints,
i.e.:

 - a (maximum/typical) instance execution time,
 - a minimum interval between consecutive instances,
 - a time constraint by which each instance must be completed.

Thus, both the data structure that holds the scheduling parameters of
the tasks and the system calls dealing with it must be extended.
Unfortunately, modifying the existing struct sched_param would break
the ABI and result in potentially serious compatibility issues with
legacy binaries.

For these reasons, this patch:

 - defines the new struct sched_attr, containing all the fields
   that are necessary for specifying a task in the computational
   model described above;

 - defines and implements the new scheduling related syscalls that
   manipulate it, i.e., sched_setattr() and sched_getattr().

Syscalls are introduced for x86 (32 and 64 bits) and ARM only, as a
proof of concept and for developing and testing purposes. Making them
available on other architectures is straightforward.

Since no "user" for these new parameters is introduced in this patch,
the implementation of the new system calls is just identical to their
already existing counterpart. Future patches that implement scheduling
policies able to exploit the new data structure must also take care of
modifying the sched_*attr() calls accordingly with their own purposes.

Signed-off-by: Dario Faggioli <raistlin@linux.it>
[ Rewrote to use sched_attr. ]
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
[ Removed sched_setscheduler2() for now. ]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-3-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 141baa3..acabef1 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -15,7 +15,7 @@
 
 #include <uapi/asm/unistd.h>
 
-#define __NR_syscalls  (380)
+#define __NR_syscalls  (384)
 #define __ARM_NR_cmpxchg		(__ARM_NR_BASE+0x00fff0)
 
 #define __ARCH_WANT_STAT64
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index af33b44..fb5584d 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -406,6 +406,8 @@
 #define __NR_process_vm_writev		(__NR_SYSCALL_BASE+377)
 #define __NR_kcmp			(__NR_SYSCALL_BASE+378)
 #define __NR_finit_module		(__NR_SYSCALL_BASE+379)
+#define __NR_sched_setattr		(__NR_SYSCALL_BASE+380)
+#define __NR_sched_getattr		(__NR_SYSCALL_BASE+381)
 
 /*
  * This may need to be greater than __NR_last_syscall+1 in order to
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index c6ca7e3..166e945 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -389,6 +389,8 @@
 		CALL(sys_process_vm_writev)
 		CALL(sys_kcmp)
 		CALL(sys_finit_module)
+/* 380 */	CALL(sys_sched_setattr)
+		CALL(sys_sched_getattr)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index aabfb83..96bc506 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -357,3 +357,5 @@
 348	i386	process_vm_writev	sys_process_vm_writev		compat_sys_process_vm_writev
 349	i386	kcmp			sys_kcmp
 350	i386	finit_module		sys_finit_module
+351	i386	sched_setattr		sys_sched_setattr
+352	i386	sched_getattr		sys_sched_getattr
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index 38ae65d..a12bddc 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -320,6 +320,8 @@
 311	64	process_vm_writev	sys_process_vm_writev
 312	common	kcmp			sys_kcmp
 313	common	finit_module		sys_finit_module
+314	common	sched_setattr		sys_sched_setattr
+315	common	sched_getattr		sys_sched_getattr
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3a1e985..86025b6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -56,6 +56,66 @@ struct sched_param {
 
 #include <asm/processor.h>
 
+#define SCHED_ATTR_SIZE_VER0	48	/* sizeof first published struct */
+
+/*
+ * Extended scheduling parameters data structure.
+ *
+ * This is needed because the original struct sched_param can not be
+ * altered without introducing ABI issues with legacy applications
+ * (e.g., in sched_getparam()).
+ *
+ * However, the possibility of specifying more than just a priority for
+ * the tasks may be useful for a wide variety of application fields, e.g.,
+ * multimedia, streaming, automation and control, and many others.
+ *
+ * This variant (sched_attr) is meant at describing a so-called
+ * sporadic time-constrained task. In such model a task is specified by:
+ *  - the activation period or minimum instance inter-arrival time;
+ *  - the maximum (or average, depending on the actual scheduling
+ *    discipline) computation time of all instances, a.k.a. runtime;
+ *  - the deadline (relative to the actual activation time) of each
+ *    instance.
+ * Very briefly, a periodic (sporadic) task asks for the execution of
+ * some specific computation --which is typically called an instance--
+ * (at most) every period. Moreover, each instance typically lasts no more
+ * than the runtime and must be completed by time instant t equal to
+ * the instance activation time + the deadline.
+ *
+ * This is reflected by the actual fields of the sched_attr structure:
+ *
+ *  @size		size of the structure, for fwd/bwd compat.
+ *
+ *  @sched_policy	task's scheduling policy
+ *  @sched_flags	for customizing the scheduler behaviour
+ *  @sched_nice		task's nice value      (SCHED_NORMAL/BATCH)
+ *  @sched_priority	task's static priority (SCHED_FIFO/RR)
+ *  @sched_deadline	representative of the task's deadline
+ *  @sched_runtime	representative of the task's runtime
+ *  @sched_period	representative of the task's period
+ *
+ * Given this task model, there are a multiplicity of scheduling algorithms
+ * and policies, that can be used to ensure all the tasks will make their
+ * timing constraints.
+ */
+struct sched_attr {
+	u32 size;
+
+	u32 sched_policy;
+	u64 sched_flags;
+
+	/* SCHED_NORMAL, SCHED_BATCH */
+	s32 sched_nice;
+
+	/* SCHED_FIFO, SCHED_RR */
+	u32 sched_priority;
+
+	/* SCHED_DEADLINE */
+	u64 sched_runtime;
+	u64 sched_deadline;
+	u64 sched_period;
+};
+
 struct exec_domain;
 struct futex_pi_state;
 struct robust_list_head;
@@ -1958,6 +2018,8 @@ extern int sched_setscheduler(struct task_struct *, int,
 			      const struct sched_param *);
 extern int sched_setscheduler_nocheck(struct task_struct *, int,
 				      const struct sched_param *);
+extern int sched_setattr(struct task_struct *,
+			 const struct sched_attr *);
 extern struct task_struct *idle_task(int cpu);
 /**
  * is_idle_task - is the specified task an idle task?
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 94273bb..40ed9e9 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -38,6 +38,7 @@ struct rlimit;
 struct rlimit64;
 struct rusage;
 struct sched_param;
+struct sched_attr;
 struct sel_arg_struct;
 struct semaphore;
 struct sembuf;
@@ -279,9 +280,14 @@ asmlinkage long sys_sched_setscheduler(pid_t pid, int policy,
 					struct sched_param __user *param);
 asmlinkage long sys_sched_setparam(pid_t pid,
 					struct sched_param __user *param);
+asmlinkage long sys_sched_setattr(pid_t pid,
+					struct sched_attr __user *attr);
 asmlinkage long sys_sched_getscheduler(pid_t pid);
 asmlinkage long sys_sched_getparam(pid_t pid,
 					struct sched_param __user *param);
+asmlinkage long sys_sched_getattr(pid_t pid,
+					struct sched_attr __user *attr,
+					unsigned int size);
 asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
 					unsigned long __user *user_mask_ptr);
 asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b21a63e..8174f88 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2817,6 +2817,7 @@ out_unlock:
 	__task_rq_unlock(rq);
 }
 #endif
+
 void set_user_nice(struct task_struct *p, long nice)
 {
 	int old_prio, delta, on_rq;
@@ -2991,22 +2992,29 @@ static struct task_struct *find_process_by_pid(pid_t pid)
 	return pid ? find_task_by_vpid(pid) : current;
 }
 
-/* Actually do priority change: must hold rq lock. */
-static void
-__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
+/* Actually do priority change: must hold pi & rq lock. */
+static void __setscheduler(struct rq *rq, struct task_struct *p,
+			   const struct sched_attr *attr)
 {
+	int policy = attr->sched_policy;
+
 	p->policy = policy;
-	p->rt_priority = prio;
+
+	if (rt_policy(policy))
+		p->rt_priority = attr->sched_priority;
+	else
+		p->static_prio = NICE_TO_PRIO(attr->sched_nice);
+
 	p->normal_prio = normal_prio(p);
-	/* we are holding p->pi_lock already */
 	p->prio = rt_mutex_getprio(p);
+
 	if (rt_prio(p->prio))
 		p->sched_class = &rt_sched_class;
 	else
 		p->sched_class = &fair_sched_class;
+
 	set_load_weight(p);
 }
-
 /*
  * check the target process has a UID that matches the current process's
  */
@@ -3023,10 +3031,12 @@ static bool check_same_owner(struct task_struct *p)
 	return match;
 }
 
-static int __sched_setscheduler(struct task_struct *p, int policy,
-				const struct sched_param *param, bool user)
+static int __sched_setscheduler(struct task_struct *p,
+				const struct sched_attr *attr,
+				bool user)
 {
 	int retval, oldprio, oldpolicy = -1, on_rq, running;
+	int policy = attr->sched_policy;
 	unsigned long flags;
 	const struct sched_class *prev_class;
 	struct rq *rq;
@@ -3054,17 +3064,22 @@ recheck:
 	 * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
 	 * SCHED_BATCH and SCHED_IDLE is 0.
 	 */
-	if (param->sched_priority < 0 ||
-	    (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) ||
-	    (!p->mm && param->sched_priority > MAX_RT_PRIO-1))
+	if (attr->sched_priority < 0 ||
+	    (p->mm && attr->sched_priority > MAX_USER_RT_PRIO-1) ||
+	    (!p->mm && attr->sched_priority > MAX_RT_PRIO-1))
 		return -EINVAL;
-	if (rt_policy(policy) != (param->sched_priority != 0))
+	if (rt_policy(policy) != (attr->sched_priority != 0))
 		return -EINVAL;
 
 	/*
 	 * Allow unprivileged RT tasks to decrease priority:
 	 */
 	if (user && !capable(CAP_SYS_NICE)) {
+		if (fair_policy(policy)) {
+			if (!can_nice(p, attr->sched_nice))
+				return -EPERM;
+		}
+
 		if (rt_policy(policy)) {
 			unsigned long rlim_rtprio =
 					task_rlimit(p, RLIMIT_RTPRIO);
@@ -3074,8 +3089,8 @@ recheck:
 				return -EPERM;
 
 			/* can't increase priority */
-			if (param->sched_priority > p->rt_priority &&
-			    param->sched_priority > rlim_rtprio)
+			if (attr->sched_priority > p->rt_priority &&
+			    attr->sched_priority > rlim_rtprio)
 				return -EPERM;
 		}
 
@@ -3123,11 +3138,16 @@ recheck:
 	/*
 	 * If not changing anything there's no need to proceed further:
 	 */
-	if (unlikely(policy == p->policy && (!rt_policy(policy) ||
-			param->sched_priority == p->rt_priority))) {
+	if (unlikely(policy == p->policy)) {
+		if (fair_policy(policy) && attr->sched_nice != TASK_NICE(p))
+			goto change;
+		if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
+			goto change;
+
 		task_rq_unlock(rq, p, &flags);
 		return 0;
 	}
+change:
 
 #ifdef CONFIG_RT_GROUP_SCHED
 	if (user) {
@@ -3161,7 +3181,7 @@ recheck:
 
 	oldprio = p->prio;
 	prev_class = p->sched_class;
-	__setscheduler(rq, p, policy, param->sched_priority);
+	__setscheduler(rq, p, attr);
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
@@ -3189,10 +3209,20 @@ recheck:
 int sched_setscheduler(struct task_struct *p, int policy,
 		       const struct sched_param *param)
 {
-	return __sched_setscheduler(p, policy, param, true);
+	struct sched_attr attr = {
+		.sched_policy   = policy,
+		.sched_priority = param->sched_priority
+	};
+	return __sched_setscheduler(p, &attr, true);
 }
 EXPORT_SYMBOL_GPL(sched_setscheduler);
 
+int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
+{
+	return __sched_setscheduler(p, attr, true);
+}
+EXPORT_SYMBOL_GPL(sched_setattr);
+
 /**
  * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
  * @p: the task in question.
@@ -3209,7 +3239,11 @@ EXPORT_SYMBOL_GPL(sched_setscheduler);
 int sched_setscheduler_nocheck(struct task_struct *p, int policy,
 			       const struct sched_param *param)
 {
-	return __sched_setscheduler(p, policy, param, false);
+	struct sched_attr attr = {
+		.sched_policy   = policy,
+		.sched_priority = param->sched_priority
+	};
+	return __sched_setscheduler(p, &attr, false);
 }
 
 static int
@@ -3234,6 +3268,79 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
 	return retval;
 }
 
+/*
+ * Mimics kernel/events/core.c perf_copy_attr().
+ */
+static int sched_copy_attr(struct sched_attr __user *uattr,
+			   struct sched_attr *attr)
+{
+	u32 size;
+	int ret;
+
+	if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0))
+		return -EFAULT;
+
+	/*
+	 * zero the full structure, so that a short copy will be nice.
+	 */
+	memset(attr, 0, sizeof(*attr));
+
+	ret = get_user(size, &uattr->size);
+	if (ret)
+		return ret;
+
+	if (size > PAGE_SIZE)	/* silly large */
+		goto err_size;
+
+	if (!size)		/* abi compat */
+		size = SCHED_ATTR_SIZE_VER0;
+
+	if (size < SCHED_ATTR_SIZE_VER0)
+		goto err_size;
+
+	/*
+	 * If we're handed a bigger struct than we know of,
+	 * ensure all the unknown bits are 0 - i.e. new
+	 * user-space does not rely on any kernel feature
+	 * extensions we dont know about yet.
+	 */
+	if (size > sizeof(*attr)) {
+		unsigned char __user *addr;
+		unsigned char __user *end;
+		unsigned char val;
+
+		addr = (void __user *)uattr + sizeof(*attr);
+		end  = (void __user *)uattr + size;
+
+		for (; addr < end; addr++) {
+			ret = get_user(val, addr);
+			if (ret)
+				return ret;
+			if (val)
+				goto err_size;
+		}
+		size = sizeof(*attr);
+	}
+
+	ret = copy_from_user(attr, uattr, size);
+	if (ret)
+		return -EFAULT;
+
+	/*
+	 * XXX: do we want to be lenient like existing syscalls; or do we want
+	 * to be strict and return an error on out-of-bounds values?
+	 */
+	attr->sched_nice = clamp(attr->sched_nice, -20, 19);
+
+out:
+	return ret;
+
+err_size:
+	put_user(sizeof(*attr), &uattr->size);
+	ret = -E2BIG;
+	goto out;
+}
+
 /**
  * sys_sched_setscheduler - set/change the scheduler policy and RT priority
  * @pid: the pid in question.
@@ -3265,6 +3372,33 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
 }
 
 /**
+ * sys_sched_setattr - same as above, but with extended sched_attr
+ * @pid: the pid in question.
+ * @attr: structure containing the extended parameters.
+ */
+SYSCALL_DEFINE2(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr)
+{
+	struct sched_attr attr;
+	struct task_struct *p;
+	int retval;
+
+	if (!uattr || pid < 0)
+		return -EINVAL;
+
+	if (sched_copy_attr(uattr, &attr))
+		return -EFAULT;
+
+	rcu_read_lock();
+	retval = -ESRCH;
+	p = find_process_by_pid(pid);
+	if (p != NULL)
+		retval = sched_setattr(p, &attr);
+	rcu_read_unlock();
+
+	return retval;
+}
+
+/**
  * sys_sched_getscheduler - get the policy (scheduling class) of a thread
  * @pid: the pid in question.
  *
@@ -3334,6 +3468,92 @@ out_unlock:
 	return retval;
 }
 
+static int sched_read_attr(struct sched_attr __user *uattr,
+			   struct sched_attr *attr,
+			   unsigned int usize)
+{
+	int ret;
+
+	if (!access_ok(VERIFY_WRITE, uattr, usize))
+		return -EFAULT;
+
+	/*
+	 * If we're handed a smaller struct than we know of,
+	 * ensure all the unknown bits are 0 - i.e. old
+	 * user-space does not get uncomplete information.
+	 */
+	if (usize < sizeof(*attr)) {
+		unsigned char *addr;
+		unsigned char *end;
+
+		addr = (void *)attr + usize;
+		end  = (void *)attr + sizeof(*attr);
+
+		for (; addr < end; addr++) {
+			if (*addr)
+				goto err_size;
+		}
+
+		attr->size = usize;
+	}
+
+	ret = copy_to_user(uattr, attr, usize);
+	if (ret)
+		return -EFAULT;
+
+out:
+	return ret;
+
+err_size:
+	ret = -E2BIG;
+	goto out;
+}
+
+/**
+ * sys_sched_getattr - same as above, but with extended "sched_param"
+ * @pid: the pid in question.
+ * @attr: structure containing the extended parameters.
+ * @size: sizeof(attr) for fwd/bwd comp.
+ */
+SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
+		unsigned int, size)
+{
+	struct sched_attr attr = {
+		.size = sizeof(struct sched_attr),
+	};
+	struct task_struct *p;
+	int retval;
+
+	if (!uattr || pid < 0 || size > PAGE_SIZE ||
+	    size < SCHED_ATTR_SIZE_VER0)
+		return -EINVAL;
+
+	rcu_read_lock();
+	p = find_process_by_pid(pid);
+	retval = -ESRCH;
+	if (!p)
+		goto out_unlock;
+
+	retval = security_task_getscheduler(p);
+	if (retval)
+		goto out_unlock;
+
+	attr.sched_policy = p->policy;
+	if (task_has_rt_policy(p))
+		attr.sched_priority = p->rt_priority;
+	else
+		attr.sched_nice = TASK_NICE(p);
+
+	rcu_read_unlock();
+
+	retval = sched_read_attr(uattr, &attr, size);
+	return retval;
+
+out_unlock:
+	rcu_read_unlock();
+	return retval;
+}
+
 long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 {
 	cpumask_var_t cpus_allowed, new_mask;
@@ -6400,13 +6620,16 @@ EXPORT_SYMBOL(__might_sleep);
 static void normalize_task(struct rq *rq, struct task_struct *p)
 {
 	const struct sched_class *prev_class = p->sched_class;
+	struct sched_attr attr = {
+		.sched_policy = SCHED_NORMAL,
+	};
 	int old_prio = p->prio;
 	int on_rq;
 
 	on_rq = p->on_rq;
 	if (on_rq)
 		dequeue_task(rq, p, 0);
-	__setscheduler(rq, p, SCHED_NORMAL, 0);
+	__setscheduler(rq, p, &attr);
 	if (on_rq) {
 		enqueue_task(rq, p, 0);
 		resched_task(rq->curr);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b3b4a49..df023db 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -81,11 +81,14 @@ extern void update_cpu_load_active(struct rq *this_rq);
  */
 #define RUNTIME_INF	((u64)~0ULL)
 
+static inline int fair_policy(int policy)
+{
+	return policy == SCHED_NORMAL || policy == SCHED_BATCH;
+}
+
 static inline int rt_policy(int policy)
 {
-	if (policy == SCHED_FIFO || policy == SCHED_RR)
-		return 1;
-	return 0;
+	return policy == SCHED_FIFO || policy == SCHED_RR;
 }
 
 static inline int task_has_rt_policy(struct task_struct *p)
-- 
cgit v0.10.2


From aab03e05e8f7e26f51dee792beddcb5cca9215a5 Mon Sep 17 00:00:00 2001
From: Dario Faggioli <raistlin@linux.it>
Date: Thu, 28 Nov 2013 11:14:43 +0100
Subject: sched/deadline: Add SCHED_DEADLINE structures & implementation

Introduces the data structures, constants and symbols needed for
SCHED_DEADLINE implementation.

Core data structure of SCHED_DEADLINE are defined, along with their
initializers. Hooks for checking if a task belong to the new policy
are also added where they are needed.

Adds a scheduling class, in sched/dl.c and a new policy called
SCHED_DEADLINE. It is an implementation of the Earliest Deadline
First (EDF) scheduling algorithm, augmented with a mechanism (called
Constant Bandwidth Server, CBS) that makes it possible to isolate
the behaviour of tasks between each other.

The typical -deadline task will be made up of a computation phase
(instance) which is activated on a periodic or sporadic fashion. The
expected (maximum) duration of such computation is called the task's
runtime; the time interval by which each instance need to be completed
is called the task's relative deadline. The task's absolute deadline
is dynamically calculated as the time instant a task (better, an
instance) activates plus the relative deadline.

The EDF algorithms selects the task with the smallest absolute
deadline as the one to be executed first, while the CBS ensures each
task to run for at most its runtime every (relative) deadline
length time interval, avoiding any interference between different
tasks (bandwidth isolation).
Thanks to this feature, also tasks that do not strictly comply with
the computational model sketched above can effectively use the new
policy.

To summarize, this patch:
 - introduces the data structures, constants and symbols needed;
 - implements the core logic of the scheduling algorithm in the new
   scheduling class file;
 - provides all the glue code between the new scheduling class and
   the core scheduler and refines the interactions between sched/dl
   and the other existing scheduling classes.

Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Michael Trimarchi <michael@amarulasolutions.com>
Signed-off-by: Fabio Checconi <fchecconi@gmail.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-4-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 86025b6..6c19679 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -97,6 +97,10 @@ struct sched_param {
  * Given this task model, there are a multiplicity of scheduling algorithms
  * and policies, that can be used to ensure all the tasks will make their
  * timing constraints.
+ *
+ * As of now, the SCHED_DEADLINE policy (sched_dl scheduling class) is the
+ * only user of this new interface. More information about the algorithm
+ * available in the scheduling class file or in Documentation/.
  */
 struct sched_attr {
 	u32 size;
@@ -1088,6 +1092,45 @@ struct sched_rt_entity {
 #endif
 };
 
+struct sched_dl_entity {
+	struct rb_node	rb_node;
+
+	/*
+	 * Original scheduling parameters. Copied here from sched_attr
+	 * during sched_setscheduler2(), they will remain the same until
+	 * the next sched_setscheduler2().
+	 */
+	u64 dl_runtime;		/* maximum runtime for each instance	*/
+	u64 dl_deadline;	/* relative deadline of each instance	*/
+
+	/*
+	 * Actual scheduling parameters. Initialized with the values above,
+	 * they are continously updated during task execution. Note that
+	 * the remaining runtime could be < 0 in case we are in overrun.
+	 */
+	s64 runtime;		/* remaining runtime for this instance	*/
+	u64 deadline;		/* absolute deadline for this instance	*/
+	unsigned int flags;	/* specifying the scheduler behaviour	*/
+
+	/*
+	 * Some bool flags:
+	 *
+	 * @dl_throttled tells if we exhausted the runtime. If so, the
+	 * task has to wait for a replenishment to be performed at the
+	 * next firing of dl_timer.
+	 *
+	 * @dl_new tells if a new instance arrived. If so we must
+	 * start executing it with full runtime and reset its absolute
+	 * deadline;
+	 */
+	int dl_throttled, dl_new;
+
+	/*
+	 * Bandwidth enforcement timer. Each -deadline task has its
+	 * own bandwidth to be enforced, thus we need one timer per task.
+	 */
+	struct hrtimer dl_timer;
+};
 
 struct rcu_node;
 
@@ -1124,6 +1167,7 @@ struct task_struct {
 #ifdef CONFIG_CGROUP_SCHED
 	struct task_group *sched_task_group;
 #endif
+	struct sched_dl_entity dl;
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 	/* list of struct preempt_notifier: */
@@ -2099,7 +2143,7 @@ extern void wake_up_new_task(struct task_struct *tsk);
 #else
  static inline void kick_process(struct task_struct *tsk) { }
 #endif
-extern void sched_fork(unsigned long clone_flags, struct task_struct *p);
+extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
 extern void sched_dead(struct task_struct *p);
 
 extern void proc_caches_init(void);
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
new file mode 100644
index 0000000..9d303b8
--- /dev/null
+++ b/include/linux/sched/deadline.h
@@ -0,0 +1,24 @@
+#ifndef _SCHED_DEADLINE_H
+#define _SCHED_DEADLINE_H
+
+/*
+ * SCHED_DEADLINE tasks has negative priorities, reflecting
+ * the fact that any of them has higher prio than RT and
+ * NORMAL/BATCH tasks.
+ */
+
+#define MAX_DL_PRIO		0
+
+static inline int dl_prio(int prio)
+{
+	if (unlikely(prio < MAX_DL_PRIO))
+		return 1;
+	return 0;
+}
+
+static inline int dl_task(struct task_struct *p)
+{
+	return dl_prio(p->prio);
+}
+
+#endif /* _SCHED_DEADLINE_H */
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 5a0f945..2d5e49a 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -39,6 +39,7 @@
 #define SCHED_BATCH		3
 /* SCHED_ISO: reserved but not implemented yet */
 #define SCHED_IDLE		5
+#define SCHED_DEADLINE		6
 /* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
 #define SCHED_RESET_ON_FORK     0x40000000
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 6023d15..e6c0f1a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1311,7 +1311,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
-	sched_fork(clone_flags, p);
+	retval = sched_fork(clone_flags, p);
+	if (retval)
+		goto bad_fork_cleanup_policy;
 
 	retval = perf_event_init_task(p);
 	if (retval)
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 383319b..0909436 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -46,6 +46,7 @@
 #include <linux/sched.h>
 #include <linux/sched/sysctl.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
 #include <linux/timer.h>
 #include <linux/freezer.h>
 
@@ -1610,7 +1611,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
 	unsigned long slack;
 
 	slack = current->timer_slack_ns;
-	if (rt_task(current))
+	if (dl_task(current) || rt_task(current))
 		slack = 0;
 
 	hrtimer_init_on_stack(&t.timer, clockid, mode);
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 7b62140..b039035 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -11,7 +11,8 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
 endif
 
-obj-y += core.o proc.o clock.o cputime.o idle_task.o fair.o rt.o stop_task.o
+obj-y += core.o proc.o clock.o cputime.o
+obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
 obj-y += wait.o completion.o
 obj-$(CONFIG_SMP) += cpupri.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8174f88..203aecd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -899,7 +899,9 @@ static inline int normal_prio(struct task_struct *p)
 {
 	int prio;
 
-	if (task_has_rt_policy(p))
+	if (task_has_dl_policy(p))
+		prio = MAX_DL_PRIO-1;
+	else if (task_has_rt_policy(p))
 		prio = MAX_RT_PRIO-1 - p->rt_priority;
 	else
 		prio = __normal_prio(p);
@@ -1717,6 +1719,12 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
 #endif
 
+	RB_CLEAR_NODE(&p->dl.rb_node);
+	hrtimer_init(&p->dl.dl_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	p->dl.dl_runtime = p->dl.runtime = 0;
+	p->dl.dl_deadline = p->dl.deadline = 0;
+	p->dl.flags = 0;
+
 	INIT_LIST_HEAD(&p->rt.run_list);
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
@@ -1768,7 +1776,7 @@ void set_numabalancing_state(bool enabled)
 /*
  * fork()/clone()-time setup:
  */
-void sched_fork(unsigned long clone_flags, struct task_struct *p)
+int sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
 	unsigned long flags;
 	int cpu = get_cpu();
@@ -1790,7 +1798,7 @@ void sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 * Revert to default priority/policy on fork if requested.
 	 */
 	if (unlikely(p->sched_reset_on_fork)) {
-		if (task_has_rt_policy(p)) {
+		if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
 			p->policy = SCHED_NORMAL;
 			p->static_prio = NICE_TO_PRIO(0);
 			p->rt_priority = 0;
@@ -1807,8 +1815,14 @@ void sched_fork(unsigned long clone_flags, struct task_struct *p)
 		p->sched_reset_on_fork = 0;
 	}
 
-	if (!rt_prio(p->prio))
+	if (dl_prio(p->prio)) {
+		put_cpu();
+		return -EAGAIN;
+	} else if (rt_prio(p->prio)) {
+		p->sched_class = &rt_sched_class;
+	} else {
 		p->sched_class = &fair_sched_class;
+	}
 
 	if (p->sched_class->task_fork)
 		p->sched_class->task_fork(p);
@@ -1837,6 +1851,7 @@ void sched_fork(unsigned long clone_flags, struct task_struct *p)
 #endif
 
 	put_cpu();
+	return 0;
 }
 
 /*
@@ -2768,7 +2783,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	struct rq *rq;
 	const struct sched_class *prev_class;
 
-	BUG_ON(prio < 0 || prio > MAX_PRIO);
+	BUG_ON(prio > MAX_PRIO);
 
 	rq = __task_rq_lock(p);
 
@@ -2800,7 +2815,9 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	if (running)
 		p->sched_class->put_prev_task(rq, p);
 
-	if (rt_prio(prio))
+	if (dl_prio(prio))
+		p->sched_class = &dl_sched_class;
+	else if (rt_prio(prio))
 		p->sched_class = &rt_sched_class;
 	else
 		p->sched_class = &fair_sched_class;
@@ -2835,9 +2852,9 @@ void set_user_nice(struct task_struct *p, long nice)
 	 * The RT priorities are set via sched_setscheduler(), but we still
 	 * allow the 'normal' nice value to be set - but as expected
 	 * it wont have any effect on scheduling until the task is
-	 * SCHED_FIFO/SCHED_RR:
+	 * SCHED_DEADLINE, SCHED_FIFO or SCHED_RR:
 	 */
-	if (task_has_rt_policy(p)) {
+	if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
 		p->static_prio = NICE_TO_PRIO(nice);
 		goto out_unlock;
 	}
@@ -2992,6 +3009,27 @@ static struct task_struct *find_process_by_pid(pid_t pid)
 	return pid ? find_task_by_vpid(pid) : current;
 }
 
+/*
+ * This function initializes the sched_dl_entity of a newly becoming
+ * SCHED_DEADLINE task.
+ *
+ * Only the static values are considered here, the actual runtime and the
+ * absolute deadline will be properly calculated when the task is enqueued
+ * for the first time with its new policy.
+ */
+static void
+__setparam_dl(struct task_struct *p, const struct sched_attr *attr)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+
+	init_dl_task_timer(dl_se);
+	dl_se->dl_runtime = attr->sched_runtime;
+	dl_se->dl_deadline = attr->sched_deadline;
+	dl_se->flags = attr->sched_flags;
+	dl_se->dl_throttled = 0;
+	dl_se->dl_new = 1;
+}
+
 /* Actually do priority change: must hold pi & rq lock. */
 static void __setscheduler(struct rq *rq, struct task_struct *p,
 			   const struct sched_attr *attr)
@@ -3000,7 +3038,9 @@ static void __setscheduler(struct rq *rq, struct task_struct *p,
 
 	p->policy = policy;
 
-	if (rt_policy(policy))
+	if (dl_policy(policy))
+		__setparam_dl(p, attr);
+	else if (rt_policy(policy))
 		p->rt_priority = attr->sched_priority;
 	else
 		p->static_prio = NICE_TO_PRIO(attr->sched_nice);
@@ -3008,13 +3048,39 @@ static void __setscheduler(struct rq *rq, struct task_struct *p,
 	p->normal_prio = normal_prio(p);
 	p->prio = rt_mutex_getprio(p);
 
-	if (rt_prio(p->prio))
+	if (dl_prio(p->prio))
+		p->sched_class = &dl_sched_class;
+	else if (rt_prio(p->prio))
 		p->sched_class = &rt_sched_class;
 	else
 		p->sched_class = &fair_sched_class;
 
 	set_load_weight(p);
 }
+
+static void
+__getparam_dl(struct task_struct *p, struct sched_attr *attr)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+
+	attr->sched_priority = p->rt_priority;
+	attr->sched_runtime = dl_se->dl_runtime;
+	attr->sched_deadline = dl_se->dl_deadline;
+	attr->sched_flags = dl_se->flags;
+}
+
+/*
+ * This function validates the new parameters of a -deadline task.
+ * We ask for the deadline not being zero, and greater or equal
+ * than the runtime.
+ */
+static bool
+__checkparam_dl(const struct sched_attr *attr)
+{
+	return attr && attr->sched_deadline != 0 &&
+	       (s64)(attr->sched_deadline - attr->sched_runtime) >= 0;
+}
+
 /*
  * check the target process has a UID that matches the current process's
  */
@@ -3053,7 +3119,8 @@ recheck:
 		reset_on_fork = !!(policy & SCHED_RESET_ON_FORK);
 		policy &= ~SCHED_RESET_ON_FORK;
 
-		if (policy != SCHED_FIFO && policy != SCHED_RR &&
+		if (policy != SCHED_DEADLINE &&
+				policy != SCHED_FIFO && policy != SCHED_RR &&
 				policy != SCHED_NORMAL && policy != SCHED_BATCH &&
 				policy != SCHED_IDLE)
 			return -EINVAL;
@@ -3068,7 +3135,8 @@ recheck:
 	    (p->mm && attr->sched_priority > MAX_USER_RT_PRIO-1) ||
 	    (!p->mm && attr->sched_priority > MAX_RT_PRIO-1))
 		return -EINVAL;
-	if (rt_policy(policy) != (attr->sched_priority != 0))
+	if ((dl_policy(policy) && !__checkparam_dl(attr)) ||
+	    (rt_policy(policy) != (attr->sched_priority != 0)))
 		return -EINVAL;
 
 	/*
@@ -3143,6 +3211,8 @@ recheck:
 			goto change;
 		if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
 			goto change;
+		if (dl_policy(policy))
+			goto change;
 
 		task_rq_unlock(rq, p, &flags);
 		return 0;
@@ -3453,6 +3523,10 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
 	if (retval)
 		goto out_unlock;
 
+	if (task_has_dl_policy(p)) {
+		retval = -EINVAL;
+		goto out_unlock;
+	}
 	lp.sched_priority = p->rt_priority;
 	rcu_read_unlock();
 
@@ -3510,7 +3584,7 @@ err_size:
 }
 
 /**
- * sys_sched_getattr - same as above, but with extended "sched_param"
+ * sys_sched_getattr - similar to sched_getparam, but with sched_attr
  * @pid: the pid in question.
  * @attr: structure containing the extended parameters.
  * @size: sizeof(attr) for fwd/bwd comp.
@@ -3539,7 +3613,9 @@ SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 		goto out_unlock;
 
 	attr.sched_policy = p->policy;
-	if (task_has_rt_policy(p))
+	if (task_has_dl_policy(p))
+		__getparam_dl(p, &attr);
+	else if (task_has_rt_policy(p))
 		attr.sched_priority = p->rt_priority;
 	else
 		attr.sched_nice = TASK_NICE(p);
@@ -3965,6 +4041,7 @@ SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
 	case SCHED_RR:
 		ret = MAX_USER_RT_PRIO-1;
 		break;
+	case SCHED_DEADLINE:
 	case SCHED_NORMAL:
 	case SCHED_BATCH:
 	case SCHED_IDLE:
@@ -3991,6 +4068,7 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
 	case SCHED_RR:
 		ret = 1;
 		break;
+	case SCHED_DEADLINE:
 	case SCHED_NORMAL:
 	case SCHED_BATCH:
 	case SCHED_IDLE:
@@ -6472,6 +6550,7 @@ void __init sched_init(void)
 		rq->calc_load_update = jiffies + LOAD_FREQ;
 		init_cfs_rq(&rq->cfs);
 		init_rt_rq(&rq->rt, rq);
+		init_dl_rq(&rq->dl, rq);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 		root_task_group.shares = ROOT_TASK_GROUP_LOAD;
 		INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
@@ -6659,7 +6738,7 @@ void normalize_rt_tasks(void)
 		p->se.statistics.block_start	= 0;
 #endif
 
-		if (!rt_task(p)) {
+		if (!dl_task(p) && !rt_task(p)) {
 			/*
 			 * Renice negative nice level userspace
 			 * tasks back to 0:
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
new file mode 100644
index 0000000..93d82b2
--- /dev/null
+++ b/kernel/sched/deadline.c
@@ -0,0 +1,684 @@
+/*
+ * Deadline Scheduling Class (SCHED_DEADLINE)
+ *
+ * Earliest Deadline First (EDF) + Constant Bandwidth Server (CBS).
+ *
+ * Tasks that periodically executes their instances for less than their
+ * runtime won't miss any of their deadlines.
+ * Tasks that are not periodic or sporadic or that tries to execute more
+ * than their reserved bandwidth will be slowed down (and may potentially
+ * miss some of their deadlines), and won't affect any other task.
+ *
+ * Copyright (C) 2012 Dario Faggioli <raistlin@linux.it>,
+ *                    Michael Trimarchi <michael@amarulasolutions.com>,
+ *                    Fabio Checconi <fchecconi@gmail.com>
+ */
+#include "sched.h"
+
+static inline int dl_time_before(u64 a, u64 b)
+{
+	return (s64)(a - b) < 0;
+}
+
+static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
+{
+	return container_of(dl_se, struct task_struct, dl);
+}
+
+static inline struct rq *rq_of_dl_rq(struct dl_rq *dl_rq)
+{
+	return container_of(dl_rq, struct rq, dl);
+}
+
+static inline struct dl_rq *dl_rq_of_se(struct sched_dl_entity *dl_se)
+{
+	struct task_struct *p = dl_task_of(dl_se);
+	struct rq *rq = task_rq(p);
+
+	return &rq->dl;
+}
+
+static inline int on_dl_rq(struct sched_dl_entity *dl_se)
+{
+	return !RB_EMPTY_NODE(&dl_se->rb_node);
+}
+
+static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+
+	return dl_rq->rb_leftmost == &dl_se->rb_node;
+}
+
+void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq)
+{
+	dl_rq->rb_root = RB_ROOT;
+}
+
+static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
+static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags);
+static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
+				  int flags);
+
+/*
+ * We are being explicitly informed that a new instance is starting,
+ * and this means that:
+ *  - the absolute deadline of the entity has to be placed at
+ *    current time + relative deadline;
+ *  - the runtime of the entity has to be set to the maximum value.
+ *
+ * The capability of specifying such event is useful whenever a -deadline
+ * entity wants to (try to!) synchronize its behaviour with the scheduler's
+ * one, and to (try to!) reconcile itself with its own scheduling
+ * parameters.
+ */
+static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se)
+{
+	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+	struct rq *rq = rq_of_dl_rq(dl_rq);
+
+	WARN_ON(!dl_se->dl_new || dl_se->dl_throttled);
+
+	/*
+	 * We use the regular wall clock time to set deadlines in the
+	 * future; in fact, we must consider execution overheads (time
+	 * spent on hardirq context, etc.).
+	 */
+	dl_se->deadline = rq_clock(rq) + dl_se->dl_deadline;
+	dl_se->runtime = dl_se->dl_runtime;
+	dl_se->dl_new = 0;
+}
+
+/*
+ * Pure Earliest Deadline First (EDF) scheduling does not deal with the
+ * possibility of a entity lasting more than what it declared, and thus
+ * exhausting its runtime.
+ *
+ * Here we are interested in making runtime overrun possible, but we do
+ * not want a entity which is misbehaving to affect the scheduling of all
+ * other entities.
+ * Therefore, a budgeting strategy called Constant Bandwidth Server (CBS)
+ * is used, in order to confine each entity within its own bandwidth.
+ *
+ * This function deals exactly with that, and ensures that when the runtime
+ * of a entity is replenished, its deadline is also postponed. That ensures
+ * the overrunning entity can't interfere with other entity in the system and
+ * can't make them miss their deadlines. Reasons why this kind of overruns
+ * could happen are, typically, a entity voluntarily trying to overcome its
+ * runtime, or it just underestimated it during sched_setscheduler_ex().
+ */
+static void replenish_dl_entity(struct sched_dl_entity *dl_se)
+{
+	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+	struct rq *rq = rq_of_dl_rq(dl_rq);
+
+	/*
+	 * We keep moving the deadline away until we get some
+	 * available runtime for the entity. This ensures correct
+	 * handling of situations where the runtime overrun is
+	 * arbitrary large.
+	 */
+	while (dl_se->runtime <= 0) {
+		dl_se->deadline += dl_se->dl_deadline;
+		dl_se->runtime += dl_se->dl_runtime;
+	}
+
+	/*
+	 * At this point, the deadline really should be "in
+	 * the future" with respect to rq->clock. If it's
+	 * not, we are, for some reason, lagging too much!
+	 * Anyway, after having warn userspace abut that,
+	 * we still try to keep the things running by
+	 * resetting the deadline and the budget of the
+	 * entity.
+	 */
+	if (dl_time_before(dl_se->deadline, rq_clock(rq))) {
+		static bool lag_once = false;
+
+		if (!lag_once) {
+			lag_once = true;
+			printk_sched("sched: DL replenish lagged to much\n");
+		}
+		dl_se->deadline = rq_clock(rq) + dl_se->dl_deadline;
+		dl_se->runtime = dl_se->dl_runtime;
+	}
+}
+
+/*
+ * Here we check if --at time t-- an entity (which is probably being
+ * [re]activated or, in general, enqueued) can use its remaining runtime
+ * and its current deadline _without_ exceeding the bandwidth it is
+ * assigned (function returns true if it can't). We are in fact applying
+ * one of the CBS rules: when a task wakes up, if the residual runtime
+ * over residual deadline fits within the allocated bandwidth, then we
+ * can keep the current (absolute) deadline and residual budget without
+ * disrupting the schedulability of the system. Otherwise, we should
+ * refill the runtime and set the deadline a period in the future,
+ * because keeping the current (absolute) deadline of the task would
+ * result in breaking guarantees promised to other tasks.
+ *
+ * This function returns true if:
+ *
+ *   runtime / (deadline - t) > dl_runtime / dl_deadline ,
+ *
+ * IOW we can't recycle current parameters.
+ */
+static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t)
+{
+	u64 left, right;
+
+	/*
+	 * left and right are the two sides of the equation above,
+	 * after a bit of shuffling to use multiplications instead
+	 * of divisions.
+	 *
+	 * Note that none of the time values involved in the two
+	 * multiplications are absolute: dl_deadline and dl_runtime
+	 * are the relative deadline and the maximum runtime of each
+	 * instance, runtime is the runtime left for the last instance
+	 * and (deadline - t), since t is rq->clock, is the time left
+	 * to the (absolute) deadline. Even if overflowing the u64 type
+	 * is very unlikely to occur in both cases, here we scale down
+	 * as we want to avoid that risk at all. Scaling down by 10
+	 * means that we reduce granularity to 1us. We are fine with it,
+	 * since this is only a true/false check and, anyway, thinking
+	 * of anything below microseconds resolution is actually fiction
+	 * (but still we want to give the user that illusion >;).
+	 */
+	left = (dl_se->dl_deadline >> 10) * (dl_se->runtime >> 10);
+	right = ((dl_se->deadline - t) >> 10) * (dl_se->dl_runtime >> 10);
+
+	return dl_time_before(right, left);
+}
+
+/*
+ * When a -deadline entity is queued back on the runqueue, its runtime and
+ * deadline might need updating.
+ *
+ * The policy here is that we update the deadline of the entity only if:
+ *  - the current deadline is in the past,
+ *  - using the remaining runtime with the current deadline would make
+ *    the entity exceed its bandwidth.
+ */
+static void update_dl_entity(struct sched_dl_entity *dl_se)
+{
+	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+	struct rq *rq = rq_of_dl_rq(dl_rq);
+
+	/*
+	 * The arrival of a new instance needs special treatment, i.e.,
+	 * the actual scheduling parameters have to be "renewed".
+	 */
+	if (dl_se->dl_new) {
+		setup_new_dl_entity(dl_se);
+		return;
+	}
+
+	if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
+	    dl_entity_overflow(dl_se, rq_clock(rq))) {
+		dl_se->deadline = rq_clock(rq) + dl_se->dl_deadline;
+		dl_se->runtime = dl_se->dl_runtime;
+	}
+}
+
+/*
+ * If the entity depleted all its runtime, and if we want it to sleep
+ * while waiting for some new execution time to become available, we
+ * set the bandwidth enforcement timer to the replenishment instant
+ * and try to activate it.
+ *
+ * Notice that it is important for the caller to know if the timer
+ * actually started or not (i.e., the replenishment instant is in
+ * the future or in the past).
+ */
+static int start_dl_timer(struct sched_dl_entity *dl_se)
+{
+	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+	struct rq *rq = rq_of_dl_rq(dl_rq);
+	ktime_t now, act;
+	ktime_t soft, hard;
+	unsigned long range;
+	s64 delta;
+
+	/*
+	 * We want the timer to fire at the deadline, but considering
+	 * that it is actually coming from rq->clock and not from
+	 * hrtimer's time base reading.
+	 */
+	act = ns_to_ktime(dl_se->deadline);
+	now = hrtimer_cb_get_time(&dl_se->dl_timer);
+	delta = ktime_to_ns(now) - rq_clock(rq);
+	act = ktime_add_ns(act, delta);
+
+	/*
+	 * If the expiry time already passed, e.g., because the value
+	 * chosen as the deadline is too small, don't even try to
+	 * start the timer in the past!
+	 */
+	if (ktime_us_delta(act, now) < 0)
+		return 0;
+
+	hrtimer_set_expires(&dl_se->dl_timer, act);
+
+	soft = hrtimer_get_softexpires(&dl_se->dl_timer);
+	hard = hrtimer_get_expires(&dl_se->dl_timer);
+	range = ktime_to_ns(ktime_sub(hard, soft));
+	__hrtimer_start_range_ns(&dl_se->dl_timer, soft,
+				 range, HRTIMER_MODE_ABS, 0);
+
+	return hrtimer_active(&dl_se->dl_timer);
+}
+
+/*
+ * This is the bandwidth enforcement timer callback. If here, we know
+ * a task is not on its dl_rq, since the fact that the timer was running
+ * means the task is throttled and needs a runtime replenishment.
+ *
+ * However, what we actually do depends on the fact the task is active,
+ * (it is on its rq) or has been removed from there by a call to
+ * dequeue_task_dl(). In the former case we must issue the runtime
+ * replenishment and add the task back to the dl_rq; in the latter, we just
+ * do nothing but clearing dl_throttled, so that runtime and deadline
+ * updating (and the queueing back to dl_rq) will be done by the
+ * next call to enqueue_task_dl().
+ */
+static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
+{
+	struct sched_dl_entity *dl_se = container_of(timer,
+						     struct sched_dl_entity,
+						     dl_timer);
+	struct task_struct *p = dl_task_of(dl_se);
+	struct rq *rq = task_rq(p);
+	raw_spin_lock(&rq->lock);
+
+	/*
+	 * We need to take care of a possible races here. In fact, the
+	 * task might have changed its scheduling policy to something
+	 * different from SCHED_DEADLINE or changed its reservation
+	 * parameters (through sched_setscheduler()).
+	 */
+	if (!dl_task(p) || dl_se->dl_new)
+		goto unlock;
+
+	sched_clock_tick();
+	update_rq_clock(rq);
+	dl_se->dl_throttled = 0;
+	if (p->on_rq) {
+		enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
+		if (task_has_dl_policy(rq->curr))
+			check_preempt_curr_dl(rq, p, 0);
+		else
+			resched_task(rq->curr);
+	}
+unlock:
+	raw_spin_unlock(&rq->lock);
+
+	return HRTIMER_NORESTART;
+}
+
+void init_dl_task_timer(struct sched_dl_entity *dl_se)
+{
+	struct hrtimer *timer = &dl_se->dl_timer;
+
+	if (hrtimer_active(timer)) {
+		hrtimer_try_to_cancel(timer);
+		return;
+	}
+
+	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	timer->function = dl_task_timer;
+}
+
+static
+int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
+{
+	int dmiss = dl_time_before(dl_se->deadline, rq_clock(rq));
+	int rorun = dl_se->runtime <= 0;
+
+	if (!rorun && !dmiss)
+		return 0;
+
+	/*
+	 * If we are beyond our current deadline and we are still
+	 * executing, then we have already used some of the runtime of
+	 * the next instance. Thus, if we do not account that, we are
+	 * stealing bandwidth from the system at each deadline miss!
+	 */
+	if (dmiss) {
+		dl_se->runtime = rorun ? dl_se->runtime : 0;
+		dl_se->runtime -= rq_clock(rq) - dl_se->deadline;
+	}
+
+	return 1;
+}
+
+/*
+ * Update the current task's runtime statistics (provided it is still
+ * a -deadline task and has not been removed from the dl_rq).
+ */
+static void update_curr_dl(struct rq *rq)
+{
+	struct task_struct *curr = rq->curr;
+	struct sched_dl_entity *dl_se = &curr->dl;
+	u64 delta_exec;
+
+	if (!dl_task(curr) || !on_dl_rq(dl_se))
+		return;
+
+	/*
+	 * Consumed budget is computed considering the time as
+	 * observed by schedulable tasks (excluding time spent
+	 * in hardirq context, etc.). Deadlines are instead
+	 * computed using hard walltime. This seems to be the more
+	 * natural solution, but the full ramifications of this
+	 * approach need further study.
+	 */
+	delta_exec = rq_clock_task(rq) - curr->se.exec_start;
+	if (unlikely((s64)delta_exec < 0))
+		delta_exec = 0;
+
+	schedstat_set(curr->se.statistics.exec_max,
+		      max(curr->se.statistics.exec_max, delta_exec));
+
+	curr->se.sum_exec_runtime += delta_exec;
+	account_group_exec_runtime(curr, delta_exec);
+
+	curr->se.exec_start = rq_clock_task(rq);
+	cpuacct_charge(curr, delta_exec);
+
+	dl_se->runtime -= delta_exec;
+	if (dl_runtime_exceeded(rq, dl_se)) {
+		__dequeue_task_dl(rq, curr, 0);
+		if (likely(start_dl_timer(dl_se)))
+			dl_se->dl_throttled = 1;
+		else
+			enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
+
+		if (!is_leftmost(curr, &rq->dl))
+			resched_task(curr);
+	}
+}
+
+static void __enqueue_dl_entity(struct sched_dl_entity *dl_se)
+{
+	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+	struct rb_node **link = &dl_rq->rb_root.rb_node;
+	struct rb_node *parent = NULL;
+	struct sched_dl_entity *entry;
+	int leftmost = 1;
+
+	BUG_ON(!RB_EMPTY_NODE(&dl_se->rb_node));
+
+	while (*link) {
+		parent = *link;
+		entry = rb_entry(parent, struct sched_dl_entity, rb_node);
+		if (dl_time_before(dl_se->deadline, entry->deadline))
+			link = &parent->rb_left;
+		else {
+			link = &parent->rb_right;
+			leftmost = 0;
+		}
+	}
+
+	if (leftmost)
+		dl_rq->rb_leftmost = &dl_se->rb_node;
+
+	rb_link_node(&dl_se->rb_node, parent, link);
+	rb_insert_color(&dl_se->rb_node, &dl_rq->rb_root);
+
+	dl_rq->dl_nr_running++;
+}
+
+static void __dequeue_dl_entity(struct sched_dl_entity *dl_se)
+{
+	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+
+	if (RB_EMPTY_NODE(&dl_se->rb_node))
+		return;
+
+	if (dl_rq->rb_leftmost == &dl_se->rb_node) {
+		struct rb_node *next_node;
+
+		next_node = rb_next(&dl_se->rb_node);
+		dl_rq->rb_leftmost = next_node;
+	}
+
+	rb_erase(&dl_se->rb_node, &dl_rq->rb_root);
+	RB_CLEAR_NODE(&dl_se->rb_node);
+
+	dl_rq->dl_nr_running--;
+}
+
+static void
+enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
+{
+	BUG_ON(on_dl_rq(dl_se));
+
+	/*
+	 * If this is a wakeup or a new instance, the scheduling
+	 * parameters of the task might need updating. Otherwise,
+	 * we want a replenishment of its runtime.
+	 */
+	if (!dl_se->dl_new && flags & ENQUEUE_REPLENISH)
+		replenish_dl_entity(dl_se);
+	else
+		update_dl_entity(dl_se);
+
+	__enqueue_dl_entity(dl_se);
+}
+
+static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
+{
+	__dequeue_dl_entity(dl_se);
+}
+
+static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
+{
+	/*
+	 * If p is throttled, we do nothing. In fact, if it exhausted
+	 * its budget it needs a replenishment and, since it now is on
+	 * its rq, the bandwidth timer callback (which clearly has not
+	 * run yet) will take care of this.
+	 */
+	if (p->dl.dl_throttled)
+		return;
+
+	enqueue_dl_entity(&p->dl, flags);
+	inc_nr_running(rq);
+}
+
+static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
+{
+	dequeue_dl_entity(&p->dl);
+}
+
+static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
+{
+	update_curr_dl(rq);
+	__dequeue_task_dl(rq, p, flags);
+
+	dec_nr_running(rq);
+}
+
+/*
+ * Yield task semantic for -deadline tasks is:
+ *
+ *   get off from the CPU until our next instance, with
+ *   a new runtime. This is of little use now, since we
+ *   don't have a bandwidth reclaiming mechanism. Anyway,
+ *   bandwidth reclaiming is planned for the future, and
+ *   yield_task_dl will indicate that some spare budget
+ *   is available for other task instances to use it.
+ */
+static void yield_task_dl(struct rq *rq)
+{
+	struct task_struct *p = rq->curr;
+
+	/*
+	 * We make the task go to sleep until its current deadline by
+	 * forcing its runtime to zero. This way, update_curr_dl() stops
+	 * it and the bandwidth timer will wake it up and will give it
+	 * new scheduling parameters (thanks to dl_new=1).
+	 */
+	if (p->dl.runtime > 0) {
+		rq->curr->dl.dl_new = 1;
+		p->dl.runtime = 0;
+	}
+	update_curr_dl(rq);
+}
+
+/*
+ * Only called when both the current and waking task are -deadline
+ * tasks.
+ */
+static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
+				  int flags)
+{
+	if (dl_time_before(p->dl.deadline, rq->curr->dl.deadline))
+		resched_task(rq->curr);
+}
+
+#ifdef CONFIG_SCHED_HRTICK
+static void start_hrtick_dl(struct rq *rq, struct task_struct *p)
+{
+	s64 delta = p->dl.dl_runtime - p->dl.runtime;
+
+	if (delta > 10000)
+		hrtick_start(rq, p->dl.runtime);
+}
+#endif
+
+static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
+						   struct dl_rq *dl_rq)
+{
+	struct rb_node *left = dl_rq->rb_leftmost;
+
+	if (!left)
+		return NULL;
+
+	return rb_entry(left, struct sched_dl_entity, rb_node);
+}
+
+struct task_struct *pick_next_task_dl(struct rq *rq)
+{
+	struct sched_dl_entity *dl_se;
+	struct task_struct *p;
+	struct dl_rq *dl_rq;
+
+	dl_rq = &rq->dl;
+
+	if (unlikely(!dl_rq->dl_nr_running))
+		return NULL;
+
+	dl_se = pick_next_dl_entity(rq, dl_rq);
+	BUG_ON(!dl_se);
+
+	p = dl_task_of(dl_se);
+	p->se.exec_start = rq_clock_task(rq);
+#ifdef CONFIG_SCHED_HRTICK
+	if (hrtick_enabled(rq))
+		start_hrtick_dl(rq, p);
+#endif
+	return p;
+}
+
+static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
+{
+	update_curr_dl(rq);
+}
+
+static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
+{
+	update_curr_dl(rq);
+
+#ifdef CONFIG_SCHED_HRTICK
+	if (hrtick_enabled(rq) && queued && p->dl.runtime > 0)
+		start_hrtick_dl(rq, p);
+#endif
+}
+
+static void task_fork_dl(struct task_struct *p)
+{
+	/*
+	 * SCHED_DEADLINE tasks cannot fork and this is achieved through
+	 * sched_fork()
+	 */
+}
+
+static void task_dead_dl(struct task_struct *p)
+{
+	struct hrtimer *timer = &p->dl.dl_timer;
+
+	if (hrtimer_active(timer))
+		hrtimer_try_to_cancel(timer);
+}
+
+static void set_curr_task_dl(struct rq *rq)
+{
+	struct task_struct *p = rq->curr;
+
+	p->se.exec_start = rq_clock_task(rq);
+}
+
+static void switched_from_dl(struct rq *rq, struct task_struct *p)
+{
+	if (hrtimer_active(&p->dl.dl_timer))
+		hrtimer_try_to_cancel(&p->dl.dl_timer);
+}
+
+static void switched_to_dl(struct rq *rq, struct task_struct *p)
+{
+	/*
+	 * If p is throttled, don't consider the possibility
+	 * of preempting rq->curr, the check will be done right
+	 * after its runtime will get replenished.
+	 */
+	if (unlikely(p->dl.dl_throttled))
+		return;
+
+	if (p->on_rq || rq->curr != p) {
+		if (task_has_dl_policy(rq->curr))
+			check_preempt_curr_dl(rq, p, 0);
+		else
+			resched_task(rq->curr);
+	}
+}
+
+static void prio_changed_dl(struct rq *rq, struct task_struct *p,
+			    int oldprio)
+{
+	switched_to_dl(rq, p);
+}
+
+#ifdef CONFIG_SMP
+static int
+select_task_rq_dl(struct task_struct *p, int prev_cpu, int sd_flag, int flags)
+{
+	return task_cpu(p);
+}
+#endif
+
+const struct sched_class dl_sched_class = {
+	.next			= &rt_sched_class,
+	.enqueue_task		= enqueue_task_dl,
+	.dequeue_task		= dequeue_task_dl,
+	.yield_task		= yield_task_dl,
+
+	.check_preempt_curr	= check_preempt_curr_dl,
+
+	.pick_next_task		= pick_next_task_dl,
+	.put_prev_task		= put_prev_task_dl,
+
+#ifdef CONFIG_SMP
+	.select_task_rq		= select_task_rq_dl,
+#endif
+
+	.set_curr_task		= set_curr_task_dl,
+	.task_tick		= task_tick_dl,
+	.task_fork              = task_fork_dl,
+	.task_dead		= task_dead_dl,
+
+	.prio_changed           = prio_changed_dl,
+	.switched_from		= switched_from_dl,
+	.switched_to		= switched_to_dl,
+};
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index df023db..83eb539 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2,6 +2,7 @@
 #include <linux/sched.h>
 #include <linux/sched/sysctl.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/stop_machine.h>
@@ -91,11 +92,21 @@ static inline int rt_policy(int policy)
 	return policy == SCHED_FIFO || policy == SCHED_RR;
 }
 
+static inline int dl_policy(int policy)
+{
+	return policy == SCHED_DEADLINE;
+}
+
 static inline int task_has_rt_policy(struct task_struct *p)
 {
 	return rt_policy(p->policy);
 }
 
+static inline int task_has_dl_policy(struct task_struct *p)
+{
+	return dl_policy(p->policy);
+}
+
 /*
  * This is the priority-queue data structure of the RT scheduling class:
  */
@@ -367,6 +378,15 @@ struct rt_rq {
 #endif
 };
 
+/* Deadline class' related fields in a runqueue */
+struct dl_rq {
+	/* runqueue is an rbtree, ordered by deadline */
+	struct rb_root rb_root;
+	struct rb_node *rb_leftmost;
+
+	unsigned long dl_nr_running;
+};
+
 #ifdef CONFIG_SMP
 
 /*
@@ -435,6 +455,7 @@ struct rq {
 
 	struct cfs_rq cfs;
 	struct rt_rq rt;
+	struct dl_rq dl;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* list of leaf cfs_rq on this cpu: */
@@ -991,6 +1012,7 @@ static const u32 prio_to_wmult[40] = {
 #else
 #define ENQUEUE_WAKING		0
 #endif
+#define ENQUEUE_REPLENISH	8
 
 #define DEQUEUE_SLEEP		1
 
@@ -1046,6 +1068,7 @@ struct sched_class {
    for (class = sched_class_highest; class; class = class->next)
 
 extern const struct sched_class stop_sched_class;
+extern const struct sched_class dl_sched_class;
 extern const struct sched_class rt_sched_class;
 extern const struct sched_class fair_sched_class;
 extern const struct sched_class idle_sched_class;
@@ -1081,6 +1104,8 @@ extern void resched_cpu(int cpu);
 extern struct rt_bandwidth def_rt_bandwidth;
 extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
 
+extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
+
 extern void update_idle_cpu_load(struct rq *this_rq);
 
 extern void init_task_runnable_average(struct task_struct *p);
@@ -1357,6 +1382,7 @@ extern void print_rt_stats(struct seq_file *m, int cpu);
 
 extern void init_cfs_rq(struct cfs_rq *cfs_rq);
 extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq);
+extern void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq);
 
 extern void cfs_bandwidth_usage_inc(void);
 extern void cfs_bandwidth_usage_dec(void);
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 47197de..fdb6bb0 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -103,7 +103,7 @@ get_rr_interval_stop(struct rq *rq, struct task_struct *task)
  * Simple, special scheduling class for the per-CPU stop tasks:
  */
 const struct sched_class stop_sched_class = {
-	.next			= &rt_sched_class,
+	.next			= &dl_sched_class,
 
 	.enqueue_task		= enqueue_task_stop,
 	.dequeue_task		= dequeue_task_stop,
-- 
cgit v0.10.2


From 1baca4ce16b8cc7d4f50be1f7914799af30a2861 Mon Sep 17 00:00:00 2001
From: Juri Lelli <juri.lelli@gmail.com>
Date: Thu, 7 Nov 2013 14:43:38 +0100
Subject: sched/deadline: Add SCHED_DEADLINE SMP-related data structures &
 logic

Introduces data structures relevant for implementing dynamic
migration of -deadline tasks and the logic for checking if
runqueues are overloaded with -deadline tasks and for choosing
where a task should migrate, when it is the case.

Adds also dynamic migrations to SCHED_DEADLINE, so that tasks can
be moved among CPUs when necessary. It is also possible to bind a
task to a (set of) CPU(s), thus restricting its capability of
migrating, or forbidding migrations at all.

The very same approach used in sched_rt is utilised:
 - -deadline tasks are kept into CPU-specific runqueues,
 - -deadline tasks are migrated among runqueues to achieve the
   following:
    * on an M-CPU system the M earliest deadline ready tasks
      are always running;
    * affinity/cpusets settings of all the -deadline tasks is
      always respected.

Therefore, this very special form of "load balancing" is done with
an active method, i.e., the scheduler pushes or pulls tasks between
runqueues when they are woken up and/or (de)scheduled.
IOW, every time a preemption occurs, the descheduled task might be sent
to some other CPU (depending on its deadline) to continue executing
(push). On the other hand, every time a CPU becomes idle, it might pull
the second earliest deadline ready task from some other CPU.

To enforce this, a pull operation is always attempted before taking any
scheduling decision (pre_schedule()), as well as a push one after each
scheduling decision (post_schedule()). In addition, when a task arrives
or wakes up, the best CPU where to resume it is selected taking into
account its affinity mask, the system topology, but also its deadline.
E.g., from the scheduling point of view, the best CPU where to wake
up (and also where to push) a task is the one which is running the task
with the latest deadline among the M executing ones.

In order to facilitate these decisions, per-runqueue "caching" of the
deadlines of the currently running and of the first ready task is used.
Queued but not running tasks are also parked in another rb-tree to
speed-up pushes.

Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-5-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6c19679..cc66f26 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1201,6 +1201,7 @@ struct task_struct {
 	struct list_head tasks;
 #ifdef CONFIG_SMP
 	struct plist_node pushable_tasks;
+	struct rb_node pushable_dl_tasks;
 #endif
 
 	struct mm_struct *mm, *active_mm;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 203aecd..548cc04 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1848,6 +1848,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	init_task_preempt_count(p);
 #ifdef CONFIG_SMP
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
+	RB_CLEAR_NODE(&p->pushable_dl_tasks);
 #endif
 
 	put_cpu();
@@ -5040,6 +5041,7 @@ static void free_rootdomain(struct rcu_head *rcu)
 	struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
 
 	cpupri_cleanup(&rd->cpupri);
+	free_cpumask_var(rd->dlo_mask);
 	free_cpumask_var(rd->rto_mask);
 	free_cpumask_var(rd->online);
 	free_cpumask_var(rd->span);
@@ -5091,8 +5093,10 @@ static int init_rootdomain(struct root_domain *rd)
 		goto out;
 	if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
 		goto free_span;
-	if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+	if (!alloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
 		goto free_online;
+	if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+		goto free_dlo_mask;
 
 	if (cpupri_init(&rd->cpupri) != 0)
 		goto free_rto_mask;
@@ -5100,6 +5104,8 @@ static int init_rootdomain(struct root_domain *rd)
 
 free_rto_mask:
 	free_cpumask_var(rd->rto_mask);
+free_dlo_mask:
+	free_cpumask_var(rd->dlo_mask);
 free_online:
 	free_cpumask_var(rd->online);
 free_span:
@@ -6451,6 +6457,7 @@ void __init sched_init_smp(void)
 	free_cpumask_var(non_isolated_cpus);
 
 	init_sched_rt_class();
+	init_sched_dl_class();
 }
 #else
 void __init sched_init_smp(void)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 93d82b2..fcc02c9 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -10,6 +10,7 @@
  * miss some of their deadlines), and won't affect any other task.
  *
  * Copyright (C) 2012 Dario Faggioli <raistlin@linux.it>,
+ *                    Juri Lelli <juri.lelli@gmail.com>,
  *                    Michael Trimarchi <michael@amarulasolutions.com>,
  *                    Fabio Checconi <fchecconi@gmail.com>
  */
@@ -20,6 +21,15 @@ static inline int dl_time_before(u64 a, u64 b)
 	return (s64)(a - b) < 0;
 }
 
+/*
+ * Tells if entity @a should preempt entity @b.
+ */
+static inline
+int dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b)
+{
+	return dl_time_before(a->deadline, b->deadline);
+}
+
 static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
 {
 	return container_of(dl_se, struct task_struct, dl);
@@ -53,8 +63,168 @@ static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
 void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq)
 {
 	dl_rq->rb_root = RB_ROOT;
+
+#ifdef CONFIG_SMP
+	/* zero means no -deadline tasks */
+	dl_rq->earliest_dl.curr = dl_rq->earliest_dl.next = 0;
+
+	dl_rq->dl_nr_migratory = 0;
+	dl_rq->overloaded = 0;
+	dl_rq->pushable_dl_tasks_root = RB_ROOT;
+#endif
+}
+
+#ifdef CONFIG_SMP
+
+static inline int dl_overloaded(struct rq *rq)
+{
+	return atomic_read(&rq->rd->dlo_count);
+}
+
+static inline void dl_set_overload(struct rq *rq)
+{
+	if (!rq->online)
+		return;
+
+	cpumask_set_cpu(rq->cpu, rq->rd->dlo_mask);
+	/*
+	 * Must be visible before the overload count is
+	 * set (as in sched_rt.c).
+	 *
+	 * Matched by the barrier in pull_dl_task().
+	 */
+	smp_wmb();
+	atomic_inc(&rq->rd->dlo_count);
+}
+
+static inline void dl_clear_overload(struct rq *rq)
+{
+	if (!rq->online)
+		return;
+
+	atomic_dec(&rq->rd->dlo_count);
+	cpumask_clear_cpu(rq->cpu, rq->rd->dlo_mask);
+}
+
+static void update_dl_migration(struct dl_rq *dl_rq)
+{
+	if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_total > 1) {
+		if (!dl_rq->overloaded) {
+			dl_set_overload(rq_of_dl_rq(dl_rq));
+			dl_rq->overloaded = 1;
+		}
+	} else if (dl_rq->overloaded) {
+		dl_clear_overload(rq_of_dl_rq(dl_rq));
+		dl_rq->overloaded = 0;
+	}
+}
+
+static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+	struct task_struct *p = dl_task_of(dl_se);
+	dl_rq = &rq_of_dl_rq(dl_rq)->dl;
+
+	dl_rq->dl_nr_total++;
+	if (p->nr_cpus_allowed > 1)
+		dl_rq->dl_nr_migratory++;
+
+	update_dl_migration(dl_rq);
+}
+
+static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+	struct task_struct *p = dl_task_of(dl_se);
+	dl_rq = &rq_of_dl_rq(dl_rq)->dl;
+
+	dl_rq->dl_nr_total--;
+	if (p->nr_cpus_allowed > 1)
+		dl_rq->dl_nr_migratory--;
+
+	update_dl_migration(dl_rq);
+}
+
+/*
+ * The list of pushable -deadline task is not a plist, like in
+ * sched_rt.c, it is an rb-tree with tasks ordered by deadline.
+ */
+static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+	struct dl_rq *dl_rq = &rq->dl;
+	struct rb_node **link = &dl_rq->pushable_dl_tasks_root.rb_node;
+	struct rb_node *parent = NULL;
+	struct task_struct *entry;
+	int leftmost = 1;
+
+	BUG_ON(!RB_EMPTY_NODE(&p->pushable_dl_tasks));
+
+	while (*link) {
+		parent = *link;
+		entry = rb_entry(parent, struct task_struct,
+				 pushable_dl_tasks);
+		if (dl_entity_preempt(&p->dl, &entry->dl))
+			link = &parent->rb_left;
+		else {
+			link = &parent->rb_right;
+			leftmost = 0;
+		}
+	}
+
+	if (leftmost)
+		dl_rq->pushable_dl_tasks_leftmost = &p->pushable_dl_tasks;
+
+	rb_link_node(&p->pushable_dl_tasks, parent, link);
+	rb_insert_color(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
 }
 
+static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+	struct dl_rq *dl_rq = &rq->dl;
+
+	if (RB_EMPTY_NODE(&p->pushable_dl_tasks))
+		return;
+
+	if (dl_rq->pushable_dl_tasks_leftmost == &p->pushable_dl_tasks) {
+		struct rb_node *next_node;
+
+		next_node = rb_next(&p->pushable_dl_tasks);
+		dl_rq->pushable_dl_tasks_leftmost = next_node;
+	}
+
+	rb_erase(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
+	RB_CLEAR_NODE(&p->pushable_dl_tasks);
+}
+
+static inline int has_pushable_dl_tasks(struct rq *rq)
+{
+	return !RB_EMPTY_ROOT(&rq->dl.pushable_dl_tasks_root);
+}
+
+static int push_dl_task(struct rq *rq);
+
+#else
+
+static inline
+void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+}
+
+static inline
+void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+}
+
+static inline
+void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+}
+
+static inline
+void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+}
+
+#endif /* CONFIG_SMP */
+
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
 static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags);
 static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
@@ -309,6 +479,14 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 			check_preempt_curr_dl(rq, p, 0);
 		else
 			resched_task(rq->curr);
+#ifdef CONFIG_SMP
+		/*
+		 * Queueing this task back might have overloaded rq,
+		 * check if we need to kick someone away.
+		 */
+		if (has_pushable_dl_tasks(rq))
+			push_dl_task(rq);
+#endif
 	}
 unlock:
 	raw_spin_unlock(&rq->lock);
@@ -399,6 +577,100 @@ static void update_curr_dl(struct rq *rq)
 	}
 }
 
+#ifdef CONFIG_SMP
+
+static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu);
+
+static inline u64 next_deadline(struct rq *rq)
+{
+	struct task_struct *next = pick_next_earliest_dl_task(rq, rq->cpu);
+
+	if (next && dl_prio(next->prio))
+		return next->dl.deadline;
+	else
+		return 0;
+}
+
+static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
+{
+	struct rq *rq = rq_of_dl_rq(dl_rq);
+
+	if (dl_rq->earliest_dl.curr == 0 ||
+	    dl_time_before(deadline, dl_rq->earliest_dl.curr)) {
+		/*
+		 * If the dl_rq had no -deadline tasks, or if the new task
+		 * has shorter deadline than the current one on dl_rq, we
+		 * know that the previous earliest becomes our next earliest,
+		 * as the new task becomes the earliest itself.
+		 */
+		dl_rq->earliest_dl.next = dl_rq->earliest_dl.curr;
+		dl_rq->earliest_dl.curr = deadline;
+	} else if (dl_rq->earliest_dl.next == 0 ||
+		   dl_time_before(deadline, dl_rq->earliest_dl.next)) {
+		/*
+		 * On the other hand, if the new -deadline task has a
+		 * a later deadline than the earliest one on dl_rq, but
+		 * it is earlier than the next (if any), we must
+		 * recompute the next-earliest.
+		 */
+		dl_rq->earliest_dl.next = next_deadline(rq);
+	}
+}
+
+static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
+{
+	struct rq *rq = rq_of_dl_rq(dl_rq);
+
+	/*
+	 * Since we may have removed our earliest (and/or next earliest)
+	 * task we must recompute them.
+	 */
+	if (!dl_rq->dl_nr_running) {
+		dl_rq->earliest_dl.curr = 0;
+		dl_rq->earliest_dl.next = 0;
+	} else {
+		struct rb_node *leftmost = dl_rq->rb_leftmost;
+		struct sched_dl_entity *entry;
+
+		entry = rb_entry(leftmost, struct sched_dl_entity, rb_node);
+		dl_rq->earliest_dl.curr = entry->deadline;
+		dl_rq->earliest_dl.next = next_deadline(rq);
+	}
+}
+
+#else
+
+static inline void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {}
+static inline void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {}
+
+#endif /* CONFIG_SMP */
+
+static inline
+void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+	int prio = dl_task_of(dl_se)->prio;
+	u64 deadline = dl_se->deadline;
+
+	WARN_ON(!dl_prio(prio));
+	dl_rq->dl_nr_running++;
+
+	inc_dl_deadline(dl_rq, deadline);
+	inc_dl_migration(dl_se, dl_rq);
+}
+
+static inline
+void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+	int prio = dl_task_of(dl_se)->prio;
+
+	WARN_ON(!dl_prio(prio));
+	WARN_ON(!dl_rq->dl_nr_running);
+	dl_rq->dl_nr_running--;
+
+	dec_dl_deadline(dl_rq, dl_se->deadline);
+	dec_dl_migration(dl_se, dl_rq);
+}
+
 static void __enqueue_dl_entity(struct sched_dl_entity *dl_se)
 {
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
@@ -426,7 +698,7 @@ static void __enqueue_dl_entity(struct sched_dl_entity *dl_se)
 	rb_link_node(&dl_se->rb_node, parent, link);
 	rb_insert_color(&dl_se->rb_node, &dl_rq->rb_root);
 
-	dl_rq->dl_nr_running++;
+	inc_dl_tasks(dl_se, dl_rq);
 }
 
 static void __dequeue_dl_entity(struct sched_dl_entity *dl_se)
@@ -446,7 +718,7 @@ static void __dequeue_dl_entity(struct sched_dl_entity *dl_se)
 	rb_erase(&dl_se->rb_node, &dl_rq->rb_root);
 	RB_CLEAR_NODE(&dl_se->rb_node);
 
-	dl_rq->dl_nr_running--;
+	dec_dl_tasks(dl_se, dl_rq);
 }
 
 static void
@@ -484,12 +756,17 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 		return;
 
 	enqueue_dl_entity(&p->dl, flags);
+
+	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
+		enqueue_pushable_dl_task(rq, p);
+
 	inc_nr_running(rq);
 }
 
 static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
 	dequeue_dl_entity(&p->dl);
+	dequeue_pushable_dl_task(rq, p);
 }
 
 static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
@@ -527,6 +804,74 @@ static void yield_task_dl(struct rq *rq)
 	update_curr_dl(rq);
 }
 
+#ifdef CONFIG_SMP
+
+static int find_later_rq(struct task_struct *task);
+static int latest_cpu_find(struct cpumask *span,
+			   struct task_struct *task,
+			   struct cpumask *later_mask);
+
+static int
+select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
+{
+	struct task_struct *curr;
+	struct rq *rq;
+
+	if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
+		goto out;
+
+	rq = cpu_rq(cpu);
+
+	rcu_read_lock();
+	curr = ACCESS_ONCE(rq->curr); /* unlocked access */
+
+	/*
+	 * If we are dealing with a -deadline task, we must
+	 * decide where to wake it up.
+	 * If it has a later deadline and the current task
+	 * on this rq can't move (provided the waking task
+	 * can!) we prefer to send it somewhere else. On the
+	 * other hand, if it has a shorter deadline, we
+	 * try to make it stay here, it might be important.
+	 */
+	if (unlikely(dl_task(curr)) &&
+	    (curr->nr_cpus_allowed < 2 ||
+	     !dl_entity_preempt(&p->dl, &curr->dl)) &&
+	    (p->nr_cpus_allowed > 1)) {
+		int target = find_later_rq(p);
+
+		if (target != -1)
+			cpu = target;
+	}
+	rcu_read_unlock();
+
+out:
+	return cpu;
+}
+
+static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
+{
+	/*
+	 * Current can't be migrated, useless to reschedule,
+	 * let's hope p can move out.
+	 */
+	if (rq->curr->nr_cpus_allowed == 1 ||
+	    latest_cpu_find(rq->rd->span, rq->curr, NULL) == -1)
+		return;
+
+	/*
+	 * p is migratable, so let's not schedule it and
+	 * see if it is pushed or pulled somewhere else.
+	 */
+	if (p->nr_cpus_allowed != 1 &&
+	    latest_cpu_find(rq->rd->span, p, NULL) != -1)
+		return;
+
+	resched_task(rq->curr);
+}
+
+#endif /* CONFIG_SMP */
+
 /*
  * Only called when both the current and waking task are -deadline
  * tasks.
@@ -534,8 +879,20 @@ static void yield_task_dl(struct rq *rq)
 static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
 				  int flags)
 {
-	if (dl_time_before(p->dl.deadline, rq->curr->dl.deadline))
+	if (dl_entity_preempt(&p->dl, &rq->curr->dl)) {
 		resched_task(rq->curr);
+		return;
+	}
+
+#ifdef CONFIG_SMP
+	/*
+	 * In the unlikely case current and p have the same deadline
+	 * let us try to decide what's the best thing to do...
+	 */
+	if ((s64)(p->dl.deadline - rq->curr->dl.deadline) == 0 &&
+	    !need_resched())
+		check_preempt_equal_dl(rq, p);
+#endif /* CONFIG_SMP */
 }
 
 #ifdef CONFIG_SCHED_HRTICK
@@ -575,16 +932,29 @@ struct task_struct *pick_next_task_dl(struct rq *rq)
 
 	p = dl_task_of(dl_se);
 	p->se.exec_start = rq_clock_task(rq);
+
+	/* Running task will never be pushed. */
+	if (p)
+		dequeue_pushable_dl_task(rq, p);
+
 #ifdef CONFIG_SCHED_HRTICK
 	if (hrtick_enabled(rq))
 		start_hrtick_dl(rq, p);
 #endif
+
+#ifdef CONFIG_SMP
+	rq->post_schedule = has_pushable_dl_tasks(rq);
+#endif /* CONFIG_SMP */
+
 	return p;
 }
 
 static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
 {
 	update_curr_dl(rq);
+
+	if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
+		enqueue_pushable_dl_task(rq, p);
 }
 
 static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
@@ -618,16 +988,517 @@ static void set_curr_task_dl(struct rq *rq)
 	struct task_struct *p = rq->curr;
 
 	p->se.exec_start = rq_clock_task(rq);
+
+	/* You can't push away the running task */
+	dequeue_pushable_dl_task(rq, p);
+}
+
+#ifdef CONFIG_SMP
+
+/* Only try algorithms three times */
+#define DL_MAX_TRIES 3
+
+static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
+{
+	if (!task_running(rq, p) &&
+	    (cpu < 0 || cpumask_test_cpu(cpu, &p->cpus_allowed)) &&
+	    (p->nr_cpus_allowed > 1))
+		return 1;
+
+	return 0;
+}
+
+/* Returns the second earliest -deadline task, NULL otherwise */
+static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu)
+{
+	struct rb_node *next_node = rq->dl.rb_leftmost;
+	struct sched_dl_entity *dl_se;
+	struct task_struct *p = NULL;
+
+next_node:
+	next_node = rb_next(next_node);
+	if (next_node) {
+		dl_se = rb_entry(next_node, struct sched_dl_entity, rb_node);
+		p = dl_task_of(dl_se);
+
+		if (pick_dl_task(rq, p, cpu))
+			return p;
+
+		goto next_node;
+	}
+
+	return NULL;
+}
+
+static int latest_cpu_find(struct cpumask *span,
+			   struct task_struct *task,
+			   struct cpumask *later_mask)
+{
+	const struct sched_dl_entity *dl_se = &task->dl;
+	int cpu, found = -1, best = 0;
+	u64 max_dl = 0;
+
+	for_each_cpu(cpu, span) {
+		struct rq *rq = cpu_rq(cpu);
+		struct dl_rq *dl_rq = &rq->dl;
+
+		if (cpumask_test_cpu(cpu, &task->cpus_allowed) &&
+		    (!dl_rq->dl_nr_running || dl_time_before(dl_se->deadline,
+		     dl_rq->earliest_dl.curr))) {
+			if (later_mask)
+				cpumask_set_cpu(cpu, later_mask);
+			if (!best && !dl_rq->dl_nr_running) {
+				best = 1;
+				found = cpu;
+			} else if (!best &&
+				   dl_time_before(max_dl,
+						  dl_rq->earliest_dl.curr)) {
+				max_dl = dl_rq->earliest_dl.curr;
+				found = cpu;
+			}
+		} else if (later_mask)
+			cpumask_clear_cpu(cpu, later_mask);
+	}
+
+	return found;
+}
+
+static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
+
+static int find_later_rq(struct task_struct *task)
+{
+	struct sched_domain *sd;
+	struct cpumask *later_mask = __get_cpu_var(local_cpu_mask_dl);
+	int this_cpu = smp_processor_id();
+	int best_cpu, cpu = task_cpu(task);
+
+	/* Make sure the mask is initialized first */
+	if (unlikely(!later_mask))
+		return -1;
+
+	if (task->nr_cpus_allowed == 1)
+		return -1;
+
+	best_cpu = latest_cpu_find(task_rq(task)->rd->span, task, later_mask);
+	if (best_cpu == -1)
+		return -1;
+
+	/*
+	 * If we are here, some target has been found,
+	 * the most suitable of which is cached in best_cpu.
+	 * This is, among the runqueues where the current tasks
+	 * have later deadlines than the task's one, the rq
+	 * with the latest possible one.
+	 *
+	 * Now we check how well this matches with task's
+	 * affinity and system topology.
+	 *
+	 * The last cpu where the task run is our first
+	 * guess, since it is most likely cache-hot there.
+	 */
+	if (cpumask_test_cpu(cpu, later_mask))
+		return cpu;
+	/*
+	 * Check if this_cpu is to be skipped (i.e., it is
+	 * not in the mask) or not.
+	 */
+	if (!cpumask_test_cpu(this_cpu, later_mask))
+		this_cpu = -1;
+
+	rcu_read_lock();
+	for_each_domain(cpu, sd) {
+		if (sd->flags & SD_WAKE_AFFINE) {
+
+			/*
+			 * If possible, preempting this_cpu is
+			 * cheaper than migrating.
+			 */
+			if (this_cpu != -1 &&
+			    cpumask_test_cpu(this_cpu, sched_domain_span(sd))) {
+				rcu_read_unlock();
+				return this_cpu;
+			}
+
+			/*
+			 * Last chance: if best_cpu is valid and is
+			 * in the mask, that becomes our choice.
+			 */
+			if (best_cpu < nr_cpu_ids &&
+			    cpumask_test_cpu(best_cpu, sched_domain_span(sd))) {
+				rcu_read_unlock();
+				return best_cpu;
+			}
+		}
+	}
+	rcu_read_unlock();
+
+	/*
+	 * At this point, all our guesses failed, we just return
+	 * 'something', and let the caller sort the things out.
+	 */
+	if (this_cpu != -1)
+		return this_cpu;
+
+	cpu = cpumask_any(later_mask);
+	if (cpu < nr_cpu_ids)
+		return cpu;
+
+	return -1;
+}
+
+/* Locks the rq it finds */
+static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
+{
+	struct rq *later_rq = NULL;
+	int tries;
+	int cpu;
+
+	for (tries = 0; tries < DL_MAX_TRIES; tries++) {
+		cpu = find_later_rq(task);
+
+		if ((cpu == -1) || (cpu == rq->cpu))
+			break;
+
+		later_rq = cpu_rq(cpu);
+
+		/* Retry if something changed. */
+		if (double_lock_balance(rq, later_rq)) {
+			if (unlikely(task_rq(task) != rq ||
+				     !cpumask_test_cpu(later_rq->cpu,
+				                       &task->cpus_allowed) ||
+				     task_running(rq, task) || !task->on_rq)) {
+				double_unlock_balance(rq, later_rq);
+				later_rq = NULL;
+				break;
+			}
+		}
+
+		/*
+		 * If the rq we found has no -deadline task, or
+		 * its earliest one has a later deadline than our
+		 * task, the rq is a good one.
+		 */
+		if (!later_rq->dl.dl_nr_running ||
+		    dl_time_before(task->dl.deadline,
+				   later_rq->dl.earliest_dl.curr))
+			break;
+
+		/* Otherwise we try again. */
+		double_unlock_balance(rq, later_rq);
+		later_rq = NULL;
+	}
+
+	return later_rq;
+}
+
+static struct task_struct *pick_next_pushable_dl_task(struct rq *rq)
+{
+	struct task_struct *p;
+
+	if (!has_pushable_dl_tasks(rq))
+		return NULL;
+
+	p = rb_entry(rq->dl.pushable_dl_tasks_leftmost,
+		     struct task_struct, pushable_dl_tasks);
+
+	BUG_ON(rq->cpu != task_cpu(p));
+	BUG_ON(task_current(rq, p));
+	BUG_ON(p->nr_cpus_allowed <= 1);
+
+	BUG_ON(!p->se.on_rq);
+	BUG_ON(!dl_task(p));
+
+	return p;
+}
+
+/*
+ * See if the non running -deadline tasks on this rq
+ * can be sent to some other CPU where they can preempt
+ * and start executing.
+ */
+static int push_dl_task(struct rq *rq)
+{
+	struct task_struct *next_task;
+	struct rq *later_rq;
+
+	if (!rq->dl.overloaded)
+		return 0;
+
+	next_task = pick_next_pushable_dl_task(rq);
+	if (!next_task)
+		return 0;
+
+retry:
+	if (unlikely(next_task == rq->curr)) {
+		WARN_ON(1);
+		return 0;
+	}
+
+	/*
+	 * If next_task preempts rq->curr, and rq->curr
+	 * can move away, it makes sense to just reschedule
+	 * without going further in pushing next_task.
+	 */
+	if (dl_task(rq->curr) &&
+	    dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) &&
+	    rq->curr->nr_cpus_allowed > 1) {
+		resched_task(rq->curr);
+		return 0;
+	}
+
+	/* We might release rq lock */
+	get_task_struct(next_task);
+
+	/* Will lock the rq it'll find */
+	later_rq = find_lock_later_rq(next_task, rq);
+	if (!later_rq) {
+		struct task_struct *task;
+
+		/*
+		 * We must check all this again, since
+		 * find_lock_later_rq releases rq->lock and it is
+		 * then possible that next_task has migrated.
+		 */
+		task = pick_next_pushable_dl_task(rq);
+		if (task_cpu(next_task) == rq->cpu && task == next_task) {
+			/*
+			 * The task is still there. We don't try
+			 * again, some other cpu will pull it when ready.
+			 */
+			dequeue_pushable_dl_task(rq, next_task);
+			goto out;
+		}
+
+		if (!task)
+			/* No more tasks */
+			goto out;
+
+		put_task_struct(next_task);
+		next_task = task;
+		goto retry;
+	}
+
+	deactivate_task(rq, next_task, 0);
+	set_task_cpu(next_task, later_rq->cpu);
+	activate_task(later_rq, next_task, 0);
+
+	resched_task(later_rq->curr);
+
+	double_unlock_balance(rq, later_rq);
+
+out:
+	put_task_struct(next_task);
+
+	return 1;
+}
+
+static void push_dl_tasks(struct rq *rq)
+{
+	/* Terminates as it moves a -deadline task */
+	while (push_dl_task(rq))
+		;
 }
 
+static int pull_dl_task(struct rq *this_rq)
+{
+	int this_cpu = this_rq->cpu, ret = 0, cpu;
+	struct task_struct *p;
+	struct rq *src_rq;
+	u64 dmin = LONG_MAX;
+
+	if (likely(!dl_overloaded(this_rq)))
+		return 0;
+
+	/*
+	 * Match the barrier from dl_set_overloaded; this guarantees that if we
+	 * see overloaded we must also see the dlo_mask bit.
+	 */
+	smp_rmb();
+
+	for_each_cpu(cpu, this_rq->rd->dlo_mask) {
+		if (this_cpu == cpu)
+			continue;
+
+		src_rq = cpu_rq(cpu);
+
+		/*
+		 * It looks racy, abd it is! However, as in sched_rt.c,
+		 * we are fine with this.
+		 */
+		if (this_rq->dl.dl_nr_running &&
+		    dl_time_before(this_rq->dl.earliest_dl.curr,
+				   src_rq->dl.earliest_dl.next))
+			continue;
+
+		/* Might drop this_rq->lock */
+		double_lock_balance(this_rq, src_rq);
+
+		/*
+		 * If there are no more pullable tasks on the
+		 * rq, we're done with it.
+		 */
+		if (src_rq->dl.dl_nr_running <= 1)
+			goto skip;
+
+		p = pick_next_earliest_dl_task(src_rq, this_cpu);
+
+		/*
+		 * We found a task to be pulled if:
+		 *  - it preempts our current (if there's one),
+		 *  - it will preempt the last one we pulled (if any).
+		 */
+		if (p && dl_time_before(p->dl.deadline, dmin) &&
+		    (!this_rq->dl.dl_nr_running ||
+		     dl_time_before(p->dl.deadline,
+				    this_rq->dl.earliest_dl.curr))) {
+			WARN_ON(p == src_rq->curr);
+			WARN_ON(!p->se.on_rq);
+
+			/*
+			 * Then we pull iff p has actually an earlier
+			 * deadline than the current task of its runqueue.
+			 */
+			if (dl_time_before(p->dl.deadline,
+					   src_rq->curr->dl.deadline))
+				goto skip;
+
+			ret = 1;
+
+			deactivate_task(src_rq, p, 0);
+			set_task_cpu(p, this_cpu);
+			activate_task(this_rq, p, 0);
+			dmin = p->dl.deadline;
+
+			/* Is there any other task even earlier? */
+		}
+skip:
+		double_unlock_balance(this_rq, src_rq);
+	}
+
+	return ret;
+}
+
+static void pre_schedule_dl(struct rq *rq, struct task_struct *prev)
+{
+	/* Try to pull other tasks here */
+	if (dl_task(prev))
+		pull_dl_task(rq);
+}
+
+static void post_schedule_dl(struct rq *rq)
+{
+	push_dl_tasks(rq);
+}
+
+/*
+ * Since the task is not running and a reschedule is not going to happen
+ * anytime soon on its runqueue, we try pushing it away now.
+ */
+static void task_woken_dl(struct rq *rq, struct task_struct *p)
+{
+	if (!task_running(rq, p) &&
+	    !test_tsk_need_resched(rq->curr) &&
+	    has_pushable_dl_tasks(rq) &&
+	    p->nr_cpus_allowed > 1 &&
+	    dl_task(rq->curr) &&
+	    (rq->curr->nr_cpus_allowed < 2 ||
+	     dl_entity_preempt(&rq->curr->dl, &p->dl))) {
+		push_dl_tasks(rq);
+	}
+}
+
+static void set_cpus_allowed_dl(struct task_struct *p,
+				const struct cpumask *new_mask)
+{
+	struct rq *rq;
+	int weight;
+
+	BUG_ON(!dl_task(p));
+
+	/*
+	 * Update only if the task is actually running (i.e.,
+	 * it is on the rq AND it is not throttled).
+	 */
+	if (!on_dl_rq(&p->dl))
+		return;
+
+	weight = cpumask_weight(new_mask);
+
+	/*
+	 * Only update if the process changes its state from whether it
+	 * can migrate or not.
+	 */
+	if ((p->nr_cpus_allowed > 1) == (weight > 1))
+		return;
+
+	rq = task_rq(p);
+
+	/*
+	 * The process used to be able to migrate OR it can now migrate
+	 */
+	if (weight <= 1) {
+		if (!task_current(rq, p))
+			dequeue_pushable_dl_task(rq, p);
+		BUG_ON(!rq->dl.dl_nr_migratory);
+		rq->dl.dl_nr_migratory--;
+	} else {
+		if (!task_current(rq, p))
+			enqueue_pushable_dl_task(rq, p);
+		rq->dl.dl_nr_migratory++;
+	}
+
+	update_dl_migration(&rq->dl);
+}
+
+/* Assumes rq->lock is held */
+static void rq_online_dl(struct rq *rq)
+{
+	if (rq->dl.overloaded)
+		dl_set_overload(rq);
+}
+
+/* Assumes rq->lock is held */
+static void rq_offline_dl(struct rq *rq)
+{
+	if (rq->dl.overloaded)
+		dl_clear_overload(rq);
+}
+
+void init_sched_dl_class(void)
+{
+	unsigned int i;
+
+	for_each_possible_cpu(i)
+		zalloc_cpumask_var_node(&per_cpu(local_cpu_mask_dl, i),
+					GFP_KERNEL, cpu_to_node(i));
+}
+
+#endif /* CONFIG_SMP */
+
 static void switched_from_dl(struct rq *rq, struct task_struct *p)
 {
-	if (hrtimer_active(&p->dl.dl_timer))
+	if (hrtimer_active(&p->dl.dl_timer) && !dl_policy(p->policy))
 		hrtimer_try_to_cancel(&p->dl.dl_timer);
+
+#ifdef CONFIG_SMP
+	/*
+	 * Since this might be the only -deadline task on the rq,
+	 * this is the right place to try to pull some other one
+	 * from an overloaded cpu, if any.
+	 */
+	if (!rq->dl.dl_nr_running)
+		pull_dl_task(rq);
+#endif
 }
 
+/*
+ * When switching to -deadline, we may overload the rq, then
+ * we try to push someone off, if possible.
+ */
 static void switched_to_dl(struct rq *rq, struct task_struct *p)
 {
+	int check_resched = 1;
+
 	/*
 	 * If p is throttled, don't consider the possibility
 	 * of preempting rq->curr, the check will be done right
@@ -637,26 +1508,53 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 		return;
 
 	if (p->on_rq || rq->curr != p) {
-		if (task_has_dl_policy(rq->curr))
+#ifdef CONFIG_SMP
+		if (rq->dl.overloaded && push_dl_task(rq) && rq != task_rq(p))
+			/* Only reschedule if pushing failed */
+			check_resched = 0;
+#endif /* CONFIG_SMP */
+		if (check_resched && task_has_dl_policy(rq->curr))
 			check_preempt_curr_dl(rq, p, 0);
-		else
-			resched_task(rq->curr);
 	}
 }
 
+/*
+ * If the scheduling parameters of a -deadline task changed,
+ * a push or pull operation might be needed.
+ */
 static void prio_changed_dl(struct rq *rq, struct task_struct *p,
 			    int oldprio)
 {
-	switched_to_dl(rq, p);
-}
-
+	if (p->on_rq || rq->curr == p) {
 #ifdef CONFIG_SMP
-static int
-select_task_rq_dl(struct task_struct *p, int prev_cpu, int sd_flag, int flags)
-{
-	return task_cpu(p);
+		/*
+		 * This might be too much, but unfortunately
+		 * we don't have the old deadline value, and
+		 * we can't argue if the task is increasing
+		 * or lowering its prio, so...
+		 */
+		if (!rq->dl.overloaded)
+			pull_dl_task(rq);
+
+		/*
+		 * If we now have a earlier deadline task than p,
+		 * then reschedule, provided p is still on this
+		 * runqueue.
+		 */
+		if (dl_time_before(rq->dl.earliest_dl.curr, p->dl.deadline) &&
+		    rq->curr == p)
+			resched_task(p);
+#else
+		/*
+		 * Again, we don't know if p has a earlier
+		 * or later deadline, so let's blindly set a
+		 * (maybe not needed) rescheduling point.
+		 */
+		resched_task(p);
+#endif /* CONFIG_SMP */
+	} else
+		switched_to_dl(rq, p);
 }
-#endif
 
 const struct sched_class dl_sched_class = {
 	.next			= &rt_sched_class,
@@ -671,6 +1569,12 @@ const struct sched_class dl_sched_class = {
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_dl,
+	.set_cpus_allowed       = set_cpus_allowed_dl,
+	.rq_online              = rq_online_dl,
+	.rq_offline             = rq_offline_dl,
+	.pre_schedule		= pre_schedule_dl,
+	.post_schedule		= post_schedule_dl,
+	.task_woken		= task_woken_dl,
 #endif
 
 	.set_curr_task		= set_curr_task_dl,
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 1c40655..a2740b7 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1738,7 +1738,7 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
 	    !test_tsk_need_resched(rq->curr) &&
 	    has_pushable_tasks(rq) &&
 	    p->nr_cpus_allowed > 1 &&
-	    rt_task(rq->curr) &&
+	    (dl_task(rq->curr) || rt_task(rq->curr)) &&
 	    (rq->curr->nr_cpus_allowed < 2 ||
 	     rq->curr->prio <= p->prio))
 		push_rt_tasks(rq);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 83eb539..93ea627 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -385,6 +385,31 @@ struct dl_rq {
 	struct rb_node *rb_leftmost;
 
 	unsigned long dl_nr_running;
+
+#ifdef CONFIG_SMP
+	/*
+	 * Deadline values of the currently executing and the
+	 * earliest ready task on this rq. Caching these facilitates
+	 * the decision wether or not a ready but not running task
+	 * should migrate somewhere else.
+	 */
+	struct {
+		u64 curr;
+		u64 next;
+	} earliest_dl;
+
+	unsigned long dl_nr_migratory;
+	unsigned long dl_nr_total;
+	int overloaded;
+
+	/*
+	 * Tasks on this rq that can be pushed away. They are kept in
+	 * an rb-tree, ordered by tasks' deadlines, with caching
+	 * of the leftmost (earliest deadline) element.
+	 */
+	struct rb_root pushable_dl_tasks_root;
+	struct rb_node *pushable_dl_tasks_leftmost;
+#endif
 };
 
 #ifdef CONFIG_SMP
@@ -405,6 +430,13 @@ struct root_domain {
 	cpumask_var_t online;
 
 	/*
+	 * The bit corresponding to a CPU gets set here if such CPU has more
+	 * than one runnable -deadline task (as it is below for RT tasks).
+	 */
+	cpumask_var_t dlo_mask;
+	atomic_t dlo_count;
+
+	/*
 	 * The "RT overload" flag: it gets set if a CPU has more than
 	 * one runnable RT task.
 	 */
@@ -1095,6 +1127,8 @@ static inline void idle_balance(int cpu, struct rq *rq)
 extern void sysrq_sched_debug_show(void);
 extern void sched_init_granularity(void);
 extern void update_max_interval(void);
+
+extern void init_sched_dl_class(void);
 extern void init_sched_rt_class(void);
 extern void init_sched_fair_class(void);
 
-- 
cgit v0.10.2


From 239be4a982154ea0c979fca5846349bb68973aed Mon Sep 17 00:00:00 2001
From: Dario Faggioli <raistlin@linux.it>
Date: Thu, 7 Nov 2013 14:43:39 +0100
Subject: sched/deadline: Add SCHED_DEADLINE avg_update accounting

Make the core scheduler and load balancer aware of the load
produced by -deadline tasks, by updating the moving average
like for sched_rt.

Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-6-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fcc02c9..21f58d26 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -564,6 +564,8 @@ static void update_curr_dl(struct rq *rq)
 	curr->se.exec_start = rq_clock_task(rq);
 	cpuacct_charge(curr, delta_exec);
 
+	sched_rt_avg_update(rq, delta_exec);
+
 	dl_se->runtime -= delta_exec;
 	if (dl_runtime_exceeded(rq, dl_se)) {
 		__dequeue_task_dl(rq, curr, 0);
-- 
cgit v0.10.2


From 755378a47192a3d1f7c3a8ca6c15c1cf76de0af2 Mon Sep 17 00:00:00 2001
From: Harald Gustafsson <harald.gustafsson@ericsson.com>
Date: Thu, 7 Nov 2013 14:43:40 +0100
Subject: sched/deadline: Add period support for SCHED_DEADLINE tasks

Make it possible to specify a period (different or equal than
deadline) for -deadline tasks. Relative deadlines (D_i) are used on
task arrivals to generate new scheduling (absolute) deadlines as "d =
t + D_i", and periods (P_i) to postpone the scheduling deadlines as "d
= d + P_i" when the budget is zero.

This is in general useful to model (and schedule) tasks that have slow
activation rates (long periods), but have to be scheduled soon once
activated (short deadlines).

Signed-off-by: Harald Gustafsson <harald.gustafsson@ericsson.com>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-7-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index cc66f26..158f4c2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1102,6 +1102,7 @@ struct sched_dl_entity {
 	 */
 	u64 dl_runtime;		/* maximum runtime for each instance	*/
 	u64 dl_deadline;	/* relative deadline of each instance	*/
+	u64 dl_period;		/* separation of two instances (period) */
 
 	/*
 	 * Actual scheduling parameters. Initialized with the values above,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 548cc04..069230b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1723,6 +1723,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	hrtimer_init(&p->dl.dl_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	p->dl.dl_runtime = p->dl.runtime = 0;
 	p->dl.dl_deadline = p->dl.deadline = 0;
+	p->dl.dl_period = 0;
 	p->dl.flags = 0;
 
 	INIT_LIST_HEAD(&p->rt.run_list);
@@ -3026,6 +3027,7 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
 	init_dl_task_timer(dl_se);
 	dl_se->dl_runtime = attr->sched_runtime;
 	dl_se->dl_deadline = attr->sched_deadline;
+	dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
 	dl_se->flags = attr->sched_flags;
 	dl_se->dl_throttled = 0;
 	dl_se->dl_new = 1;
@@ -3067,19 +3069,23 @@ __getparam_dl(struct task_struct *p, struct sched_attr *attr)
 	attr->sched_priority = p->rt_priority;
 	attr->sched_runtime = dl_se->dl_runtime;
 	attr->sched_deadline = dl_se->dl_deadline;
+	attr->sched_period = dl_se->dl_period;
 	attr->sched_flags = dl_se->flags;
 }
 
 /*
  * This function validates the new parameters of a -deadline task.
  * We ask for the deadline not being zero, and greater or equal
- * than the runtime.
+ * than the runtime, as well as the period of being zero or
+ * greater than deadline.
  */
 static bool
 __checkparam_dl(const struct sched_attr *attr)
 {
 	return attr && attr->sched_deadline != 0 &&
-	       (s64)(attr->sched_deadline - attr->sched_runtime) >= 0;
+		(attr->sched_period == 0 ||
+		(s64)(attr->sched_period   - attr->sched_deadline) >= 0) &&
+		(s64)(attr->sched_deadline - attr->sched_runtime ) >= 0;
 }
 
 /*
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 21f58d26..3958bc57 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -289,7 +289,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
 	 * arbitrary large.
 	 */
 	while (dl_se->runtime <= 0) {
-		dl_se->deadline += dl_se->dl_deadline;
+		dl_se->deadline += dl_se->dl_period;
 		dl_se->runtime += dl_se->dl_runtime;
 	}
 
@@ -329,9 +329,13 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
  *
  * This function returns true if:
  *
- *   runtime / (deadline - t) > dl_runtime / dl_deadline ,
+ *   runtime / (deadline - t) > dl_runtime / dl_period ,
  *
  * IOW we can't recycle current parameters.
+ *
+ * Notice that the bandwidth check is done against the period. For
+ * task with deadline equal to period this is the same of using
+ * dl_deadline instead of dl_period in the equation above.
  */
 static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t)
 {
@@ -355,7 +359,7 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t)
 	 * of anything below microseconds resolution is actually fiction
 	 * (but still we want to give the user that illusion >;).
 	 */
-	left = (dl_se->dl_deadline >> 10) * (dl_se->runtime >> 10);
+	left = (dl_se->dl_period >> 10) * (dl_se->runtime >> 10);
 	right = ((dl_se->deadline - t) >> 10) * (dl_se->dl_runtime >> 10);
 
 	return dl_time_before(right, left);
-- 
cgit v0.10.2


From af6ace764d03900524e9b1ac621a1c520ee49fc6 Mon Sep 17 00:00:00 2001
From: Dario Faggioli <raistlin@linux.it>
Date: Thu, 7 Nov 2013 14:43:42 +0100
Subject: sched/deadline: Add latency tracing for SCHED_DEADLINE tasks

It is very likely that systems that wants/needs to use the new
SCHED_DEADLINE policy also want to have the scheduling latency of
the -deadline tasks under control.

For this reason a new version of the scheduling wakeup latency,
called "wakeup_dl", is introduced.

As a consequence of applying this patch there will be three wakeup
latency tracer:

 * "wakeup", that deals with all tasks in the system;
 * "wakeup_rt", that deals with -rt and -deadline tasks only;
 * "wakeup_dl", that deals with -deadline tasks only.

Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-9-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index fee77e1..090c4d9 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -27,6 +27,8 @@ static int			wakeup_cpu;
 static int			wakeup_current_cpu;
 static unsigned			wakeup_prio = -1;
 static int			wakeup_rt;
+static int			wakeup_dl;
+static int			tracing_dl = 0;
 
 static arch_spinlock_t wakeup_lock =
 	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
@@ -437,6 +439,7 @@ static void __wakeup_reset(struct trace_array *tr)
 {
 	wakeup_cpu = -1;
 	wakeup_prio = -1;
+	tracing_dl = 0;
 
 	if (wakeup_task)
 		put_task_struct(wakeup_task);
@@ -472,9 +475,17 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
 	tracing_record_cmdline(p);
 	tracing_record_cmdline(current);
 
-	if ((wakeup_rt && !rt_task(p)) ||
-			p->prio >= wakeup_prio ||
-			p->prio >= current->prio)
+	/*
+	 * Semantic is like this:
+	 *  - wakeup tracer handles all tasks in the system, independently
+	 *    from their scheduling class;
+	 *  - wakeup_rt tracer handles tasks belonging to sched_dl and
+	 *    sched_rt class;
+	 *  - wakeup_dl handles tasks belonging to sched_dl class only.
+	 */
+	if (tracing_dl || (wakeup_dl && !dl_task(p)) ||
+	    (wakeup_rt && !dl_task(p) && !rt_task(p)) ||
+	    (!dl_task(p) && (p->prio >= wakeup_prio || p->prio >= current->prio)))
 		return;
 
 	pc = preempt_count();
@@ -486,7 +497,8 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
 	arch_spin_lock(&wakeup_lock);
 
 	/* check for races. */
-	if (!tracer_enabled || p->prio >= wakeup_prio)
+	if (!tracer_enabled || tracing_dl ||
+	    (!dl_task(p) && p->prio >= wakeup_prio))
 		goto out_locked;
 
 	/* reset the trace */
@@ -496,6 +508,15 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
 	wakeup_current_cpu = wakeup_cpu;
 	wakeup_prio = p->prio;
 
+	/*
+	 * Once you start tracing a -deadline task, don't bother tracing
+	 * another task until the first one wakes up.
+	 */
+	if (dl_task(p))
+		tracing_dl = 1;
+	else
+		tracing_dl = 0;
+
 	wakeup_task = p;
 	get_task_struct(wakeup_task);
 
@@ -597,16 +618,25 @@ static int __wakeup_tracer_init(struct trace_array *tr)
 
 static int wakeup_tracer_init(struct trace_array *tr)
 {
+	wakeup_dl = 0;
 	wakeup_rt = 0;
 	return __wakeup_tracer_init(tr);
 }
 
 static int wakeup_rt_tracer_init(struct trace_array *tr)
 {
+	wakeup_dl = 0;
 	wakeup_rt = 1;
 	return __wakeup_tracer_init(tr);
 }
 
+static int wakeup_dl_tracer_init(struct trace_array *tr)
+{
+	wakeup_dl = 1;
+	wakeup_rt = 0;
+	return __wakeup_tracer_init(tr);
+}
+
 static void wakeup_tracer_reset(struct trace_array *tr)
 {
 	int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT;
@@ -674,6 +704,28 @@ static struct tracer wakeup_rt_tracer __read_mostly =
 	.use_max_tr	= true,
 };
 
+static struct tracer wakeup_dl_tracer __read_mostly =
+{
+	.name		= "wakeup_dl",
+	.init		= wakeup_dl_tracer_init,
+	.reset		= wakeup_tracer_reset,
+	.start		= wakeup_tracer_start,
+	.stop		= wakeup_tracer_stop,
+	.wait_pipe	= poll_wait_pipe,
+	.print_max	= true,
+	.print_header	= wakeup_print_header,
+	.print_line	= wakeup_print_line,
+	.flags		= &tracer_flags,
+	.set_flag	= wakeup_set_flag,
+	.flag_changed	= wakeup_flag_changed,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest    = trace_selftest_startup_wakeup,
+#endif
+	.open		= wakeup_trace_open,
+	.close		= wakeup_trace_close,
+	.use_max_tr	= true,
+};
+
 __init static int init_wakeup_tracer(void)
 {
 	int ret;
@@ -686,6 +738,10 @@ __init static int init_wakeup_tracer(void)
 	if (ret)
 		return ret;
 
+	ret = register_tracer(&wakeup_dl_tracer);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 core_initcall(init_wakeup_tracer);
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index a7329b7..e98fca6 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -1022,11 +1022,16 @@ trace_selftest_startup_nop(struct tracer *trace, struct trace_array *tr)
 #ifdef CONFIG_SCHED_TRACER
 static int trace_wakeup_test_thread(void *data)
 {
-	/* Make this a RT thread, doesn't need to be too high */
-	static const struct sched_param param = { .sched_priority = 5 };
+	/* Make this a -deadline thread */
+	static const struct sched_attr attr = {
+		.sched_policy = SCHED_DEADLINE,
+		.sched_runtime = 100000ULL,
+		.sched_deadline = 10000000ULL,
+		.sched_period = 10000000ULL
+	};
 	struct completion *x = data;
 
-	sched_setscheduler(current, SCHED_FIFO, &param);
+	sched_setattr(current, &attr);
 
 	/* Make it know we have a new prio */
 	complete(x);
@@ -1040,8 +1045,8 @@ static int trace_wakeup_test_thread(void *data)
 	/* we are awake, now wait to disappear */
 	while (!kthread_should_stop()) {
 		/*
-		 * This is an RT task, do short sleeps to let
-		 * others run.
+		 * This will likely be the system top priority
+		 * task, do short sleeps to let others run.
 		 */
 		msleep(100);
 	}
@@ -1054,21 +1059,21 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 {
 	unsigned long save_max = tracing_max_latency;
 	struct task_struct *p;
-	struct completion isrt;
+	struct completion is_ready;
 	unsigned long count;
 	int ret;
 
-	init_completion(&isrt);
+	init_completion(&is_ready);
 
-	/* create a high prio thread */
-	p = kthread_run(trace_wakeup_test_thread, &isrt, "ftrace-test");
+	/* create a -deadline thread */
+	p = kthread_run(trace_wakeup_test_thread, &is_ready, "ftrace-test");
 	if (IS_ERR(p)) {
 		printk(KERN_CONT "Failed to create ftrace wakeup test thread ");
 		return -1;
 	}
 
-	/* make sure the thread is running at an RT prio */
-	wait_for_completion(&isrt);
+	/* make sure the thread is running at -deadline policy */
+	wait_for_completion(&is_ready);
 
 	/* start the tracing */
 	ret = tracer_init(trace, tr);
@@ -1082,19 +1087,19 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 
 	while (p->on_rq) {
 		/*
-		 * Sleep to make sure the RT thread is asleep too.
+		 * Sleep to make sure the -deadline thread is asleep too.
 		 * On virtual machines we can't rely on timings,
 		 * but we want to make sure this test still works.
 		 */
 		msleep(100);
 	}
 
-	init_completion(&isrt);
+	init_completion(&is_ready);
 
 	wake_up_process(p);
 
 	/* Wait for the task to wake up */
-	wait_for_completion(&isrt);
+	wait_for_completion(&is_ready);
 
 	/* stop the tracing. */
 	tracing_stop();
-- 
cgit v0.10.2


From fb00aca474405f4fa8a8519c3179fed722eabd83 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 7 Nov 2013 14:43:43 +0100
Subject: rtmutex: Turn the plist into an rb-tree

Turn the pi-chains from plist to rb-tree, in the rt_mutex code,
and provide a proper comparison function for -deadline and
-priority tasks.

This is done mainly because:
 - classical prio field of the plist is just an int, which might
   not be enough for representing a deadline;
 - manipulating such a list would become O(nr_deadline_tasks),
   which might be to much, as the number of -deadline task increases.

Therefore, an rb-tree is used, and tasks are queued in it according
to the following logic:
 - among two -priority (i.e., SCHED_BATCH/OTHER/RR/FIFO) tasks, the
   one with the higher (lower, actually!) prio wins;
 - among a -priority and a -deadline task, the latter always wins;
 - among two -deadline tasks, the one with the earliest deadline
   wins.

Queueing and dequeueing functions are changed accordingly, for both
the list of a task's pi-waiters and the list of tasks blocked on
a pi-lock.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-again-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-10-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index b0ed422..f0e5238 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -11,6 +11,7 @@
 #include <linux/user_namespace.h>
 #include <linux/securebits.h>
 #include <linux/seqlock.h>
+#include <linux/rbtree.h>
 #include <net/net_namespace.h>
 #include <linux/sched/rt.h>
 
@@ -154,6 +155,14 @@ extern struct task_group root_task_group;
 
 #define INIT_TASK_COMM "swapper"
 
+#ifdef CONFIG_RT_MUTEXES
+# define INIT_RT_MUTEXES(tsk)						\
+	.pi_waiters = RB_ROOT,						\
+	.pi_waiters_leftmost = NULL,
+#else
+# define INIT_RT_MUTEXES(tsk)
+#endif
+
 /*
  *  INIT_TASK is used to set up the first task table, touch at
  * your own risk!. Base=0, limit=0x1fffff (=2MB)
@@ -221,6 +230,7 @@ extern struct task_group root_task_group;
 	INIT_TRACE_RECURSION						\
 	INIT_TASK_RCU_PREEMPT(tsk)					\
 	INIT_CPUSET_SEQ(tsk)						\
+	INIT_RT_MUTEXES(tsk)						\
 	INIT_VTIME(tsk)							\
 }
 
diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h
index de17134..3aed8d7 100644
--- a/include/linux/rtmutex.h
+++ b/include/linux/rtmutex.h
@@ -13,7 +13,7 @@
 #define __LINUX_RT_MUTEX_H
 
 #include <linux/linkage.h>
-#include <linux/plist.h>
+#include <linux/rbtree.h>
 #include <linux/spinlock_types.h>
 
 extern int max_lock_depth; /* for sysctl */
@@ -22,12 +22,14 @@ extern int max_lock_depth; /* for sysctl */
  * The rt_mutex structure
  *
  * @wait_lock:	spinlock to protect the structure
- * @wait_list:	pilist head to enqueue waiters in priority order
+ * @waiters:	rbtree root to enqueue waiters in priority order
+ * @waiters_leftmost: top waiter
  * @owner:	the mutex owner
  */
 struct rt_mutex {
 	raw_spinlock_t		wait_lock;
-	struct plist_head	wait_list;
+	struct rb_root          waiters;
+	struct rb_node          *waiters_leftmost;
 	struct task_struct	*owner;
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 	int			save_state;
@@ -66,7 +68,7 @@ struct hrtimer_sleeper;
 
 #define __RT_MUTEX_INITIALIZER(mutexname) \
 	{ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \
-	, .wait_list = PLIST_HEAD_INIT(mutexname.wait_list) \
+	, .waiters = RB_ROOT \
 	, .owner = NULL \
 	__DEBUG_RT_MUTEX_INITIALIZER(mutexname)}
 
@@ -98,12 +100,4 @@ extern int rt_mutex_trylock(struct rt_mutex *lock);
 
 extern void rt_mutex_unlock(struct rt_mutex *lock);
 
-#ifdef CONFIG_RT_MUTEXES
-# define INIT_RT_MUTEXES(tsk)						\
-	.pi_waiters	= PLIST_HEAD_INIT(tsk.pi_waiters),	\
-	INIT_RT_MUTEX_DEBUG(tsk)
-#else
-# define INIT_RT_MUTEXES(tsk)
-#endif
-
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 158f4c2..9ea1501 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -16,6 +16,7 @@ struct sched_param {
 #include <linux/types.h>
 #include <linux/timex.h>
 #include <linux/jiffies.h>
+#include <linux/plist.h>
 #include <linux/rbtree.h>
 #include <linux/thread_info.h>
 #include <linux/cpumask.h>
@@ -1354,7 +1355,8 @@ struct task_struct {
 
 #ifdef CONFIG_RT_MUTEXES
 	/* PI waiters blocked on a rt_mutex held by this task */
-	struct plist_head pi_waiters;
+	struct rb_root pi_waiters;
+	struct rb_node *pi_waiters_leftmost;
 	/* Deadlock detection and priority inheritance handling */
 	struct rt_mutex_waiter *pi_blocked_on;
 #endif
diff --git a/kernel/fork.c b/kernel/fork.c
index e6c0f1a..7049ae5 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1087,7 +1087,8 @@ static void rt_mutex_init_task(struct task_struct *p)
 {
 	raw_spin_lock_init(&p->pi_lock);
 #ifdef CONFIG_RT_MUTEXES
-	plist_head_init(&p->pi_waiters);
+	p->pi_waiters = RB_ROOT;
+	p->pi_waiters_leftmost = NULL;
 	p->pi_blocked_on = NULL;
 #endif
 }
diff --git a/kernel/futex.c b/kernel/futex.c
index f6ff019..679531c 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2316,6 +2316,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	 * code while we sleep on uaddr.
 	 */
 	debug_rt_mutex_init_waiter(&rt_waiter);
+	RB_CLEAR_NODE(&rt_waiter.pi_tree_entry);
+	RB_CLEAR_NODE(&rt_waiter.tree_entry);
 	rt_waiter.task = NULL;
 
 	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c
index 13b243a..49b2ed3 100644
--- a/kernel/locking/rtmutex-debug.c
+++ b/kernel/locking/rtmutex-debug.c
@@ -24,7 +24,7 @@
 #include <linux/kallsyms.h>
 #include <linux/syscalls.h>
 #include <linux/interrupt.h>
-#include <linux/plist.h>
+#include <linux/rbtree.h>
 #include <linux/fs.h>
 #include <linux/debug_locks.h>
 
@@ -57,7 +57,7 @@ static void printk_lock(struct rt_mutex *lock, int print_owner)
 
 void rt_mutex_debug_task_free(struct task_struct *task)
 {
-	DEBUG_LOCKS_WARN_ON(!plist_head_empty(&task->pi_waiters));
+	DEBUG_LOCKS_WARN_ON(!RB_EMPTY_ROOT(&task->pi_waiters));
 	DEBUG_LOCKS_WARN_ON(task->pi_blocked_on);
 }
 
@@ -154,16 +154,12 @@ void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock)
 void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
 {
 	memset(waiter, 0x11, sizeof(*waiter));
-	plist_node_init(&waiter->list_entry, MAX_PRIO);
-	plist_node_init(&waiter->pi_list_entry, MAX_PRIO);
 	waiter->deadlock_task_pid = NULL;
 }
 
 void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter)
 {
 	put_pid(waiter->deadlock_task_pid);
-	DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->list_entry));
-	DEBUG_LOCKS_WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
 	memset(waiter, 0x22, sizeof(*waiter));
 }
 
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 0dd6aec..3bf0aa6 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -14,6 +14,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
 #include <linux/timer.h>
 
 #include "rtmutex_common.h"
@@ -91,10 +92,104 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock)
 }
 #endif
 
+static inline int
+rt_mutex_waiter_less(struct rt_mutex_waiter *left,
+		     struct rt_mutex_waiter *right)
+{
+	if (left->task->prio < right->task->prio)
+		return 1;
+
+	/*
+	 * If both tasks are dl_task(), we check their deadlines.
+	 */
+	if (dl_prio(left->task->prio) && dl_prio(right->task->prio))
+		return (left->task->dl.deadline < right->task->dl.deadline);
+
+	return 0;
+}
+
+static void
+rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
+{
+	struct rb_node **link = &lock->waiters.rb_node;
+	struct rb_node *parent = NULL;
+	struct rt_mutex_waiter *entry;
+	int leftmost = 1;
+
+	while (*link) {
+		parent = *link;
+		entry = rb_entry(parent, struct rt_mutex_waiter, tree_entry);
+		if (rt_mutex_waiter_less(waiter, entry)) {
+			link = &parent->rb_left;
+		} else {
+			link = &parent->rb_right;
+			leftmost = 0;
+		}
+	}
+
+	if (leftmost)
+		lock->waiters_leftmost = &waiter->tree_entry;
+
+	rb_link_node(&waiter->tree_entry, parent, link);
+	rb_insert_color(&waiter->tree_entry, &lock->waiters);
+}
+
+static void
+rt_mutex_dequeue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
+{
+	if (RB_EMPTY_NODE(&waiter->tree_entry))
+		return;
+
+	if (lock->waiters_leftmost == &waiter->tree_entry)
+		lock->waiters_leftmost = rb_next(&waiter->tree_entry);
+
+	rb_erase(&waiter->tree_entry, &lock->waiters);
+	RB_CLEAR_NODE(&waiter->tree_entry);
+}
+
+static void
+rt_mutex_enqueue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
+{
+	struct rb_node **link = &task->pi_waiters.rb_node;
+	struct rb_node *parent = NULL;
+	struct rt_mutex_waiter *entry;
+	int leftmost = 1;
+
+	while (*link) {
+		parent = *link;
+		entry = rb_entry(parent, struct rt_mutex_waiter, pi_tree_entry);
+		if (rt_mutex_waiter_less(waiter, entry)) {
+			link = &parent->rb_left;
+		} else {
+			link = &parent->rb_right;
+			leftmost = 0;
+		}
+	}
+
+	if (leftmost)
+		task->pi_waiters_leftmost = &waiter->pi_tree_entry;
+
+	rb_link_node(&waiter->pi_tree_entry, parent, link);
+	rb_insert_color(&waiter->pi_tree_entry, &task->pi_waiters);
+}
+
+static void
+rt_mutex_dequeue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
+{
+	if (RB_EMPTY_NODE(&waiter->pi_tree_entry))
+		return;
+
+	if (task->pi_waiters_leftmost == &waiter->pi_tree_entry)
+		task->pi_waiters_leftmost = rb_next(&waiter->pi_tree_entry);
+
+	rb_erase(&waiter->pi_tree_entry, &task->pi_waiters);
+	RB_CLEAR_NODE(&waiter->pi_tree_entry);
+}
+
 /*
- * Calculate task priority from the waiter list priority
+ * Calculate task priority from the waiter tree priority
  *
- * Return task->normal_prio when the waiter list is empty or when
+ * Return task->normal_prio when the waiter tree is empty or when
  * the waiter is not allowed to do priority boosting
  */
 int rt_mutex_getprio(struct task_struct *task)
@@ -102,7 +197,7 @@ int rt_mutex_getprio(struct task_struct *task)
 	if (likely(!task_has_pi_waiters(task)))
 		return task->normal_prio;
 
-	return min(task_top_pi_waiter(task)->pi_list_entry.prio,
+	return min(task_top_pi_waiter(task)->task->prio,
 		   task->normal_prio);
 }
 
@@ -233,7 +328,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	 * When deadlock detection is off then we check, if further
 	 * priority adjustment is necessary.
 	 */
-	if (!detect_deadlock && waiter->list_entry.prio == task->prio)
+	if (!detect_deadlock && waiter->task->prio == task->prio)
 		goto out_unlock_pi;
 
 	lock = waiter->lock;
@@ -254,9 +349,9 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	top_waiter = rt_mutex_top_waiter(lock);
 
 	/* Requeue the waiter */
-	plist_del(&waiter->list_entry, &lock->wait_list);
-	waiter->list_entry.prio = task->prio;
-	plist_add(&waiter->list_entry, &lock->wait_list);
+	rt_mutex_dequeue(lock, waiter);
+	waiter->task->prio = task->prio;
+	rt_mutex_enqueue(lock, waiter);
 
 	/* Release the task */
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
@@ -280,17 +375,15 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 
 	if (waiter == rt_mutex_top_waiter(lock)) {
 		/* Boost the owner */
-		plist_del(&top_waiter->pi_list_entry, &task->pi_waiters);
-		waiter->pi_list_entry.prio = waiter->list_entry.prio;
-		plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+		rt_mutex_dequeue_pi(task, top_waiter);
+		rt_mutex_enqueue_pi(task, waiter);
 		__rt_mutex_adjust_prio(task);
 
 	} else if (top_waiter == waiter) {
 		/* Deboost the owner */
-		plist_del(&waiter->pi_list_entry, &task->pi_waiters);
+		rt_mutex_dequeue_pi(task, waiter);
 		waiter = rt_mutex_top_waiter(lock);
-		waiter->pi_list_entry.prio = waiter->list_entry.prio;
-		plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+		rt_mutex_enqueue_pi(task, waiter);
 		__rt_mutex_adjust_prio(task);
 	}
 
@@ -355,7 +448,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 	 * 3) it is top waiter
 	 */
 	if (rt_mutex_has_waiters(lock)) {
-		if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) {
+		if (task->prio >= rt_mutex_top_waiter(lock)->task->prio) {
 			if (!waiter || waiter != rt_mutex_top_waiter(lock))
 				return 0;
 		}
@@ -369,7 +462,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 
 		/* remove the queued waiter. */
 		if (waiter) {
-			plist_del(&waiter->list_entry, &lock->wait_list);
+			rt_mutex_dequeue(lock, waiter);
 			task->pi_blocked_on = NULL;
 		}
 
@@ -379,8 +472,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 		 */
 		if (rt_mutex_has_waiters(lock)) {
 			top = rt_mutex_top_waiter(lock);
-			top->pi_list_entry.prio = top->list_entry.prio;
-			plist_add(&top->pi_list_entry, &task->pi_waiters);
+			rt_mutex_enqueue_pi(task, top);
 		}
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 	}
@@ -416,13 +508,11 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	__rt_mutex_adjust_prio(task);
 	waiter->task = task;
 	waiter->lock = lock;
-	plist_node_init(&waiter->list_entry, task->prio);
-	plist_node_init(&waiter->pi_list_entry, task->prio);
 
 	/* Get the top priority waiter on the lock */
 	if (rt_mutex_has_waiters(lock))
 		top_waiter = rt_mutex_top_waiter(lock);
-	plist_add(&waiter->list_entry, &lock->wait_list);
+	rt_mutex_enqueue(lock, waiter);
 
 	task->pi_blocked_on = waiter;
 
@@ -433,8 +523,8 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 
 	if (waiter == rt_mutex_top_waiter(lock)) {
 		raw_spin_lock_irqsave(&owner->pi_lock, flags);
-		plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
-		plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
+		rt_mutex_dequeue_pi(owner, top_waiter);
+		rt_mutex_enqueue_pi(owner, waiter);
 
 		__rt_mutex_adjust_prio(owner);
 		if (owner->pi_blocked_on)
@@ -486,7 +576,7 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
 	 * boosted mode and go back to normal after releasing
 	 * lock->wait_lock.
 	 */
-	plist_del(&waiter->pi_list_entry, &current->pi_waiters);
+	rt_mutex_dequeue_pi(current, waiter);
 
 	rt_mutex_set_owner(lock, NULL);
 
@@ -510,7 +600,7 @@ static void remove_waiter(struct rt_mutex *lock,
 	int chain_walk = 0;
 
 	raw_spin_lock_irqsave(&current->pi_lock, flags);
-	plist_del(&waiter->list_entry, &lock->wait_list);
+	rt_mutex_dequeue(lock, waiter);
 	current->pi_blocked_on = NULL;
 	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
@@ -521,13 +611,13 @@ static void remove_waiter(struct rt_mutex *lock,
 
 		raw_spin_lock_irqsave(&owner->pi_lock, flags);
 
-		plist_del(&waiter->pi_list_entry, &owner->pi_waiters);
+		rt_mutex_dequeue_pi(owner, waiter);
 
 		if (rt_mutex_has_waiters(lock)) {
 			struct rt_mutex_waiter *next;
 
 			next = rt_mutex_top_waiter(lock);
-			plist_add(&next->pi_list_entry, &owner->pi_waiters);
+			rt_mutex_enqueue_pi(owner, next);
 		}
 		__rt_mutex_adjust_prio(owner);
 
@@ -537,8 +627,6 @@ static void remove_waiter(struct rt_mutex *lock,
 		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
 	}
 
-	WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
-
 	if (!chain_walk)
 		return;
 
@@ -565,7 +653,7 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
 	waiter = task->pi_blocked_on;
-	if (!waiter || waiter->list_entry.prio == task->prio) {
+	if (!waiter || waiter->task->prio == task->prio) {
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		return;
 	}
@@ -638,6 +726,8 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	int ret = 0;
 
 	debug_rt_mutex_init_waiter(&waiter);
+	RB_CLEAR_NODE(&waiter.pi_tree_entry);
+	RB_CLEAR_NODE(&waiter.tree_entry);
 
 	raw_spin_lock(&lock->wait_lock);
 
@@ -904,7 +994,8 @@ void __rt_mutex_init(struct rt_mutex *lock, const char *name)
 {
 	lock->owner = NULL;
 	raw_spin_lock_init(&lock->wait_lock);
-	plist_head_init(&lock->wait_list);
+	lock->waiters = RB_ROOT;
+	lock->waiters_leftmost = NULL;
 
 	debug_rt_mutex_init(lock, name);
 }
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 53a66c8..b65442f 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -40,13 +40,13 @@ extern void schedule_rt_mutex_test(struct rt_mutex *lock);
  * This is the control structure for tasks blocked on a rt_mutex,
  * which is allocated on the kernel stack on of the blocked task.
  *
- * @list_entry:		pi node to enqueue into the mutex waiters list
- * @pi_list_entry:	pi node to enqueue into the mutex owner waiters list
+ * @tree_entry:		pi node to enqueue into the mutex waiters tree
+ * @pi_tree_entry:	pi node to enqueue into the mutex owner waiters tree
  * @task:		task reference to the blocked task
  */
 struct rt_mutex_waiter {
-	struct plist_node	list_entry;
-	struct plist_node	pi_list_entry;
+	struct rb_node          tree_entry;
+	struct rb_node          pi_tree_entry;
 	struct task_struct	*task;
 	struct rt_mutex		*lock;
 #ifdef CONFIG_DEBUG_RT_MUTEXES
@@ -57,11 +57,11 @@ struct rt_mutex_waiter {
 };
 
 /*
- * Various helpers to access the waiters-plist:
+ * Various helpers to access the waiters-tree:
  */
 static inline int rt_mutex_has_waiters(struct rt_mutex *lock)
 {
-	return !plist_head_empty(&lock->wait_list);
+	return !RB_EMPTY_ROOT(&lock->waiters);
 }
 
 static inline struct rt_mutex_waiter *
@@ -69,8 +69,8 @@ rt_mutex_top_waiter(struct rt_mutex *lock)
 {
 	struct rt_mutex_waiter *w;
 
-	w = plist_first_entry(&lock->wait_list, struct rt_mutex_waiter,
-			       list_entry);
+	w = rb_entry(lock->waiters_leftmost, struct rt_mutex_waiter,
+		     tree_entry);
 	BUG_ON(w->lock != lock);
 
 	return w;
@@ -78,14 +78,14 @@ rt_mutex_top_waiter(struct rt_mutex *lock)
 
 static inline int task_has_pi_waiters(struct task_struct *p)
 {
-	return !plist_head_empty(&p->pi_waiters);
+	return !RB_EMPTY_ROOT(&p->pi_waiters);
 }
 
 static inline struct rt_mutex_waiter *
 task_top_pi_waiter(struct task_struct *p)
 {
-	return plist_first_entry(&p->pi_waiters, struct rt_mutex_waiter,
-				  pi_list_entry);
+	return rb_entry(p->pi_waiters_leftmost, struct rt_mutex_waiter,
+			pi_tree_entry);
 }
 
 /*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 069230b..aebcc70 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6635,10 +6635,6 @@ void __init sched_init(void)
 	INIT_HLIST_HEAD(&init_task.preempt_notifiers);
 #endif
 
-#ifdef CONFIG_RT_MUTEXES
-	plist_head_init(&init_task.pi_waiters);
-#endif
-
 	/*
 	 * The boot idle thread does lazy MMU switching as well:
 	 */
-- 
cgit v0.10.2


From 2d3d891d3344159d5b452a645e355bbe29591e8b Mon Sep 17 00:00:00 2001
From: Dario Faggioli <raistlin@linux.it>
Date: Thu, 7 Nov 2013 14:43:44 +0100
Subject: sched/deadline: Add SCHED_DEADLINE inheritance logic

Some method to deal with rt-mutexes and make sched_dl interact with
the current PI-coded is needed, raising all but trivial issues, that
needs (according to us) to be solved with some restructuring of
the pi-code (i.e., going toward a proxy execution-ish implementation).

This is under development, in the meanwhile, as a temporary solution,
what this commits does is:

 - ensure a pi-lock owner with waiters is never throttled down. Instead,
   when it runs out of runtime, it immediately gets replenished and it's
   deadline is postponed;

 - the scheduling parameters (relative deadline and default runtime)
   used for that replenishments --during the whole period it holds the
   pi-lock-- are the ones of the waiting task with earliest deadline.

Acting this way, we provide some kind of boosting to the lock-owner,
still by using the existing (actually, slightly modified by the previous
commit) pi-architecture.

We would stress the fact that this is only a surely needed, all but
clean solution to the problem. In the end it's only a way to re-start
discussion within the community. So, as always, comments, ideas, rants,
etc.. are welcome! :-)

Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
[ Added !RT_MUTEXES build fix. ]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-11-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9ea1501..13c53a9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1124,8 +1124,12 @@ struct sched_dl_entity {
 	 * @dl_new tells if a new instance arrived. If so we must
 	 * start executing it with full runtime and reset its absolute
 	 * deadline;
+	 *
+	 * @dl_boosted tells if we are boosted due to DI. If so we are
+	 * outside bandwidth enforcement mechanism (but only until we
+	 * exit the critical section).
 	 */
-	int dl_throttled, dl_new;
+	int dl_throttled, dl_new, dl_boosted;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its
@@ -1359,6 +1363,8 @@ struct task_struct {
 	struct rb_node *pi_waiters_leftmost;
 	/* Deadlock detection and priority inheritance handling */
 	struct rt_mutex_waiter *pi_blocked_on;
+	/* Top pi_waiters task */
+	struct task_struct *pi_top_task;
 #endif
 
 #ifdef CONFIG_DEBUG_MUTEXES
diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
index 440434d..34e4ebe 100644
--- a/include/linux/sched/rt.h
+++ b/include/linux/sched/rt.h
@@ -35,6 +35,7 @@ static inline int rt_task(struct task_struct *p)
 #ifdef CONFIG_RT_MUTEXES
 extern int rt_mutex_getprio(struct task_struct *p);
 extern void rt_mutex_setprio(struct task_struct *p, int prio);
+extern struct task_struct *rt_mutex_get_top_task(struct task_struct *task);
 extern void rt_mutex_adjust_pi(struct task_struct *p);
 static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
 {
@@ -45,6 +46,10 @@ static inline int rt_mutex_getprio(struct task_struct *p)
 {
 	return p->normal_prio;
 }
+static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
+{
+	return NULL;
+}
 # define rt_mutex_adjust_pi(p)		do { } while (0)
 static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
 {
diff --git a/kernel/fork.c b/kernel/fork.c
index 7049ae5..01b450a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1090,6 +1090,7 @@ static void rt_mutex_init_task(struct task_struct *p)
 	p->pi_waiters = RB_ROOT;
 	p->pi_waiters_leftmost = NULL;
 	p->pi_blocked_on = NULL;
+	p->pi_top_task = NULL;
 #endif
 }
 
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 3bf0aa6..2e960a2 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -96,13 +96,16 @@ static inline int
 rt_mutex_waiter_less(struct rt_mutex_waiter *left,
 		     struct rt_mutex_waiter *right)
 {
-	if (left->task->prio < right->task->prio)
+	if (left->prio < right->prio)
 		return 1;
 
 	/*
-	 * If both tasks are dl_task(), we check their deadlines.
+	 * If both waiters have dl_prio(), we check the deadlines of the
+	 * associated tasks.
+	 * If left waiter has a dl_prio(), and we didn't return 1 above,
+	 * then right waiter has a dl_prio() too.
 	 */
-	if (dl_prio(left->task->prio) && dl_prio(right->task->prio))
+	if (dl_prio(left->prio))
 		return (left->task->dl.deadline < right->task->dl.deadline);
 
 	return 0;
@@ -197,10 +200,18 @@ int rt_mutex_getprio(struct task_struct *task)
 	if (likely(!task_has_pi_waiters(task)))
 		return task->normal_prio;
 
-	return min(task_top_pi_waiter(task)->task->prio,
+	return min(task_top_pi_waiter(task)->prio,
 		   task->normal_prio);
 }
 
+struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
+{
+	if (likely(!task_has_pi_waiters(task)))
+		return NULL;
+
+	return task_top_pi_waiter(task)->task;
+}
+
 /*
  * Adjust the priority of a task, after its pi_waiters got modified.
  *
@@ -210,7 +221,7 @@ static void __rt_mutex_adjust_prio(struct task_struct *task)
 {
 	int prio = rt_mutex_getprio(task);
 
-	if (task->prio != prio)
+	if (task->prio != prio || dl_prio(prio))
 		rt_mutex_setprio(task, prio);
 }
 
@@ -328,7 +339,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	 * When deadlock detection is off then we check, if further
 	 * priority adjustment is necessary.
 	 */
-	if (!detect_deadlock && waiter->task->prio == task->prio)
+	if (!detect_deadlock && waiter->prio == task->prio)
 		goto out_unlock_pi;
 
 	lock = waiter->lock;
@@ -350,7 +361,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 
 	/* Requeue the waiter */
 	rt_mutex_dequeue(lock, waiter);
-	waiter->task->prio = task->prio;
+	waiter->prio = task->prio;
 	rt_mutex_enqueue(lock, waiter);
 
 	/* Release the task */
@@ -448,7 +459,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 	 * 3) it is top waiter
 	 */
 	if (rt_mutex_has_waiters(lock)) {
-		if (task->prio >= rt_mutex_top_waiter(lock)->task->prio) {
+		if (task->prio >= rt_mutex_top_waiter(lock)->prio) {
 			if (!waiter || waiter != rt_mutex_top_waiter(lock))
 				return 0;
 		}
@@ -508,6 +519,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 	__rt_mutex_adjust_prio(task);
 	waiter->task = task;
 	waiter->lock = lock;
+	waiter->prio = task->prio;
 
 	/* Get the top priority waiter on the lock */
 	if (rt_mutex_has_waiters(lock))
@@ -653,7 +665,8 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
 	waiter = task->pi_blocked_on;
-	if (!waiter || waiter->task->prio == task->prio) {
+	if (!waiter || (waiter->prio == task->prio &&
+			!dl_prio(task->prio))) {
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		return;
 	}
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index b65442f..7431a9c 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -54,6 +54,7 @@ struct rt_mutex_waiter {
 	struct pid		*deadlock_task_pid;
 	struct rt_mutex		*deadlock_lock;
 #endif
+	int prio;
 };
 
 /*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index aebcc70..599ee3b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -947,7 +947,7 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 		if (prev_class->switched_from)
 			prev_class->switched_from(rq, p);
 		p->sched_class->switched_to(rq, p);
-	} else if (oldprio != p->prio)
+	} else if (oldprio != p->prio || dl_task(p))
 		p->sched_class->prio_changed(rq, p, oldprio);
 }
 
@@ -2781,7 +2781,7 @@ EXPORT_SYMBOL(sleep_on_timeout);
  */
 void rt_mutex_setprio(struct task_struct *p, int prio)
 {
-	int oldprio, on_rq, running;
+	int oldprio, on_rq, running, enqueue_flag = 0;
 	struct rq *rq;
 	const struct sched_class *prev_class;
 
@@ -2808,6 +2808,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	}
 
 	trace_sched_pi_setprio(p, prio);
+	p->pi_top_task = rt_mutex_get_top_task(p);
 	oldprio = p->prio;
 	prev_class = p->sched_class;
 	on_rq = p->on_rq;
@@ -2817,19 +2818,42 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	if (running)
 		p->sched_class->put_prev_task(rq, p);
 
-	if (dl_prio(prio))
+	/*
+	 * Boosting condition are:
+	 * 1. -rt task is running and holds mutex A
+	 *      --> -dl task blocks on mutex A
+	 *
+	 * 2. -dl task is running and holds mutex A
+	 *      --> -dl task blocks on mutex A and could preempt the
+	 *          running task
+	 */
+	if (dl_prio(prio)) {
+		if (!dl_prio(p->normal_prio) || (p->pi_top_task &&
+			dl_entity_preempt(&p->pi_top_task->dl, &p->dl))) {
+			p->dl.dl_boosted = 1;
+			p->dl.dl_throttled = 0;
+			enqueue_flag = ENQUEUE_REPLENISH;
+		} else
+			p->dl.dl_boosted = 0;
 		p->sched_class = &dl_sched_class;
-	else if (rt_prio(prio))
+	} else if (rt_prio(prio)) {
+		if (dl_prio(oldprio))
+			p->dl.dl_boosted = 0;
+		if (oldprio < prio)
+			enqueue_flag = ENQUEUE_HEAD;
 		p->sched_class = &rt_sched_class;
-	else
+	} else {
+		if (dl_prio(oldprio))
+			p->dl.dl_boosted = 0;
 		p->sched_class = &fair_sched_class;
+	}
 
 	p->prio = prio;
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
 	if (on_rq)
-		enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
+		enqueue_task(rq, p, enqueue_flag);
 
 	check_class_changed(rq, p, prev_class, oldprio);
 out_unlock:
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 3958bc57..7f6de43 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -16,20 +16,6 @@
  */
 #include "sched.h"
 
-static inline int dl_time_before(u64 a, u64 b)
-{
-	return (s64)(a - b) < 0;
-}
-
-/*
- * Tells if entity @a should preempt entity @b.
- */
-static inline
-int dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b)
-{
-	return dl_time_before(a->deadline, b->deadline);
-}
-
 static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
 {
 	return container_of(dl_se, struct task_struct, dl);
@@ -242,7 +228,8 @@ static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
  * one, and to (try to!) reconcile itself with its own scheduling
  * parameters.
  */
-static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se)
+static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se,
+				       struct sched_dl_entity *pi_se)
 {
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
@@ -254,8 +241,8 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se)
 	 * future; in fact, we must consider execution overheads (time
 	 * spent on hardirq context, etc.).
 	 */
-	dl_se->deadline = rq_clock(rq) + dl_se->dl_deadline;
-	dl_se->runtime = dl_se->dl_runtime;
+	dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+	dl_se->runtime = pi_se->dl_runtime;
 	dl_se->dl_new = 0;
 }
 
@@ -277,11 +264,23 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se)
  * could happen are, typically, a entity voluntarily trying to overcome its
  * runtime, or it just underestimated it during sched_setscheduler_ex().
  */
-static void replenish_dl_entity(struct sched_dl_entity *dl_se)
+static void replenish_dl_entity(struct sched_dl_entity *dl_se,
+				struct sched_dl_entity *pi_se)
 {
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
 
+	BUG_ON(pi_se->dl_runtime <= 0);
+
+	/*
+	 * This could be the case for a !-dl task that is boosted.
+	 * Just go with full inherited parameters.
+	 */
+	if (dl_se->dl_deadline == 0) {
+		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+		dl_se->runtime = pi_se->dl_runtime;
+	}
+
 	/*
 	 * We keep moving the deadline away until we get some
 	 * available runtime for the entity. This ensures correct
@@ -289,8 +288,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
 	 * arbitrary large.
 	 */
 	while (dl_se->runtime <= 0) {
-		dl_se->deadline += dl_se->dl_period;
-		dl_se->runtime += dl_se->dl_runtime;
+		dl_se->deadline += pi_se->dl_period;
+		dl_se->runtime += pi_se->dl_runtime;
 	}
 
 	/*
@@ -309,8 +308,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
 			lag_once = true;
 			printk_sched("sched: DL replenish lagged to much\n");
 		}
-		dl_se->deadline = rq_clock(rq) + dl_se->dl_deadline;
-		dl_se->runtime = dl_se->dl_runtime;
+		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+		dl_se->runtime = pi_se->dl_runtime;
 	}
 }
 
@@ -337,7 +336,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
  * task with deadline equal to period this is the same of using
  * dl_deadline instead of dl_period in the equation above.
  */
-static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t)
+static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
+			       struct sched_dl_entity *pi_se, u64 t)
 {
 	u64 left, right;
 
@@ -359,8 +359,8 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t)
 	 * of anything below microseconds resolution is actually fiction
 	 * (but still we want to give the user that illusion >;).
 	 */
-	left = (dl_se->dl_period >> 10) * (dl_se->runtime >> 10);
-	right = ((dl_se->deadline - t) >> 10) * (dl_se->dl_runtime >> 10);
+	left = (pi_se->dl_period >> 10) * (dl_se->runtime >> 10);
+	right = ((dl_se->deadline - t) >> 10) * (pi_se->dl_runtime >> 10);
 
 	return dl_time_before(right, left);
 }
@@ -374,7 +374,8 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, u64 t)
  *  - using the remaining runtime with the current deadline would make
  *    the entity exceed its bandwidth.
  */
-static void update_dl_entity(struct sched_dl_entity *dl_se)
+static void update_dl_entity(struct sched_dl_entity *dl_se,
+			     struct sched_dl_entity *pi_se)
 {
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
@@ -384,14 +385,14 @@ static void update_dl_entity(struct sched_dl_entity *dl_se)
 	 * the actual scheduling parameters have to be "renewed".
 	 */
 	if (dl_se->dl_new) {
-		setup_new_dl_entity(dl_se);
+		setup_new_dl_entity(dl_se, pi_se);
 		return;
 	}
 
 	if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
-	    dl_entity_overflow(dl_se, rq_clock(rq))) {
-		dl_se->deadline = rq_clock(rq) + dl_se->dl_deadline;
-		dl_se->runtime = dl_se->dl_runtime;
+	    dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) {
+		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
+		dl_se->runtime = pi_se->dl_runtime;
 	}
 }
 
@@ -405,7 +406,7 @@ static void update_dl_entity(struct sched_dl_entity *dl_se)
  * actually started or not (i.e., the replenishment instant is in
  * the future or in the past).
  */
-static int start_dl_timer(struct sched_dl_entity *dl_se)
+static int start_dl_timer(struct sched_dl_entity *dl_se, bool boosted)
 {
 	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
 	struct rq *rq = rq_of_dl_rq(dl_rq);
@@ -414,6 +415,8 @@ static int start_dl_timer(struct sched_dl_entity *dl_se)
 	unsigned long range;
 	s64 delta;
 
+	if (boosted)
+		return 0;
 	/*
 	 * We want the timer to fire at the deadline, but considering
 	 * that it is actually coming from rq->clock and not from
@@ -573,7 +576,7 @@ static void update_curr_dl(struct rq *rq)
 	dl_se->runtime -= delta_exec;
 	if (dl_runtime_exceeded(rq, dl_se)) {
 		__dequeue_task_dl(rq, curr, 0);
-		if (likely(start_dl_timer(dl_se)))
+		if (likely(start_dl_timer(dl_se, curr->dl.dl_boosted)))
 			dl_se->dl_throttled = 1;
 		else
 			enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
@@ -728,7 +731,8 @@ static void __dequeue_dl_entity(struct sched_dl_entity *dl_se)
 }
 
 static void
-enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
+enqueue_dl_entity(struct sched_dl_entity *dl_se,
+		  struct sched_dl_entity *pi_se, int flags)
 {
 	BUG_ON(on_dl_rq(dl_se));
 
@@ -738,9 +742,9 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags)
 	 * we want a replenishment of its runtime.
 	 */
 	if (!dl_se->dl_new && flags & ENQUEUE_REPLENISH)
-		replenish_dl_entity(dl_se);
+		replenish_dl_entity(dl_se, pi_se);
 	else
-		update_dl_entity(dl_se);
+		update_dl_entity(dl_se, pi_se);
 
 	__enqueue_dl_entity(dl_se);
 }
@@ -752,6 +756,18 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
 
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
+	struct task_struct *pi_task = rt_mutex_get_top_task(p);
+	struct sched_dl_entity *pi_se = &p->dl;
+
+	/*
+	 * Use the scheduling parameters of the top pi-waiter
+	 * task if we have one and its (relative) deadline is
+	 * smaller than our one... OTW we keep our runtime and
+	 * deadline.
+	 */
+	if (pi_task && p->dl.dl_boosted && dl_prio(pi_task->normal_prio))
+		pi_se = &pi_task->dl;
+
 	/*
 	 * If p is throttled, we do nothing. In fact, if it exhausted
 	 * its budget it needs a replenishment and, since it now is on
@@ -761,7 +777,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 	if (p->dl.dl_throttled)
 		return;
 
-	enqueue_dl_entity(&p->dl, flags);
+	enqueue_dl_entity(&p->dl, pi_se, flags);
 
 	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_dl_task(rq, p);
@@ -985,8 +1001,7 @@ static void task_dead_dl(struct task_struct *p)
 {
 	struct hrtimer *timer = &p->dl.dl_timer;
 
-	if (hrtimer_active(timer))
-		hrtimer_try_to_cancel(timer);
+	hrtimer_cancel(timer);
 }
 
 static void set_curr_task_dl(struct rq *rq)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 93ea627..52453a2 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -107,6 +107,20 @@ static inline int task_has_dl_policy(struct task_struct *p)
 	return dl_policy(p->policy);
 }
 
+static inline int dl_time_before(u64 a, u64 b)
+{
+	return (s64)(a - b) < 0;
+}
+
+/*
+ * Tells if entity @a should preempt entity @b.
+ */
+static inline
+int dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b)
+{
+	return dl_time_before(a->deadline, b->deadline);
+}
+
 /*
  * This is the priority-queue data structure of the RT scheduling class:
  */
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 090c4d9..6e32635 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -16,6 +16,7 @@
 #include <linux/uaccess.h>
 #include <linux/ftrace.h>
 #include <linux/sched/rt.h>
+#include <linux/sched/deadline.h>
 #include <trace/events/sched.h>
 #include "trace.h"
 
-- 
cgit v0.10.2


From 332ac17ef5bfcff4766dfdfd3b4cdf10b8f8f155 Mon Sep 17 00:00:00 2001
From: Dario Faggioli <raistlin@linux.it>
Date: Thu, 7 Nov 2013 14:43:45 +0100
Subject: sched/deadline: Add bandwidth management for SCHED_DEADLINE tasks

In order of deadline scheduling to be effective and useful, it is
important that some method of having the allocation of the available
CPU bandwidth to tasks and task groups under control.
This is usually called "admission control" and if it is not performed
at all, no guarantee can be given on the actual scheduling of the
-deadline tasks.

Since when RT-throttling has been introduced each task group have a
bandwidth associated to itself, calculated as a certain amount of
runtime over a period. Moreover, to make it possible to manipulate
such bandwidth, readable/writable controls have been added to both
procfs (for system wide settings) and cgroupfs (for per-group
settings).

Therefore, the same interface is being used for controlling the
bandwidth distrubution to -deadline tasks and task groups, i.e.,
new controls but with similar names, equivalent meaning and with
the same usage paradigm are added.

However, more discussion is needed in order to figure out how
we want to manage SCHED_DEADLINE bandwidth at the task group level.
Therefore, this patch adds a less sophisticated, but actually
very sensible, mechanism to ensure that a certain utilization
cap is not overcome per each root_domain (the single rq for !SMP
configurations).

Another main difference between deadline bandwidth management and
RT-throttling is that -deadline tasks have bandwidth on their own
(while -rt ones doesn't!), and thus we don't need an higher level
throttling mechanism to enforce the desired bandwidth.

This patch, therefore:

 - adds system wide deadline bandwidth management by means of:
    * /proc/sys/kernel/sched_dl_runtime_us,
    * /proc/sys/kernel/sched_dl_period_us,
   that determine (i.e., runtime / period) the total bandwidth
   available on each CPU of each root_domain for -deadline tasks;

 - couples the RT and deadline bandwidth management, i.e., enforces
   that the sum of how much bandwidth is being devoted to -rt
   -deadline tasks to stay below 100%.

This means that, for a root_domain comprising M CPUs, -deadline tasks
can be created until the sum of their bandwidths stay below:

    M * (sched_dl_runtime_us / sched_dl_period_us)

It is also possible to disable this bandwidth management logic, and
be thus free of oversubscribing the system up to any arbitrary level.

Signed-off-by: Dario Faggioli <raistlin@linux.it>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-12-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 13c53a9..a196cb7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1104,6 +1104,7 @@ struct sched_dl_entity {
 	u64 dl_runtime;		/* maximum runtime for each instance	*/
 	u64 dl_deadline;	/* relative deadline of each instance	*/
 	u64 dl_period;		/* separation of two instances (period) */
+	u64 dl_bw;		/* dl_runtime / dl_deadline		*/
 
 	/*
 	 * Actual scheduling parameters. Initialized with the values above,
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 31e0193..8070a83 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -81,6 +81,15 @@ static inline unsigned int get_sysctl_timer_migration(void)
 extern unsigned int sysctl_sched_rt_period;
 extern int sysctl_sched_rt_runtime;
 
+/*
+ *  control SCHED_DEADLINE reservations:
+ *
+ *  /proc/sys/kernel/sched_dl_period_us
+ *  /proc/sys/kernel/sched_dl_runtime_us
+ */
+extern unsigned int sysctl_sched_dl_period;
+extern int sysctl_sched_dl_runtime;
+
 #ifdef CONFIG_CFS_BANDWIDTH
 extern unsigned int sysctl_sched_cfs_bandwidth_slice;
 #endif
@@ -99,4 +108,8 @@ extern int sched_rt_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos);
 
+int sched_dl_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos);
+
 #endif /* _SCHED_SYSCTL_H */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 599ee3b..c7c68e6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -296,6 +296,15 @@ __read_mostly int scheduler_running;
  */
 int sysctl_sched_rt_runtime = 950000;
 
+/*
+ * Maximum bandwidth available for all -deadline tasks and groups
+ * (if group scheduling is configured) on each CPU.
+ *
+ * default: 5%
+ */
+unsigned int sysctl_sched_dl_period = 1000000;
+int sysctl_sched_dl_runtime = 50000;
+
 
 
 /*
@@ -1856,6 +1865,111 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	return 0;
 }
 
+unsigned long to_ratio(u64 period, u64 runtime)
+{
+	if (runtime == RUNTIME_INF)
+		return 1ULL << 20;
+
+	/*
+	 * Doing this here saves a lot of checks in all
+	 * the calling paths, and returning zero seems
+	 * safe for them anyway.
+	 */
+	if (period == 0)
+		return 0;
+
+	return div64_u64(runtime << 20, period);
+}
+
+#ifdef CONFIG_SMP
+inline struct dl_bw *dl_bw_of(int i)
+{
+	return &cpu_rq(i)->rd->dl_bw;
+}
+
+static inline int __dl_span_weight(struct rq *rq)
+{
+	return cpumask_weight(rq->rd->span);
+}
+#else
+inline struct dl_bw *dl_bw_of(int i)
+{
+	return &cpu_rq(i)->dl.dl_bw;
+}
+
+static inline int __dl_span_weight(struct rq *rq)
+{
+	return 1;
+}
+#endif
+
+static inline
+void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw)
+{
+	dl_b->total_bw -= tsk_bw;
+}
+
+static inline
+void __dl_add(struct dl_bw *dl_b, u64 tsk_bw)
+{
+	dl_b->total_bw += tsk_bw;
+}
+
+static inline
+bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
+{
+	return dl_b->bw != -1 &&
+	       dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
+}
+
+/*
+ * We must be sure that accepting a new task (or allowing changing the
+ * parameters of an existing one) is consistent with the bandwidth
+ * constraints. If yes, this function also accordingly updates the currently
+ * allocated bandwidth to reflect the new situation.
+ *
+ * This function is called while holding p's rq->lock.
+ */
+static int dl_overflow(struct task_struct *p, int policy,
+		       const struct sched_attr *attr)
+{
+
+	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+	u64 period = attr->sched_period;
+	u64 runtime = attr->sched_runtime;
+	u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
+	int cpus = __dl_span_weight(task_rq(p));
+	int err = -1;
+
+	if (new_bw == p->dl.dl_bw)
+		return 0;
+
+	/*
+	 * Either if a task, enters, leave, or stays -deadline but changes
+	 * its parameters, we may need to update accordingly the total
+	 * allocated bandwidth of the container.
+	 */
+	raw_spin_lock(&dl_b->lock);
+	if (dl_policy(policy) && !task_has_dl_policy(p) &&
+	    !__dl_overflow(dl_b, cpus, 0, new_bw)) {
+		__dl_add(dl_b, new_bw);
+		err = 0;
+	} else if (dl_policy(policy) && task_has_dl_policy(p) &&
+		   !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) {
+		__dl_clear(dl_b, p->dl.dl_bw);
+		__dl_add(dl_b, new_bw);
+		err = 0;
+	} else if (!dl_policy(policy) && task_has_dl_policy(p)) {
+		__dl_clear(dl_b, p->dl.dl_bw);
+		err = 0;
+	}
+	raw_spin_unlock(&dl_b->lock);
+
+	return err;
+}
+
+extern void init_dl_bw(struct dl_bw *dl_b);
+
 /*
  * wake_up_new_task - wake up a newly created task for the first time.
  *
@@ -3053,6 +3167,7 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
 	dl_se->dl_deadline = attr->sched_deadline;
 	dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
 	dl_se->flags = attr->sched_flags;
+	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
 	dl_se->dl_throttled = 0;
 	dl_se->dl_new = 1;
 }
@@ -3101,7 +3216,9 @@ __getparam_dl(struct task_struct *p, struct sched_attr *attr)
  * This function validates the new parameters of a -deadline task.
  * We ask for the deadline not being zero, and greater or equal
  * than the runtime, as well as the period of being zero or
- * greater than deadline.
+ * greater than deadline. Furthermore, we have to be sure that
+ * user parameters are above the internal resolution (1us); we
+ * check sched_runtime only since it is always the smaller one.
  */
 static bool
 __checkparam_dl(const struct sched_attr *attr)
@@ -3109,7 +3226,8 @@ __checkparam_dl(const struct sched_attr *attr)
 	return attr && attr->sched_deadline != 0 &&
 		(attr->sched_period == 0 ||
 		(s64)(attr->sched_period   - attr->sched_deadline) >= 0) &&
-		(s64)(attr->sched_deadline - attr->sched_runtime ) >= 0;
+		(s64)(attr->sched_deadline - attr->sched_runtime ) >= 0  &&
+		attr->sched_runtime >= (2 << (DL_SCALE - 1));
 }
 
 /*
@@ -3250,8 +3368,8 @@ recheck:
 	}
 change:
 
-#ifdef CONFIG_RT_GROUP_SCHED
 	if (user) {
+#ifdef CONFIG_RT_GROUP_SCHED
 		/*
 		 * Do not allow realtime tasks into groups that have no runtime
 		 * assigned.
@@ -3262,8 +3380,33 @@ change:
 			task_rq_unlock(rq, p, &flags);
 			return -EPERM;
 		}
-	}
 #endif
+#ifdef CONFIG_SMP
+		if (dl_bandwidth_enabled() && dl_policy(policy)) {
+			cpumask_t *span = rq->rd->span;
+			cpumask_t act_affinity;
+
+			/*
+			 * cpus_allowed mask is statically initialized with
+			 * CPU_MASK_ALL, span is instead dynamic. Here we
+			 * compute the "dynamic" affinity of a task.
+			 */
+			cpumask_and(&act_affinity, &p->cpus_allowed,
+				    cpu_active_mask);
+
+			/*
+			 * Don't allow tasks with an affinity mask smaller than
+			 * the entire root_domain to become SCHED_DEADLINE. We
+			 * will also fail if there's no bandwidth available.
+			 */
+			if (!cpumask_equal(&act_affinity, span) ||
+					   rq->rd->dl_bw.bw == 0) {
+				task_rq_unlock(rq, p, &flags);
+				return -EPERM;
+			}
+		}
+#endif
+	}
 
 	/* recheck policy now with rq lock held */
 	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
@@ -3271,6 +3414,18 @@ change:
 		task_rq_unlock(rq, p, &flags);
 		goto recheck;
 	}
+
+	/*
+	 * If setscheduling to SCHED_DEADLINE (or changing the parameters
+	 * of a SCHED_DEADLINE task) we need to check if enough bandwidth
+	 * is available.
+	 */
+	if ((dl_policy(policy) || dl_task(p)) &&
+	    dl_overflow(p, policy, attr)) {
+		task_rq_unlock(rq, p, &flags);
+		return -EBUSY;
+	}
+
 	on_rq = p->on_rq;
 	running = task_current(rq, p);
 	if (on_rq)
@@ -3705,6 +3860,24 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	if (retval)
 		goto out_unlock;
 
+	/*
+	 * Since bandwidth control happens on root_domain basis,
+	 * if admission test is enabled, we only admit -deadline
+	 * tasks allowed to run on all the CPUs in the task's
+	 * root_domain.
+	 */
+#ifdef CONFIG_SMP
+	if (task_has_dl_policy(p)) {
+		const struct cpumask *span = task_rq(p)->rd->span;
+
+		if (dl_bandwidth_enabled() &&
+		    !cpumask_equal(in_mask, span)) {
+			retval = -EBUSY;
+			goto out_unlock;
+		}
+	}
+#endif
+
 	cpuset_cpus_allowed(p, cpus_allowed);
 	cpumask_and(new_mask, in_mask, cpus_allowed);
 again:
@@ -4359,6 +4532,42 @@ out:
 EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
 
 /*
+ * When dealing with a -deadline task, we have to check if moving it to
+ * a new CPU is possible or not. In fact, this is only true iff there
+ * is enough bandwidth available on such CPU, otherwise we want the
+ * whole migration progedure to fail over.
+ */
+static inline
+bool set_task_cpu_dl(struct task_struct *p, unsigned int cpu)
+{
+	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+	struct dl_bw *cpu_b = dl_bw_of(cpu);
+	int ret = 1;
+	u64 bw;
+
+	if (dl_b == cpu_b)
+		return 1;
+
+	raw_spin_lock(&dl_b->lock);
+	raw_spin_lock(&cpu_b->lock);
+
+	bw = cpu_b->bw * cpumask_weight(cpu_rq(cpu)->rd->span);
+	if (dl_bandwidth_enabled() &&
+	    bw < cpu_b->total_bw + p->dl.dl_bw) {
+		ret = 0;
+		goto unlock;
+	}
+	dl_b->total_bw -= p->dl.dl_bw;
+	cpu_b->total_bw += p->dl.dl_bw;
+
+unlock:
+	raw_spin_unlock(&cpu_b->lock);
+	raw_spin_unlock(&dl_b->lock);
+
+	return ret;
+}
+
+/*
  * Move (not current) task off this cpu, onto dest cpu. We're doing
  * this because either it can't run here any more (set_cpus_allowed()
  * away from this CPU, or CPU going down), or because we're
@@ -4390,6 +4599,13 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
 		goto fail;
 
 	/*
+	 * If p is -deadline, proceed only if there is enough
+	 * bandwidth available on dest_cpu
+	 */
+	if (unlikely(dl_task(p)) && !set_task_cpu_dl(p, dest_cpu))
+		goto fail;
+
+	/*
 	 * If we're not on a rq, the next wake-up will ensure we're
 	 * placed properly.
 	 */
@@ -5128,6 +5344,8 @@ static int init_rootdomain(struct root_domain *rd)
 	if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
 		goto free_dlo_mask;
 
+	init_dl_bw(&rd->dl_bw);
+
 	if (cpupri_init(&rd->cpupri) != 0)
 		goto free_rto_mask;
 	return 0;
@@ -6557,13 +6775,15 @@ void __init sched_init(void)
 #endif /* CONFIG_CPUMASK_OFFSTACK */
 	}
 
+	init_rt_bandwidth(&def_rt_bandwidth,
+			global_rt_period(), global_rt_runtime());
+	init_dl_bandwidth(&def_dl_bandwidth,
+			global_dl_period(), global_dl_runtime());
+
 #ifdef CONFIG_SMP
 	init_defrootdomain();
 #endif
 
-	init_rt_bandwidth(&def_rt_bandwidth,
-			global_rt_period(), global_rt_runtime());
-
 #ifdef CONFIG_RT_GROUP_SCHED
 	init_rt_bandwidth(&root_task_group.rt_bandwidth,
 			global_rt_period(), global_rt_runtime());
@@ -6966,16 +7186,6 @@ void sched_move_task(struct task_struct *tsk)
 }
 #endif /* CONFIG_CGROUP_SCHED */
 
-#if defined(CONFIG_RT_GROUP_SCHED) || defined(CONFIG_CFS_BANDWIDTH)
-static unsigned long to_ratio(u64 period, u64 runtime)
-{
-	if (runtime == RUNTIME_INF)
-		return 1ULL << 20;
-
-	return div64_u64(runtime << 20, period);
-}
-#endif
-
 #ifdef CONFIG_RT_GROUP_SCHED
 /*
  * Ensure that the real time constraints are schedulable.
@@ -7149,10 +7359,48 @@ static long sched_group_rt_period(struct task_group *tg)
 	do_div(rt_period_us, NSEC_PER_USEC);
 	return rt_period_us;
 }
+#endif /* CONFIG_RT_GROUP_SCHED */
 
+/*
+ * Coupling of -rt and -deadline bandwidth.
+ *
+ * Here we check if the new -rt bandwidth value is consistent
+ * with the system settings for the bandwidth available
+ * to -deadline tasks.
+ *
+ * IOW, we want to enforce that
+ *
+ *   rt_bandwidth + dl_bandwidth <= 100%
+ *
+ * is always true.
+ */
+static bool __sched_rt_dl_global_constraints(u64 rt_bw)
+{
+	unsigned long flags;
+	u64 dl_bw;
+	bool ret;
+
+	raw_spin_lock_irqsave(&def_dl_bandwidth.dl_runtime_lock, flags);
+	if (global_rt_runtime() == RUNTIME_INF ||
+	    global_dl_runtime() == RUNTIME_INF) {
+		ret = true;
+		goto unlock;
+	}
+
+	dl_bw = to_ratio(def_dl_bandwidth.dl_period,
+			 def_dl_bandwidth.dl_runtime);
+
+	ret = rt_bw + dl_bw <= to_ratio(RUNTIME_INF, RUNTIME_INF);
+unlock:
+	raw_spin_unlock_irqrestore(&def_dl_bandwidth.dl_runtime_lock, flags);
+
+	return ret;
+}
+
+#ifdef CONFIG_RT_GROUP_SCHED
 static int sched_rt_global_constraints(void)
 {
-	u64 runtime, period;
+	u64 runtime, period, bw;
 	int ret = 0;
 
 	if (sysctl_sched_rt_period <= 0)
@@ -7167,6 +7415,10 @@ static int sched_rt_global_constraints(void)
 	if (runtime > period && runtime != RUNTIME_INF)
 		return -EINVAL;
 
+	bw = to_ratio(period, runtime);
+	if (!__sched_rt_dl_global_constraints(bw))
+		return -EINVAL;
+
 	mutex_lock(&rt_constraints_mutex);
 	read_lock(&tasklist_lock);
 	ret = __rt_schedulable(NULL, 0, 0);
@@ -7189,19 +7441,19 @@ static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
 static int sched_rt_global_constraints(void)
 {
 	unsigned long flags;
-	int i;
+	int i, ret = 0;
+	u64 bw;
 
 	if (sysctl_sched_rt_period <= 0)
 		return -EINVAL;
 
-	/*
-	 * There's always some RT tasks in the root group
-	 * -- migration, kstopmachine etc..
-	 */
-	if (sysctl_sched_rt_runtime == 0)
-		return -EBUSY;
-
 	raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
+	bw = to_ratio(global_rt_period(), global_rt_runtime());
+	if (!__sched_rt_dl_global_constraints(bw)) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
 	for_each_possible_cpu(i) {
 		struct rt_rq *rt_rq = &cpu_rq(i)->rt;
 
@@ -7209,12 +7461,93 @@ static int sched_rt_global_constraints(void)
 		rt_rq->rt_runtime = global_rt_runtime();
 		raw_spin_unlock(&rt_rq->rt_runtime_lock);
 	}
+unlock:
 	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
 
-	return 0;
+	return ret;
 }
 #endif /* CONFIG_RT_GROUP_SCHED */
 
+/*
+ * Coupling of -dl and -rt bandwidth.
+ *
+ * Here we check, while setting the system wide bandwidth available
+ * for -dl tasks and groups, if the new values are consistent with
+ * the system settings for the bandwidth available to -rt entities.
+ *
+ * IOW, we want to enforce that
+ *
+ *   rt_bandwidth + dl_bandwidth <= 100%
+ *
+ * is always true.
+ */
+static bool __sched_dl_rt_global_constraints(u64 dl_bw)
+{
+	u64 rt_bw;
+	bool ret;
+
+	raw_spin_lock(&def_rt_bandwidth.rt_runtime_lock);
+	if (global_dl_runtime() == RUNTIME_INF ||
+	    global_rt_runtime() == RUNTIME_INF) {
+		ret = true;
+		goto unlock;
+	}
+
+	rt_bw = to_ratio(ktime_to_ns(def_rt_bandwidth.rt_period),
+			 def_rt_bandwidth.rt_runtime);
+
+	ret = rt_bw + dl_bw <= to_ratio(RUNTIME_INF, RUNTIME_INF);
+unlock:
+	raw_spin_unlock(&def_rt_bandwidth.rt_runtime_lock);
+
+	return ret;
+}
+
+static bool __sched_dl_global_constraints(u64 runtime, u64 period)
+{
+	if (!period || (runtime != RUNTIME_INF && runtime > period))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int sched_dl_global_constraints(void)
+{
+	u64 runtime = global_dl_runtime();
+	u64 period = global_dl_period();
+	u64 new_bw = to_ratio(period, runtime);
+	int ret, i;
+
+	ret = __sched_dl_global_constraints(runtime, period);
+	if (ret)
+		return ret;
+
+	if (!__sched_dl_rt_global_constraints(new_bw))
+		return -EINVAL;
+
+	/*
+	 * Here we want to check the bandwidth not being set to some
+	 * value smaller than the currently allocated bandwidth in
+	 * any of the root_domains.
+	 *
+	 * FIXME: Cycling on all the CPUs is overdoing, but simpler than
+	 * cycling on root_domains... Discussion on different/better
+	 * solutions is welcome!
+	 */
+	for_each_possible_cpu(i) {
+		struct dl_bw *dl_b = dl_bw_of(i);
+
+		raw_spin_lock(&dl_b->lock);
+		if (new_bw < dl_b->total_bw) {
+			raw_spin_unlock(&dl_b->lock);
+			return -EBUSY;
+		}
+		raw_spin_unlock(&dl_b->lock);
+	}
+
+	return 0;
+}
+
 int sched_rr_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
@@ -7264,6 +7597,60 @@ int sched_rt_handler(struct ctl_table *table, int write,
 	return ret;
 }
 
+int sched_dl_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos)
+{
+	int ret;
+	int old_period, old_runtime;
+	static DEFINE_MUTEX(mutex);
+	unsigned long flags;
+
+	mutex_lock(&mutex);
+	old_period = sysctl_sched_dl_period;
+	old_runtime = sysctl_sched_dl_runtime;
+
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+	if (!ret && write) {
+		raw_spin_lock_irqsave(&def_dl_bandwidth.dl_runtime_lock,
+				      flags);
+
+		ret = sched_dl_global_constraints();
+		if (ret) {
+			sysctl_sched_dl_period = old_period;
+			sysctl_sched_dl_runtime = old_runtime;
+		} else {
+			u64 new_bw;
+			int i;
+
+			def_dl_bandwidth.dl_period = global_dl_period();
+			def_dl_bandwidth.dl_runtime = global_dl_runtime();
+			if (global_dl_runtime() == RUNTIME_INF)
+				new_bw = -1;
+			else
+				new_bw = to_ratio(global_dl_period(),
+						  global_dl_runtime());
+			/*
+			 * FIXME: As above...
+			 */
+			for_each_possible_cpu(i) {
+				struct dl_bw *dl_b = dl_bw_of(i);
+
+				raw_spin_lock(&dl_b->lock);
+				dl_b->bw = new_bw;
+				raw_spin_unlock(&dl_b->lock);
+			}
+		}
+
+		raw_spin_unlock_irqrestore(&def_dl_bandwidth.dl_runtime_lock,
+					   flags);
+	}
+	mutex_unlock(&mutex);
+
+	return ret;
+}
+
 #ifdef CONFIG_CGROUP_SCHED
 
 static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 7f6de43..802188f 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -16,6 +16,8 @@
  */
 #include "sched.h"
 
+struct dl_bandwidth def_dl_bandwidth;
+
 static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
 {
 	return container_of(dl_se, struct task_struct, dl);
@@ -46,6 +48,27 @@ static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
 	return dl_rq->rb_leftmost == &dl_se->rb_node;
 }
 
+void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime)
+{
+	raw_spin_lock_init(&dl_b->dl_runtime_lock);
+	dl_b->dl_period = period;
+	dl_b->dl_runtime = runtime;
+}
+
+extern unsigned long to_ratio(u64 period, u64 runtime);
+
+void init_dl_bw(struct dl_bw *dl_b)
+{
+	raw_spin_lock_init(&dl_b->lock);
+	raw_spin_lock(&def_dl_bandwidth.dl_runtime_lock);
+	if (global_dl_runtime() == RUNTIME_INF)
+		dl_b->bw = -1;
+	else
+		dl_b->bw = to_ratio(global_dl_period(), global_dl_runtime());
+	raw_spin_unlock(&def_dl_bandwidth.dl_runtime_lock);
+	dl_b->total_bw = 0;
+}
+
 void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq)
 {
 	dl_rq->rb_root = RB_ROOT;
@@ -57,6 +80,8 @@ void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq)
 	dl_rq->dl_nr_migratory = 0;
 	dl_rq->overloaded = 0;
 	dl_rq->pushable_dl_tasks_root = RB_ROOT;
+#else
+	init_dl_bw(&dl_rq->dl_bw);
 #endif
 }
 
@@ -359,8 +384,9 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
 	 * of anything below microseconds resolution is actually fiction
 	 * (but still we want to give the user that illusion >;).
 	 */
-	left = (pi_se->dl_period >> 10) * (dl_se->runtime >> 10);
-	right = ((dl_se->deadline - t) >> 10) * (pi_se->dl_runtime >> 10);
+	left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE);
+	right = ((dl_se->deadline - t) >> DL_SCALE) *
+		(pi_se->dl_runtime >> DL_SCALE);
 
 	return dl_time_before(right, left);
 }
@@ -911,8 +937,8 @@ static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
 	 * In the unlikely case current and p have the same deadline
 	 * let us try to decide what's the best thing to do...
 	 */
-	if ((s64)(p->dl.deadline - rq->curr->dl.deadline) == 0 &&
-	    !need_resched())
+	if ((p->dl.deadline == rq->curr->dl.deadline) &&
+	    !test_tsk_need_resched(rq->curr))
 		check_preempt_equal_dl(rq, p);
 #endif /* CONFIG_SMP */
 }
@@ -1000,6 +1026,14 @@ static void task_fork_dl(struct task_struct *p)
 static void task_dead_dl(struct task_struct *p)
 {
 	struct hrtimer *timer = &p->dl.dl_timer;
+	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+
+	/*
+	 * Since we are TASK_DEAD we won't slip out of the domain!
+	 */
+	raw_spin_lock_irq(&dl_b->lock);
+	dl_b->total_bw -= p->dl.dl_bw;
+	raw_spin_unlock_irq(&dl_b->lock);
 
 	hrtimer_cancel(timer);
 }
@@ -1226,7 +1260,7 @@ static struct task_struct *pick_next_pushable_dl_task(struct rq *rq)
 	BUG_ON(task_current(rq, p));
 	BUG_ON(p->nr_cpus_allowed <= 1);
 
-	BUG_ON(!p->se.on_rq);
+	BUG_ON(!p->on_rq);
 	BUG_ON(!dl_task(p));
 
 	return p;
@@ -1373,7 +1407,7 @@ static int pull_dl_task(struct rq *this_rq)
 		     dl_time_before(p->dl.deadline,
 				    this_rq->dl.earliest_dl.curr))) {
 			WARN_ON(p == src_rq->curr);
-			WARN_ON(!p->se.on_rq);
+			WARN_ON(!p->on_rq);
 
 			/*
 			 * Then we pull iff p has actually an earlier
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 52453a2..ad4f4fb 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -74,6 +74,13 @@ extern void update_cpu_load_active(struct rq *this_rq);
 #define NICE_0_SHIFT		SCHED_LOAD_SHIFT
 
 /*
+ * Single value that decides SCHED_DEADLINE internal math precision.
+ * 10 -> just above 1us
+ * 9  -> just above 0.5us
+ */
+#define DL_SCALE (10)
+
+/*
  * These are the 'tuning knobs' of the scheduler:
  */
 
@@ -107,7 +114,7 @@ static inline int task_has_dl_policy(struct task_struct *p)
 	return dl_policy(p->policy);
 }
 
-static inline int dl_time_before(u64 a, u64 b)
+static inline bool dl_time_before(u64 a, u64 b)
 {
 	return (s64)(a - b) < 0;
 }
@@ -115,8 +122,8 @@ static inline int dl_time_before(u64 a, u64 b)
 /*
  * Tells if entity @a should preempt entity @b.
  */
-static inline
-int dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b)
+static inline bool
+dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b)
 {
 	return dl_time_before(a->deadline, b->deadline);
 }
@@ -136,6 +143,50 @@ struct rt_bandwidth {
 	u64			rt_runtime;
 	struct hrtimer		rt_period_timer;
 };
+/*
+ * To keep the bandwidth of -deadline tasks and groups under control
+ * we need some place where:
+ *  - store the maximum -deadline bandwidth of the system (the group);
+ *  - cache the fraction of that bandwidth that is currently allocated.
+ *
+ * This is all done in the data structure below. It is similar to the
+ * one used for RT-throttling (rt_bandwidth), with the main difference
+ * that, since here we are only interested in admission control, we
+ * do not decrease any runtime while the group "executes", neither we
+ * need a timer to replenish it.
+ *
+ * With respect to SMP, the bandwidth is given on a per-CPU basis,
+ * meaning that:
+ *  - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU;
+ *  - dl_total_bw array contains, in the i-eth element, the currently
+ *    allocated bandwidth on the i-eth CPU.
+ * Moreover, groups consume bandwidth on each CPU, while tasks only
+ * consume bandwidth on the CPU they're running on.
+ * Finally, dl_total_bw_cpu is used to cache the index of dl_total_bw
+ * that will be shown the next time the proc or cgroup controls will
+ * be red. It on its turn can be changed by writing on its own
+ * control.
+ */
+struct dl_bandwidth {
+	raw_spinlock_t dl_runtime_lock;
+	u64 dl_runtime;
+	u64 dl_period;
+};
+
+static inline int dl_bandwidth_enabled(void)
+{
+	return sysctl_sched_dl_runtime >= 0;
+}
+
+extern struct dl_bw *dl_bw_of(int i);
+
+struct dl_bw {
+	raw_spinlock_t lock;
+	u64 bw, total_bw;
+};
+
+static inline u64 global_dl_period(void);
+static inline u64 global_dl_runtime(void);
 
 extern struct mutex sched_domains_mutex;
 
@@ -423,6 +474,8 @@ struct dl_rq {
 	 */
 	struct rb_root pushable_dl_tasks_root;
 	struct rb_node *pushable_dl_tasks_leftmost;
+#else
+	struct dl_bw dl_bw;
 #endif
 };
 
@@ -449,6 +502,7 @@ struct root_domain {
 	 */
 	cpumask_var_t dlo_mask;
 	atomic_t dlo_count;
+	struct dl_bw dl_bw;
 
 	/*
 	 * The "RT overload" flag: it gets set if a CPU has more than
@@ -897,7 +951,18 @@ static inline u64 global_rt_runtime(void)
 	return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
 }
 
+static inline u64 global_dl_period(void)
+{
+	return (u64)sysctl_sched_dl_period * NSEC_PER_USEC;
+}
+
+static inline u64 global_dl_runtime(void)
+{
+	if (sysctl_sched_dl_runtime < 0)
+		return RUNTIME_INF;
 
+	return (u64)sysctl_sched_dl_runtime * NSEC_PER_USEC;
+}
 
 static inline int task_current(struct rq *rq, struct task_struct *p)
 {
@@ -1145,6 +1210,7 @@ extern void update_max_interval(void);
 extern void init_sched_dl_class(void);
 extern void init_sched_rt_class(void);
 extern void init_sched_fair_class(void);
+extern void init_sched_dl_class(void);
 
 extern void resched_task(struct task_struct *p);
 extern void resched_cpu(int cpu);
@@ -1152,8 +1218,12 @@ extern void resched_cpu(int cpu);
 extern struct rt_bandwidth def_rt_bandwidth;
 extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
 
+extern struct dl_bandwidth def_dl_bandwidth;
+extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
 extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
 
+unsigned long to_ratio(u64 period, u64 runtime);
+
 extern void update_idle_cpu_load(struct rq *this_rq);
 
 extern void init_task_runnable_average(struct task_struct *p);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c8da99f..c7fb079 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -414,6 +414,20 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= sched_rr_handler,
 	},
+	{
+		.procname	= "sched_dl_period_us",
+		.data		= &sysctl_sched_dl_period,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= sched_dl_handler,
+	},
+	{
+		.procname	= "sched_dl_runtime_us",
+		.data		= &sysctl_sched_dl_runtime,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= sched_dl_handler,
+	},
 #ifdef CONFIG_SCHED_AUTOGROUP
 	{
 		.procname	= "sched_autogroup_enabled",
-- 
cgit v0.10.2


From 6bfd6d72f51c51177676f2b1ba113fe0a85fdae4 Mon Sep 17 00:00:00 2001
From: Juri Lelli <juri.lelli@gmail.com>
Date: Thu, 7 Nov 2013 14:43:47 +0100
Subject: sched/deadline: speed up SCHED_DEADLINE pushes with a push-heap

Data from tests confirmed that the original active load balancing
logic didn't scale neither in the number of CPU nor in the number of
tasks (as sched_rt does).

Here we provide a global data structure to keep track of deadlines
of the running tasks in the system. The structure is composed by
a bitmask showing the free CPUs and a max-heap, needed when the system
is heavily loaded.

The implementation and concurrent access scheme are kept simple by
design. However, our measurements show that we can compete with sched_rt
on large multi-CPUs machines [1].

Only the push path is addressed, the extension to use this structure
also for pull decisions is straightforward. However, we are currently
evaluating different (in order to decrease/avoid contention) data
structures to solve possibly both problems. We are also going to re-run
tests considering recent changes inside cpupri [2].

 [1] http://retis.sssup.it/~jlelli/papers/Ospert11Lelli.pdf
 [2] http://www.spinics.net/lists/linux-rt-users/msg06778.html

Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-14-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index b039035..9a95c8c 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -14,7 +14,7 @@ endif
 obj-y += core.o proc.o clock.o cputime.o
 obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
 obj-y += wait.o completion.o
-obj-$(CONFIG_SMP) += cpupri.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c7c68e6..e30356d6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5287,6 +5287,7 @@ static void free_rootdomain(struct rcu_head *rcu)
 	struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
 
 	cpupri_cleanup(&rd->cpupri);
+	cpudl_cleanup(&rd->cpudl);
 	free_cpumask_var(rd->dlo_mask);
 	free_cpumask_var(rd->rto_mask);
 	free_cpumask_var(rd->online);
@@ -5345,6 +5346,8 @@ static int init_rootdomain(struct root_domain *rd)
 		goto free_dlo_mask;
 
 	init_dl_bw(&rd->dl_bw);
+	if (cpudl_init(&rd->cpudl) != 0)
+		goto free_dlo_mask;
 
 	if (cpupri_init(&rd->cpupri) != 0)
 		goto free_rto_mask;
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
new file mode 100644
index 0000000..3bcade5
--- /dev/null
+++ b/kernel/sched/cpudeadline.c
@@ -0,0 +1,216 @@
+/*
+ *  kernel/sched/cpudl.c
+ *
+ *  Global CPU deadline management
+ *
+ *  Author: Juri Lelli <j.lelli@sssup.it>
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; version 2
+ *  of the License.
+ */
+
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include "cpudeadline.h"
+
+static inline int parent(int i)
+{
+	return (i - 1) >> 1;
+}
+
+static inline int left_child(int i)
+{
+	return (i << 1) + 1;
+}
+
+static inline int right_child(int i)
+{
+	return (i << 1) + 2;
+}
+
+static inline int dl_time_before(u64 a, u64 b)
+{
+	return (s64)(a - b) < 0;
+}
+
+void cpudl_exchange(struct cpudl *cp, int a, int b)
+{
+	int cpu_a = cp->elements[a].cpu, cpu_b = cp->elements[b].cpu;
+
+	swap(cp->elements[a], cp->elements[b]);
+	swap(cp->cpu_to_idx[cpu_a], cp->cpu_to_idx[cpu_b]);
+}
+
+void cpudl_heapify(struct cpudl *cp, int idx)
+{
+	int l, r, largest;
+
+	/* adapted from lib/prio_heap.c */
+	while(1) {
+		l = left_child(idx);
+		r = right_child(idx);
+		largest = idx;
+
+		if ((l < cp->size) && dl_time_before(cp->elements[idx].dl,
+							cp->elements[l].dl))
+			largest = l;
+		if ((r < cp->size) && dl_time_before(cp->elements[largest].dl,
+							cp->elements[r].dl))
+			largest = r;
+		if (largest == idx)
+			break;
+
+		/* Push idx down the heap one level and bump one up */
+		cpudl_exchange(cp, largest, idx);
+		idx = largest;
+	}
+}
+
+void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
+{
+	WARN_ON(idx > num_present_cpus() || idx == IDX_INVALID);
+
+	if (dl_time_before(new_dl, cp->elements[idx].dl)) {
+		cp->elements[idx].dl = new_dl;
+		cpudl_heapify(cp, idx);
+	} else {
+		cp->elements[idx].dl = new_dl;
+		while (idx > 0 && dl_time_before(cp->elements[parent(idx)].dl,
+					cp->elements[idx].dl)) {
+			cpudl_exchange(cp, idx, parent(idx));
+			idx = parent(idx);
+		}
+	}
+}
+
+static inline int cpudl_maximum(struct cpudl *cp)
+{
+	return cp->elements[0].cpu;
+}
+
+/*
+ * cpudl_find - find the best (later-dl) CPU in the system
+ * @cp: the cpudl max-heap context
+ * @p: the task
+ * @later_mask: a mask to fill in with the selected CPUs (or NULL)
+ *
+ * Returns: int - best CPU (heap maximum if suitable)
+ */
+int cpudl_find(struct cpudl *cp, struct task_struct *p,
+	       struct cpumask *later_mask)
+{
+	int best_cpu = -1;
+	const struct sched_dl_entity *dl_se = &p->dl;
+
+	if (later_mask && cpumask_and(later_mask, cp->free_cpus,
+			&p->cpus_allowed) && cpumask_and(later_mask,
+			later_mask, cpu_active_mask)) {
+		best_cpu = cpumask_any(later_mask);
+		goto out;
+	} else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) &&
+			dl_time_before(dl_se->deadline, cp->elements[0].dl)) {
+		best_cpu = cpudl_maximum(cp);
+		if (later_mask)
+			cpumask_set_cpu(best_cpu, later_mask);
+	}
+
+out:
+	WARN_ON(best_cpu > num_present_cpus() && best_cpu != -1);
+
+	return best_cpu;
+}
+
+/*
+ * cpudl_set - update the cpudl max-heap
+ * @cp: the cpudl max-heap context
+ * @cpu: the target cpu
+ * @dl: the new earliest deadline for this cpu
+ *
+ * Notes: assumes cpu_rq(cpu)->lock is locked
+ *
+ * Returns: (void)
+ */
+void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
+{
+	int old_idx, new_cpu;
+	unsigned long flags;
+
+	WARN_ON(cpu > num_present_cpus());
+
+	raw_spin_lock_irqsave(&cp->lock, flags);
+	old_idx = cp->cpu_to_idx[cpu];
+	if (!is_valid) {
+		/* remove item */
+		if (old_idx == IDX_INVALID) {
+			/*
+			 * Nothing to remove if old_idx was invalid.
+			 * This could happen if a rq_offline_dl is
+			 * called for a CPU without -dl tasks running.
+			 */
+			goto out;
+		}
+		new_cpu = cp->elements[cp->size - 1].cpu;
+		cp->elements[old_idx].dl = cp->elements[cp->size - 1].dl;
+		cp->elements[old_idx].cpu = new_cpu;
+		cp->size--;
+		cp->cpu_to_idx[new_cpu] = old_idx;
+		cp->cpu_to_idx[cpu] = IDX_INVALID;
+		while (old_idx > 0 && dl_time_before(
+				cp->elements[parent(old_idx)].dl,
+				cp->elements[old_idx].dl)) {
+			cpudl_exchange(cp, old_idx, parent(old_idx));
+			old_idx = parent(old_idx);
+		}
+		cpumask_set_cpu(cpu, cp->free_cpus);
+                cpudl_heapify(cp, old_idx);
+
+		goto out;
+	}
+
+	if (old_idx == IDX_INVALID) {
+		cp->size++;
+		cp->elements[cp->size - 1].dl = 0;
+		cp->elements[cp->size - 1].cpu = cpu;
+		cp->cpu_to_idx[cpu] = cp->size - 1;
+		cpudl_change_key(cp, cp->size - 1, dl);
+		cpumask_clear_cpu(cpu, cp->free_cpus);
+	} else {
+		cpudl_change_key(cp, old_idx, dl);
+	}
+
+out:
+	raw_spin_unlock_irqrestore(&cp->lock, flags);
+}
+
+/*
+ * cpudl_init - initialize the cpudl structure
+ * @cp: the cpudl max-heap context
+ */
+int cpudl_init(struct cpudl *cp)
+{
+	int i;
+
+	memset(cp, 0, sizeof(*cp));
+	raw_spin_lock_init(&cp->lock);
+	cp->size = 0;
+	for (i = 0; i < NR_CPUS; i++)
+		cp->cpu_to_idx[i] = IDX_INVALID;
+	if (!alloc_cpumask_var(&cp->free_cpus, GFP_KERNEL))
+		return -ENOMEM;
+	cpumask_setall(cp->free_cpus);
+
+	return 0;
+}
+
+/*
+ * cpudl_cleanup - clean up the cpudl structure
+ * @cp: the cpudl max-heap context
+ */
+void cpudl_cleanup(struct cpudl *cp)
+{
+	/*
+	 * nothing to do for the moment
+	 */
+}
diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h
new file mode 100644
index 0000000..a202789
--- /dev/null
+++ b/kernel/sched/cpudeadline.h
@@ -0,0 +1,33 @@
+#ifndef _LINUX_CPUDL_H
+#define _LINUX_CPUDL_H
+
+#include <linux/sched.h>
+
+#define IDX_INVALID     -1
+
+struct array_item {
+	u64 dl;
+	int cpu;
+};
+
+struct cpudl {
+	raw_spinlock_t lock;
+	int size;
+	int cpu_to_idx[NR_CPUS];
+	struct array_item elements[NR_CPUS];
+	cpumask_var_t free_cpus;
+};
+
+
+#ifdef CONFIG_SMP
+int cpudl_find(struct cpudl *cp, struct task_struct *p,
+	       struct cpumask *later_mask);
+void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid);
+int cpudl_init(struct cpudl *cp);
+void cpudl_cleanup(struct cpudl *cp);
+#else
+#define cpudl_set(cp, cpu, dl) do { } while (0)
+#define cpudl_init() do { } while (0)
+#endif /* CONFIG_SMP */
+
+#endif /* _LINUX_CPUDL_H */
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 802188f..0c6b1d0 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -16,6 +16,8 @@
  */
 #include "sched.h"
 
+#include <linux/slab.h>
+
 struct dl_bandwidth def_dl_bandwidth;
 
 static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
@@ -640,6 +642,7 @@ static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
 		 */
 		dl_rq->earliest_dl.next = dl_rq->earliest_dl.curr;
 		dl_rq->earliest_dl.curr = deadline;
+		cpudl_set(&rq->rd->cpudl, rq->cpu, deadline, 1);
 	} else if (dl_rq->earliest_dl.next == 0 ||
 		   dl_time_before(deadline, dl_rq->earliest_dl.next)) {
 		/*
@@ -663,6 +666,7 @@ static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
 	if (!dl_rq->dl_nr_running) {
 		dl_rq->earliest_dl.curr = 0;
 		dl_rq->earliest_dl.next = 0;
+		cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0);
 	} else {
 		struct rb_node *leftmost = dl_rq->rb_leftmost;
 		struct sched_dl_entity *entry;
@@ -670,6 +674,7 @@ static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
 		entry = rb_entry(leftmost, struct sched_dl_entity, rb_node);
 		dl_rq->earliest_dl.curr = entry->deadline;
 		dl_rq->earliest_dl.next = next_deadline(rq);
+		cpudl_set(&rq->rd->cpudl, rq->cpu, entry->deadline, 1);
 	}
 }
 
@@ -855,9 +860,6 @@ static void yield_task_dl(struct rq *rq)
 #ifdef CONFIG_SMP
 
 static int find_later_rq(struct task_struct *task);
-static int latest_cpu_find(struct cpumask *span,
-			   struct task_struct *task,
-			   struct cpumask *later_mask);
 
 static int
 select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
@@ -904,7 +906,7 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
 	 * let's hope p can move out.
 	 */
 	if (rq->curr->nr_cpus_allowed == 1 ||
-	    latest_cpu_find(rq->rd->span, rq->curr, NULL) == -1)
+	    cpudl_find(&rq->rd->cpudl, rq->curr, NULL) == -1)
 		return;
 
 	/*
@@ -912,7 +914,7 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
 	 * see if it is pushed or pulled somewhere else.
 	 */
 	if (p->nr_cpus_allowed != 1 &&
-	    latest_cpu_find(rq->rd->span, p, NULL) != -1)
+	    cpudl_find(&rq->rd->cpudl, p, NULL) != -1)
 		return;
 
 	resched_task(rq->curr);
@@ -1085,39 +1087,6 @@ next_node:
 	return NULL;
 }
 
-static int latest_cpu_find(struct cpumask *span,
-			   struct task_struct *task,
-			   struct cpumask *later_mask)
-{
-	const struct sched_dl_entity *dl_se = &task->dl;
-	int cpu, found = -1, best = 0;
-	u64 max_dl = 0;
-
-	for_each_cpu(cpu, span) {
-		struct rq *rq = cpu_rq(cpu);
-		struct dl_rq *dl_rq = &rq->dl;
-
-		if (cpumask_test_cpu(cpu, &task->cpus_allowed) &&
-		    (!dl_rq->dl_nr_running || dl_time_before(dl_se->deadline,
-		     dl_rq->earliest_dl.curr))) {
-			if (later_mask)
-				cpumask_set_cpu(cpu, later_mask);
-			if (!best && !dl_rq->dl_nr_running) {
-				best = 1;
-				found = cpu;
-			} else if (!best &&
-				   dl_time_before(max_dl,
-						  dl_rq->earliest_dl.curr)) {
-				max_dl = dl_rq->earliest_dl.curr;
-				found = cpu;
-			}
-		} else if (later_mask)
-			cpumask_clear_cpu(cpu, later_mask);
-	}
-
-	return found;
-}
-
 static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
 
 static int find_later_rq(struct task_struct *task)
@@ -1134,7 +1103,8 @@ static int find_later_rq(struct task_struct *task)
 	if (task->nr_cpus_allowed == 1)
 		return -1;
 
-	best_cpu = latest_cpu_find(task_rq(task)->rd->span, task, later_mask);
+	best_cpu = cpudl_find(&task_rq(task)->rd->cpudl,
+			task, later_mask);
 	if (best_cpu == -1)
 		return -1;
 
@@ -1510,6 +1480,9 @@ static void rq_online_dl(struct rq *rq)
 {
 	if (rq->dl.overloaded)
 		dl_set_overload(rq);
+
+	if (rq->dl.dl_nr_running > 0)
+		cpudl_set(&rq->rd->cpudl, rq->cpu, rq->dl.earliest_dl.curr, 1);
 }
 
 /* Assumes rq->lock is held */
@@ -1517,6 +1490,8 @@ static void rq_offline_dl(struct rq *rq)
 {
 	if (rq->dl.overloaded)
 		dl_clear_overload(rq);
+
+	cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0);
 }
 
 void init_sched_dl_class(void)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ad4f4fb..2b7421d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 
 #include "cpupri.h"
+#include "cpudeadline.h"
 #include "cpuacct.h"
 
 struct rq;
@@ -503,6 +504,7 @@ struct root_domain {
 	cpumask_var_t dlo_mask;
 	atomic_t dlo_count;
 	struct dl_bw dl_bw;
+	struct cpudl cpudl;
 
 	/*
 	 * The "RT overload" flag: it gets set if a CPU has more than
-- 
cgit v0.10.2


From e4099a5e929435cd6349343f002583f29868c900 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 17 Dec 2013 10:03:34 +0100
Subject: sched/deadline: Fix up the smp-affinity mask tests

For now deadline tasks are not allowed to set smp affinity; however
the current tests are wrong, cure this.

The test in __sched_setscheduler() also uses an on-stack cpumask_t
which is a no-no.

Change both tests to use cpumask_subset() such that we test the root
domain span to be a subset of the cpus_allowed mask. This way we're
sure the tasks can always run on all CPUs they can be balanced over,
and have no effective affinity constraints.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-fyqtb1lapxca3lhsxv9cumdc@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e30356d6..27c6375 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3384,23 +3384,14 @@ change:
 #ifdef CONFIG_SMP
 		if (dl_bandwidth_enabled() && dl_policy(policy)) {
 			cpumask_t *span = rq->rd->span;
-			cpumask_t act_affinity;
-
-			/*
-			 * cpus_allowed mask is statically initialized with
-			 * CPU_MASK_ALL, span is instead dynamic. Here we
-			 * compute the "dynamic" affinity of a task.
-			 */
-			cpumask_and(&act_affinity, &p->cpus_allowed,
-				    cpu_active_mask);
 
 			/*
 			 * Don't allow tasks with an affinity mask smaller than
 			 * the entire root_domain to become SCHED_DEADLINE. We
 			 * will also fail if there's no bandwidth available.
 			 */
-			if (!cpumask_equal(&act_affinity, span) ||
-					   rq->rd->dl_bw.bw == 0) {
+			if (!cpumask_subset(span, &p->cpus_allowed) ||
+			    rq->rd->dl_bw.bw == 0) {
 				task_rq_unlock(rq, p, &flags);
 				return -EPERM;
 			}
@@ -3420,8 +3411,7 @@ change:
 	 * of a SCHED_DEADLINE task) we need to check if enough bandwidth
 	 * is available.
 	 */
-	if ((dl_policy(policy) || dl_task(p)) &&
-	    dl_overflow(p, policy, attr)) {
+	if ((dl_policy(policy) || dl_task(p)) && dl_overflow(p, policy, attr)) {
 		task_rq_unlock(rq, p, &flags);
 		return -EBUSY;
 	}
@@ -3860,6 +3850,10 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	if (retval)
 		goto out_unlock;
 
+
+	cpuset_cpus_allowed(p, cpus_allowed);
+	cpumask_and(new_mask, in_mask, cpus_allowed);
+
 	/*
 	 * Since bandwidth control happens on root_domain basis,
 	 * if admission test is enabled, we only admit -deadline
@@ -3870,16 +3864,12 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	if (task_has_dl_policy(p)) {
 		const struct cpumask *span = task_rq(p)->rd->span;
 
-		if (dl_bandwidth_enabled() &&
-		    !cpumask_equal(in_mask, span)) {
+		if (dl_bandwidth_enabled() && !cpumask_subset(span, new_mask)) {
 			retval = -EBUSY;
 			goto out_unlock;
 		}
 	}
 #endif
-
-	cpuset_cpus_allowed(p, cpus_allowed);
-	cpumask_and(new_mask, in_mask, cpus_allowed);
 again:
 	retval = set_cpus_allowed_ptr(p, new_mask);
 
@@ -4535,7 +4525,7 @@ EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
  * When dealing with a -deadline task, we have to check if moving it to
  * a new CPU is possible or not. In fact, this is only true iff there
  * is enough bandwidth available on such CPU, otherwise we want the
- * whole migration progedure to fail over.
+ * whole migration procedure to fail over.
  */
 static inline
 bool set_task_cpu_dl(struct task_struct *p, unsigned int cpu)
-- 
cgit v0.10.2


From 1724813d9f2c7ff702b46d3e4a4f6d9b10a8f8c2 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 17 Dec 2013 12:44:49 +0100
Subject: sched/deadline: Remove the sysctl_sched_dl knobs

Remove the deadline specific sysctls for now. The problem with them is
that the interaction with the exisiting rt knobs is nearly impossible
to get right.

The current (as per before this patch) situation is that the rt and dl
bandwidth is completely separate and we enforce rt+dl < 100%. This is
undesirable because this means that the rt default of 95% leaves us
hardly any room, even though dl tasks are saver than rt tasks.

Another proposed solution was (a discarted patch) to have the dl
bandwidth be a fraction of the rt bandwidth. This is highly
confusing imo.

Furthermore neither proposal is consistent with the situation we
actually want; which is rt tasks ran from a dl server. In which case
the rt bandwidth is a direct subset of dl.

So whichever way we go, the introduction of dl controls at this point
is painful. Therefore remove them and instead share the rt budget.

This means that for now the rt knobs are used for dl admission control
and the dl runtime is accounted against the rt runtime. I realise that
this isn't entirely desirable either; but whatever we do we appear to
need to change the interface later, so better have a small interface
for now.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-zpyqbqds1r0vyxtxza1e7rdc@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 8070a83..31e0193 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -81,15 +81,6 @@ static inline unsigned int get_sysctl_timer_migration(void)
 extern unsigned int sysctl_sched_rt_period;
 extern int sysctl_sched_rt_runtime;
 
-/*
- *  control SCHED_DEADLINE reservations:
- *
- *  /proc/sys/kernel/sched_dl_period_us
- *  /proc/sys/kernel/sched_dl_runtime_us
- */
-extern unsigned int sysctl_sched_dl_period;
-extern int sysctl_sched_dl_runtime;
-
 #ifdef CONFIG_CFS_BANDWIDTH
 extern unsigned int sysctl_sched_cfs_bandwidth_slice;
 #endif
@@ -108,8 +99,4 @@ extern int sched_rt_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos);
 
-int sched_dl_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos);
-
 #endif /* _SCHED_SYSCTL_H */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 27c6375..1d33eb8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6771,7 +6771,7 @@ void __init sched_init(void)
 	init_rt_bandwidth(&def_rt_bandwidth,
 			global_rt_period(), global_rt_runtime());
 	init_dl_bandwidth(&def_dl_bandwidth,
-			global_dl_period(), global_dl_runtime());
+			global_rt_period(), global_rt_runtime());
 
 #ifdef CONFIG_SMP
 	init_defrootdomain();
@@ -7354,64 +7354,11 @@ static long sched_group_rt_period(struct task_group *tg)
 }
 #endif /* CONFIG_RT_GROUP_SCHED */
 
-/*
- * Coupling of -rt and -deadline bandwidth.
- *
- * Here we check if the new -rt bandwidth value is consistent
- * with the system settings for the bandwidth available
- * to -deadline tasks.
- *
- * IOW, we want to enforce that
- *
- *   rt_bandwidth + dl_bandwidth <= 100%
- *
- * is always true.
- */
-static bool __sched_rt_dl_global_constraints(u64 rt_bw)
-{
-	unsigned long flags;
-	u64 dl_bw;
-	bool ret;
-
-	raw_spin_lock_irqsave(&def_dl_bandwidth.dl_runtime_lock, flags);
-	if (global_rt_runtime() == RUNTIME_INF ||
-	    global_dl_runtime() == RUNTIME_INF) {
-		ret = true;
-		goto unlock;
-	}
-
-	dl_bw = to_ratio(def_dl_bandwidth.dl_period,
-			 def_dl_bandwidth.dl_runtime);
-
-	ret = rt_bw + dl_bw <= to_ratio(RUNTIME_INF, RUNTIME_INF);
-unlock:
-	raw_spin_unlock_irqrestore(&def_dl_bandwidth.dl_runtime_lock, flags);
-
-	return ret;
-}
-
 #ifdef CONFIG_RT_GROUP_SCHED
 static int sched_rt_global_constraints(void)
 {
-	u64 runtime, period, bw;
 	int ret = 0;
 
-	if (sysctl_sched_rt_period <= 0)
-		return -EINVAL;
-
-	runtime = global_rt_runtime();
-	period = global_rt_period();
-
-	/*
-	 * Sanity check on the sysctl variables.
-	 */
-	if (runtime > period && runtime != RUNTIME_INF)
-		return -EINVAL;
-
-	bw = to_ratio(period, runtime);
-	if (!__sched_rt_dl_global_constraints(bw))
-		return -EINVAL;
-
 	mutex_lock(&rt_constraints_mutex);
 	read_lock(&tasklist_lock);
 	ret = __rt_schedulable(NULL, 0, 0);
@@ -7435,18 +7382,8 @@ static int sched_rt_global_constraints(void)
 {
 	unsigned long flags;
 	int i, ret = 0;
-	u64 bw;
-
-	if (sysctl_sched_rt_period <= 0)
-		return -EINVAL;
 
 	raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
-	bw = to_ratio(global_rt_period(), global_rt_runtime());
-	if (!__sched_rt_dl_global_constraints(bw)) {
-		ret = -EINVAL;
-		goto unlock;
-	}
-
 	for_each_possible_cpu(i) {
 		struct rt_rq *rt_rq = &cpu_rq(i)->rt;
 
@@ -7454,69 +7391,18 @@ static int sched_rt_global_constraints(void)
 		rt_rq->rt_runtime = global_rt_runtime();
 		raw_spin_unlock(&rt_rq->rt_runtime_lock);
 	}
-unlock:
 	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
 
 	return ret;
 }
 #endif /* CONFIG_RT_GROUP_SCHED */
 
-/*
- * Coupling of -dl and -rt bandwidth.
- *
- * Here we check, while setting the system wide bandwidth available
- * for -dl tasks and groups, if the new values are consistent with
- * the system settings for the bandwidth available to -rt entities.
- *
- * IOW, we want to enforce that
- *
- *   rt_bandwidth + dl_bandwidth <= 100%
- *
- * is always true.
- */
-static bool __sched_dl_rt_global_constraints(u64 dl_bw)
-{
-	u64 rt_bw;
-	bool ret;
-
-	raw_spin_lock(&def_rt_bandwidth.rt_runtime_lock);
-	if (global_dl_runtime() == RUNTIME_INF ||
-	    global_rt_runtime() == RUNTIME_INF) {
-		ret = true;
-		goto unlock;
-	}
-
-	rt_bw = to_ratio(ktime_to_ns(def_rt_bandwidth.rt_period),
-			 def_rt_bandwidth.rt_runtime);
-
-	ret = rt_bw + dl_bw <= to_ratio(RUNTIME_INF, RUNTIME_INF);
-unlock:
-	raw_spin_unlock(&def_rt_bandwidth.rt_runtime_lock);
-
-	return ret;
-}
-
-static bool __sched_dl_global_constraints(u64 runtime, u64 period)
-{
-	if (!period || (runtime != RUNTIME_INF && runtime > period))
-		return -EINVAL;
-
-	return 0;
-}
-
 static int sched_dl_global_constraints(void)
 {
-	u64 runtime = global_dl_runtime();
-	u64 period = global_dl_period();
+	u64 runtime = global_rt_runtime();
+	u64 period = global_rt_period();
 	u64 new_bw = to_ratio(period, runtime);
-	int ret, i;
-
-	ret = __sched_dl_global_constraints(runtime, period);
-	if (ret)
-		return ret;
-
-	if (!__sched_dl_rt_global_constraints(new_bw))
-		return -EINVAL;
+	int cpu, ret = 0;
 
 	/*
 	 * Here we want to check the bandwidth not being set to some
@@ -7527,46 +7413,68 @@ static int sched_dl_global_constraints(void)
 	 * cycling on root_domains... Discussion on different/better
 	 * solutions is welcome!
 	 */
-	for_each_possible_cpu(i) {
-		struct dl_bw *dl_b = dl_bw_of(i);
+	for_each_possible_cpu(cpu) {
+		struct dl_bw *dl_b = dl_bw_of(cpu);
 
 		raw_spin_lock(&dl_b->lock);
-		if (new_bw < dl_b->total_bw) {
-			raw_spin_unlock(&dl_b->lock);
-			return -EBUSY;
-		}
+		if (new_bw < dl_b->total_bw)
+			ret = -EBUSY;
 		raw_spin_unlock(&dl_b->lock);
+
+		if (ret)
+			break;
 	}
 
-	return 0;
+	return ret;
 }
 
-int sched_rr_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos)
+static void sched_dl_do_global(void)
 {
-	int ret;
-	static DEFINE_MUTEX(mutex);
+	u64 new_bw = -1;
+	int cpu;
 
-	mutex_lock(&mutex);
-	ret = proc_dointvec(table, write, buffer, lenp, ppos);
-	/* make sure that internally we keep jiffies */
-	/* also, writing zero resets timeslice to default */
-	if (!ret && write) {
-		sched_rr_timeslice = sched_rr_timeslice <= 0 ?
-			RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice);
+	def_dl_bandwidth.dl_period = global_rt_period();
+	def_dl_bandwidth.dl_runtime = global_rt_runtime();
+
+	if (global_rt_runtime() != RUNTIME_INF)
+		new_bw = to_ratio(global_rt_period(), global_rt_runtime());
+
+	/*
+	 * FIXME: As above...
+	 */
+	for_each_possible_cpu(cpu) {
+		struct dl_bw *dl_b = dl_bw_of(cpu);
+
+		raw_spin_lock(&dl_b->lock);
+		dl_b->bw = new_bw;
+		raw_spin_unlock(&dl_b->lock);
 	}
-	mutex_unlock(&mutex);
-	return ret;
+}
+
+static int sched_rt_global_validate(void)
+{
+	if (sysctl_sched_rt_period <= 0)
+		return -EINVAL;
+
+	if (sysctl_sched_rt_runtime > sysctl_sched_rt_period)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void sched_rt_do_global(void)
+{
+	def_rt_bandwidth.rt_runtime = global_rt_runtime();
+	def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
 }
 
 int sched_rt_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
 {
-	int ret;
 	int old_period, old_runtime;
 	static DEFINE_MUTEX(mutex);
+	int ret;
 
 	mutex_lock(&mutex);
 	old_period = sysctl_sched_rt_period;
@@ -7575,72 +7483,47 @@ int sched_rt_handler(struct ctl_table *table, int write,
 	ret = proc_dointvec(table, write, buffer, lenp, ppos);
 
 	if (!ret && write) {
+		ret = sched_rt_global_validate();
+		if (ret)
+			goto undo;
+
 		ret = sched_rt_global_constraints();
-		if (ret) {
-			sysctl_sched_rt_period = old_period;
-			sysctl_sched_rt_runtime = old_runtime;
-		} else {
-			def_rt_bandwidth.rt_runtime = global_rt_runtime();
-			def_rt_bandwidth.rt_period =
-				ns_to_ktime(global_rt_period());
-		}
+		if (ret)
+			goto undo;
+
+		ret = sched_dl_global_constraints();
+		if (ret)
+			goto undo;
+
+		sched_rt_do_global();
+		sched_dl_do_global();
+	}
+	if (0) {
+undo:
+		sysctl_sched_rt_period = old_period;
+		sysctl_sched_rt_runtime = old_runtime;
 	}
 	mutex_unlock(&mutex);
 
 	return ret;
 }
 
-int sched_dl_handler(struct ctl_table *table, int write,
+int sched_rr_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
 {
 	int ret;
-	int old_period, old_runtime;
 	static DEFINE_MUTEX(mutex);
-	unsigned long flags;
 
 	mutex_lock(&mutex);
-	old_period = sysctl_sched_dl_period;
-	old_runtime = sysctl_sched_dl_runtime;
-
 	ret = proc_dointvec(table, write, buffer, lenp, ppos);
-
+	/* make sure that internally we keep jiffies */
+	/* also, writing zero resets timeslice to default */
 	if (!ret && write) {
-		raw_spin_lock_irqsave(&def_dl_bandwidth.dl_runtime_lock,
-				      flags);
-
-		ret = sched_dl_global_constraints();
-		if (ret) {
-			sysctl_sched_dl_period = old_period;
-			sysctl_sched_dl_runtime = old_runtime;
-		} else {
-			u64 new_bw;
-			int i;
-
-			def_dl_bandwidth.dl_period = global_dl_period();
-			def_dl_bandwidth.dl_runtime = global_dl_runtime();
-			if (global_dl_runtime() == RUNTIME_INF)
-				new_bw = -1;
-			else
-				new_bw = to_ratio(global_dl_period(),
-						  global_dl_runtime());
-			/*
-			 * FIXME: As above...
-			 */
-			for_each_possible_cpu(i) {
-				struct dl_bw *dl_b = dl_bw_of(i);
-
-				raw_spin_lock(&dl_b->lock);
-				dl_b->bw = new_bw;
-				raw_spin_unlock(&dl_b->lock);
-			}
-		}
-
-		raw_spin_unlock_irqrestore(&def_dl_bandwidth.dl_runtime_lock,
-					   flags);
+		sched_rr_timeslice = sched_rr_timeslice <= 0 ?
+			RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice);
 	}
 	mutex_unlock(&mutex);
-
 	return ret;
 }
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 0c6b1d0..ee25361 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -63,10 +63,10 @@ void init_dl_bw(struct dl_bw *dl_b)
 {
 	raw_spin_lock_init(&dl_b->lock);
 	raw_spin_lock(&def_dl_bandwidth.dl_runtime_lock);
-	if (global_dl_runtime() == RUNTIME_INF)
+	if (global_rt_runtime() == RUNTIME_INF)
 		dl_b->bw = -1;
 	else
-		dl_b->bw = to_ratio(global_dl_period(), global_dl_runtime());
+		dl_b->bw = to_ratio(global_rt_period(), global_rt_runtime());
 	raw_spin_unlock(&def_dl_bandwidth.dl_runtime_lock);
 	dl_b->total_bw = 0;
 }
@@ -612,6 +612,29 @@ static void update_curr_dl(struct rq *rq)
 		if (!is_leftmost(curr, &rq->dl))
 			resched_task(curr);
 	}
+
+	/*
+	 * Because -- for now -- we share the rt bandwidth, we need to
+	 * account our runtime there too, otherwise actual rt tasks
+	 * would be able to exceed the shared quota.
+	 *
+	 * Account to the root rt group for now.
+	 *
+	 * The solution we're working towards is having the RT groups scheduled
+	 * using deadline servers -- however there's a few nasties to figure
+	 * out before that can happen.
+	 */
+	if (rt_bandwidth_enabled()) {
+		struct rt_rq *rt_rq = &rq->rt;
+
+		raw_spin_lock(&rt_rq->rt_runtime_lock);
+		rt_rq->rt_time += delta_exec;
+		/*
+		 * We'll let actual RT tasks worry about the overflow here, we
+		 * have our own CBS to keep us inline -- see above.
+		 */
+		raw_spin_unlock(&rt_rq->rt_runtime_lock);
+	}
 }
 
 #ifdef CONFIG_SMP
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 2b7421d..890339099 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -176,7 +176,7 @@ struct dl_bandwidth {
 
 static inline int dl_bandwidth_enabled(void)
 {
-	return sysctl_sched_dl_runtime >= 0;
+	return sysctl_sched_rt_runtime >= 0;
 }
 
 extern struct dl_bw *dl_bw_of(int i);
@@ -186,9 +186,6 @@ struct dl_bw {
 	u64 bw, total_bw;
 };
 
-static inline u64 global_dl_period(void);
-static inline u64 global_dl_runtime(void);
-
 extern struct mutex sched_domains_mutex;
 
 #ifdef CONFIG_CGROUP_SCHED
@@ -953,19 +950,6 @@ static inline u64 global_rt_runtime(void)
 	return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
 }
 
-static inline u64 global_dl_period(void)
-{
-	return (u64)sysctl_sched_dl_period * NSEC_PER_USEC;
-}
-
-static inline u64 global_dl_runtime(void)
-{
-	if (sysctl_sched_dl_runtime < 0)
-		return RUNTIME_INF;
-
-	return (u64)sysctl_sched_dl_runtime * NSEC_PER_USEC;
-}
-
 static inline int task_current(struct rq *rq, struct task_struct *p)
 {
 	return rq->curr == p;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index c7fb079..c8da99f 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -414,20 +414,6 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= sched_rr_handler,
 	},
-	{
-		.procname	= "sched_dl_period_us",
-		.data		= &sysctl_sched_dl_period,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= sched_dl_handler,
-	},
-	{
-		.procname	= "sched_dl_runtime_us",
-		.data		= &sysctl_sched_dl_runtime,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= sched_dl_handler,
-	},
 #ifdef CONFIG_SCHED_AUTOGROUP
 	{
 		.procname	= "sched_autogroup_enabled",
-- 
cgit v0.10.2


From de212f18e92c952533d57c5510d2790199c75734 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 19 Dec 2013 11:54:45 +0100
Subject: sched/deadline: Fix hotplug admission control

The current hotplug admission control is broken because:

  CPU_DYING -> migration_call() -> migrate_tasks() -> __migrate_task()

cannot fail and hard assumes it _will_ move all tasks off of the dying
cpu, failing this will break hotplug.

The much simpler solution is a DOWN_PREPARE handler that fails when
removing one CPU gets us below the total allocated bandwidth.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131220171343.GL2480@laptop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1d33eb8..a549d9a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1887,9 +1887,15 @@ inline struct dl_bw *dl_bw_of(int i)
 	return &cpu_rq(i)->rd->dl_bw;
 }
 
-static inline int __dl_span_weight(struct rq *rq)
+static inline int dl_bw_cpus(int i)
 {
-	return cpumask_weight(rq->rd->span);
+	struct root_domain *rd = cpu_rq(i)->rd;
+	int cpus = 0;
+
+	for_each_cpu_and(i, rd->span, cpu_active_mask)
+		cpus++;
+
+	return cpus;
 }
 #else
 inline struct dl_bw *dl_bw_of(int i)
@@ -1897,7 +1903,7 @@ inline struct dl_bw *dl_bw_of(int i)
 	return &cpu_rq(i)->dl.dl_bw;
 }
 
-static inline int __dl_span_weight(struct rq *rq)
+static inline int dl_bw_cpus(int i)
 {
 	return 1;
 }
@@ -1938,8 +1944,7 @@ static int dl_overflow(struct task_struct *p, int policy,
 	u64 period = attr->sched_period;
 	u64 runtime = attr->sched_runtime;
 	u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
-	int cpus = __dl_span_weight(task_rq(p));
-	int err = -1;
+	int cpus, err = -1;
 
 	if (new_bw == p->dl.dl_bw)
 		return 0;
@@ -1950,6 +1955,7 @@ static int dl_overflow(struct task_struct *p, int policy,
 	 * allocated bandwidth of the container.
 	 */
 	raw_spin_lock(&dl_b->lock);
+	cpus = dl_bw_cpus(task_cpu(p));
 	if (dl_policy(policy) && !task_has_dl_policy(p) &&
 	    !__dl_overflow(dl_b, cpus, 0, new_bw)) {
 		__dl_add(dl_b, new_bw);
@@ -4522,42 +4528,6 @@ out:
 EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
 
 /*
- * When dealing with a -deadline task, we have to check if moving it to
- * a new CPU is possible or not. In fact, this is only true iff there
- * is enough bandwidth available on such CPU, otherwise we want the
- * whole migration procedure to fail over.
- */
-static inline
-bool set_task_cpu_dl(struct task_struct *p, unsigned int cpu)
-{
-	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
-	struct dl_bw *cpu_b = dl_bw_of(cpu);
-	int ret = 1;
-	u64 bw;
-
-	if (dl_b == cpu_b)
-		return 1;
-
-	raw_spin_lock(&dl_b->lock);
-	raw_spin_lock(&cpu_b->lock);
-
-	bw = cpu_b->bw * cpumask_weight(cpu_rq(cpu)->rd->span);
-	if (dl_bandwidth_enabled() &&
-	    bw < cpu_b->total_bw + p->dl.dl_bw) {
-		ret = 0;
-		goto unlock;
-	}
-	dl_b->total_bw -= p->dl.dl_bw;
-	cpu_b->total_bw += p->dl.dl_bw;
-
-unlock:
-	raw_spin_unlock(&cpu_b->lock);
-	raw_spin_unlock(&dl_b->lock);
-
-	return ret;
-}
-
-/*
  * Move (not current) task off this cpu, onto dest cpu. We're doing
  * this because either it can't run here any more (set_cpus_allowed()
  * away from this CPU, or CPU going down), or because we're
@@ -4589,13 +4559,6 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
 		goto fail;
 
 	/*
-	 * If p is -deadline, proceed only if there is enough
-	 * bandwidth available on dest_cpu
-	 */
-	if (unlikely(dl_task(p)) && !set_task_cpu_dl(p, dest_cpu))
-		goto fail;
-
-	/*
 	 * If we're not on a rq, the next wake-up will ensure we're
 	 * placed properly.
 	 */
@@ -5052,13 +5015,31 @@ static int sched_cpu_active(struct notifier_block *nfb,
 static int sched_cpu_inactive(struct notifier_block *nfb,
 					unsigned long action, void *hcpu)
 {
+	unsigned long flags;
+	long cpu = (long)hcpu;
+
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_DOWN_PREPARE:
-		set_cpu_active((long)hcpu, false);
+		set_cpu_active(cpu, false);
+
+		/* explicitly allow suspend */
+		if (!(action & CPU_TASKS_FROZEN)) {
+			struct dl_bw *dl_b = dl_bw_of(cpu);
+			bool overflow;
+			int cpus;
+
+			raw_spin_lock_irqsave(&dl_b->lock, flags);
+			cpus = dl_bw_cpus(cpu);
+			overflow = __dl_overflow(dl_b, cpus, 0, 0);
+			raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+
+			if (overflow)
+				return notifier_from_errno(-EBUSY);
+		}
 		return NOTIFY_OK;
-	default:
-		return NOTIFY_DONE;
 	}
+
+	return NOTIFY_DONE;
 }
 
 static int __init migration_init(void)
-- 
cgit v0.10.2


From 7caff66f361c44d0fbc74ed1cfa60a357fc84cf2 Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Mon, 6 Jan 2014 12:34:38 +0100
Subject: sched: Reduce trigger_load_balance() parameters

The cpu information is already stored in the struct rq, so no need to pass it
as parameter to the trigger_load_balance function.

Cc: linaro-kernel@lists.linaro.org
Cc: preeti.lkml@gmail.com
Cc: mingo@redhat.com
Cc: peterz@infradead.org
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1389008085-9069-2-git-send-email-daniel.lezcano@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a549d9a..392c6f8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2436,7 +2436,7 @@ void scheduler_tick(void)
 
 #ifdef CONFIG_SMP
 	rq->idle_balance = idle_cpu(cpu);
-	trigger_load_balance(rq, cpu);
+	trigger_load_balance(rq);
 #endif
 	rq_last_tick_reset(rq);
 }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b73f4ba..b35d322 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6876,8 +6876,10 @@ static inline int on_null_domain(int cpu)
 /*
  * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
  */
-void trigger_load_balance(struct rq *rq, int cpu)
+void trigger_load_balance(struct rq *rq)
 {
+	int cpu = rq->cpu;
+
 	/* Don't need to rebalance while attached to NULL domain */
 	if (time_after_eq(jiffies, rq->next_balance) &&
 	    likely(!on_null_domain(cpu)))
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 890339099..c2119fd 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1175,7 +1175,7 @@ extern const struct sched_class idle_sched_class;
 
 extern void update_group_power(struct sched_domain *sd, int cpu);
 
-extern void trigger_load_balance(struct rq *rq, int cpu);
+extern void trigger_load_balance(struct rq *rq);
 extern void idle_balance(int this_cpu, struct rq *this_rq);
 
 extern void idle_enter_fair(struct rq *this_rq);
-- 
cgit v0.10.2


From 4a725627f21df6b280a19f50bc849daaab3b1544 Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Mon, 6 Jan 2014 12:34:39 +0100
Subject: sched: Reduce nohz_kick_needed() parameters

The cpu information is already stored in the struct rq, so no need to pass it
as parameter to the nohz_kick_needed function.

The caller of this function just called idle_cpu() before to fill the
rq->idle_balance field.

Use rq->cpu and rq->idle_balance.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1389008085-9069-3-git-send-email-daniel.lezcano@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b35d322..c47b1ce 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6788,14 +6788,14 @@ end:
  *   - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler
  *     domain span are idle.
  */
-static inline int nohz_kick_needed(struct rq *rq, int cpu)
+static inline int nohz_kick_needed(struct rq *rq)
 {
 	unsigned long now = jiffies;
 	struct sched_domain *sd;
 	struct sched_group_power *sgp;
-	int nr_busy;
+	int nr_busy, cpu = rq->cpu;
 
-	if (unlikely(idle_cpu(cpu)))
+	if (unlikely(rq->idle_balance))
 		return 0;
 
        /*
@@ -6885,7 +6885,7 @@ void trigger_load_balance(struct rq *rq)
 	    likely(!on_null_domain(cpu)))
 		raise_softirq(SCHED_SOFTIRQ);
 #ifdef CONFIG_NO_HZ_COMMON
-	if (nohz_kick_needed(rq, cpu) && likely(!on_null_domain(cpu)))
+	if (nohz_kick_needed(rq) && likely(!on_null_domain(cpu)))
 		nohz_balancer_kick(cpu);
 #endif
 }
-- 
cgit v0.10.2


From 63f609b160151c9e86b26b935c9671a23afe299f Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Mon, 6 Jan 2014 12:34:40 +0100
Subject: sched: Pass 'struct rq' to on_null_domain()

The on_null_domain() function is getting the cpu to retrieve the struct rq
associated with it.

Pass 'struct rq' directly to the function as the caller already has the info.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1389008085-9069-4-git-send-email-daniel.lezcano@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c47b1ce..fc0afc5 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6868,9 +6868,9 @@ static void run_rebalance_domains(struct softirq_action *h)
 	nohz_idle_balance(this_cpu, idle);
 }
 
-static inline int on_null_domain(int cpu)
+static inline int on_null_domain(struct rq *rq)
 {
-	return !rcu_dereference_sched(cpu_rq(cpu)->sd);
+	return !rcu_dereference_sched(rq->sd);
 }
 
 /*
@@ -6882,10 +6882,10 @@ void trigger_load_balance(struct rq *rq)
 
 	/* Don't need to rebalance while attached to NULL domain */
 	if (time_after_eq(jiffies, rq->next_balance) &&
-	    likely(!on_null_domain(cpu)))
+	    likely(!on_null_domain(rq)))
 		raise_softirq(SCHED_SOFTIRQ);
 #ifdef CONFIG_NO_HZ_COMMON
-	if (nohz_kick_needed(rq) && likely(!on_null_domain(cpu)))
+	if (nohz_kick_needed(rq) && likely(!on_null_domain(rq)))
 		nohz_balancer_kick(cpu);
 #endif
 }
-- 
cgit v0.10.2


From 3dd0337d6df7d54c82ecebfa6485040f686bf8b1 Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Mon, 6 Jan 2014 12:34:41 +0100
Subject: sched: Remove unused parameter from find_new_ilb()

The 'call_cpu' is never used in the function. Remove it.

Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1389008085-9069-5-git-send-email-daniel.lezcano@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fc0afc5..5fda3c4 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6509,7 +6509,7 @@ static struct {
 	unsigned long next_balance;     /* in jiffy units */
 } nohz ____cacheline_aligned;
 
-static inline int find_new_ilb(int call_cpu)
+static inline int find_new_ilb(void)
 {
 	int ilb = cpumask_first(nohz.idle_cpus_mask);
 
@@ -6530,7 +6530,7 @@ static void nohz_balancer_kick(int cpu)
 
 	nohz.next_balance++;
 
-	ilb_cpu = find_new_ilb(cpu);
+	ilb_cpu = find_new_ilb();
 
 	if (ilb_cpu >= nr_cpu_ids)
 		return;
-- 
cgit v0.10.2


From 0aeeeebac8d8304501680f12862784341f4bee7b Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Mon, 6 Jan 2014 12:34:42 +0100
Subject: sched: Remove unused parameter from nohz_balancer_kick()

The cpu parameter is no longer needed in nohz_balancer_kick, let's remove
the parameter.

Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1389008085-9069-6-git-send-email-daniel.lezcano@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5fda3c4..b91cd93 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6524,7 +6524,7 @@ static inline int find_new_ilb(void)
  * nohz_load_balancer CPU (if there is one) otherwise fallback to any idle
  * CPU (if there is one).
  */
-static void nohz_balancer_kick(int cpu)
+static void nohz_balancer_kick(void)
 {
 	int ilb_cpu;
 
@@ -6878,15 +6878,13 @@ static inline int on_null_domain(struct rq *rq)
  */
 void trigger_load_balance(struct rq *rq)
 {
-	int cpu = rq->cpu;
-
 	/* Don't need to rebalance while attached to NULL domain */
 	if (time_after_eq(jiffies, rq->next_balance) &&
 	    likely(!on_null_domain(rq)))
 		raise_softirq(SCHED_SOFTIRQ);
 #ifdef CONFIG_NO_HZ_COMMON
 	if (nohz_kick_needed(rq) && likely(!on_null_domain(rq)))
-		nohz_balancer_kick(cpu);
+		nohz_balancer_kick();
 #endif
 }
 
-- 
cgit v0.10.2


From f7ed0a895ead0f093f59898ff9cf4e20768a5f09 Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Mon, 6 Jan 2014 12:34:43 +0100
Subject: sched: Pass 'struct rq' to rebalance_domains()

The cpu information is stored in the struct rq and the caller of the
rebalance_domains function pass the cpu to retrieve the struct rq but
it already has the struct rq info. Replace the cpu parameter with the
struct rq.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1389008085-9069-7-git-send-email-daniel.lezcano@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b91cd93..ff4e0df 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6640,10 +6640,10 @@ void update_max_interval(void)
  *
  * Balancing parameters are set up in init_sched_domains.
  */
-static void rebalance_domains(int cpu, enum cpu_idle_type idle)
+static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
 {
 	int continue_balancing = 1;
-	struct rq *rq = cpu_rq(cpu);
+	int cpu = rq->cpu;
 	unsigned long interval;
 	struct sched_domain *sd;
 	/* Earliest time when we have to do rebalance again */
@@ -6769,7 +6769,7 @@ static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle)
 		update_idle_cpu_load(rq);
 		raw_spin_unlock_irq(&rq->lock);
 
-		rebalance_domains(balance_cpu, CPU_IDLE);
+		rebalance_domains(rq, CPU_IDLE);
 
 		if (time_after(this_rq->next_balance, rq->next_balance))
 			this_rq->next_balance = rq->next_balance;
@@ -6858,7 +6858,7 @@ static void run_rebalance_domains(struct softirq_action *h)
 	enum cpu_idle_type idle = this_rq->idle_balance ?
 						CPU_IDLE : CPU_NOT_IDLE;
 
-	rebalance_domains(this_cpu, idle);
+	rebalance_domains(this_rq, idle);
 
 	/*
 	 * If this cpu has a pending nohz_balance_kick, then do the
-- 
cgit v0.10.2


From 208cb16ba325552a3935bfc002e34561b0d512d7 Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Mon, 6 Jan 2014 12:34:44 +0100
Subject: sched: Pass 'struct rq' to nohz_idle_balance()

The cpu information is stored in the struct rq. Pass the struct rq to
nohz_idle_balance, so all the functions called in run_rebalance_domains have
the same parameters and the 'this_cpu' variable becomes pointless.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
[ Added !SMP build fix. ]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1389008085-9069-8-git-send-email-daniel.lezcano@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ff4e0df..d7220d1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6740,9 +6740,9 @@ out:
  * In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the
  * rebalancing for all the cpus for whom scheduler ticks are stopped.
  */
-static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle)
+static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle)
 {
-	struct rq *this_rq = cpu_rq(this_cpu);
+	int this_cpu = this_rq->cpu;
 	struct rq *rq;
 	int balance_cpu;
 
@@ -6844,7 +6844,7 @@ need_kick:
 	return 1;
 }
 #else
-static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) { }
+static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { }
 #endif
 
 /*
@@ -6853,8 +6853,7 @@ static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) { }
  */
 static void run_rebalance_domains(struct softirq_action *h)
 {
-	int this_cpu = smp_processor_id();
-	struct rq *this_rq = cpu_rq(this_cpu);
+	struct rq *this_rq = this_rq();
 	enum cpu_idle_type idle = this_rq->idle_balance ?
 						CPU_IDLE : CPU_NOT_IDLE;
 
@@ -6865,7 +6864,7 @@ static void run_rebalance_domains(struct softirq_action *h)
 	 * balancing on behalf of the other idle cpus whose ticks are
 	 * stopped.
 	 */
-	nohz_idle_balance(this_cpu, idle);
+	nohz_idle_balance(this_rq, idle);
 }
 
 static inline int on_null_domain(struct rq *rq)
-- 
cgit v0.10.2


From c726099ec224be8078d91072207053ff9a1ad6fc Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Mon, 6 Jan 2014 12:34:45 +0100
Subject: sched: Factor out the on_null_domain() checks in
 trigger_load_balance()

The test on_null_domain is done twice in the trigger_load_balance function.

Move the test at the begin of the function, so there is only one check.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1389008085-9069-9-git-send-email-daniel.lezcano@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d7220d1..b24b6cf 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6878,11 +6878,13 @@ static inline int on_null_domain(struct rq *rq)
 void trigger_load_balance(struct rq *rq)
 {
 	/* Don't need to rebalance while attached to NULL domain */
-	if (time_after_eq(jiffies, rq->next_balance) &&
-	    likely(!on_null_domain(rq)))
+	if (unlikely(on_null_domain(rq)))
+		return;
+
+	if (time_after_eq(jiffies, rq->next_balance))
 		raise_softirq(SCHED_SOFTIRQ);
 #ifdef CONFIG_NO_HZ_COMMON
-	if (nohz_kick_needed(rq) && likely(!on_null_domain(rq)))
+	if (nohz_kick_needed(rq))
 		nohz_balancer_kick();
 #endif
 }
-- 
cgit v0.10.2


From 9ea4c380066fbe23fe0da7f4abfabc444f2467f4 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 19 Nov 2013 16:13:38 +0100
Subject: locking: Optimize lock_bh functions

Currently all _bh_ lock functions do two preempt_count operations:

  local_bh_disable();
  preempt_disable();

and for the unlock:

  preempt_enable_no_resched();
  local_bh_enable();

Since its a waste of perfectly good cycles to modify the same variable
twice when you can do it in one go; use the new
__local_bh_{dis,en}able_ip() functions that allow us to provide a
preempt_count value to add/sub.

So define SOFTIRQ_LOCK_OFFSET as the offset a _bh_ lock needs to
add/sub to be done in one go.

As a bonus it gets rid of the preempt_enable_no_resched() usage.

This reduces a 1000 loops of:

  spin_lock_bh(&bh_lock);
  spin_unlock_bh(&bh_lock);

from 53596 cycles to 51995 cycles. I didn't do enough measurements to
say for absolute sure that the result is significant but the the few
runs I did for each suggest it is so.

Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: jacob.jun.pan@linux.intel.com
Cc: Mike Galbraith <bitbucket@online.de>
Cc: hpa@zytor.com
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: lenb@kernel.org
Cc: rjw@rjwysocki.net
Cc: rui.zhang@intel.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20131119151338.GF3694@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/preempt_mask.h b/include/linux/preempt_mask.h
index d169820..b8d96bc 100644
--- a/include/linux/preempt_mask.h
+++ b/include/linux/preempt_mask.h
@@ -79,6 +79,21 @@
 #endif
 
 /*
+ * The preempt_count offset needed for things like:
+ *
+ *  spin_lock_bh()
+ *
+ * Which need to disable both preemption (CONFIG_PREEMPT_COUNT) and
+ * softirqs, such that unlock sequences of:
+ *
+ *  spin_unlock();
+ *  local_bh_enable();
+ *
+ * Work as expected.
+ */
+#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_CHECK_OFFSET)
+
+/*
  * Are we running in atomic context?  WARNING: this macro cannot
  * always detect atomic context; in particular, it cannot know about
  * held spinlocks in non-preemptible kernels.  Thus it should not be
diff --git a/include/linux/rwlock_api_smp.h b/include/linux/rwlock_api_smp.h
index 9c9f049..5b9b84b 100644
--- a/include/linux/rwlock_api_smp.h
+++ b/include/linux/rwlock_api_smp.h
@@ -172,8 +172,7 @@ static inline void __raw_read_lock_irq(rwlock_t *lock)
 
 static inline void __raw_read_lock_bh(rwlock_t *lock)
 {
-	local_bh_disable();
-	preempt_disable();
+	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
 	rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
 	LOCK_CONTENDED(lock, do_raw_read_trylock, do_raw_read_lock);
 }
@@ -200,8 +199,7 @@ static inline void __raw_write_lock_irq(rwlock_t *lock)
 
 static inline void __raw_write_lock_bh(rwlock_t *lock)
 {
-	local_bh_disable();
-	preempt_disable();
+	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
 	rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
 	LOCK_CONTENDED(lock, do_raw_write_trylock, do_raw_write_lock);
 }
@@ -250,8 +248,7 @@ static inline void __raw_read_unlock_bh(rwlock_t *lock)
 {
 	rwlock_release(&lock->dep_map, 1, _RET_IP_);
 	do_raw_read_unlock(lock);
-	preempt_enable_no_resched();
-	local_bh_enable_ip((unsigned long)__builtin_return_address(0));
+	__local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
 }
 
 static inline void __raw_write_unlock_irqrestore(rwlock_t *lock,
@@ -275,8 +272,7 @@ static inline void __raw_write_unlock_bh(rwlock_t *lock)
 {
 	rwlock_release(&lock->dep_map, 1, _RET_IP_);
 	do_raw_write_unlock(lock);
-	preempt_enable_no_resched();
-	local_bh_enable_ip((unsigned long)__builtin_return_address(0));
+	__local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
 }
 
 #endif /* __LINUX_RWLOCK_API_SMP_H */
diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
index bdb9993..42dfab8 100644
--- a/include/linux/spinlock_api_smp.h
+++ b/include/linux/spinlock_api_smp.h
@@ -131,8 +131,7 @@ static inline void __raw_spin_lock_irq(raw_spinlock_t *lock)
 
 static inline void __raw_spin_lock_bh(raw_spinlock_t *lock)
 {
-	local_bh_disable();
-	preempt_disable();
+	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
 	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
 	LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock);
 }
@@ -174,20 +173,17 @@ static inline void __raw_spin_unlock_bh(raw_spinlock_t *lock)
 {
 	spin_release(&lock->dep_map, 1, _RET_IP_);
 	do_raw_spin_unlock(lock);
-	preempt_enable_no_resched();
-	local_bh_enable_ip((unsigned long)__builtin_return_address(0));
+	__local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
 }
 
 static inline int __raw_spin_trylock_bh(raw_spinlock_t *lock)
 {
-	local_bh_disable();
-	preempt_disable();
+	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
 	if (do_raw_spin_trylock(lock)) {
 		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
 		return 1;
 	}
-	preempt_enable_no_resched();
-	local_bh_enable_ip((unsigned long)__builtin_return_address(0));
+	__local_bh_enable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
 	return 0;
 }
 
diff --git a/include/linux/spinlock_api_up.h b/include/linux/spinlock_api_up.h
index af1f472..d0d1888 100644
--- a/include/linux/spinlock_api_up.h
+++ b/include/linux/spinlock_api_up.h
@@ -24,11 +24,14 @@
  * flags straight, to suppress compiler warnings of unused lock
  * variables, and to add the proper checker annotations:
  */
+#define ___LOCK(lock) \
+  do { __acquire(lock); (void)(lock); } while (0)
+
 #define __LOCK(lock) \
-  do { preempt_disable(); __acquire(lock); (void)(lock); } while (0)
+  do { preempt_disable(); ___LOCK(lock); } while (0)
 
 #define __LOCK_BH(lock) \
-  do { local_bh_disable(); __LOCK(lock); } while (0)
+  do { __local_bh_disable_ip(_THIS_IP_, SOFTIRQ_LOCK_OFFSET); ___LOCK(lock); } while (0)
 
 #define __LOCK_IRQ(lock) \
   do { local_irq_disable(); __LOCK(lock); } while (0)
@@ -36,12 +39,15 @@
 #define __LOCK_IRQSAVE(lock, flags) \
   do { local_irq_save(flags); __LOCK(lock); } while (0)
 
+#define ___UNLOCK(lock) \
+  do { __release(lock); (void)(lock); } while (0)
+
 #define __UNLOCK(lock) \
-  do { preempt_enable(); __release(lock); (void)(lock); } while (0)
+  do { preempt_enable(); ___UNLOCK(lock); } while (0)
 
 #define __UNLOCK_BH(lock) \
-  do { preempt_enable_no_resched(); local_bh_enable(); \
-	  __release(lock); (void)(lock); } while (0)
+  do { __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_LOCK_OFFSET); \
+       ___UNLOCK(lock); } while (0)
 
 #define __UNLOCK_IRQ(lock) \
   do { local_irq_enable(); __UNLOCK(lock); } while (0)
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 11025cc..7500cce1 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -107,7 +107,7 @@ static void __local_bh_disable(unsigned long ip, unsigned int cnt)
 	/*
 	 * Were softirqs turned off above:
 	 */
-	if (softirq_count() == cnt)
+	if (softirq_count() == (cnt & SOFTIRQ_MASK))
 		trace_softirqs_off(ip);
 	raw_local_irq_restore(flags);
 
@@ -133,7 +133,7 @@ static void __local_bh_enable(unsigned int cnt)
 {
 	WARN_ON_ONCE(!irqs_disabled());
 
-	if (softirq_count() == cnt)
+	if (softirq_count() == (cnt & SOFTIRQ_MASK))
 		trace_softirqs_on(_RET_IP_);
 	preempt_count_sub(cnt);
 }
-- 
cgit v0.10.2


From 62b94a08da1bae9d187d49dfcd6665af393750f8 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 20 Nov 2013 16:52:19 +0100
Subject: sched/preempt: Take away preempt_enable_no_resched() from modules

Discourage drivers/modules to be creative with preemption.

Sadly all is implemented in macros and inline so if they want to do
evil they still can, but at least try and discourage some.

Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Eliezer Tamir <eliezer.tamir@linux.intel.com>
Cc: rui.zhang@intel.com
Cc: jacob.jun.pan@linux.intel.com
Cc: Mike Galbraith <bitbucket@online.de>
Cc: hpa@zytor.com
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: lenb@kernel.org
Cc: rjw@rjwysocki.net
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/n/tip-fn7h6vu8wtgxk0ih402qcijx@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index a3d9dc8..dd9ddf8 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -64,7 +64,11 @@ do { \
 } while (0)
 
 #else
-#define preempt_enable() preempt_enable_no_resched()
+#define preempt_enable() \
+do { \
+	barrier(); \
+	preempt_count_dec(); \
+} while (0)
 #define preempt_check_resched() do { } while (0)
 #endif
 
@@ -93,7 +97,11 @@ do { \
 		__preempt_schedule_context(); \
 } while (0)
 #else
-#define preempt_enable_notrace() preempt_enable_no_resched_notrace()
+#define preempt_enable_notrace() \
+do { \
+	barrier(); \
+	__preempt_count_dec(); \
+} while (0)
 #endif
 
 #else /* !CONFIG_PREEMPT_COUNT */
@@ -116,6 +124,16 @@ do { \
 
 #endif /* CONFIG_PREEMPT_COUNT */
 
+#ifdef MODULE
+/*
+ * Modules have no business playing preemption tricks.
+ */
+#undef sched_preempt_enable_no_resched
+#undef preempt_enable_no_resched
+#undef preempt_enable_no_resched_notrace
+#undef preempt_check_resched
+#endif
+
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 
 struct preempt_notifier;
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 9d8cf05..ecd3319 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -25,13 +25,16 @@ static inline void pagefault_disable(void)
 
 static inline void pagefault_enable(void)
 {
+#ifndef CONFIG_PREEMPT
 	/*
 	 * make sure to issue those last loads/stores before enabling
 	 * the pagefault handler again.
 	 */
 	barrier();
 	preempt_count_dec();
-	preempt_check_resched();
+#else
+	preempt_enable();
+#endif
 }
 
 #ifndef ARCH_HAS_NOCACHE_UACCESS
-- 
cgit v0.10.2


From 5dd12c2152743747ca9f50ef80281e54cc416dc0 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 29 Nov 2013 18:04:39 +0100
Subject: sched/clock, x86: Use mul_u64_u32_shr() for native_sched_clock()

Use mul_u64_u32_shr() so that x86_64 can use a single 64x64->128 mul.

Before:

0000000000000560 <native_sched_clock>:
 560:   44 8b 1d 00 00 00 00    mov    0x0(%rip),%r11d        # 567 <native_sched_clock+0x7>
 567:   55                      push   %rbp
 568:   48 89 e5                mov    %rsp,%rbp
 56b:   45 85 db                test   %r11d,%r11d
 56e:   75 4f                   jne    5bf <native_sched_clock+0x5f>
 570:   0f 31                   rdtsc
 572:   89 c0                   mov    %eax,%eax
 574:   48 c1 e2 20             shl    $0x20,%rdx
 578:   48 c7 c1 00 00 00 00    mov    $0x0,%rcx
 57f:   48 09 c2                or     %rax,%rdx
 582:   48 c7 c7 00 00 00 00    mov    $0x0,%rdi
 589:   65 8b 04 25 00 00 00    mov    %gs:0x0,%eax
 590:   00
 591:   48 98                   cltq
 593:   48 8b 34 c5 00 00 00    mov    0x0(,%rax,8),%rsi
 59a:   00
 59b:   48 89 d0                mov    %rdx,%rax
 59e:   81 e2 ff 03 00 00       and    $0x3ff,%edx
 5a4:   48 c1 e8 0a             shr    $0xa,%rax
 5a8:   48 0f af 14 0e          imul   (%rsi,%rcx,1),%rdx
 5ad:   48 0f af 04 0e          imul   (%rsi,%rcx,1),%rax
 5b2:   5d                      pop    %rbp
 5b3:   48 03 04 3e             add    (%rsi,%rdi,1),%rax
 5b7:   48 c1 ea 0a             shr    $0xa,%rdx
 5bb:   48 01 d0                add    %rdx,%rax
 5be:   c3                      retq

After:

0000000000000550 <native_sched_clock>:
 550:   8b 3d 00 00 00 00       mov    0x0(%rip),%edi        # 556 <native_sched_clock+0x6>
 556:   55                      push   %rbp
 557:   48 89 e5                mov    %rsp,%rbp
 55a:   48 83 e4 f0             and    $0xfffffffffffffff0,%rsp
 55e:   85 ff                   test   %edi,%edi
 560:   75 2c                   jne    58e <native_sched_clock+0x3e>
 562:   0f 31                   rdtsc
 564:   89 c0                   mov    %eax,%eax
 566:   48 c1 e2 20             shl    $0x20,%rdx
 56a:   48 09 c2                or     %rax,%rdx
 56d:   65 48 8b 04 25 00 00    mov    %gs:0x0,%rax
 574:   00 00
 576:   89 c0                   mov    %eax,%eax
 578:   48 f7 e2                mul    %rdx
 57b:   65 48 8b 0c 25 00 00    mov    %gs:0x0,%rcx
 582:   00 00
 584:   c9                      leaveq
 585:   48 0f ac d0 0a          shrd   $0xa,%rdx,%rax
 58a:   48 01 c8                add    %rcx,%rax
 58d:   c3                      retq

                        MAINLINE   POST

    sched_clock_stable: 1	   1
    (cold) sched_clock: 329841     331312
    (cold) local_clock: 301773     310296
    (warm) sched_clock: 38375      38247
    (warm) local_clock: 100371     102713
    (warm) rdtsc:       27340      27289
    sched_clock_stable: 0          0
    (cold) sched_clock: 382634     372706
    (cold) local_clock: 396890     399275
    (warm) sched_clock: 38194      38124
    (warm) local_clock: 143452     148698
    (warm) rdtsc:       27345      27365

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/n/tip-piu203ses5y1g36bnyw2n16x@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index 34baa0e..10a78c0 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -4,6 +4,7 @@
 #include <linux/pm.h>
 #include <linux/percpu.h>
 #include <linux/interrupt.h>
+#include <linux/math64.h>
 
 #define TICK_SIZE (tick_nsec / 1000)
 
@@ -57,10 +58,8 @@ DECLARE_PER_CPU(unsigned long long, cyc2ns_offset);
 
 static inline unsigned long long __cycles_2_ns(unsigned long long cyc)
 {
-	int cpu = smp_processor_id();
-	unsigned long long ns = per_cpu(cyc2ns_offset, cpu);
-	ns += mult_frac(cyc, per_cpu(cyc2ns, cpu),
-			(1UL << CYC2NS_SCALE_FACTOR));
+	unsigned long long ns = this_cpu_read(cyc2ns_offset);
+	ns += mul_u64_u32_shr(cyc, this_cpu_read(cyc2ns), CYC2NS_SCALE_FACTOR);
 	return ns;
 }
 
-- 
cgit v0.10.2


From 57c67da274f3fab38e08d2c9edf08b89e1d9c71d Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 29 Nov 2013 15:39:25 +0100
Subject: sched/clock, x86: Move some cyc2ns() code around

There are no __cycles_2_ns() users outside of arch/x86/kernel/tsc.c,
so move it there.

There are no cycles_2_ns() users.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-01lslnavfgo3kmbo4532zlcj@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index 10a78c0..b4c6676 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -13,66 +13,7 @@ extern int recalibrate_cpu_khz(void);
 
 extern int no_timer_check;
 
-/* Accelerators for sched_clock()
- * convert from cycles(64bits) => nanoseconds (64bits)
- *  basic equation:
- *		ns = cycles / (freq / ns_per_sec)
- *		ns = cycles * (ns_per_sec / freq)
- *		ns = cycles * (10^9 / (cpu_khz * 10^3))
- *		ns = cycles * (10^6 / cpu_khz)
- *
- *	Then we use scaling math (suggested by george@mvista.com) to get:
- *		ns = cycles * (10^6 * SC / cpu_khz) / SC
- *		ns = cycles * cyc2ns_scale / SC
- *
- *	And since SC is a constant power of two, we can convert the div
- *  into a shift.
- *
- *  We can use khz divisor instead of mhz to keep a better precision, since
- *  cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits.
- *  (mathieu.desnoyers@polymtl.ca)
- *
- *			-johnstul@us.ibm.com "math is hard, lets go shopping!"
- *
- * In:
- *
- * ns = cycles * cyc2ns_scale / SC
- *
- * Although we may still have enough bits to store the value of ns,
- * in some cases, we may not have enough bits to store cycles * cyc2ns_scale,
- * leading to an incorrect result.
- *
- * To avoid this, we can decompose 'cycles' into quotient and remainder
- * of division by SC.  Then,
- *
- * ns = (quot * SC + rem) * cyc2ns_scale / SC
- *    = quot * cyc2ns_scale + (rem * cyc2ns_scale) / SC
- *
- *			- sqazi@google.com
- */
-
 DECLARE_PER_CPU(unsigned long, cyc2ns);
 DECLARE_PER_CPU(unsigned long long, cyc2ns_offset);
 
-#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
-
-static inline unsigned long long __cycles_2_ns(unsigned long long cyc)
-{
-	unsigned long long ns = this_cpu_read(cyc2ns_offset);
-	ns += mul_u64_u32_shr(cyc, this_cpu_read(cyc2ns), CYC2NS_SCALE_FACTOR);
-	return ns;
-}
-
-static inline unsigned long long cycles_2_ns(unsigned long long cyc)
-{
-	unsigned long long ns;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	ns = __cycles_2_ns(cyc);
-	local_irq_restore(flags);
-
-	return ns;
-}
-
 #endif /* _ASM_X86_TIMER_H */
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 930e5d4..b4a04ac 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -38,6 +38,66 @@ static int __read_mostly tsc_unstable;
 static int __read_mostly tsc_disabled = -1;
 
 int tsc_clocksource_reliable;
+
+/* Accelerators for sched_clock()
+ * convert from cycles(64bits) => nanoseconds (64bits)
+ *  basic equation:
+ *              ns = cycles / (freq / ns_per_sec)
+ *              ns = cycles * (ns_per_sec / freq)
+ *              ns = cycles * (10^9 / (cpu_khz * 10^3))
+ *              ns = cycles * (10^6 / cpu_khz)
+ *
+ *      Then we use scaling math (suggested by george@mvista.com) to get:
+ *              ns = cycles * (10^6 * SC / cpu_khz) / SC
+ *              ns = cycles * cyc2ns_scale / SC
+ *
+ *      And since SC is a constant power of two, we can convert the div
+ *  into a shift.
+ *
+ *  We can use khz divisor instead of mhz to keep a better precision, since
+ *  cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits.
+ *  (mathieu.desnoyers@polymtl.ca)
+ *
+ *                      -johnstul@us.ibm.com "math is hard, lets go shopping!"
+ */
+
+DEFINE_PER_CPU(unsigned long, cyc2ns);
+DEFINE_PER_CPU(unsigned long long, cyc2ns_offset);
+
+#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
+
+static inline unsigned long long cycles_2_ns(unsigned long long cyc)
+{
+	unsigned long long ns = this_cpu_read(cyc2ns_offset);
+	ns += mul_u64_u32_shr(cyc, this_cpu_read(cyc2ns), CYC2NS_SCALE_FACTOR);
+	return ns;
+}
+
+static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
+{
+	unsigned long long tsc_now, ns_now, *offset;
+	unsigned long flags, *scale;
+
+	local_irq_save(flags);
+	sched_clock_idle_sleep_event();
+
+	scale = &per_cpu(cyc2ns, cpu);
+	offset = &per_cpu(cyc2ns_offset, cpu);
+
+	rdtscll(tsc_now);
+	ns_now = cycles_2_ns(tsc_now);
+
+	if (cpu_khz) {
+		*scale = ((NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR) +
+				cpu_khz / 2) / cpu_khz;
+		*offset = ns_now - mult_frac(tsc_now, *scale,
+					     (1UL << CYC2NS_SCALE_FACTOR));
+	}
+
+	sched_clock_idle_wakeup_event(0);
+	local_irq_restore(flags);
+}
+
 /*
  * Scheduler clock - returns current time in nanosec units.
  */
@@ -62,7 +122,7 @@ u64 native_sched_clock(void)
 	rdtscll(this_offset);
 
 	/* return the value in ns */
-	return __cycles_2_ns(this_offset);
+	return cycles_2_ns(this_offset);
 }
 
 /* We need to define a real function for sched_clock, to override the
@@ -589,56 +649,6 @@ int recalibrate_cpu_khz(void)
 EXPORT_SYMBOL(recalibrate_cpu_khz);
 
 
-/* Accelerators for sched_clock()
- * convert from cycles(64bits) => nanoseconds (64bits)
- *  basic equation:
- *              ns = cycles / (freq / ns_per_sec)
- *              ns = cycles * (ns_per_sec / freq)
- *              ns = cycles * (10^9 / (cpu_khz * 10^3))
- *              ns = cycles * (10^6 / cpu_khz)
- *
- *      Then we use scaling math (suggested by george@mvista.com) to get:
- *              ns = cycles * (10^6 * SC / cpu_khz) / SC
- *              ns = cycles * cyc2ns_scale / SC
- *
- *      And since SC is a constant power of two, we can convert the div
- *  into a shift.
- *
- *  We can use khz divisor instead of mhz to keep a better precision, since
- *  cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits.
- *  (mathieu.desnoyers@polymtl.ca)
- *
- *                      -johnstul@us.ibm.com "math is hard, lets go shopping!"
- */
-
-DEFINE_PER_CPU(unsigned long, cyc2ns);
-DEFINE_PER_CPU(unsigned long long, cyc2ns_offset);
-
-static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
-{
-	unsigned long long tsc_now, ns_now, *offset;
-	unsigned long flags, *scale;
-
-	local_irq_save(flags);
-	sched_clock_idle_sleep_event();
-
-	scale = &per_cpu(cyc2ns, cpu);
-	offset = &per_cpu(cyc2ns_offset, cpu);
-
-	rdtscll(tsc_now);
-	ns_now = __cycles_2_ns(tsc_now);
-
-	if (cpu_khz) {
-		*scale = ((NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR) +
-				cpu_khz / 2) / cpu_khz;
-		*offset = ns_now - mult_frac(tsc_now, *scale,
-					     (1UL << CYC2NS_SCALE_FACTOR));
-	}
-
-	sched_clock_idle_wakeup_event(0);
-	local_irq_restore(flags);
-}
-
 static unsigned long long cyc2ns_suspend;
 
 void tsc_save_sched_clock_state(void)
-- 
cgit v0.10.2


From 6af206fd911c825b83dd4efb2534a3a34ce77072 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Sat, 28 Dec 2013 15:45:08 -0300
Subject: perf stat: Don't show counter information when workload fails

When starting a workload 'stat' wasn't using prepare_workload evlist
method's signal based exec() error reporting mechanism.

Use it so that the we don't report 'not counted' counters.

Before:

  [acme@zoo linux]$ perf stat dfadsfa
  dfadsfa: No such file or directory

   Performance counter stats for 'dfadsfa':

       <not counted>      task-clock
       <not counted>      context-switches
       <not counted>      cpu-migrations
       <not counted>      page-faults
       <not counted>      cycles
       <not counted>      stalled-cycles-frontend
     <not supported>      stalled-cycles-backend
       <not counted>      instructions
       <not counted>      branches
       <not counted>      branch-misses

         0.001831462 seconds time elapsed

  [acme@zoo linux]$

After:

  [acme@zoo linux]$ perf stat dfadsfa
  dfadsfa: No such file or directory
  [acme@zoo linux]$

Reported-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-5yui3bv7e3hitxucnjsn6z8q@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 106a5e5..1c76c7a 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -509,6 +509,18 @@ static void handle_initial_delay(void)
 	}
 }
 
+static volatile bool workload_exec_failed;
+
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1
+ * if the fork fails, since we asked by setting its
+ * want_signal to true.
+ */
+static void workload_exec_failed_signal(int signo __maybe_unused)
+{
+	workload_exec_failed = true;
+}
+
 static int __run_perf_stat(int argc, const char **argv)
 {
 	char msg[512];
@@ -529,7 +541,7 @@ static int __run_perf_stat(int argc, const char **argv)
 
 	if (forks) {
 		if (perf_evlist__prepare_workload(evsel_list, &target, argv,
-						  false, false) < 0) {
+						  false, true) < 0) {
 			perror("failed to prepare workload");
 			return -1;
 		}
@@ -584,6 +596,14 @@ static int __run_perf_stat(int argc, const char **argv)
 	clock_gettime(CLOCK_MONOTONIC, &ref_time);
 
 	if (forks) {
+		/*
+		 * perf_evlist__prepare_workload will, after we call
+		 * perf_evlist__start_Workload, send a SIGUSR1 if the exec call
+		 * fails, that we will catch in workload_signal to flip
+		 * workload_exec_failed.
+ 		 */
+		signal(SIGUSR1, workload_exec_failed_signal);
+
 		perf_evlist__start_workload(evsel_list);
 		handle_initial_delay();
 
@@ -594,6 +614,10 @@ static int __run_perf_stat(int argc, const char **argv)
 			}
 		}
 		wait(&status);
+
+		if (workload_exec_failed)
+			return -1;
+
 		if (WIFSIGNALED(status))
 			psignal(WTERMSIG(status), argv[0]);
 	} else {
-- 
cgit v0.10.2


From f33cbe72e6166b97d6fa2400cb00a885b47999d7 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 2 Jan 2014 15:11:25 -0300
Subject: perf evlist: Send the errno in the signal when workload fails

When a tool uses perf_evlist__start_workload and the supplied workload
fails (e.g.: its binary wasn't found), perror was being used to print
the error reason.

This is undesirable, as the caller may be a GUI, when it wants to have
total control of the error reporting process.

So move to using sigaction(SA_SIGINFO) + siginfo_t->sa_value->sival_int
to communicate to the caller the errno and let it print it using the UI
of its choosing.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-epgcv7kjq8ll2udqfken92pz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 6ec0cbc..f987d38 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -341,6 +341,22 @@ static void record__init_features(struct record *rec)
 		perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
 }
 
+static volatile int workload_exec_errno;
+
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1
+ * if the fork fails, since we asked by setting its
+ * want_signal to true.
+ */
+static void workload_exec_failed_signal(int signo, siginfo_t *info,
+					void *ucontext __maybe_unused)
+{
+	workload_exec_errno = info->si_value.sival_int;
+	done = 1;
+	signr = signo;
+	child_finished = 1;
+}
+
 static int __cmd_record(struct record *rec, int argc, const char **argv)
 {
 	int err;
@@ -359,7 +375,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	on_exit(record__sig_exit, rec);
 	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);
-	signal(SIGUSR1, sig_handler);
 	signal(SIGTERM, sig_handler);
 
 	session = perf_session__new(file, false, NULL);
@@ -492,8 +507,20 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	/*
 	 * Let the child rip
 	 */
-	if (forks)
+	if (forks) {
+		struct sigaction act = {
+			.sa_flags     = SA_SIGINFO,
+			.sa_sigaction = workload_exec_failed_signal,
+		};
+		/*
+		 * perf_evlist__prepare_workload will, after we call
+		 * perf_evlist__start_Workload, send a SIGUSR1 if the exec call
+		 * fails, that we will catch in workload_signal to flip
+		 * workload_exec_errno.
+ 		 */
+		sigaction(SIGUSR1, &act, NULL);
 		perf_evlist__start_workload(evsel_list);
+	}
 
 	for (;;) {
 		int hits = rec->samples;
@@ -521,6 +548,14 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		}
 	}
 
+	if (forks && workload_exec_errno) {
+		char msg[512];
+		const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
+		pr_err("Workload failed: %s\n", emsg);
+		err = -1;
+		goto out_delete_session;
+	}
+
 	if (quiet || signr == SIGUSR1)
 		return 0;
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 1c76c7a..9d0d52d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -58,6 +58,7 @@
 #include "util/thread.h"
 #include "util/thread_map.h"
 
+#include <signal.h>
 #include <stdlib.h>
 #include <sys/prctl.h>
 #include <locale.h>
@@ -509,16 +510,17 @@ static void handle_initial_delay(void)
 	}
 }
 
-static volatile bool workload_exec_failed;
+static volatile int workload_exec_errno;
 
 /*
  * perf_evlist__prepare_workload will send a SIGUSR1
  * if the fork fails, since we asked by setting its
  * want_signal to true.
  */
-static void workload_exec_failed_signal(int signo __maybe_unused)
+static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *info,
+					void *ucontext __maybe_unused)
 {
-	workload_exec_failed = true;
+	workload_exec_errno = info->si_value.sival_int;
 }
 
 static int __run_perf_stat(int argc, const char **argv)
@@ -596,13 +598,17 @@ static int __run_perf_stat(int argc, const char **argv)
 	clock_gettime(CLOCK_MONOTONIC, &ref_time);
 
 	if (forks) {
+		struct sigaction act = {
+			.sa_flags     = SA_SIGINFO,
+			.sa_sigaction = workload_exec_failed_signal,
+		};
 		/*
 		 * perf_evlist__prepare_workload will, after we call
 		 * perf_evlist__start_Workload, send a SIGUSR1 if the exec call
 		 * fails, that we will catch in workload_signal to flip
-		 * workload_exec_failed.
+		 * workload_exec_errno.
  		 */
-		signal(SIGUSR1, workload_exec_failed_signal);
+		sigaction(SIGUSR1, &act, NULL);
 
 		perf_evlist__start_workload(evsel_list);
 		handle_initial_delay();
@@ -615,8 +621,11 @@ static int __run_perf_stat(int argc, const char **argv)
 		}
 		wait(&status);
 
-		if (workload_exec_failed)
+		if (workload_exec_errno) {
+			const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
+			pr_err("Workload failed: %s\n", emsg);
 			return -1;
+		}
 
 		if (WIFSIGNALED(status))
 			psignal(WTERMSIG(status), argv[0]);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index b08a7ec..4a30c87 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1073,9 +1073,14 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
 
 		execvp(argv[0], (char **)argv);
 
-		perror(argv[0]);
-		if (want_signal)
-			kill(getppid(), SIGUSR1);
+		if (want_signal) {
+			union sigval val;
+
+			val.sival_int = errno;
+			if (sigqueue(getppid(), SIGUSR1, val))
+				perror(argv[0]);
+		} else
+			perror(argv[0]);
 		exit(-1);
 	}
 
-- 
cgit v0.10.2


From 735f7e0bbebe755d707182188c4a5e88c581fc1c Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 3 Jan 2014 14:56:49 -0300
Subject: perf evlist: Move the SIGUSR1 error reporting logic to
 prepare_workload

So that we have the boilerplate in the preparation method, instead of
open coded in tools wanting the reporting when the exec fails.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-purbdzcphdveskh7wwmnm4t7@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index f987d38..ea7c306 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -390,7 +390,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	if (forks) {
 		err = perf_evlist__prepare_workload(evsel_list, &opts->target,
 						    argv, file->is_pipe,
-						    true);
+						    workload_exec_failed_signal);
 		if (err < 0) {
 			pr_err("Couldn't run the workload!\n");
 			goto out_delete_session;
@@ -507,20 +507,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	/*
 	 * Let the child rip
 	 */
-	if (forks) {
-		struct sigaction act = {
-			.sa_flags     = SA_SIGINFO,
-			.sa_sigaction = workload_exec_failed_signal,
-		};
-		/*
-		 * perf_evlist__prepare_workload will, after we call
-		 * perf_evlist__start_Workload, send a SIGUSR1 if the exec call
-		 * fails, that we will catch in workload_signal to flip
-		 * workload_exec_errno.
- 		 */
-		sigaction(SIGUSR1, &act, NULL);
+	if (forks)
 		perf_evlist__start_workload(evsel_list);
-	}
 
 	for (;;) {
 		int hits = rec->samples;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 9d0d52d..f8456ca 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -58,7 +58,6 @@
 #include "util/thread.h"
 #include "util/thread_map.h"
 
-#include <signal.h>
 #include <stdlib.h>
 #include <sys/prctl.h>
 #include <locale.h>
@@ -542,8 +541,8 @@ static int __run_perf_stat(int argc, const char **argv)
 	}
 
 	if (forks) {
-		if (perf_evlist__prepare_workload(evsel_list, &target, argv,
-						  false, true) < 0) {
+		if (perf_evlist__prepare_workload(evsel_list, &target, argv, false,
+						  workload_exec_failed_signal) < 0) {
 			perror("failed to prepare workload");
 			return -1;
 		}
@@ -598,18 +597,6 @@ static int __run_perf_stat(int argc, const char **argv)
 	clock_gettime(CLOCK_MONOTONIC, &ref_time);
 
 	if (forks) {
-		struct sigaction act = {
-			.sa_flags     = SA_SIGINFO,
-			.sa_sigaction = workload_exec_failed_signal,
-		};
-		/*
-		 * perf_evlist__prepare_workload will, after we call
-		 * perf_evlist__start_Workload, send a SIGUSR1 if the exec call
-		 * fails, that we will catch in workload_signal to flip
-		 * workload_exec_errno.
- 		 */
-		sigaction(SIGUSR1, &act, NULL);
-
 		perf_evlist__start_workload(evsel_list);
 		handle_initial_delay();
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index c5b4bc5..5498eac 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1895,7 +1895,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 
 	if (forks) {
 		err = perf_evlist__prepare_workload(evlist, &trace->opts.target,
-						    argv, false, false);
+						    argv, false, NULL);
 		if (err < 0) {
 			fprintf(trace->output, "Couldn't run the workload!\n");
 			goto out_delete_maps;
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index eeba562..fa0ed35 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -83,8 +83,7 @@ int test__PERF_RECORD(void)
 	 * so that we have time to open the evlist (calling sys_perf_event_open
 	 * on all the fds) and then mmap them.
 	 */
-	err = perf_evlist__prepare_workload(evlist, &opts.target, argv,
-					    false, false);
+	err = perf_evlist__prepare_workload(evlist, &opts.target, argv, false, NULL);
 	if (err < 0) {
 		pr_debug("Couldn't run the workload!\n");
 		goto out_delete_maps;
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index d09ab57..44e339d 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -9,12 +9,21 @@
 static int exited;
 static int nr_exit;
 
-static void sig_handler(int sig)
+static void sig_handler(int sig __maybe_unused)
 {
 	exited = 1;
+}
 
-	if (sig == SIGUSR1)
-		nr_exit = -1;
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
+ * we asked by setting its exec_error to this handler.
+ */
+static void workload_exec_failed_signal(int signo __maybe_unused,
+					siginfo_t *info __maybe_unused,
+					void *ucontext __maybe_unused)
+{
+	exited	= 1;
+	nr_exit = -1;
 }
 
 /*
@@ -35,7 +44,6 @@ int test__task_exit(void)
 	const char *argv[] = { "true", NULL };
 
 	signal(SIGCHLD, sig_handler);
-	signal(SIGUSR1, sig_handler);
 
 	evlist = perf_evlist__new_default();
 	if (evlist == NULL) {
@@ -57,7 +65,8 @@ int test__task_exit(void)
 		goto out_delete_maps;
 	}
 
-	err = perf_evlist__prepare_workload(evlist, &target, argv, false, true);
+	err = perf_evlist__prepare_workload(evlist, &target, argv, false,
+					    workload_exec_failed_signal);
 	if (err < 0) {
 		pr_debug("Couldn't run the workload!\n");
 		goto out_delete_maps;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 4a30c87..96b3ef5 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1029,7 +1029,7 @@ out_err:
 
 int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *target,
 				  const char *argv[], bool pipe_output,
-				  bool want_signal)
+				  void (*exec_error)(int signo, siginfo_t *info, void *ucontext))
 {
 	int child_ready_pipe[2], go_pipe[2];
 	char bf;
@@ -1073,7 +1073,7 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
 
 		execvp(argv[0], (char **)argv);
 
-		if (want_signal) {
+		if (exec_error) {
 			union sigval val;
 
 			val.sival_int = errno;
@@ -1084,6 +1084,14 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
 		exit(-1);
 	}
 
+	if (exec_error) {
+		struct sigaction act = {
+			.sa_flags     = SA_SIGINFO,
+			.sa_sigaction = exec_error,
+		};
+		sigaction(SIGUSR1, &act, NULL);
+	}
+
 	if (target__none(target))
 		evlist->threads->map[0] = evlist->workload.pid;
 
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 2fe5195..18d1222c 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -103,7 +103,8 @@ int record_opts__config(struct record_opts *opts);
 int perf_evlist__prepare_workload(struct perf_evlist *evlist,
 				  struct target *target,
 				  const char *argv[], bool pipe_output,
-				  bool want_signal);
+				  void (*exec_error)(int signo, siginfo_t *info,
+						     void *ucontext));
 int perf_evlist__start_workload(struct perf_evlist *evlist);
 
 int perf_evlist__parse_mmap_pages(const struct option *opt,
-- 
cgit v0.10.2


From 3e2be2da8f76ef5b2e8e59c3dc8acd24640b4af4 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 3 Jan 2014 15:03:26 -0300
Subject: perf record: Remove old evsel_list usage

To be consistent with other places, use just 'evlist' for the evsel list
variable, and since we have it in 'struct record', use it directly from
there.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-396bnfvmlxrsj3o2tk47b8t1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index ea7c306..6dcb8aa 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -324,7 +324,6 @@ out:
 
 static void record__init_features(struct record *rec)
 {
-	struct perf_evlist *evsel_list = rec->evlist;
 	struct perf_session *session = rec->session;
 	int feat;
 
@@ -334,7 +333,7 @@ static void record__init_features(struct record *rec)
 	if (rec->no_buildid)
 		perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
 
-	if (!have_tracepoints(&evsel_list->entries))
+	if (!have_tracepoints(&rec->evlist->entries))
 		perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
 
 	if (!rec->opts.branch_stack)
@@ -365,7 +364,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	struct machine *machine;
 	struct perf_tool *tool = &rec->tool;
 	struct record_opts *opts = &rec->opts;
-	struct perf_evlist *evsel_list = rec->evlist;
 	struct perf_data_file *file = &rec->file;
 	struct perf_session *session;
 	bool disabled = false;
@@ -388,7 +386,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	record__init_features(rec);
 
 	if (forks) {
-		err = perf_evlist__prepare_workload(evsel_list, &opts->target,
+		err = perf_evlist__prepare_workload(rec->evlist, &opts->target,
 						    argv, file->is_pipe,
 						    workload_exec_failed_signal);
 		if (err < 0) {
@@ -402,7 +400,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		goto out_delete_session;
 	}
 
-	if (!evsel_list->nr_groups)
+	if (!rec->evlist->nr_groups)
 		perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);
 
 	/*
@@ -415,7 +413,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		if (err < 0)
 			goto out_delete_session;
 	} else {
-		err = perf_session__write_header(session, evsel_list,
+		err = perf_session__write_header(session, rec->evlist,
 						 file->fd, false);
 		if (err < 0)
 			goto out_delete_session;
@@ -439,7 +437,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 			goto out_delete_session;
 		}
 
-		if (have_tracepoints(&evsel_list->entries)) {
+		if (have_tracepoints(&rec->evlist->entries)) {
 			/*
 			 * FIXME err <= 0 here actually means that
 			 * there were no tracepoints so its not really
@@ -448,7 +446,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 			 * return this more properly and also
 			 * propagate errors that now are calling die()
 			 */
-			err = perf_event__synthesize_tracing_data(tool, file->fd, evsel_list,
+			err = perf_event__synthesize_tracing_data(tool, file->fd, rec->evlist,
 								  process_synthesized_event);
 			if (err <= 0) {
 				pr_err("Couldn't record tracing data.\n");
@@ -480,7 +478,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 					 perf_event__synthesize_guest_os, tool);
 	}
 
-	err = __machine__synthesize_threads(machine, tool, &opts->target, evsel_list->threads,
+	err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
 					    process_synthesized_event, opts->sample_address);
 	if (err != 0)
 		goto out_delete_session;
@@ -502,13 +500,13 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	 * so don't spoil it by prematurely enabling them.
 	 */
 	if (!target__none(&opts->target))
-		perf_evlist__enable(evsel_list);
+		perf_evlist__enable(rec->evlist);
 
 	/*
 	 * Let the child rip
 	 */
 	if (forks)
-		perf_evlist__start_workload(evsel_list);
+		perf_evlist__start_workload(rec->evlist);
 
 	for (;;) {
 		int hits = rec->samples;
@@ -521,7 +519,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		if (hits == rec->samples) {
 			if (done)
 				break;
-			err = poll(evsel_list->pollfd, evsel_list->nr_fds, -1);
+			err = poll(rec->evlist->pollfd, rec->evlist->nr_fds, -1);
 			waking++;
 		}
 
@@ -531,7 +529,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		 * disable events in this case.
 		 */
 		if (done && !disabled && !target__none(&opts->target)) {
-			perf_evlist__disable(evsel_list);
+			perf_evlist__disable(rec->evlist);
 			disabled = true;
 		}
 	}
@@ -901,16 +899,13 @@ const struct option record_options[] = {
 int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	int err = -ENOMEM;
-	struct perf_evlist *evsel_list;
 	struct record *rec = &record;
 	char errbuf[BUFSIZ];
 
-	evsel_list = perf_evlist__new();
-	if (evsel_list == NULL)
+	rec->evlist = perf_evlist__new();
+	if (rec->evlist == NULL)
 		return -ENOMEM;
 
-	rec->evlist = evsel_list;
-
 	argc = parse_options(argc, argv, record_options, record_usage,
 			    PARSE_OPT_STOP_AT_NON_OPTION);
 	if (!argc && target__none(&rec->opts.target))
@@ -937,8 +932,8 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (rec->no_buildid_cache || rec->no_buildid)
 		disable_buildid_cache();
 
-	if (evsel_list->nr_entries == 0 &&
-	    perf_evlist__add_default(evsel_list) < 0) {
+	if (rec->evlist->nr_entries == 0 &&
+	    perf_evlist__add_default(rec->evlist) < 0) {
 		pr_err("Not enough memory for event selector list\n");
 		goto out_symbol_exit;
 	}
@@ -964,7 +959,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 	}
 
 	err = -ENOMEM;
-	if (perf_evlist__create_maps(evsel_list, &rec->opts.target) < 0)
+	if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
 		usage_with_options(record_usage, record_options);
 
 	if (record_opts__config(&rec->opts)) {
@@ -974,10 +969,10 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	err = __cmd_record(&record, argc, argv);
 
-	perf_evlist__munmap(evsel_list);
-	perf_evlist__close(evsel_list);
+	perf_evlist__munmap(rec->evlist);
+	perf_evlist__close(rec->evlist);
 out_free_fd:
-	perf_evlist__delete_maps(evsel_list);
+	perf_evlist__delete_maps(rec->evlist);
 out_symbol_exit:
 	symbol__exit();
 	return err;
-- 
cgit v0.10.2


From 03ad9747c5f2169556467101e96bc390c5aa4b83 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 3 Jan 2014 15:56:06 -0300
Subject: perf evlist: Move destruction of maps to evlist destructor

Instead of requiring tools to do an extra destructor call just before
calling perf_evlist__delete.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-0jd2ptzyikxb5wp7inzz2ah2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index a6ec105..858b11b 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1556,10 +1556,8 @@ out:
 	if (kvm->session)
 		perf_session__delete(kvm->session);
 	kvm->session = NULL;
-	if (kvm->evlist) {
-		perf_evlist__delete_maps(kvm->evlist);
+	if (kvm->evlist)
 		perf_evlist__delete(kvm->evlist);
-	}
 
 	return err;
 }
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 6dcb8aa..5149b41 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -964,15 +964,13 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	if (record_opts__config(&rec->opts)) {
 		err = -EINVAL;
-		goto out_free_fd;
+		goto out_symbol_exit;
 	}
 
 	err = __cmd_record(&record, argc, argv);
 
 	perf_evlist__munmap(rec->evlist);
 	perf_evlist__close(rec->evlist);
-out_free_fd:
-	perf_evlist__delete_maps(rec->evlist);
 out_symbol_exit:
 	symbol__exit();
 	return err;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f8456ca..6ca0766 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1782,14 +1782,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (interval && interval < 100) {
 		pr_err("print interval must be >= 100ms\n");
 		parse_options_usage(stat_usage, options, "I", 1);
-		goto out_free_maps;
+		goto out;
 	}
 
 	if (perf_evlist__alloc_stats(evsel_list, interval))
-		goto out_free_maps;
+		goto out;
 
 	if (perf_stat_init_aggr_mode())
-		goto out_free_maps;
+		goto out;
 
 	/*
 	 * We dont want to block the signals - that would cause
@@ -1821,8 +1821,6 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		print_stat(argc, argv);
 
 	perf_evlist__free_stats(evsel_list);
-out_free_maps:
-	perf_evlist__delete_maps(evsel_list);
 out:
 	perf_evlist__delete(evsel_list);
 	return status;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 172e91a..e0fd0aa 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1171,7 +1171,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (!top.evlist->nr_entries &&
 	    perf_evlist__add_default(top.evlist) < 0) {
 		ui__error("Not enough memory for event selector list\n");
-		goto out_delete_maps;
+		goto out_delete_evlist;
 	}
 
 	symbol_conf.nr_events = top.evlist->nr_entries;
@@ -1181,7 +1181,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	if (record_opts__config(opts)) {
 		status = -EINVAL;
-		goto out_delete_maps;
+		goto out_delete_evlist;
 	}
 
 	top.sym_evsel = perf_evlist__first(top.evlist);
@@ -1206,8 +1206,6 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	status = __cmd_top(&top);
 
-out_delete_maps:
-	perf_evlist__delete_maps(top.evlist);
 out_delete_evlist:
 	perf_evlist__delete(top.evlist);
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 5498eac..f4ddd14 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1885,7 +1885,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	err = trace__symbols_init(trace, evlist);
 	if (err < 0) {
 		fprintf(trace->output, "Problems initializing symbol libraries!\n");
-		goto out_delete_maps;
+		goto out_delete_evlist;
 	}
 
 	perf_evlist__config(evlist, &trace->opts);
@@ -1898,7 +1898,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 						    argv, false, NULL);
 		if (err < 0) {
 			fprintf(trace->output, "Couldn't run the workload!\n");
-			goto out_delete_maps;
+			goto out_delete_evlist;
 		}
 	}
 
@@ -1996,8 +1996,6 @@ out_disable:
 	perf_evlist__munmap(evlist);
 out_close_evlist:
 	perf_evlist__close(evlist);
-out_delete_maps:
-	perf_evlist__delete_maps(evlist);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 out:
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 4248d1e..ddbc775 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -543,11 +543,10 @@ out_err:
 		perf_evlist__munmap(evlist);
 		perf_evlist__close(evlist);
 		perf_evlist__delete(evlist);
-	}
-	if (cpus)
+	} else {
 		cpu_map__delete(cpus);
-	if (threads)
 		thread_map__delete(threads);
+	}
 	machines__destroy_kernel_maps(&machines);
 	machine__delete_threads(machine);
 	machines__exit(&machines);
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 27eb751..f9bc1fc 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -145,11 +145,10 @@ out_err:
 		perf_evlist__munmap(evlist);
 		perf_evlist__close(evlist);
 		perf_evlist__delete(evlist);
-	}
-	if (cpus)
+	} else {
 		cpu_map__delete(cpus);
-	if (threads)
 		thread_map__delete(threads);
+	}
 
 	return err;
 }
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index d64ab79..bbb334d 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -143,6 +143,8 @@ out_close_fd:
 		perf_evsel__close_fd(evsels[i], 1, threads->nr);
 out_free_evlist:
 	perf_evlist__delete(evlist);
+	cpus	= NULL;
+	threads = NULL;
 out_free_cpus:
 	cpu_map__delete(cpus);
 out_free_threads:
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
index 774620a..595b577 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -48,7 +48,7 @@ int test__syscall_open_tp_fields(void)
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("perf_evlist__open: %s\n", strerror(errno));
-		goto out_delete_maps;
+		goto out_delete_evlist;
 	}
 
 	err = perf_evlist__mmap(evlist, UINT_MAX, false);
@@ -114,8 +114,6 @@ out_munmap:
 	perf_evlist__munmap(evlist);
 out_close_evlist:
 	perf_evlist__close(evlist);
-out_delete_maps:
-	perf_evlist__delete_maps(evlist);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 out:
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index fa0ed35..266da9d 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -86,7 +86,7 @@ int test__PERF_RECORD(void)
 	err = perf_evlist__prepare_workload(evlist, &opts.target, argv, false, NULL);
 	if (err < 0) {
 		pr_debug("Couldn't run the workload!\n");
-		goto out_delete_maps;
+		goto out_delete_evlist;
 	}
 
 	/*
@@ -101,7 +101,7 @@ int test__PERF_RECORD(void)
 	err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
 	if (err < 0) {
 		pr_debug("sched__get_first_possible_cpu: %s\n", strerror(errno));
-		goto out_delete_maps;
+		goto out_delete_evlist;
 	}
 
 	cpu = err;
@@ -111,7 +111,7 @@ int test__PERF_RECORD(void)
 	 */
 	if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) {
 		pr_debug("sched_setaffinity: %s\n", strerror(errno));
-		goto out_delete_maps;
+		goto out_delete_evlist;
 	}
 
 	/*
@@ -121,7 +121,7 @@ int test__PERF_RECORD(void)
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("perf_evlist__open: %s\n", strerror(errno));
-		goto out_delete_maps;
+		goto out_delete_evlist;
 	}
 
 	/*
@@ -306,8 +306,6 @@ out_err:
 	perf_evlist__munmap(evlist);
 out_close_evlist:
 	perf_evlist__close(evlist);
-out_delete_maps:
-	perf_evlist__delete_maps(evlist);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 out:
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index c6398b9..97d08ff 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -170,10 +170,6 @@ out_err:
 		perf_evlist__close(evlist);
 		perf_evlist__delete(evlist);
 	}
-	if (cpus)
-		cpu_map__delete(cpus);
-	if (threads)
-		thread_map__delete(threads);
 
 	return err;
 }
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 6664a7c..266d381 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -45,7 +45,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	evsel = perf_evsel__new(&attr);
 	if (evsel == NULL) {
 		pr_debug("perf_evsel__new\n");
-		goto out_free_evlist;
+		goto out_delete_evlist;
 	}
 	perf_evlist__add(evlist, evsel);
 
@@ -54,7 +54,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	if (!evlist->cpus || !evlist->threads) {
 		err = -ENOMEM;
 		pr_debug("Not enough memory to create thread/cpu maps\n");
-		goto out_delete_maps;
+		goto out_delete_evlist;
 	}
 
 	if (perf_evlist__open(evlist)) {
@@ -63,7 +63,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 		err = -errno;
 		pr_debug("Couldn't open evlist: %s\nHint: check %s, using %" PRIu64 " in this test.\n",
 			 strerror(errno), knob, (u64)attr.sample_freq);
-		goto out_delete_maps;
+		goto out_delete_evlist;
 	}
 
 	err = perf_evlist__mmap(evlist, 128, true);
@@ -109,9 +109,7 @@ out_unmap_evlist:
 	perf_evlist__munmap(evlist);
 out_close_evlist:
 	perf_evlist__close(evlist);
-out_delete_maps:
-	perf_evlist__delete_maps(evlist);
-out_free_evlist:
+out_delete_evlist:
 	perf_evlist__delete(evlist);
 	return err;
 }
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 44e339d..fdeb2aa 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -62,14 +62,14 @@ int test__task_exit(void)
 	if (!evlist->cpus || !evlist->threads) {
 		err = -ENOMEM;
 		pr_debug("Not enough memory to create thread/cpu maps\n");
-		goto out_delete_maps;
+		goto out_delete_evlist;
 	}
 
 	err = perf_evlist__prepare_workload(evlist, &target, argv, false,
 					    workload_exec_failed_signal);
 	if (err < 0) {
 		pr_debug("Couldn't run the workload!\n");
-		goto out_delete_maps;
+		goto out_delete_evlist;
 	}
 
 	evsel = perf_evlist__first(evlist);
@@ -83,7 +83,7 @@ int test__task_exit(void)
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("Couldn't open the evlist: %s\n", strerror(-err));
-		goto out_delete_maps;
+		goto out_delete_evlist;
 	}
 
 	if (perf_evlist__mmap(evlist, 128, true) < 0) {
@@ -115,8 +115,7 @@ retry:
 	perf_evlist__munmap(evlist);
 out_close_evlist:
 	perf_evlist__close(evlist);
-out_delete_maps:
-	perf_evlist__delete_maps(evlist);
+out_delete_evlist:
 	perf_evlist__delete(evlist);
 	return err;
 }
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 96b3ef5..143eaf0 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -107,6 +107,10 @@ void perf_evlist__exit(struct perf_evlist *evlist)
 
 void perf_evlist__delete(struct perf_evlist *evlist)
 {
+	cpu_map__delete(evlist->cpus);
+	thread_map__delete(evlist->threads);
+	evlist->cpus = NULL;
+	evlist->threads = NULL;
 	perf_evlist__purge(evlist);
 	perf_evlist__exit(evlist);
 	free(evlist);
@@ -833,14 +837,6 @@ out_delete_threads:
 	return -1;
 }
 
-void perf_evlist__delete_maps(struct perf_evlist *evlist)
-{
-	cpu_map__delete(evlist->cpus);
-	thread_map__delete(evlist->threads);
-	evlist->cpus	= NULL;
-	evlist->threads = NULL;
-}
-
 int perf_evlist__apply_filters(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 18d1222c..518e521 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -135,7 +135,6 @@ static inline void perf_evlist__set_maps(struct perf_evlist *evlist,
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target);
-void perf_evlist__delete_maps(struct perf_evlist *evlist);
 int perf_evlist__apply_filters(struct perf_evlist *evlist);
 
 void __perf_evlist__set_leader(struct list_head *list);
-- 
cgit v0.10.2


From f26e1c7cb279051d83e0b671f48b30fe88c2c788 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 3 Jan 2014 16:54:12 -0300
Subject: perf evlist: Close fds on destructor

Since it is safe to call perf_evlist__close() multiple times, autoclose
it and remove the calls to the close from existing tools, reducing the
tooling boilerplate.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-2kq9v7p1rude1tqxa0aue2tk@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 5149b41..b7f5e43 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -970,7 +970,6 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 	err = __cmd_record(&record, argc, argv);
 
 	perf_evlist__munmap(rec->evlist);
-	perf_evlist__close(rec->evlist);
 out_symbol_exit:
 	symbol__exit();
 	return err;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index f4ddd14..aa8a5f4 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1909,7 +1909,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
 	if (err < 0) {
 		fprintf(trace->output, "Couldn't mmap the events: %s\n", strerror(errno));
-		goto out_close_evlist;
+		goto out_delete_evlist;
 	}
 
 	perf_evlist__enable(evlist);
@@ -1994,8 +1994,6 @@ out_disable:
 	}
 
 	perf_evlist__munmap(evlist);
-out_close_evlist:
-	perf_evlist__close(evlist);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 out:
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index ddbc775..2c0ce72 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -541,7 +541,6 @@ static int do_test_code_reading(bool try_kcore)
 out_err:
 	if (evlist) {
 		perf_evlist__munmap(evlist);
-		perf_evlist__close(evlist);
 		perf_evlist__delete(evlist);
 	} else {
 		cpu_map__delete(cpus);
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index f9bc1fc..dd1c677 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -143,7 +143,6 @@ out_err:
 	if (evlist) {
 		perf_evlist__disable(evlist);
 		perf_evlist__munmap(evlist);
-		perf_evlist__close(evlist);
 		perf_evlist__delete(evlist);
 	} else {
 		cpu_map__delete(cpus);
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index bbb334d..111dd4a 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -68,7 +68,7 @@ int test__basic_mmap(void)
 		evsels[i] = perf_evsel__newtp("syscalls", name);
 		if (evsels[i] == NULL) {
 			pr_debug("perf_evsel__new\n");
-			goto out_free_evlist;
+			goto out_delete_evlist;
 		}
 
 		evsels[i]->attr.wakeup_events = 1;
@@ -80,7 +80,7 @@ int test__basic_mmap(void)
 			pr_debug("failed to open counter: %s, "
 				 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
 				 strerror(errno));
-			goto out_close_fd;
+			goto out_delete_evlist;
 		}
 
 		nr_events[i] = 0;
@@ -90,7 +90,7 @@ int test__basic_mmap(void)
 	if (perf_evlist__mmap(evlist, 128, true) < 0) {
 		pr_debug("failed to mmap events: %d (%s)\n", errno,
 			 strerror(errno));
-		goto out_close_fd;
+		goto out_delete_evlist;
 	}
 
 	for (i = 0; i < nsyscalls; ++i)
@@ -138,10 +138,7 @@ int test__basic_mmap(void)
 
 out_munmap:
 	perf_evlist__munmap(evlist);
-out_close_fd:
-	for (i = 0; i < nsyscalls; ++i)
-		perf_evsel__close_fd(evsels[i], 1, threads->nr);
-out_free_evlist:
+out_delete_evlist:
 	perf_evlist__delete(evlist);
 	cpus	= NULL;
 	threads = NULL;
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
index 595b577..0a00638 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -54,7 +54,7 @@ int test__syscall_open_tp_fields(void)
 	err = perf_evlist__mmap(evlist, UINT_MAX, false);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
-		goto out_close_evlist;
+		goto out_delete_evlist;
 	}
 
 	perf_evlist__enable(evlist);
@@ -112,8 +112,6 @@ out_ok:
 	err = 0;
 out_munmap:
 	perf_evlist__munmap(evlist);
-out_close_evlist:
-	perf_evlist__close(evlist);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 out:
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 266da9d..682978e 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -132,7 +132,7 @@ int test__PERF_RECORD(void)
 	err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
-		goto out_close_evlist;
+		goto out_delete_evlist;
 	}
 
 	/*
@@ -304,8 +304,6 @@ found_exit:
 	}
 out_err:
 	perf_evlist__munmap(evlist);
-out_close_evlist:
-	perf_evlist__close(evlist);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 out:
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 97d08ff..3d50f2d 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -167,7 +167,6 @@ out_err:
 	if (evlist) {
 		perf_evlist__disable(evlist);
 		perf_evlist__munmap(evlist);
-		perf_evlist__close(evlist);
 		perf_evlist__delete(evlist);
 	}
 
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 266d381..b366f0e 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -70,7 +70,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	if (err < 0) {
 		pr_debug("failed to mmap event: %d (%s)\n", errno,
 			 strerror(errno));
-		goto out_close_evlist;
+		goto out_delete_evlist;
 	}
 
 	perf_evlist__enable(evlist);
@@ -107,8 +107,6 @@ next_event:
 
 out_unmap_evlist:
 	perf_evlist__munmap(evlist);
-out_close_evlist:
-	perf_evlist__close(evlist);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 	return err;
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index fdeb2aa..5511a0a 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -89,7 +89,7 @@ int test__task_exit(void)
 	if (perf_evlist__mmap(evlist, 128, true) < 0) {
 		pr_debug("failed to mmap events: %d (%s)\n", errno,
 			 strerror(errno));
-		goto out_close_evlist;
+		goto out_delete_evlist;
 	}
 
 	perf_evlist__start_workload(evlist);
@@ -113,8 +113,6 @@ retry:
 	}
 
 	perf_evlist__munmap(evlist);
-out_close_evlist:
-	perf_evlist__close(evlist);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 	return err;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 143eaf0..a083bdc 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -107,6 +107,7 @@ void perf_evlist__exit(struct perf_evlist *evlist)
 
 void perf_evlist__delete(struct perf_evlist *evlist)
 {
+	perf_evlist__close(evlist);
 	cpu_map__delete(evlist->cpus);
 	thread_map__delete(evlist->threads);
 	evlist->cpus = NULL;
-- 
cgit v0.10.2


From 983874d173568f584a5988888645725496c09f24 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 3 Jan 2014 17:25:49 -0300
Subject: perf evlist: Auto unmap on destructor

Removing further boilerplate after making sure perf_evlist__munmap can
be called multiple times for the same evlist.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-o0luenuld4abupm4nmrgzm6f@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index b7f5e43..cb00b53 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -968,8 +968,6 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 	}
 
 	err = __cmd_record(&record, argc, argv);
-
-	perf_evlist__munmap(rec->evlist);
 out_symbol_exit:
 	symbol__exit();
 	return err;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index aa8a5f4..399b4b9 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1993,7 +1993,6 @@ out_disable:
 		}
 	}
 
-	perf_evlist__munmap(evlist);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 out:
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 2c0ce72..653a8fe 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -540,7 +540,6 @@ static int do_test_code_reading(bool try_kcore)
 		err = TEST_CODE_READING_OK;
 out_err:
 	if (evlist) {
-		perf_evlist__munmap(evlist);
 		perf_evlist__delete(evlist);
 	} else {
 		cpu_map__delete(cpus);
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index dd1c677..497957f 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -142,7 +142,6 @@ int test__keep_tracking(void)
 out_err:
 	if (evlist) {
 		perf_evlist__disable(evlist);
-		perf_evlist__munmap(evlist);
 		perf_evlist__delete(evlist);
 	} else {
 		cpu_map__delete(cpus);
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 111dd4a..aef25f0 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -105,13 +105,13 @@ int test__basic_mmap(void)
 		if (event->header.type != PERF_RECORD_SAMPLE) {
 			pr_debug("unexpected %s event\n",
 				 perf_event__name(event->header.type));
-			goto out_munmap;
+			goto out_delete_evlist;
 		}
 
 		err = perf_evlist__parse_sample(evlist, event, &sample);
 		if (err) {
 			pr_err("Can't parse sample, err = %d\n", err);
-			goto out_munmap;
+			goto out_delete_evlist;
 		}
 
 		err = -1;
@@ -119,7 +119,7 @@ int test__basic_mmap(void)
 		if (evsel == NULL) {
 			pr_debug("event with id %" PRIu64
 				 " doesn't map to an evsel\n", sample.id);
-			goto out_munmap;
+			goto out_delete_evlist;
 		}
 		nr_events[evsel->idx]++;
 		perf_evlist__mmap_consume(evlist, 0);
@@ -132,12 +132,10 @@ int test__basic_mmap(void)
 				 expected_nr_events[evsel->idx],
 				 perf_evsel__name(evsel), nr_events[evsel->idx]);
 			err = -1;
-			goto out_munmap;
+			goto out_delete_evlist;
 		}
 	}
 
-out_munmap:
-	perf_evlist__munmap(evlist);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 	cpus	= NULL;
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
index 0a00638..5a016f6 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -85,7 +85,7 @@ int test__syscall_open_tp_fields(void)
 				err = perf_evsel__parse_sample(evsel, event, &sample);
 				if (err) {
 					pr_err("Can't parse sample, err = %d\n", err);
-					goto out_munmap;
+					goto out_delete_evlist;
 				}
 
 				tp_flags = perf_evsel__intval(evsel, &sample, "flags");
@@ -93,7 +93,7 @@ int test__syscall_open_tp_fields(void)
 				if (flags != tp_flags) {
 					pr_debug("%s: Expected flags=%#x, got %#x\n",
 						 __func__, flags, tp_flags);
-					goto out_munmap;
+					goto out_delete_evlist;
 				}
 
 				goto out_ok;
@@ -105,13 +105,11 @@ int test__syscall_open_tp_fields(void)
 
 		if (++nr_polls > 5) {
 			pr_debug("%s: no events!\n", __func__);
-			goto out_munmap;
+			goto out_delete_evlist;
 		}
 	}
 out_ok:
 	err = 0;
-out_munmap:
-	perf_evlist__munmap(evlist);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 out:
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 682978e..39cc7c3 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -165,7 +165,7 @@ int test__PERF_RECORD(void)
 					if (verbose)
 						perf_event__fprintf(event, stderr);
 					pr_debug("Couldn't parse sample\n");
-					goto out_err;
+					goto out_delete_evlist;
 				}
 
 				if (verbose) {
@@ -302,8 +302,6 @@ found_exit:
 		pr_debug("PERF_RECORD_MMAP for %s missing!\n", "[vdso]");
 		++errs;
 	}
-out_err:
-	perf_evlist__munmap(evlist);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 out:
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 3d50f2d..47146d3 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -166,7 +166,6 @@ next_event:
 out_err:
 	if (evlist) {
 		perf_evlist__disable(evlist);
-		perf_evlist__munmap(evlist);
 		perf_evlist__delete(evlist);
 	}
 
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index b366f0e..983d6b8 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -90,7 +90,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 		err = perf_evlist__parse_sample(evlist, event, &sample);
 		if (err < 0) {
 			pr_debug("Error during parse sample\n");
-			goto out_unmap_evlist;
+			goto out_delete_evlist;
 		}
 
 		total_periods += sample.period;
@@ -105,8 +105,6 @@ next_event:
 		err = -1;
 	}
 
-out_unmap_evlist:
-	perf_evlist__munmap(evlist);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 	return err;
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 5511a0a..5ff3db3 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -112,7 +112,6 @@ retry:
 		err = -1;
 	}
 
-	perf_evlist__munmap(evlist);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 	return err;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index a083bdc..0810f5c 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -107,6 +107,7 @@ void perf_evlist__exit(struct perf_evlist *evlist)
 
 void perf_evlist__delete(struct perf_evlist *evlist)
 {
+	perf_evlist__munmap(evlist);
 	perf_evlist__close(evlist);
 	cpu_map__delete(evlist->cpus);
 	thread_map__delete(evlist->threads);
@@ -587,6 +588,9 @@ void perf_evlist__munmap(struct perf_evlist *evlist)
 {
 	int i;
 
+	if (evlist->mmap == NULL)
+		return;
+
 	for (i = 0; i < evlist->nr_mmaps; i++)
 		__perf_evlist__munmap(evlist, i);
 
-- 
cgit v0.10.2


From 2d4352c077b98215771cc081626c7a69289c4fac Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 3 Jan 2014 17:30:04 -0300
Subject: perf tests: Fixup leak on error path in parse events test

We need to call the evlist destructor when failing to parse events.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ilslu69s7v7bpvdgqtrlp8f5@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index e4ce8ae..41dee5e 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1385,10 +1385,10 @@ static int test_event(struct evlist_test *e)
 	if (ret) {
 		pr_debug("failed to parse event '%s', err %d\n",
 			 e->name, ret);
-		return ret;
+	} else {
+		ret = e->check(evlist);
 	}
-
-	ret = e->check(evlist);
+	
 	perf_evlist__delete(evlist);
 
 	return ret;
-- 
cgit v0.10.2


From 41cde47675de62ee0f3877c00ab44373b2b2f4ca Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 3 Jan 2014 17:34:42 -0300
Subject: perf stat: Remove misplaced __maybe_unused

That 'argc' argument _is_ being used.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-t2gsxc15zulkorieg8zq996o@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 6ca0766..b27b264 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -645,7 +645,7 @@ static int __run_perf_stat(int argc, const char **argv)
 	return WEXITSTATUS(status);
 }
 
-static int run_perf_stat(int argc __maybe_unused, const char **argv)
+static int run_perf_stat(int argc, const char **argv)
 {
 	int ret;
 
-- 
cgit v0.10.2


From a6cf5f39236c2ea6008a2f5cb908c3181c123096 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Fri, 3 Jan 2014 15:32:32 +0100
Subject: perf tools: Move arch setup into seprate Makefile

I need to use arch related setup in the tests/make, so moving arch setup
into Makefile.arch.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1388759553-12974-1-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 14faeeb..f2bc659 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -1,28 +1,26 @@
-uname_M := $(shell uname -m 2>/dev/null || echo not)
 
-ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
-                                  -e s/arm.*/arm/ -e s/sa110/arm/ \
-                                  -e s/s390x/s390/ -e s/parisc64/parisc/ \
-                                  -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
-                                  -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ )
-NO_PERF_REGS := 1
-CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS)
+ifeq ($(src-perf),)
+src-perf := $(srctree)/tools/perf
+endif
 
-# Additional ARCH settings for x86
-ifeq ($(ARCH),i386)
-  override ARCH := x86
-  NO_PERF_REGS := 0
-  LIBUNWIND_LIBS = -lunwind -lunwind-x86
+ifeq ($(obj-perf),)
+obj-perf := $(OUTPUT)
 endif
 
-ifeq ($(ARCH),x86_64)
-  override ARCH := x86
-  IS_X86_64 := 0
-  ifeq (, $(findstring m32,$(CFLAGS)))
-    IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1)
-  endif
+ifneq ($(obj-perf),)
+obj-perf := $(abspath $(obj-perf))/
+endif
+
+LIB_INCLUDE := $(srctree)/tools/lib/
+CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS)
+
+include $(src-perf)/config/Makefile.arch
+
+NO_PERF_REGS := 1
+
+# Additional ARCH settings for x86
+ifeq ($(ARCH),x86)
   ifeq (${IS_X86_64}, 1)
-    RAW_ARCH := x86_64
     CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT
     ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
     LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
@@ -64,20 +62,6 @@ ifeq ($(NO_PERF_REGS),0)
   CFLAGS += -DHAVE_PERF_REGS_SUPPORT
 endif
 
-ifeq ($(src-perf),)
-src-perf := $(srctree)/tools/perf
-endif
-
-ifeq ($(obj-perf),)
-obj-perf := $(OUTPUT)
-endif
-
-ifneq ($(obj-perf),)
-obj-perf := $(abspath $(obj-perf))/
-endif
-
-LIB_INCLUDE := $(srctree)/tools/lib/
-
 # include ARCH specific config
 -include $(src-perf)/arch/$(ARCH)/Makefile
 
diff --git a/tools/perf/config/Makefile.arch b/tools/perf/config/Makefile.arch
new file mode 100644
index 0000000..fef8ae9
--- /dev/null
+++ b/tools/perf/config/Makefile.arch
@@ -0,0 +1,22 @@
+
+uname_M := $(shell uname -m 2>/dev/null || echo not)
+
+ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
+                                  -e s/arm.*/arm/ -e s/sa110/arm/ \
+                                  -e s/s390x/s390/ -e s/parisc64/parisc/ \
+                                  -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
+                                  -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ )
+
+# Additional ARCH settings for x86
+ifeq ($(ARCH),i386)
+  override ARCH := x86
+endif
+
+ifeq ($(ARCH),x86_64)
+  override ARCH := x86
+  IS_X86_64 := 0
+  ifeq (, $(findstring m32,$(CFLAGS)))
+    IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1)
+    RAW_ARCH := x86_64
+  endif
+endif
-- 
cgit v0.10.2


From f7c64474242701eb24f6fe96f8df0389a2b800f7 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Fri, 3 Jan 2014 15:32:33 +0100
Subject: perf tests: Fix installation tests path setup

Currently installation tests work only over x86_64, adding arch check to
make it work over i386 as well.

NOTE looks like x86 is the only arch running tests, we need some
IS_(32/64) flag to make this generic.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1388759553-12974-2-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index f641c35..e341088 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -1,6 +1,16 @@
 PERF := .
 MK   := Makefile
 
+include config/Makefile.arch
+
+# FIXME looks like x86 is the only arch running tests ;-)
+# we need some IS_(32/64) flag to make this generic
+ifeq ($(IS_X86_64),1)
+lib = lib64
+else
+lib = lib
+endif
+
 has = $(shell which $1 2>/dev/null)
 
 # standard single make variable specified
@@ -118,16 +128,16 @@ installed_files_bin := bin/perf
 installed_files_bin += etc/bash_completion.d/perf
 installed_files_bin += libexec/perf-core/perf-archive
 
-installed_files_plugins := lib64/traceevent/plugins/plugin_cfg80211.so
-installed_files_plugins += lib64/traceevent/plugins/plugin_scsi.so
-installed_files_plugins += lib64/traceevent/plugins/plugin_xen.so
-installed_files_plugins += lib64/traceevent/plugins/plugin_function.so
-installed_files_plugins += lib64/traceevent/plugins/plugin_sched_switch.so
-installed_files_plugins += lib64/traceevent/plugins/plugin_mac80211.so
-installed_files_plugins += lib64/traceevent/plugins/plugin_kvm.so
-installed_files_plugins += lib64/traceevent/plugins/plugin_kmem.so
-installed_files_plugins += lib64/traceevent/plugins/plugin_hrtimer.so
-installed_files_plugins += lib64/traceevent/plugins/plugin_jbd2.so
+installed_files_plugins := $(lib)/traceevent/plugins/plugin_cfg80211.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_scsi.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_xen.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_function.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_sched_switch.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_mac80211.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_kvm.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_kmem.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_hrtimer.so
+installed_files_plugins += $(lib)/traceevent/plugins/plugin_jbd2.so
 
 installed_files_all := $(installed_files_bin)
 installed_files_all += $(installed_files_plugins)
-- 
cgit v0.10.2


From 198430b56d4ab49d77381ef7cd3daf418a2c00c0 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 2 Jan 2014 10:53:04 +0100
Subject: tools lib traceevent: Replace tabs with spaces for all non-commands
 statements

The tabbed indentation in non-commands statements could be sometimes
considered as follow up for the rule command in the Makefile.

This error is hard to find, so as a precaution replacing tabs with
spaces for all non-commands statements.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://marc.info/?t=136484403900003&r=1&w=2
Link: http://lkml.kernel.org/r/20140102095304.GA1196@krava.brq.redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index ca4ab78..76fe0ae 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -86,8 +86,8 @@ ifeq ($(BUILD_SRC),)
 ifneq ($(OUTPUT),)
 
 define build_output
-	$(if $(VERBOSE:1=),@)+$(MAKE) -C $(OUTPUT) \
-	BUILD_SRC=$(CURDIR)/ -f $(CURDIR)/Makefile $1
+  $(if $(VERBOSE:1=),@)+$(MAKE) -C $(OUTPUT) \
+  BUILD_SRC=$(CURDIR)/ -f $(CURDIR)/Makefile $1
 endef
 
 all: sub-make
@@ -221,23 +221,23 @@ $(PLUGINS): %.so: %.o
 	$(QUIET_LINK)$(CC) $(CFLAGS) -shared -nostartfiles -o $@ $<
 
 define make_version.h
-	(echo '/* This file is automatically generated. Do not modify. */';		\
-	echo \#define VERSION_CODE $(shell						\
-	expr $(VERSION) \* 256 + $(PATCHLEVEL));					\
-	echo '#define EXTRAVERSION ' $(EXTRAVERSION);					\
-	echo '#define VERSION_STRING "'$(VERSION).$(PATCHLEVEL).$(EXTRAVERSION)'"';	\
-	echo '#define FILE_VERSION '$(FILE_VERSION);					\
-	) > $1
+  (echo '/* This file is automatically generated. Do not modify. */';		\
+   echo \#define VERSION_CODE $(shell						\
+   expr $(VERSION) \* 256 + $(PATCHLEVEL));					\
+   echo '#define EXTRAVERSION ' $(EXTRAVERSION);				\
+   echo '#define VERSION_STRING "'$(VERSION).$(PATCHLEVEL).$(EXTRAVERSION)'"';	\
+   echo '#define FILE_VERSION '$(FILE_VERSION);					\
+  ) > $1
 endef
 
 define update_version.h
-	($(call make_version.h, $@.tmp);		\
-	if [ -r $@ ] && cmp -s $@ $@.tmp; then		\
-		rm -f $@.tmp;				\
-	else						\
-		echo '  UPDATE                 $@';	\
-		mv -f $@.tmp $@;			\
-	fi);
+  ($(call make_version.h, $@.tmp);		\
+    if [ -r $@ ] && cmp -s $@ $@.tmp; then	\
+      rm -f $@.tmp;				\
+    else					\
+      echo '  UPDATE                 $@';	\
+      mv -f $@.tmp $@;				\
+    fi);
 endef
 
 ep_version.h: force
@@ -246,13 +246,13 @@ ep_version.h: force
 VERSION_FILES = ep_version.h
 
 define update_dir
-	(echo $1 > $@.tmp;	\
-	if [ -r $@ ] && cmp -s $@ $@.tmp; then		\
-		rm -f $@.tmp;				\
-	else						\
-		echo '  UPDATE                 $@';	\
-		mv -f $@.tmp $@;			\
-	fi);
+  (echo $1 > $@.tmp;				\
+   if [ -r $@ ] && cmp -s $@ $@.tmp; then	\
+     rm -f $@.tmp;				\
+   else						\
+     echo '  UPDATE                 $@';	\
+     mv -f $@.tmp $@;				\
+   fi);
 endef
 
 ## make deps
@@ -262,10 +262,10 @@ all_deps := $(all_objs:%.o=.%.d)
 
 # let .d file also depends on the source and header files
 define check_deps
-		@set -e; $(RM) $@; \
-		$(CC) -MM $(CFLAGS) $< > $@.$$$$; \
-		sed 's,\($*\)\.o[ :]*,\1.o $@ : ,g' < $@.$$$$ > $@; \
-		$(RM) $@.$$$$
+  @set -e; $(RM) $@; \
+  $(CC) -MM $(CFLAGS) $< > $@.$$$$; \
+  sed 's,\($*\)\.o[ :]*,\1.o $@ : ,g' < $@.$$$$ > $@; \
+  $(RM) $@.$$$$
 endef
 
 $(all_deps): .%.d: $(src)/%.c
-- 
cgit v0.10.2


From 9bb8e5edcf37182d0c97e98131cc3c5c03014b0e Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Wed, 1 Jan 2014 17:50:50 +0100
Subject: tools lib traceevent: Shut up plugins make message

Getting rid of following build output:

  $ make O=/tmp/build/perf -C tools/perf/ install-bin
  ...
  make[3]: Nothing to be done for `plugins'.
  make[2]: Nothing to be done for `plugins'.
  ...

which triggers when traceevent library needs to be rebuilt, but we have
plugins built already.

Adding extra 'plugins' target with nop which is visible and triggers in
both Makefile parts (for detached output directory (O=...) the
traceevent Makefile spawns sub make for the build itself).

Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1388595050-23005-2-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 76fe0ae..f778d48 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -329,9 +329,12 @@ clean:
 
 endif # skip-makefile
 
-PHONY += force
+PHONY += force plugins
 force:
 
+plugins:
+	@echo > /dev/null
+
 # Declare the contents of the .PHONY variable as phony.  We keep that
 # information in a variable so we can use it in if_changed and friends.
 .PHONY: $(PHONY)
-- 
cgit v0.10.2


From 3ba4d2e1a8235d862657ded9f20b3170b477768b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 6 Jan 2014 15:28:35 -0300
Subject: perf header: Pack 'struct perf_session_env'

Initial struct:

[acme@ssdandy linux]$ pahole -C perf_session_env ~/bin/perf
struct perf_session_env {
	char *                     hostname;             /*     0     8 */
	char *                     os_release;           /*     8     8 */
	char *                     version;              /*    16     8 */
	char *                     arch;                 /*    24     8 */
	int                        nr_cpus_online;       /*    32     4 */
	int                        nr_cpus_avail;        /*    36     4 */
	char *                     cpu_desc;             /*    40     8 */
	char *                     cpuid;                /*    48     8 */
	long long unsigned int     total_mem;            /*    56     8 */
	/* --- cacheline 1 boundary (64 bytes) --- */
	int                        nr_cmdline;           /*    64     4 */

	/* XXX 4 bytes hole, try to pack */

	char *                     cmdline;              /*    72     8 */
	int                        nr_sibling_cores;     /*    80     4 */

	/* XXX 4 bytes hole, try to pack */

	char *                     sibling_cores;        /*    88     8 */
	int                        nr_sibling_threads;   /*    96     4 */

	/* XXX 4 bytes hole, try to pack */

	char *                     sibling_threads;      /*   104     8 */
	int                        nr_numa_nodes;        /*   112     4 */

	/* XXX 4 bytes hole, try to pack */

	char *                     numa_nodes;           /*   120     8 */
	/* --- cacheline 2 boundary (128 bytes) --- */
	int                        nr_pmu_mappings;      /*   128     4 */

	/* XXX 4 bytes hole, try to pack */

	char *                     pmu_mappings;         /*   136     8 */
	int                        nr_groups;            /*   144     4 */

	/* size: 152, cachelines: 3, members: 20 */
	/* sum members: 128, holes: 5, sum holes: 20 */
	/* padding: 4 */
	/* last cacheline: 24 bytes */
};
[acme@ssdandy linux]$

[acme@ssdandy linux]$ pahole -C perf_session_env --reorganize --show_reorg_steps ~/bin/perf | grep ^/ | grep -v Final
/* Moving 'nr_sibling_cores' from after 'cmdline' to after 'nr_cmdline' */
/* Moving 'nr_numa_nodes' from after 'sibling_threads' to after 'nr_sibling_threads' */
/* Moving 'nr_groups' from after 'pmu_mappings' to after 'nr_pmu_mappings' */
[acme@ssdandy linux]$

Final struct stats:

[acme@ssdandy linux]$ pahole -C perf_session_env --reorganize --show_reorg_steps ~/bin/perf | tail -4
	/* --- cacheline 2 boundary (128 bytes) --- */

	/* size: 128, cachelines: 2, members: 20 */
};   /* saved 24 bytes and 1 cacheline! */
[acme@ssdandy linux]$

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-3d9tshamloinzxcqeb7mtd1n@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 307c9ae..a2d047b 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -77,16 +77,16 @@ struct perf_session_env {
 	unsigned long long	total_mem;
 
 	int			nr_cmdline;
-	char			*cmdline;
 	int			nr_sibling_cores;
-	char			*sibling_cores;
 	int			nr_sibling_threads;
-	char			*sibling_threads;
 	int			nr_numa_nodes;
-	char			*numa_nodes;
 	int			nr_pmu_mappings;
-	char			*pmu_mappings;
 	int			nr_groups;
+	char			*cmdline;
+	char			*sibling_cores;
+	char			*sibling_threads;
+	char			*numa_nodes;
+	char			*pmu_mappings;
 };
 
 struct perf_header {
-- 
cgit v0.10.2


From 98eafce6bda705529e90d33b7f23706b346a6c8a Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 6 Jan 2014 15:43:02 -0300
Subject: perf trace: Pack 'struct trace'

Initial struct stats:

	/* size: 368, cachelines: 6, members: 24 */
	/* sum members: 353, holes: 3, sum holes: 15 */
	/* last cacheline: 48 bytes */

After reorg:

[acme@ssdandy linux]$ pahole -C trace ~/bin/trace | tail -4
	/* size: 360, cachelines: 6, members: 24 */
	/* padding: 7 */
	/* last cacheline: 40 bytes */
};
[acme@ssdandy linux]$

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-6jimc80yu89qkx6zb8465s6t@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 399b4b9..4bd44ab 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1160,26 +1160,27 @@ struct trace {
 	struct record_opts	opts;
 	struct machine		*host;
 	u64			base_time;
-	bool			full_time;
 	FILE			*output;
 	unsigned long		nr_events;
 	struct strlist		*ev_qualifier;
-	bool			not_ev_qualifier;
-	bool			live;
 	const char 		*last_vfs_getname;
 	struct intlist		*tid_list;
 	struct intlist		*pid_list;
+	double			duration_filter;
+	double			runtime_ms;
+	struct {
+		u64		vfs_getname,
+				proc_getname;
+	} stats;
+	bool			not_ev_qualifier;
+	bool			live;
+	bool			full_time;
 	bool			sched;
 	bool			multiple_threads;
 	bool			summary;
 	bool			summary_only;
 	bool			show_comm;
 	bool			show_tool_stats;
-	double			duration_filter;
-	double			runtime_ms;
-	struct {
-		u64		vfs_getname, proc_getname;
-	} stats;
 };
 
 static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
-- 
cgit v0.10.2


From c4eb6c0e7aa3a5106a3382880bc41c696e72adb4 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 7 Jan 2014 13:47:18 +0100
Subject: perf tools: Automate setup of FEATURE_CHECK_(C|LD)FLAGS-all variables

Instead of explicitly adding same value into
FEATURE_CHECK_(C|LD)FLAGS-all variables we can do that automatically.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jean Pihet <jean.pihet@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1389098853-14466-2-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index f2bc659..5d15b43 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -53,9 +53,6 @@ else
   FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS)
   FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS)
   FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS)
-  #  and the flags for the test-all case
-  FEATURE_CHECK_CFLAGS-all += $(LIBUNWIND_CFLAGS)
-  FEATURE_CHECK_LDFLAGS-all += $(LIBUNWIND_LDFLAGS)
 endif
 
 ifeq ($(NO_PERF_REGS),0)
@@ -152,6 +149,17 @@ CORE_FEATURE_TESTS =			\
 	stackprotector-all		\
 	timerfd
 
+# Set FEATURE_CHECK_(C|LD)FLAGS-all for all CORE_FEATURE_TESTS features.
+# If in the future we need per-feature checks/flags for features not
+# mentioned in this list we need to refactor this ;-).
+set_test_all_flags = $(eval $(set_test_all_flags_code))
+define set_test_all_flags_code
+  FEATURE_CHECK_CFLAGS-all  += $(FEATURE_CHECK_CFLAGS-$(1))
+  FEATURE_CHECK_LDFLAGS-all += $(FEATURE_CHECK_LDFLAGS-$(1))
+endef
+
+$(foreach feat,$(CORE_FEATURE_TESTS),$(call set_test_all_flags,$(feat)))
+
 #
 # So here we detect whether test-all was rebuilt, to be able
 # to skip the print-out of the long features list if the file
-- 
cgit v0.10.2


From 14bd6d20fef603060474701967085442b716b6a9 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 7 Jan 2014 13:47:19 +0100
Subject: perf machine: Fix id_hdr_size initialization

The id_hdr_size field was not properly initialized, set it to zero, as
the machine struct may have come from some non zeroing allocation
routine or from the stack without any field being initialized.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jean Pihet <jean.pihet@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1389098853-14466-3-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index a98538d..0130279 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -27,6 +27,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	machine->pid = pid;
 
 	machine->symbol_filter = NULL;
+	machine->id_hdr_size = 0;
 
 	machine->root_dir = strdup(root_dir);
 	if (machine->root_dir == NULL)
-- 
cgit v0.10.2


From a18382b68f8bf1a8d43e3cb08b3479cb768913ea Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Tue, 7 Jan 2014 13:47:20 +0100
Subject: perf tools: Make perf_event__synthesize_mmap_events global

Making perf_event__synthesize_mmap_events global, it will be used in
following patch from test code.

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jean Pihet <jean.pihet@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1389098853-14466-4-git-send-email-jolsa@redhat.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 45a76c6..1fc1c2f 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -175,12 +175,12 @@ out:
 	return tgid;
 }
 
-static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
-					      union perf_event *event,
-					      pid_t pid, pid_t tgid,
-					      perf_event__handler_t process,
-					      struct machine *machine,
-					      bool mmap_data)
+int perf_event__synthesize_mmap_events(struct perf_tool *tool,
+				       union perf_event *event,
+				       pid_t pid, pid_t tgid,
+				       perf_event__handler_t process,
+				       struct machine *machine,
+				       bool mmap_data)
 {
 	char filename[PATH_MAX];
 	FILE *fp;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 30fec99..faf6e21 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -266,6 +266,13 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 				  const struct perf_sample *sample,
 				  bool swapped);
 
+int perf_event__synthesize_mmap_events(struct perf_tool *tool,
+				       union perf_event *event,
+				       pid_t pid, pid_t tgid,
+				       perf_event__handler_t process,
+				       struct machine *machine,
+				       bool mmap_data);
+
 size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
-- 
cgit v0.10.2


From 8f3dd2b096c348033e55d4a4fb8c0f672559657e Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Tue, 7 Jan 2014 14:14:06 -0800
Subject: perf stat: Fix --delay option in man page

The --delay option was documented as --initial-delay in the manpage. Fix this.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1389132847-31982-1-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 80c7da6..29ee857 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -133,7 +133,7 @@ use --per-core in addition to -a. (system-wide).  The output includes the
 core number and the number of online logical processors on that physical processor.
 
 -D msecs::
---initial-delay msecs::
+--delay msecs::
 After starting the program, wait msecs before measuring. This is useful to
 filter out the startup phase of the program, which is often very different.
 
-- 
cgit v0.10.2


From 88aca8d966a1349631a0946ed77c7ed360519ed4 Mon Sep 17 00:00:00 2001
From: Cody P Schafer <cody@linux.vnet.ibm.com>
Date: Wed, 8 Jan 2014 08:43:51 -0800
Subject: tools perf: Comment typo fix

s/temr/term/

Signed-off-by: Cody P Schafer <cody@linux.vnet.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1389199434-21761-1-git-send-email-cody@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 0934d64..d9cab4d 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -505,7 +505,7 @@ static __u64 pmu_format_value(unsigned long *format, __u64 value)
 
 /*
  * Setup one of config[12] attr members based on the
- * user input data - temr parameter.
+ * user input data - term parameter.
  */
 static int pmu_config_term(struct list_head *formats,
 			   struct perf_event_attr *attr,
-- 
cgit v0.10.2


From fad2918ed5171e6299a9b4b885d0459f35ee7377 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 8 Jan 2014 10:10:00 -0300
Subject: perf report: Move logic to warn about kptr_restrict'ed kernels to
 separate function

Its too big, better have a separate function for it so that the main
logic gets shorter/clearer.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ahh6vfzyh8fsygjwrsbroeu0@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index bf8dd2e..f2ff860 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -412,14 +412,41 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 	return 0;
 }
 
+static void report__warn_kptr_restrict(const struct report *rep)
+{
+	struct map *kernel_map = rep->session->machines.host.vmlinux_maps[MAP__FUNCTION];
+	struct kmap *kernel_kmap = map__kmap(kernel_map);
+
+	if (kernel_map == NULL ||
+	    (kernel_map->dso->hit &&
+	     (kernel_kmap->ref_reloc_sym == NULL ||
+	      kernel_kmap->ref_reloc_sym->addr == 0))) {
+		const char *desc =
+		    "As no suitable kallsyms nor vmlinux was found, kernel samples\n"
+		    "can't be resolved.";
+
+		if (kernel_map) {
+			const struct dso *kdso = kernel_map->dso;
+			if (!RB_EMPTY_ROOT(&kdso->symbols[MAP__FUNCTION])) {
+				desc = "If some relocation was applied (e.g. "
+				       "kexec) symbols may be misresolved.";
+			}
+		}
+
+		ui__warning(
+"Kernel address maps (/proc/{kallsyms,modules}) were restricted.\n\n"
+"Check /proc/sys/kernel/kptr_restrict before running 'perf record'.\n\n%s\n\n"
+"Samples in kernel modules can't be resolved as well.\n\n",
+		desc);
+	}
+}
+
 static int __cmd_report(struct report *rep)
 {
 	int ret = -EINVAL;
 	u64 nr_samples;
 	struct perf_session *session = rep->session;
 	struct perf_evsel *pos;
-	struct map *kernel_map;
-	struct kmap *kernel_kmap;
 	const char *help = "For a higher level overview, try: perf report --sort comm,dso";
 	struct ui_progress prog;
 	struct perf_data_file *file = session->file;
@@ -444,30 +471,7 @@ static int __cmd_report(struct report *rep)
 	if (ret)
 		return ret;
 
-	kernel_map = session->machines.host.vmlinux_maps[MAP__FUNCTION];
-	kernel_kmap = map__kmap(kernel_map);
-	if (kernel_map == NULL ||
-	    (kernel_map->dso->hit &&
-	     (kernel_kmap->ref_reloc_sym == NULL ||
-	      kernel_kmap->ref_reloc_sym->addr == 0))) {
-		const char *desc =
-		    "As no suitable kallsyms nor vmlinux was found, kernel samples\n"
-		    "can't be resolved.";
-
-		if (kernel_map) {
-			const struct dso *kdso = kernel_map->dso;
-			if (!RB_EMPTY_ROOT(&kdso->symbols[MAP__FUNCTION])) {
-				desc = "If some relocation was applied (e.g. "
-				       "kexec) symbols may be misresolved.";
-			}
-		}
-
-		ui__warning(
-"Kernel address maps (/proc/{kallsyms,modules}) were restricted.\n\n"
-"Check /proc/sys/kernel/kptr_restrict before running 'perf record'.\n\n%s\n\n"
-"Samples in kernel modules can't be resolved as well.\n\n",
-		desc);
-	}
+	report__warn_kptr_restrict(rep);
 
 	if (use_browser == 0) {
 		if (verbose > 3)
-- 
cgit v0.10.2


From 8362951b7b0618687beddac90aeee43940d20659 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 8 Jan 2014 12:22:07 -0300
Subject: perf report: Move hist browser selection code to separate function

To unclutter the main function.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-agvxwpazlucy6h5sejuttw9t@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index f2ff860..03941ad 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -441,13 +441,57 @@ static void report__warn_kptr_restrict(const struct report *rep)
 	}
 }
 
+static int report__gtk_browse_hists(struct report *rep, const char *help)
+{
+	int (*hist_browser)(struct perf_evlist *evlist, const char *help,
+			    struct hist_browser_timer *timer, float min_pcnt);
+
+	hist_browser = dlsym(perf_gtk_handle, "perf_evlist__gtk_browse_hists");
+
+	if (hist_browser == NULL) {
+		ui__error("GTK browser not found!\n");
+		return -1;
+	}
+
+	return hist_browser(rep->session->evlist, help, NULL, rep->min_percent);
+}
+
+static int report__browse_hists(struct report *rep)
+{
+	int ret;
+	struct perf_session *session = rep->session;
+	struct perf_evlist *evlist = session->evlist;
+	const char *help = "For a higher level overview, try: perf report --sort comm,dso";
+
+	switch (use_browser) {
+	case 1:
+		ret = perf_evlist__tui_browse_hists(evlist, help, NULL,
+						    rep->min_percent,
+						    &session->header.env);
+		/*
+		 * Usually "ret" is the last pressed key, and we only
+		 * care if the key notifies us to switch data file.
+		 */
+		if (ret != K_SWITCH_INPUT_DATA)
+			ret = 0;
+		break;
+	case 2:
+		ret = report__gtk_browse_hists(rep, help);
+		break;
+	default:
+		ret = perf_evlist__tty_browse_hists(evlist, rep, help);
+		break;
+	}
+
+	return ret;
+}
+
 static int __cmd_report(struct report *rep)
 {
 	int ret = -EINVAL;
 	u64 nr_samples;
 	struct perf_session *session = rep->session;
 	struct perf_evsel *pos;
-	const char *help = "For a higher level overview, try: perf report --sort comm,dso";
 	struct ui_progress prog;
 	struct perf_data_file *file = session->file;
 
@@ -524,38 +568,7 @@ static int __cmd_report(struct report *rep)
 	list_for_each_entry(pos, &session->evlist->entries, node)
 		hists__output_resort(&pos->hists);
 
-	if (use_browser > 0) {
-		if (use_browser == 1) {
-			ret = perf_evlist__tui_browse_hists(session->evlist,
-							help, NULL,
-							rep->min_percent,
-							&session->header.env);
-			/*
-			 * Usually "ret" is the last pressed key, and we only
-			 * care if the key notifies us to switch data file.
-			 */
-			if (ret != K_SWITCH_INPUT_DATA)
-				ret = 0;
-
-		} else if (use_browser == 2) {
-			int (*hist_browser)(struct perf_evlist *,
-					    const char *,
-					    struct hist_browser_timer *,
-					    float min_pcnt);
-
-			hist_browser = dlsym(perf_gtk_handle,
-					     "perf_evlist__gtk_browse_hists");
-			if (hist_browser == NULL) {
-				ui__error("GTK browser not found!\n");
-				return ret;
-			}
-			hist_browser(session->evlist, help, NULL,
-				     rep->min_percent);
-		}
-	} else
-		perf_evlist__tty_browse_hists(session->evlist, rep, help);
-
-	return ret;
+	return report__browse_hists(rep);
 }
 
 static int
-- 
cgit v0.10.2


From f6d8b0571c9ac8f273d18c112c2fc3c9533c9f0a Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 8 Jan 2014 14:45:24 -0300
Subject: perf report: Move histogram entries collapsing to separate function

Further uncluttering the main 'report' function by group related code in
separate function.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-b594zsbwke8khir13kudwqmj@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 03941ad..cff9465 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -486,13 +486,55 @@ static int report__browse_hists(struct report *rep)
 	return ret;
 }
 
+static u64 report__collapse_hists(struct report *rep)
+{
+	struct ui_progress prog;
+	struct perf_evsel *pos;
+	u64 nr_samples = 0;
+	/*
+ 	 * Count number of histogram entries to use when showing progress,
+ 	 * reusing nr_samples variable.
+ 	 */
+	list_for_each_entry(pos, &rep->session->evlist->entries, node)
+		nr_samples += pos->hists.nr_entries;
+
+	ui_progress__init(&prog, nr_samples, "Merging related events...");
+	/*
+	 * Count total number of samples, will be used to check if this
+ 	 * session had any.
+ 	 */
+	nr_samples = 0;
+
+	list_for_each_entry(pos, &rep->session->evlist->entries, node) {
+		struct hists *hists = &pos->hists;
+
+		if (pos->idx == 0)
+			hists->symbol_filter_str = rep->symbol_filter_str;
+
+		hists__collapse_resort(hists, &prog);
+		nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE];
+
+		/* Non-group events are considered as leader */
+		if (symbol_conf.event_group &&
+		    !perf_evsel__is_group_leader(pos)) {
+			struct hists *leader_hists = &pos->leader->hists;
+
+			hists__match(leader_hists, hists);
+			hists__link(leader_hists, hists);
+		}
+	}
+
+	ui_progress__finish();
+
+	return nr_samples;
+}
+
 static int __cmd_report(struct report *rep)
 {
-	int ret = -EINVAL;
+	int ret;
 	u64 nr_samples;
 	struct perf_session *session = rep->session;
 	struct perf_evsel *pos;
-	struct ui_progress prog;
 	struct perf_data_file *file = session->file;
 
 	signal(SIGINT, sig_handler);
@@ -530,32 +572,7 @@ static int __cmd_report(struct report *rep)
 		}
 	}
 
-	nr_samples = 0;
-	list_for_each_entry(pos, &session->evlist->entries, node)
-		nr_samples += pos->hists.nr_entries;
-
-	ui_progress__init(&prog, nr_samples, "Merging related events...");
-
-	nr_samples = 0;
-	list_for_each_entry(pos, &session->evlist->entries, node) {
-		struct hists *hists = &pos->hists;
-
-		if (pos->idx == 0)
-			hists->symbol_filter_str = rep->symbol_filter_str;
-
-		hists__collapse_resort(hists, &prog);
-		nr_samples += hists->stats.nr_events[PERF_RECORD_SAMPLE];
-
-		/* Non-group events are considered as leader */
-		if (symbol_conf.event_group &&
-		    !perf_evsel__is_group_leader(pos)) {
-			struct hists *leader_hists = &pos->leader->hists;
-
-			hists__match(leader_hists, hists);
-			hists__link(leader_hists, hists);
-		}
-	}
-	ui_progress__finish();
+	nr_samples = report__collapse_hists(rep);
 
 	if (session_done())
 		return 0;
-- 
cgit v0.10.2


From 0050f7aa182e3e8ed34dd6cc4318e52b3df6347a Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 10 Jan 2014 10:37:27 -0300
Subject: perf evlist: Introduce evlist__for_each() & friends

For the common evsel list traversal, so that it becomes more compact.

Use the opportunity to start ditching the 'perf_' from 'perf_evlist__',
as discussed, as the whole conversion touches a lot of places, lets do
it piecemeal when we have the chance due to other work, like in this
case.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-qnkx7dzm2h6m6uptkfk03ni6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index ab65057..0da603b 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -232,7 +232,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
 		perf_session__fprintf_dsos(session, stdout);
 
 	total_nr_samples = 0;
-	list_for_each_entry(pos, &session->evlist->entries, node) {
+	evlist__for_each(session->evlist, pos) {
 		struct hists *hists = &pos->hists;
 		u32 nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index e6a0844..987cac3 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -356,9 +356,10 @@ static struct perf_evsel *evsel_match(struct perf_evsel *evsel,
 {
 	struct perf_evsel *e;
 
-	list_for_each_entry(e, &evlist->entries, node)
+	evlist__for_each(evlist, e) {
 		if (perf_evsel__match2(evsel, e))
 			return e;
+	}
 
 	return NULL;
 }
@@ -367,7 +368,7 @@ static void perf_evlist__collapse_resort(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		struct hists *hists = &evsel->hists;
 
 		hists__collapse_resort(hists, NULL);
@@ -614,7 +615,7 @@ static void data_process(void)
 	struct perf_evsel *evsel_base;
 	bool first = true;
 
-	list_for_each_entry(evsel_base, &evlist_base->entries, node) {
+	evlist__for_each(evlist_base, evsel_base) {
 		struct data__file *d;
 		int i;
 
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index 20b0f12..c99e0de 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -29,7 +29,7 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
 	if (session == NULL)
 		return -ENOMEM;
 
-	list_for_each_entry(pos, &session->evlist->entries, node)
+	evlist__for_each(session->evlist, pos)
 		perf_evsel__fprintf(pos, details, stdout);
 
 	perf_session__delete(session);
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index c9f6d74..b346601 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -369,7 +369,7 @@ static int __cmd_inject(struct perf_inject *inject)
 
 		inject->tool.ordered_samples = true;
 
-		list_for_each_entry(evsel, &session->evlist->entries, node) {
+		evlist__for_each(session->evlist, evsel) {
 			const char *name = perf_evsel__name(evsel);
 
 			if (!strcmp(name, "sched:sched_switch")) {
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 858b11b..a735051 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1174,7 +1174,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
 	 * Note: exclude_{guest,host} do not apply here.
 	 *       This command processes KVM tracepoints from host only
 	 */
-	list_for_each_entry(pos, &evlist->entries, node) {
+	evlist__for_each(evlist, pos) {
 		struct perf_event_attr *attr = &pos->attr;
 
 		/* make sure these *are* set */
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index cb00b53..8860015 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -183,7 +183,7 @@ static int record__open(struct record *rec)
 
 	perf_evlist__config(evlist, opts);
 
-	list_for_each_entry(pos, &evlist->entries, node) {
+	evlist__for_each(evlist, pos) {
 try_again:
 		if (perf_evsel__open(pos, evlist->cpus, evlist->threads) < 0) {
 			if (perf_evsel__fallback(pos, errno, msg, sizeof(msg))) {
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index cff9465..46864dd 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -384,7 +384,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 {
 	struct perf_evsel *pos;
 
-	list_for_each_entry(pos, &evlist->entries, node) {
+	evlist__for_each(evlist, pos) {
 		struct hists *hists = &pos->hists;
 		const char *evname = perf_evsel__name(pos);
 
@@ -495,7 +495,7 @@ static u64 report__collapse_hists(struct report *rep)
  	 * Count number of histogram entries to use when showing progress,
  	 * reusing nr_samples variable.
  	 */
-	list_for_each_entry(pos, &rep->session->evlist->entries, node)
+	evlist__for_each(rep->session->evlist, pos)
 		nr_samples += pos->hists.nr_entries;
 
 	ui_progress__init(&prog, nr_samples, "Merging related events...");
@@ -505,7 +505,7 @@ static u64 report__collapse_hists(struct report *rep)
  	 */
 	nr_samples = 0;
 
-	list_for_each_entry(pos, &rep->session->evlist->entries, node) {
+	evlist__for_each(rep->session->evlist, pos) {
 		struct hists *hists = &pos->hists;
 
 		if (pos->idx == 0)
@@ -582,7 +582,7 @@ static int __cmd_report(struct report *rep)
 		return 0;
 	}
 
-	list_for_each_entry(pos, &session->evlist->entries, node)
+	evlist__for_each(session->evlist, pos)
 		hists__output_resort(&pos->hists);
 
 	return report__browse_hists(rep);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 6040000..9e9c91f 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -603,7 +603,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	if (evsel->attr.type >= PERF_TYPE_MAX)
 		return 0;
 
-	list_for_each_entry(pos, &evlist->entries, node) {
+	evlist__for_each(evlist, pos) {
 		if (pos->attr.type == evsel->attr.type && pos != evsel)
 			return 0;
 	}
@@ -1309,8 +1309,7 @@ static int check_ev_match(char *dir_name, char *scriptname,
 			snprintf(evname, len + 1, "%s", p);
 
 			match = 0;
-			list_for_each_entry(pos,
-					&session->evlist->entries, node) {
+			evlist__for_each(session->evlist, pos) {
 				if (!strcmp(perf_evsel__name(pos), evname)) {
 					match = 1;
 					break;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index b27b264..8b0e1c9 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -214,7 +214,7 @@ static void perf_evlist__free_stats(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		perf_evsel__free_stat_priv(evsel);
 		perf_evsel__free_counts(evsel);
 		perf_evsel__free_prev_raw_counts(evsel);
@@ -225,7 +225,7 @@ static int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
 {
 	struct perf_evsel *evsel;
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
 		    perf_evsel__alloc_counts(evsel, perf_evsel__nr_cpus(evsel)) < 0 ||
 		    (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel) < 0))
@@ -259,7 +259,7 @@ static void perf_stat__reset_stats(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		perf_evsel__reset_stat_priv(evsel);
 		perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel));
 	}
@@ -326,13 +326,13 @@ static struct perf_evsel *nth_evsel(int n)
 
 	/* Assumes this only called when evsel_list does not change anymore. */
 	if (!array) {
-		list_for_each_entry(ev, &evsel_list->entries, node)
+		evlist__for_each(evsel_list, ev)
 			array_len++;
 		array = malloc(array_len * sizeof(void *));
 		if (!array)
 			exit(ENOMEM);
 		j = 0;
-		list_for_each_entry(ev, &evsel_list->entries, node)
+		evlist__for_each(evsel_list, ev)
 			array[j++] = ev;
 	}
 	if (n < array_len)
@@ -440,13 +440,13 @@ static void print_interval(void)
 	char prefix[64];
 
 	if (aggr_mode == AGGR_GLOBAL) {
-		list_for_each_entry(counter, &evsel_list->entries, node) {
+		evlist__for_each(evsel_list, counter) {
 			ps = counter->priv;
 			memset(ps->res_stats, 0, sizeof(ps->res_stats));
 			read_counter_aggr(counter);
 		}
 	} else	{
-		list_for_each_entry(counter, &evsel_list->entries, node) {
+		evlist__for_each(evsel_list, counter) {
 			ps = counter->priv;
 			memset(ps->res_stats, 0, sizeof(ps->res_stats));
 			read_counter(counter);
@@ -483,12 +483,12 @@ static void print_interval(void)
 		print_aggr(prefix);
 		break;
 	case AGGR_NONE:
-		list_for_each_entry(counter, &evsel_list->entries, node)
+		evlist__for_each(evsel_list, counter)
 			print_counter(counter, prefix);
 		break;
 	case AGGR_GLOBAL:
 	default:
-		list_for_each_entry(counter, &evsel_list->entries, node)
+		evlist__for_each(evsel_list, counter)
 			print_counter_aggr(counter, prefix);
 	}
 
@@ -504,7 +504,7 @@ static void handle_initial_delay(void)
 			nthreads = thread_map__nr(evsel_list->threads);
 
 		usleep(initial_delay * 1000);
-		list_for_each_entry(counter, &evsel_list->entries, node)
+		evlist__for_each(evsel_list, counter)
 			perf_evsel__enable(counter, ncpus, nthreads);
 	}
 }
@@ -552,7 +552,7 @@ static int __run_perf_stat(int argc, const char **argv)
 	if (group)
 		perf_evlist__set_leader(evsel_list);
 
-	list_for_each_entry(counter, &evsel_list->entries, node) {
+	evlist__for_each(evsel_list, counter) {
 		if (create_perf_stat_counter(counter) < 0) {
 			/*
 			 * PPC returns ENXIO for HW counters until 2.6.37
@@ -630,13 +630,13 @@ static int __run_perf_stat(int argc, const char **argv)
 	update_stats(&walltime_nsecs_stats, t1 - t0);
 
 	if (aggr_mode == AGGR_GLOBAL) {
-		list_for_each_entry(counter, &evsel_list->entries, node) {
+		evlist__for_each(evsel_list, counter) {
 			read_counter_aggr(counter);
 			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
 					     thread_map__nr(evsel_list->threads));
 		}
 	} else {
-		list_for_each_entry(counter, &evsel_list->entries, node) {
+		evlist__for_each(evsel_list, counter) {
 			read_counter(counter);
 			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), 1);
 		}
@@ -1117,7 +1117,7 @@ static void print_aggr(char *prefix)
 
 	for (s = 0; s < aggr_map->nr; s++) {
 		id = aggr_map->map[s];
-		list_for_each_entry(counter, &evsel_list->entries, node) {
+		evlist__for_each(evsel_list, counter) {
 			val = ena = run = 0;
 			nr = 0;
 			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
@@ -1328,11 +1328,11 @@ static void print_stat(int argc, const char **argv)
 		print_aggr(NULL);
 		break;
 	case AGGR_GLOBAL:
-		list_for_each_entry(counter, &evsel_list->entries, node)
+		evlist__for_each(evsel_list, counter)
 			print_counter_aggr(counter, NULL);
 		break;
 	case AGGR_NONE:
-		list_for_each_entry(counter, &evsel_list->entries, node)
+		evlist__for_each(evsel_list, counter)
 			print_counter(counter, NULL);
 		break;
 	default:
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index e0fd0aa..569dd87 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -482,7 +482,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 
 				fprintf(stderr, "\nAvailable events:");
 
-				list_for_each_entry(top->sym_evsel, &top->evlist->entries, node)
+				evlist__for_each(top->evlist, top->sym_evsel)
 					fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, perf_evsel__name(top->sym_evsel));
 
 				prompt_integer(&counter, "Enter details event counter");
@@ -493,7 +493,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 					sleep(1);
 					break;
 				}
-				list_for_each_entry(top->sym_evsel, &top->evlist->entries, node)
+				evlist__for_each(top->evlist, top->sym_evsel)
 					if (top->sym_evsel->idx == counter)
 						break;
 			} else
@@ -575,7 +575,7 @@ static void *display_thread_tui(void *arg)
 	 * Zooming in/out UIDs. For now juse use whatever the user passed
 	 * via --uid.
 	 */
-	list_for_each_entry(pos, &top->evlist->entries, node)
+	evlist__for_each(top->evlist, pos)
 		pos->hists.uid_filter_str = top->record_opts.target.uid_str;
 
 	perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent,
@@ -858,7 +858,7 @@ static int perf_top__start_counters(struct perf_top *top)
 
 	perf_evlist__config(evlist, opts);
 
-	list_for_each_entry(counter, &evlist->entries, node) {
+	evlist__for_each(evlist, counter) {
 try_again:
 		if (perf_evsel__open(counter, top->evlist->cpus,
 				     top->evlist->threads) < 0) {
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index 0197bda..465cdbc 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -79,7 +79,7 @@ static int __perf_evsel__name_array_test(const char *names[], int nr_names)
 	}
 
 	err = 0;
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		if (strcmp(perf_evsel__name(evsel), names[evsel->idx])) {
 			--err;
 			pr_debug("%s != %s\n", perf_evsel__name(evsel), names[evsel->idx]);
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 173bf42..2b6519e 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -208,7 +208,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 	 * However the second evsel also has a collapsed entry for
 	 * "bash [libc] malloc" so total 9 entries will be in the tree.
 	 */
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		for (k = 0; k < ARRAY_SIZE(fake_common_samples); k++) {
 			const union perf_event event = {
 				.header = {
@@ -466,7 +466,7 @@ int test__hists_link(void)
 	if (err < 0)
 		goto out;
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		hists__collapse_resort(&evsel->hists, NULL);
 
 		if (verbose > 2)
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index aef25f0..1422634 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -126,7 +126,7 @@ int test__basic_mmap(void)
 	}
 
 	err = 0;
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) {
 			pr_debug("expected %d %s events, got %d\n",
 				 expected_nr_events[evsel->idx],
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 41dee5e..4db0ae6 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -30,7 +30,7 @@ static int test__checkevent_tracepoint_multi(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
 	TEST_ASSERT_VAL("wrong number of groups", 0 == evlist->nr_groups);
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		TEST_ASSERT_VAL("wrong type",
 			PERF_TYPE_TRACEPOINT == evsel->attr.type);
 		TEST_ASSERT_VAL("wrong sample_type",
@@ -201,7 +201,7 @@ test__checkevent_tracepoint_multi_modifier(struct perf_evlist *evlist)
 
 	TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		TEST_ASSERT_VAL("wrong exclude_user",
 				!evsel->attr.exclude_user);
 		TEST_ASSERT_VAL("wrong exclude_kernel",
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index a7045ea..b720b92 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1938,7 +1938,7 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
 
 	ui_helpline__push("Press ESC to exit");
 
-	list_for_each_entry(pos, &evlist->entries, node) {
+	evlist__for_each(evlist, pos) {
 		const char *ev_name = perf_evsel__name(pos);
 		size_t line_len = strlen(ev_name) + 7;
 
@@ -1970,9 +1970,10 @@ single_entry:
 		struct perf_evsel *pos;
 
 		nr_entries = 0;
-		list_for_each_entry(pos, &evlist->entries, node)
+		evlist__for_each(evlist, pos) {
 			if (perf_evsel__is_group_leader(pos))
 				nr_entries++;
+		}
 
 		if (nr_entries == 1)
 			goto single_entry;
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 2ca66cc..5b95c44 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -375,7 +375,7 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 
 	gtk_container_add(GTK_CONTAINER(window), vbox);
 
-	list_for_each_entry(pos, &evlist->entries, node) {
+	evlist__for_each(evlist, pos) {
 		struct hists *hists = &pos->hists;
 		const char *evname = perf_evsel__name(pos);
 		GtkWidget *scrolled_window;
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 0922aa4..88f7be3 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -81,7 +81,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 	/*
 	 * check if cgrp is already defined, if so we reuse it
 	 */
-	list_for_each_entry(counter, &evlist->entries, node) {
+	evlist__for_each(evlist, counter) {
 		cgrp = counter->cgrp;
 		if (!cgrp)
 			continue;
@@ -110,7 +110,7 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 	 * if add cgroup N, then need to find event N
 	 */
 	n = 0;
-	list_for_each_entry(counter, &evlist->entries, node) {
+	evlist__for_each(evlist, counter) {
 		if (n == nr_cgroups)
 			goto found;
 		n++;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 0810f5c..40bd2c0 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -81,7 +81,7 @@ static void perf_evlist__update_id_pos(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
-	list_for_each_entry(evsel, &evlist->entries, node)
+	evlist__for_each(evlist, evsel)
 		perf_evsel__calc_id_pos(evsel);
 
 	perf_evlist__set_id_pos(evlist);
@@ -91,7 +91,7 @@ static void perf_evlist__purge(struct perf_evlist *evlist)
 {
 	struct perf_evsel *pos, *n;
 
-	list_for_each_entry_safe(pos, n, &evlist->entries, node) {
+	evlist__for_each_safe(evlist, n, pos) {
 		list_del_init(&pos->node);
 		perf_evsel__delete(pos);
 	}
@@ -148,7 +148,7 @@ void __perf_evlist__set_leader(struct list_head *list)
 
 	leader->nr_members = evsel->idx - leader->idx + 1;
 
-	list_for_each_entry(evsel, list, node) {
+	__evlist__for_each(list, evsel) {
 		evsel->leader = leader;
 	}
 }
@@ -207,7 +207,7 @@ static int perf_evlist__add_attrs(struct perf_evlist *evlist,
 	return 0;
 
 out_delete_partial_list:
-	list_for_each_entry_safe(evsel, n, &head, node)
+	__evlist__for_each_safe(&head, n, evsel)
 		perf_evsel__delete(evsel);
 	return -1;
 }
@@ -228,7 +228,7 @@ perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id)
 {
 	struct perf_evsel *evsel;
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		if (evsel->attr.type   == PERF_TYPE_TRACEPOINT &&
 		    (int)evsel->attr.config == id)
 			return evsel;
@@ -243,7 +243,7 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
 {
 	struct perf_evsel *evsel;
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		if ((evsel->attr.type == PERF_TYPE_TRACEPOINT) &&
 		    (strcmp(evsel->name, name) == 0))
 			return evsel;
@@ -273,7 +273,7 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 	int nr_threads = thread_map__nr(evlist->threads);
 
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		list_for_each_entry(pos, &evlist->entries, node) {
+		evlist__for_each(evlist, pos) {
 			if (!perf_evsel__is_group_leader(pos) || !pos->fd)
 				continue;
 			for (thread = 0; thread < nr_threads; thread++)
@@ -291,7 +291,7 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 	int nr_threads = thread_map__nr(evlist->threads);
 
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		list_for_each_entry(pos, &evlist->entries, node) {
+		evlist__for_each(evlist, pos) {
 			if (!perf_evsel__is_group_leader(pos) || !pos->fd)
 				continue;
 			for (thread = 0; thread < nr_threads; thread++)
@@ -630,7 +630,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 {
 	struct perf_evsel *evsel;
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		int fd = FD(evsel, cpu, thread);
 
 		if (*output == -1) {
@@ -806,7 +806,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	pr_debug("mmap size %zuB\n", evlist->mmap_len);
 	mask = evlist->mmap_len - page_size - 1;
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
 		    evsel->sample_id == NULL &&
 		    perf_evsel__alloc_id(evsel, cpu_map__nr(cpus), threads->nr) < 0)
@@ -849,7 +849,7 @@ int perf_evlist__apply_filters(struct perf_evlist *evlist)
 	const int ncpus = cpu_map__nr(evlist->cpus),
 		  nthreads = thread_map__nr(evlist->threads);
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		if (evsel->filter == NULL)
 			continue;
 
@@ -868,7 +868,7 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
 	const int ncpus = cpu_map__nr(evlist->cpus),
 		  nthreads = thread_map__nr(evlist->threads);
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		err = perf_evsel__set_filter(evsel, ncpus, nthreads, filter);
 		if (err)
 			break;
@@ -887,7 +887,7 @@ bool perf_evlist__valid_sample_type(struct perf_evlist *evlist)
 	if (evlist->id_pos < 0 || evlist->is_pos < 0)
 		return false;
 
-	list_for_each_entry(pos, &evlist->entries, node) {
+	evlist__for_each(evlist, pos) {
 		if (pos->id_pos != evlist->id_pos ||
 		    pos->is_pos != evlist->is_pos)
 			return false;
@@ -903,7 +903,7 @@ u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist)
 	if (evlist->combined_sample_type)
 		return evlist->combined_sample_type;
 
-	list_for_each_entry(evsel, &evlist->entries, node)
+	evlist__for_each(evlist, evsel)
 		evlist->combined_sample_type |= evsel->attr.sample_type;
 
 	return evlist->combined_sample_type;
@@ -921,7 +921,7 @@ bool perf_evlist__valid_read_format(struct perf_evlist *evlist)
 	u64 read_format = first->attr.read_format;
 	u64 sample_type = first->attr.sample_type;
 
-	list_for_each_entry_continue(pos, &evlist->entries, node) {
+	evlist__for_each(evlist, pos) {
 		if (read_format != pos->attr.read_format)
 			return false;
 	}
@@ -978,7 +978,7 @@ bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist)
 {
 	struct perf_evsel *first = perf_evlist__first(evlist), *pos = first;
 
-	list_for_each_entry_continue(pos, &evlist->entries, node) {
+	evlist__for_each_continue(evlist, pos) {
 		if (first->attr.sample_id_all != pos->attr.sample_id_all)
 			return false;
 	}
@@ -1004,7 +1004,7 @@ void perf_evlist__close(struct perf_evlist *evlist)
 	int ncpus = cpu_map__nr(evlist->cpus);
 	int nthreads = thread_map__nr(evlist->threads);
 
-	list_for_each_entry_reverse(evsel, &evlist->entries, node)
+	evlist__for_each_reverse(evlist, evsel)
 		perf_evsel__close(evsel, ncpus, nthreads);
 }
 
@@ -1015,7 +1015,7 @@ int perf_evlist__open(struct perf_evlist *evlist)
 
 	perf_evlist__update_id_pos(evlist);
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		err = perf_evsel__open(evsel, evlist->cpus, evlist->threads);
 		if (err < 0)
 			goto out_err;
@@ -1154,7 +1154,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)
 	struct perf_evsel *evsel;
 	size_t printed = 0;
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		printed += fprintf(fp, "%s%s", evsel->idx ? ", " : "",
 				   perf_evsel__name(evsel));
 	}
@@ -1233,7 +1233,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 	if (move_evsel == perf_evlist__first(evlist))
 		return;
 
-	list_for_each_entry_safe(evsel, n, &evlist->entries, node) {
+	evlist__for_each_safe(evlist, n, evsel) {
 		if (evsel->leader == move_evsel->leader)
 			list_move_tail(&evsel->node, &move);
 	}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 518e521..f5173cd 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -196,5 +196,70 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str);
 void perf_evlist__to_front(struct perf_evlist *evlist,
 			   struct perf_evsel *move_evsel);
 
+/**
+ * __evlist__for_each - iterate thru all the evsels
+ * @list: list_head instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define __evlist__for_each(list, evsel) \
+        list_for_each_entry(evsel, list, node)
+
+/**
+ * evlist__for_each - iterate thru all the evsels
+ * @evlist: evlist instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define evlist__for_each(evlist, evsel) \
+	__evlist__for_each(&(evlist)->entries, evsel)
+
+/**
+ * __evlist__for_each_continue - continue iteration thru all the evsels
+ * @list: list_head instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define __evlist__for_each_continue(list, evsel) \
+        list_for_each_entry_continue(evsel, list, node)
+
+/**
+ * evlist__for_each_continue - continue iteration thru all the evsels
+ * @evlist: evlist instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define evlist__for_each_continue(evlist, evsel) \
+	__evlist__for_each_continue(&(evlist)->entries, evsel)
+
+/**
+ * __evlist__for_each_reverse - iterate thru all the evsels in reverse order
+ * @list: list_head instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define __evlist__for_each_reverse(list, evsel) \
+        list_for_each_entry_reverse(evsel, list, node)
+
+/**
+ * evlist__for_each_reverse - iterate thru all the evsels in reverse order
+ * @evlist: evlist instance to iterate
+ * @evsel: struct evsel iterator
+ */
+#define evlist__for_each_reverse(evlist, evsel) \
+	__evlist__for_each_reverse(&(evlist)->entries, evsel)
+
+/**
+ * __evlist__for_each_safe - safely iterate thru all the evsels
+ * @list: list_head instance to iterate
+ * @tmp: struct evsel temp iterator
+ * @evsel: struct evsel iterator
+ */
+#define __evlist__for_each_safe(list, tmp, evsel) \
+        list_for_each_entry_safe(evsel, tmp, list, node)
+
+/**
+ * evlist__for_each_safe - safely iterate thru all the evsels
+ * @evlist: evlist instance to iterate
+ * @evsel: struct evsel iterator
+ * @tmp: struct evsel temp iterator
+ */
+#define evlist__for_each_safe(evlist, tmp, evsel) \
+	__evlist__for_each_safe(&(evlist)->entries, tmp, evsel)
 
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index a4a60b7..bb3e0ed 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -643,8 +643,7 @@ static int write_event_desc(int fd, struct perf_header *h __maybe_unused,
 	if (ret < 0)
 		return ret;
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
-
+	evlist__for_each(evlist, evsel) {
 		ret = do_write(fd, &evsel->attr, sz);
 		if (ret < 0)
 			return ret;
@@ -1092,7 +1091,7 @@ static int write_group_desc(int fd, struct perf_header *h __maybe_unused,
 	if (ret < 0)
 		return ret;
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		if (perf_evsel__is_group_leader(evsel) &&
 		    evsel->nr_members > 1) {
 			const char *name = evsel->group_name ?: "{anon_group}";
@@ -1487,7 +1486,7 @@ static void print_group_desc(struct perf_header *ph, int fd __maybe_unused,
 
 	session = container_of(ph, struct perf_session, header);
 
-	list_for_each_entry(evsel, &session->evlist->entries, node) {
+	evlist__for_each(session->evlist, evsel) {
 		if (perf_evsel__is_group_leader(evsel) &&
 		    evsel->nr_members > 1) {
 			fprintf(fp, "# group: %s{%s", evsel->group_name ?: "",
@@ -1768,7 +1767,7 @@ perf_evlist__find_by_index(struct perf_evlist *evlist, int idx)
 {
 	struct perf_evsel *evsel;
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		if (evsel->idx == idx)
 			return evsel;
 	}
@@ -2071,7 +2070,7 @@ static int process_group_desc(struct perf_file_section *section __maybe_unused,
 	session->evlist->nr_groups = nr_groups;
 
 	i = nr = 0;
-	list_for_each_entry(evsel, &session->evlist->entries, node) {
+	evlist__for_each(session->evlist, evsel) {
 		if (evsel->idx == (int) desc[i].leader_idx) {
 			evsel->leader = evsel;
 			/* {anon_group} is a dummy name */
@@ -2298,7 +2297,7 @@ int perf_session__write_header(struct perf_session *session,
 
 	lseek(fd, sizeof(f_header), SEEK_SET);
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(session->evlist, evsel) {
 		evsel->id_offset = lseek(fd, 0, SEEK_CUR);
 		err = do_write(fd, evsel->id, evsel->ids * sizeof(u64));
 		if (err < 0) {
@@ -2309,7 +2308,7 @@ int perf_session__write_header(struct perf_session *session,
 
 	attr_offset = lseek(fd, 0, SEEK_CUR);
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		f_attr = (struct perf_file_attr){
 			.attr = evsel->attr,
 			.ids  = {
@@ -2742,7 +2741,7 @@ static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist,
 {
 	struct perf_evsel *pos;
 
-	list_for_each_entry(pos, &evlist->entries, node) {
+	evlist__for_each(evlist, pos) {
 		if (pos->attr.type == PERF_TYPE_TRACEPOINT &&
 		    perf_evsel__prepare_tracepoint_event(pos, pevent))
 			return -1;
@@ -2890,7 +2889,7 @@ int perf_event__synthesize_attrs(struct perf_tool *tool,
 	struct perf_evsel *evsel;
 	int err = 0;
 
-	list_for_each_entry(evsel, &session->evlist->entries, node) {
+	evlist__for_each(session->evlist, evsel) {
 		err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids,
 						  evsel->id, process);
 		if (err) {
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 0153435..a7f1b6a 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -820,8 +820,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add)
 	if (!add && get_event_modifier(&mod, str, NULL))
 		return -EINVAL;
 
-	list_for_each_entry(evsel, list, node) {
-
+	__evlist__for_each(list, evsel) {
 		if (add && get_event_modifier(&mod, str, evsel))
 			return -EINVAL;
 
@@ -845,7 +844,7 @@ int parse_events_name(struct list_head *list, char *name)
 {
 	struct perf_evsel *evsel;
 
-	list_for_each_entry(evsel, list, node) {
+	__evlist__for_each(list, evsel) {
 		if (!evsel->name)
 			evsel->name = strdup(name);
 	}
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 4bf8ace..122669c 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -908,9 +908,10 @@ static PyObject *pyrf_evlist__item(PyObject *obj, Py_ssize_t i)
 	if (i >= pevlist->evlist.nr_entries)
 		return NULL;
 
-	list_for_each_entry(pos, &pevlist->evlist.entries, node)
+	evlist__for_each(&pevlist->evlist, pos) {
 		if (i-- == 0)
 			break;
+	}
 
 	return Py_BuildValue("O", container_of(pos, struct pyrf_evsel, evsel));
 }
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 104a475..3737625 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -89,19 +89,19 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 	if (evlist->cpus->map[0] < 0)
 		opts->no_inherit = true;
 
-	list_for_each_entry(evsel, &evlist->entries, node)
+	evlist__for_each(evlist, evsel)
 		perf_evsel__config(evsel, opts);
 
 	if (evlist->nr_entries > 1) {
 		struct perf_evsel *first = perf_evlist__first(evlist);
 
-		list_for_each_entry(evsel, &evlist->entries, node) {
+		evlist__for_each(evlist, evsel) {
 			if (evsel->attr.sample_type == first->attr.sample_type)
 				continue;
 			use_sample_identifier = perf_can_sample_identifier();
 			break;
 		}
-		list_for_each_entry(evsel, &evlist->entries, node)
+		evlist__for_each(evlist, evsel)
 			perf_evsel__set_sample_id(evsel, use_sample_identifier);
 	}
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8ffe29c..7acc03e 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1384,7 +1384,7 @@ bool perf_session__has_traces(struct perf_session *session, const char *msg)
 {
 	struct perf_evsel *evsel;
 
-	list_for_each_entry(evsel, &session->evlist->entries, node) {
+	evlist__for_each(session->evlist, evsel) {
 		if (evsel->attr.type == PERF_TYPE_TRACEPOINT)
 			return true;
 	}
@@ -1442,7 +1442,7 @@ size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
 
 	ret += events_stats__fprintf(&session->stats, fp);
 
-	list_for_each_entry(pos, &session->evlist->entries, node) {
+	evlist__for_each(session->evlist, pos) {
 		ret += fprintf(fp, "%s stats:\n", perf_evsel__name(pos));
 		ret += events_stats__fprintf(&pos->hists.stats, fp);
 	}
@@ -1464,7 +1464,7 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
 {
 	struct perf_evsel *pos;
 
-	list_for_each_entry(pos, &session->evlist->entries, node) {
+	evlist__for_each(session->evlist, pos) {
 		if (pos->attr.type == type)
 			return pos;
 	}
-- 
cgit v0.10.2


From 8a625c1f61f3dd5e4ea4b5b642650416aa101ce5 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 9 Jan 2014 23:00:52 +0900
Subject: tools include: Move perf's linux/compiler.h to a generic place

So that it can be shared with others like libtraceevent.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Borislav Petkov <bp@suse.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389276059-8829-2-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
new file mode 100644
index 0000000..0135ccf
--- /dev/null
+++ b/tools/include/linux/compiler.h
@@ -0,0 +1,30 @@
+#ifndef _TOOLS_LINUX_COMPILER_H_
+#define _TOOLS_LINUX_COMPILER_H_
+
+#ifndef __always_inline
+# define __always_inline	inline __attribute__((always_inline))
+#endif
+
+#define __user
+
+#ifndef __attribute_const__
+# define __attribute_const__
+#endif
+
+#ifndef __maybe_unused
+# define __maybe_unused		__attribute__((unused))
+#endif
+
+#ifndef __packed
+# define __packed		__attribute__((__packed__))
+#endif
+
+#ifndef __force
+# define __force
+#endif
+
+#ifndef __weak
+# define __weak			__attribute__((weak))
+#endif
+
+#endif /* _TOOLS_LINUX_COMPILER_H */
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 3638b0b..6be0676 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -211,7 +211,7 @@ LIB_H += ../../include/linux/hash.h
 LIB_H += ../../include/linux/stringify.h
 LIB_H += util/include/linux/bitmap.h
 LIB_H += util/include/linux/bitops.h
-LIB_H += util/include/linux/compiler.h
+LIB_H += ../include/linux/compiler.h
 LIB_H += util/include/linux/const.h
 LIB_H += util/include/linux/ctype.h
 LIB_H += util/include/linux/kernel.h
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 5d15b43..01dd43d 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -232,6 +232,7 @@ endif
 
 CFLAGS += -I$(src-perf)/util/include
 CFLAGS += -I$(src-perf)/arch/$(ARCH)/include
+CFLAGS += -I$(srctree)/tools/include/
 CFLAGS += -I$(srctree)/arch/$(ARCH)/include/uapi
 CFLAGS += -I$(srctree)/arch/$(ARCH)/include
 CFLAGS += -I$(srctree)/include/uapi
diff --git a/tools/perf/util/include/linux/compiler.h b/tools/perf/util/include/linux/compiler.h
deleted file mode 100644
index b003ad7..0000000
--- a/tools/perf/util/include/linux/compiler.h
+++ /dev/null
@@ -1,30 +0,0 @@
-#ifndef _PERF_LINUX_COMPILER_H_
-#define _PERF_LINUX_COMPILER_H_
-
-#ifndef __always_inline
-# define __always_inline	inline __attribute__((always_inline))
-#endif
-
-#define __user
-
-#ifndef __attribute_const__
-# define __attribute_const__
-#endif
-
-#ifndef __maybe_unused
-# define __maybe_unused		__attribute__((unused))
-#endif
-
-#ifndef __packed
-# define __packed		__attribute__((__packed__))
-#endif
-
-#ifndef __force
-# define __force
-#endif
-
-#ifndef __weak
-# define __weak			__attribute__((weak))
-#endif
-
-#endif
-- 
cgit v0.10.2


From 835d44b9041e578e3e553a57dfffc7003605c93b Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 9 Jan 2014 23:00:53 +0900
Subject: tools include: Define likely/unlikely in linux/compiler.h

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389276059-8829-3-git-send-email-namhyung@kernel.org
[ Added the new header to tools/perf/MANIFEST ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 0135ccf..fbc6665 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -27,4 +27,12 @@
 # define __weak			__attribute__((weak))
 #endif
 
+#ifndef likely
+# define likely(x)		__builtin_expect(!!(x), 1)
+#endif
+
+#ifndef unlikely
+# define unlikely(x)		__builtin_expect(!!(x), 0)
+#endif
+
 #endif /* _TOOLS_LINUX_COMPILER_H */
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 3170a7f..285f28f 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -4,6 +4,7 @@ tools/lib/traceevent
 tools/lib/lk
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
+tools/include/linux/compiler.h
 include/linux/const.h
 include/linux/perf_event.h
 include/linux/rbtree.h
-- 
cgit v0.10.2


From 02dfc8d775f0709ab494d4b2cce12c8429ff7530 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 9 Jan 2014 23:00:54 +0900
Subject: tools include: Move perf's bug.h to a generic place

So that it can be shared with others like libtraceevent.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389276059-8829-4-git-send-email-namhyung@kernel.org
[ Added the new header to tools/perf/MANIFEST ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/include/asm/bug.h b/tools/include/asm/bug.h
new file mode 100644
index 0000000..eca78df
--- /dev/null
+++ b/tools/include/asm/bug.h
@@ -0,0 +1,23 @@
+#ifndef _TOOLS_ASM_BUG_H
+#define _TOOLS_ASM_BUG_H
+
+#define __WARN_printf(arg...)	do { fprintf(stderr, arg); } while (0)
+
+#define WARN(condition, format...) ({		\
+	int __ret_warn_on = !!(condition);	\
+	if (unlikely(__ret_warn_on))		\
+		__WARN_printf(format);		\
+	unlikely(__ret_warn_on);		\
+})
+
+#define WARN_ONCE(condition, format...)	({	\
+	static int __warned;			\
+	int __ret_warn_once = !!(condition);	\
+						\
+	if (unlikely(__ret_warn_once))		\
+		if (WARN(!__warned, format)) 	\
+			__warned = 1;		\
+	unlikely(__ret_warn_once);		\
+})
+
+#endif /* _TOOLS_ASM_BUG_H */
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 285f28f..4e53535 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -4,6 +4,7 @@ tools/lib/traceevent
 tools/lib/lk
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
+tools/include/asm/bug.h
 tools/include/linux/compiler.h
 include/linux/const.h
 include/linux/perf_event.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 6be0676..87d7726 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -226,7 +226,7 @@ LIB_H += util/include/linux/string.h
 LIB_H += util/include/linux/types.h
 LIB_H += util/include/linux/linkage.h
 LIB_H += util/include/asm/asm-offsets.h
-LIB_H += util/include/asm/bug.h
+LIB_H += ../include/asm/bug.h
 LIB_H += util/include/asm/byteorder.h
 LIB_H += util/include/asm/hweight.h
 LIB_H += util/include/asm/swab.h
diff --git a/tools/perf/util/include/asm/bug.h b/tools/perf/util/include/asm/bug.h
deleted file mode 100644
index 7fcc681..0000000
--- a/tools/perf/util/include/asm/bug.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef _PERF_ASM_GENERIC_BUG_H
-#define _PERF_ASM_GENERIC_BUG_H
-
-#define __WARN_printf(arg...)	do { fprintf(stderr, arg); } while (0)
-
-#define WARN(condition, format...) ({		\
-	int __ret_warn_on = !!(condition);	\
-	if (unlikely(__ret_warn_on))		\
-		__WARN_printf(format);		\
-	unlikely(__ret_warn_on);		\
-})
-
-#define WARN_ONCE(condition, format...)	({	\
-	static int __warned;			\
-	int __ret_warn_once = !!(condition);	\
-						\
-	if (unlikely(__ret_warn_once))		\
-		if (WARN(!__warned, format)) 	\
-			__warned = 1;		\
-	unlikely(__ret_warn_once);		\
-})
-#endif
-- 
cgit v0.10.2


From c023f534c31f69a658fc21d619116ad12c7be464 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 10 Jan 2014 16:25:05 -0300
Subject: perf tools: Include tools/lib/api/ in MANIFEST

When 553873e1df63 renamed tools/lib/lk to tools/lib/api we forgot to
do the switch in tools/perf/MANIFEST, breaking tarball building:

  [acme@ssdandy linux]$ make perf-targz-src-pkg
    TAR
  [acme@ssdandy linux]$ tar xf perf-3.13.0-rc4.tar.gz -C /tmp/tmp.OgdYyvp77p/
  [acme@ssdandy linux]$ make -C /tmp/tmp.OgdYyvp77p/perf-3.13.0-rc4/tools/perf
  make: Entering directory
  `/tmp/tmp.OgdYyvp77p/perf-3.13.0-rc4/tools/perf'
    BUILD:   Doing 'make -j8' parallel build
    FLEX     util/pmu-flex.c
    CC       util/evlist.o
    CC       util/evsel.o
  util/evsel.c:12:28: fatal error: api/fs/debugfs.h: No such file or directory compilation terminated.
  In file included from util/cache.h:5:0,
  <SNIP>

Fix it.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-1wwjs01rt3xbyhn6kjl2gfs9@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 4e53535..f41572d 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,7 +1,7 @@
 tools/perf
 tools/scripts
 tools/lib/traceevent
-tools/lib/lk
+tools/lib/api
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
 tools/include/asm/bug.h
-- 
cgit v0.10.2


From 4887805384751717ef62a8f41439d1d3e4268b39 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 10 Jan 2014 16:46:45 -0300
Subject: perf tools: Add test for building detached source tarballs

Test one of the main kernel Makefile targets to generate a perf sources
tarball suitable for build outside the full kernel sources.

This is to test that the tools/perf/MANIFEST file lists all the files
needed to be in such tarball, which sometimes gets broken when we move
files around, like when we made some files that were in tools/perf/
available to other tools/ codebases by moving it to tools/include/, etc.

Now everytime we use 'make -C tools/perf -f tests/make' this test will
be performed, helping detect such problems earlier in the devel cycle.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-gyivwbbu2j7c4j4pwpmttg2p@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index e341088..00544b8 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -216,10 +216,16 @@ $(run_O):
 	rm -rf $$TMP_O \
 	rm -rf $$TMP_DEST
 
-all: $(run) $(run_O)
+tarpkg:
+	@cmd="$(PERF)/tests/perf-targz-src-pkg $(PERF)"; \
+	echo "- $@: $$cmd" && echo $$cmd > $@ && \
+	( eval $$cmd ) >> $@ 2>&1
+	
+
+all: $(run) $(run_O) tarpkg
 	@echo OK
 
 out: $(run_O)
 	@echo OK
 
-.PHONY: all $(run) $(run_O) clean
+.PHONY: all $(run) $(run_O) tarpkg clean
diff --git a/tools/perf/tests/perf-targz-src-pkg b/tools/perf/tests/perf-targz-src-pkg
new file mode 100755
index 0000000..238aa39
--- /dev/null
+++ b/tools/perf/tests/perf-targz-src-pkg
@@ -0,0 +1,21 @@
+#!/bin/sh
+# Test one of the main kernel Makefile targets to generate a perf sources tarball
+# suitable for build outside the full kernel sources.
+#
+# This is to test that the tools/perf/MANIFEST file lists all the files needed to
+# be in such tarball, which sometimes gets broken when we move files around,
+# like when we made some files that were in tools/perf/ available to other tools/
+# codebases by moving it to tools/include/, etc.
+
+PERF=$1
+cd ${PERF}/../..
+make perf-targz-src-pkg > /dev/null
+TARBALL=$(ls -rt perf-*.tar.gz)
+TMP_DEST=$(mktemp -d)
+tar xf ${TARBALL} -C $TMP_DEST
+rm -f ${TARBALL}
+cd - > /dev/null
+make -C $TMP_DEST/perf*/tools/perf > /dev/null 2>&1
+RC=$?
+rm -rf ${TMP_DEST}
+exit $RC
-- 
cgit v0.10.2


From d11416e76b3e2f60ed6cfa7c532d3b6777f66527 Mon Sep 17 00:00:00 2001
From: Jean Pihet <jean.pihet@linaro.org>
Date: Mon, 16 Dec 2013 17:43:14 +0100
Subject: perf tools: Use the DWARF unwind info only if loaded

Use the info only if it has been found in the .debug_frame section of
the ELF binary.

Signed-off-by: Jean Pihet <jean.pihet@linaro.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linaro-kernel@lists.linaro.org
Cc: patches@linaro.org
Link: http://lkml.kernel.org/r/1387212194-8028-1-git-send-email-jean.pihet@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind.c
index 0efd539..416f22b 100644
--- a/tools/perf/util/unwind.c
+++ b/tools/perf/util/unwind.c
@@ -340,10 +340,10 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
 	/* Check the .debug_frame section for unwinding info */
 	if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
 		memset(&di, 0, sizeof(di));
-		dwarf_find_debug_frame(0, &di, ip, 0, map->dso->name,
-				       map->start, map->end);
-		return dwarf_search_unwind_table(as, ip, &di, pi,
-						 need_unwind_info, arg);
+		if (dwarf_find_debug_frame(0, &di, ip, 0, map->dso->name,
+					   map->start, map->end))
+			return dwarf_search_unwind_table(as, ip, &di, pi,
+							 need_unwind_info, arg);
 	}
 #endif
 
-- 
cgit v0.10.2


From 6619a53ef7572b9eaf7aa71ff7f74c0d06b3817b Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Sat, 11 Jan 2014 13:38:27 -0800
Subject: perf record: Add --initial-delay option

perf stat has a --delay option to delay measuring the workload.

This is useful to skip measuring the startup phase of the program, which
is often very different from the main workload.

The same is useful for perf record when sampling.

--no-delay was already taken, so add a --initial-delay
to perf record too.
-D was already taken for record, so there is only a long option.

v2: Don't disable group members (Namhyung Kim)
v3: port to latest perf/core
    rename to --initial-delay to avoid conflict with --no-delay

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1389476307-2124-1-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index c407897..82bffac 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -209,6 +209,10 @@ overrides that and uses per-thread mmaps.  A side-effect of that is that
 inheritance is automatically disabled.  --per-thread is ignored with a warning
 if combined with -a or -C options.
 
+--initial-delay msecs::
+After starting the program, wait msecs before measuring. This is useful to
+filter out the startup phase of the program, which is often very different.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 8860015..07d4cf8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -499,7 +499,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	 * (apart from group members) have enable_on_exec=1 set,
 	 * so don't spoil it by prematurely enabling them.
 	 */
-	if (!target__none(&opts->target))
+	if (!target__none(&opts->target) && !opts->initial_delay)
 		perf_evlist__enable(rec->evlist);
 
 	/*
@@ -508,6 +508,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	if (forks)
 		perf_evlist__start_workload(rec->evlist);
 
+	if (opts->initial_delay) {
+		usleep(opts->initial_delay * 1000);
+		perf_evlist__enable(rec->evlist);
+	}
+
 	for (;;) {
 		int hits = rec->samples;
 
@@ -877,6 +882,8 @@ const struct option record_options[] = {
 	OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
 		     "monitor event in cgroup name only",
 		     parse_cgroups),
+	OPT_UINTEGER(0, "initial-delay", &record.opts.initial_delay,
+		  "ms to wait before starting measurement after program start"),
 	OPT_STRING('u', "uid", &record.opts.target.uid_str, "user",
 		   "user to profile"),
 
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index b1cc84b..af1ce6e 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -269,6 +269,7 @@ struct record_opts {
 	u64	     user_interval;
 	u16	     stack_dump_size;
 	bool	     sample_transaction;
+	unsigned     initial_delay;
 };
 
 #endif
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ade8d9c..cd4630a 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -658,7 +658,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	 * Setting enable_on_exec for independent events and
 	 * group leaders for traced executed by perf.
 	 */
-	if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel))
+	if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel) &&
+		!opts->initial_delay)
 		attr->enable_on_exec = 1;
 }
 
-- 
cgit v0.10.2


From 741a0c59032faeddac80a6237f3d7846231a3740 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 9 Jan 2014 23:00:55 +0900
Subject: tools include: Include <linux/compiler.h> from asm/bug.h

Since it uses unlikely() macro inside WARN()

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389276059-8829-5-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/include/asm/bug.h b/tools/include/asm/bug.h
index eca78df..9e5f484 100644
--- a/tools/include/asm/bug.h
+++ b/tools/include/asm/bug.h
@@ -1,6 +1,8 @@
 #ifndef _TOOLS_ASM_BUG_H
 #define _TOOLS_ASM_BUG_H
 
+#include <linux/compiler.h>
+
 #define __WARN_printf(arg...)	do { fprintf(stderr, arg); } while (0)
 
 #define WARN(condition, format...) ({		\
-- 
cgit v0.10.2


From f77c6e9c8f9c444cd44423df0c2708e86a06a696 Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <artagnon@gmail.com>
Date: Mon, 30 Dec 2013 13:04:18 +0530
Subject: perf tools: Generalize percent_color_snprintf()

Make percent_color_snprintf() handle negative values correctly.

Signed-off-by: Ramkumar Ramachandra <artagnon@gmail.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1388388861-7931-2-git-send-email-artagnon@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 66e44a5..8cda46c 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -1,6 +1,7 @@
 #include <linux/kernel.h>
 #include "cache.h"
 #include "color.h"
+#include <math.h>
 
 int perf_use_color_default = -1;
 
@@ -298,10 +299,10 @@ const char *get_percent_color(double percent)
 	 * entries in green - and keep the low overhead places
 	 * normal:
 	 */
-	if (percent >= MIN_RED)
+	if (fabs(percent) >= MIN_RED)
 		color = PERF_COLOR_RED;
 	else {
-		if (percent > MIN_GREEN)
+		if (fabs(percent) > MIN_GREEN)
 			color = PERF_COLOR_GREEN;
 	}
 	return color;
-- 
cgit v0.10.2


From c7a730fa4624092e2d1c0cb7b750816e87c32364 Mon Sep 17 00:00:00 2001
From: Prarit Bhargava <prarit@redhat.com>
Date: Mon, 13 Jan 2014 08:40:20 -0500
Subject: x86/irq: Fix kbuild warning in smp_irq_move_cleanup_interrupt()

Fengguang Wu's 0day kernel build service reported the following build warning:

  arch/x86/kernel/apic/io_apic.c:2211
  smp_irq_move_cleanup_interrupt() warn: always true condition '(irq <= -1) => (0-u32max <= (-1))'

because irq is defined as an unsigned int instead of an int.
Fix this trivial error by redefining irq as a signed int.  The
remaining consumers of the int are okay.

Signed-off-by: Prarit Bhargava <prarit@redhat.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Link: http://lkml.kernel.org/r/1389620420-7110-1-git-send-email-prarit@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 6df0b66..a43f068 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2202,7 +2202,7 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
 
 	me = smp_processor_id();
 	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
-		unsigned int irq;
+		int irq;
 		unsigned int irr;
 		struct irq_desc *desc;
 		struct irq_cfg *cfg;
-- 
cgit v0.10.2


From 20d1c86a57762f0a33a78988e3fc8818316badd4 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 29 Nov 2013 15:40:29 +0100
Subject: sched/clock, x86: Rewrite cyc2ns() to avoid the need to disable IRQs

Use a ring-buffer like multi-version object structure which allows
always having a coherent object; we use this to avoid having to
disable IRQs while reading sched_clock() and avoids a problem when
getting an NMI while changing the cyc2ns data.

                        MAINLINE   PRE        POST

    sched_clock_stable: 1          1          1
    (cold) sched_clock: 329841     331312     257223
    (cold) local_clock: 301773     310296     309889
    (warm) sched_clock: 38375      38247      25280
    (warm) local_clock: 100371     102713     85268
    (warm) rdtsc:       27340      27289      24247
    sched_clock_stable: 0          0          0
    (cold) sched_clock: 382634     372706     301224
    (cold) local_clock: 396890     399275     399870
    (warm) sched_clock: 38194      38124      25630
    (warm) local_clock: 143452     148698     129629
    (warm) rdtsc:       27345      27365      24307

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/n/tip-s567in1e5ekq2nlyhn8f987r@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index b4c6676..3de54ef 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -13,7 +13,26 @@ extern int recalibrate_cpu_khz(void);
 
 extern int no_timer_check;
 
-DECLARE_PER_CPU(unsigned long, cyc2ns);
-DECLARE_PER_CPU(unsigned long long, cyc2ns_offset);
+/*
+ * We use the full linear equation: f(x) = a + b*x, in order to allow
+ * a continuous function in the face of dynamic freq changes.
+ *
+ * Continuity means that when our frequency changes our slope (b); we want to
+ * ensure that: f(t) == f'(t), which gives: a + b*t == a' + b'*t.
+ *
+ * Without an offset (a) the above would not be possible.
+ *
+ * See the comment near cycles_2_ns() for details on how we compute (b).
+ */
+struct cyc2ns_data {
+	u32 cyc2ns_mul;
+	u32 cyc2ns_shift;
+	u64 cyc2ns_offset;
+	u32 __count;
+	/* u32 hole */
+}; /* 24 bytes -- do not grow */
+
+extern struct cyc2ns_data *cyc2ns_read_begin(void);
+extern void cyc2ns_read_end(struct cyc2ns_data *);
 
 #endif /* _ASM_X86_TIMER_H */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8e13293..9f97bd0 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1883,6 +1883,8 @@ static struct pmu pmu = {
 
 void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 {
+	struct cyc2ns_data *data;
+
 	userpg->cap_user_time = 0;
 	userpg->cap_user_time_zero = 0;
 	userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc;
@@ -1891,13 +1893,17 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 	if (!sched_clock_stable)
 		return;
 
+	data = cyc2ns_read_begin();
+
 	userpg->cap_user_time = 1;
-	userpg->time_mult = this_cpu_read(cyc2ns);
-	userpg->time_shift = CYC2NS_SCALE_FACTOR;
-	userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
+	userpg->time_mult = data->cyc2ns_mul;
+	userpg->time_shift = data->cyc2ns_shift;
+	userpg->time_offset = data->cyc2ns_offset - now;
 
 	userpg->cap_user_time_zero = 1;
-	userpg->time_zero = this_cpu_read(cyc2ns_offset);
+	userpg->time_zero = data->cyc2ns_offset;
+
+	cyc2ns_read_end(data);
 }
 
 /*
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index b4a04ac..92b090b 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -39,7 +39,119 @@ static int __read_mostly tsc_disabled = -1;
 
 int tsc_clocksource_reliable;
 
-/* Accelerators for sched_clock()
+/*
+ * Use a ring-buffer like data structure, where a writer advances the head by
+ * writing a new data entry and a reader advances the tail when it observes a
+ * new entry.
+ *
+ * Writers are made to wait on readers until there's space to write a new
+ * entry.
+ *
+ * This means that we can always use an {offset, mul} pair to compute a ns
+ * value that is 'roughly' in the right direction, even if we're writing a new
+ * {offset, mul} pair during the clock read.
+ *
+ * The down-side is that we can no longer guarantee strict monotonicity anymore
+ * (assuming the TSC was that to begin with), because while we compute the
+ * intersection point of the two clock slopes and make sure the time is
+ * continuous at the point of switching; we can no longer guarantee a reader is
+ * strictly before or after the switch point.
+ *
+ * It does mean a reader no longer needs to disable IRQs in order to avoid
+ * CPU-Freq updates messing with his times, and similarly an NMI reader will
+ * no longer run the risk of hitting half-written state.
+ */
+
+struct cyc2ns {
+	struct cyc2ns_data data[2];	/*  0 + 2*24 = 48 */
+	struct cyc2ns_data *head;	/* 48 + 8    = 56 */
+	struct cyc2ns_data *tail;	/* 56 + 8    = 64 */
+}; /* exactly fits one cacheline */
+
+static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns);
+
+struct cyc2ns_data *cyc2ns_read_begin(void)
+{
+	struct cyc2ns_data *head;
+
+	preempt_disable();
+
+	head = this_cpu_read(cyc2ns.head);
+	/*
+	 * Ensure we observe the entry when we observe the pointer to it.
+	 * matches the wmb from cyc2ns_write_end().
+	 */
+	smp_read_barrier_depends();
+	head->__count++;
+	barrier();
+
+	return head;
+}
+
+void cyc2ns_read_end(struct cyc2ns_data *head)
+{
+	barrier();
+	/*
+	 * If we're the outer most nested read; update the tail pointer
+	 * when we're done. This notifies possible pending writers
+	 * that we've observed the head pointer and that the other
+	 * entry is now free.
+	 */
+	if (!--head->__count) {
+		/*
+		 * x86-TSO does not reorder writes with older reads;
+		 * therefore once this write becomes visible to another
+		 * cpu, we must be finished reading the cyc2ns_data.
+		 *
+		 * matches with cyc2ns_write_begin().
+		 */
+		this_cpu_write(cyc2ns.tail, head);
+	}
+	preempt_enable();
+}
+
+/*
+ * Begin writing a new @data entry for @cpu.
+ *
+ * Assumes some sort of write side lock; currently 'provided' by the assumption
+ * that cpufreq will call its notifiers sequentially.
+ */
+static struct cyc2ns_data *cyc2ns_write_begin(int cpu)
+{
+	struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu);
+	struct cyc2ns_data *data = c2n->data;
+
+	if (data == c2n->head)
+		data++;
+
+	/* XXX send an IPI to @cpu in order to guarantee a read? */
+
+	/*
+	 * When we observe the tail write from cyc2ns_read_end(),
+	 * the cpu must be done with that entry and its safe
+	 * to start writing to it.
+	 */
+	while (c2n->tail == data)
+		cpu_relax();
+
+	return data;
+}
+
+static void cyc2ns_write_end(int cpu, struct cyc2ns_data *data)
+{
+	struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu);
+
+	/*
+	 * Ensure the @data writes are visible before we publish the
+	 * entry. Matches the data-depencency in cyc2ns_read_begin().
+	 */
+	smp_wmb();
+
+	ACCESS_ONCE(c2n->head) = data;
+}
+
+/*
+ * Accelerators for sched_clock()
  * convert from cycles(64bits) => nanoseconds (64bits)
  *  basic equation:
  *              ns = cycles / (freq / ns_per_sec)
@@ -61,49 +173,106 @@ int tsc_clocksource_reliable;
  *                      -johnstul@us.ibm.com "math is hard, lets go shopping!"
  */
 
-DEFINE_PER_CPU(unsigned long, cyc2ns);
-DEFINE_PER_CPU(unsigned long long, cyc2ns_offset);
-
 #define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
 
+static void cyc2ns_data_init(struct cyc2ns_data *data)
+{
+	data->cyc2ns_mul = 1U << CYC2NS_SCALE_FACTOR;
+	data->cyc2ns_shift = CYC2NS_SCALE_FACTOR;
+	data->cyc2ns_offset = 0;
+	data->__count = 0;
+}
+
+static void cyc2ns_init(int cpu)
+{
+	struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu);
+
+	cyc2ns_data_init(&c2n->data[0]);
+	cyc2ns_data_init(&c2n->data[1]);
+
+	c2n->head = c2n->data;
+	c2n->tail = c2n->data;
+}
+
 static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 {
-	unsigned long long ns = this_cpu_read(cyc2ns_offset);
-	ns += mul_u64_u32_shr(cyc, this_cpu_read(cyc2ns), CYC2NS_SCALE_FACTOR);
+	struct cyc2ns_data *data, *tail;
+	unsigned long long ns;
+
+	/*
+	 * See cyc2ns_read_*() for details; replicated in order to avoid
+	 * an extra few instructions that came with the abstraction.
+	 * Notable, it allows us to only do the __count and tail update
+	 * dance when its actually needed.
+	 */
+
+	preempt_disable();
+	data = this_cpu_read(cyc2ns.head);
+	tail = this_cpu_read(cyc2ns.tail);
+
+	if (likely(data == tail)) {
+		ns = data->cyc2ns_offset;
+		ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR);
+	} else {
+		data->__count++;
+
+		barrier();
+
+		ns = data->cyc2ns_offset;
+		ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR);
+
+		barrier();
+
+		if (!--data->__count)
+			this_cpu_write(cyc2ns.tail, data);
+	}
+	preempt_enable();
+
 	return ns;
 }
 
+/* XXX surely we already have this someplace in the kernel?! */
+#define DIV_ROUND(n, d) (((n) + ((d) / 2)) / (d))
+
 static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
 {
-	unsigned long long tsc_now, ns_now, *offset;
-	unsigned long flags, *scale;
+	unsigned long long tsc_now, ns_now;
+	struct cyc2ns_data *data;
+	unsigned long flags;
 
 	local_irq_save(flags);
 	sched_clock_idle_sleep_event();
 
-	scale = &per_cpu(cyc2ns, cpu);
-	offset = &per_cpu(cyc2ns_offset, cpu);
+	if (!cpu_khz)
+		goto done;
+
+	data = cyc2ns_write_begin(cpu);
 
 	rdtscll(tsc_now);
 	ns_now = cycles_2_ns(tsc_now);
 
-	if (cpu_khz) {
-		*scale = ((NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR) +
-				cpu_khz / 2) / cpu_khz;
-		*offset = ns_now - mult_frac(tsc_now, *scale,
-					     (1UL << CYC2NS_SCALE_FACTOR));
-	}
+	/*
+	 * Compute a new multiplier as per the above comment and ensure our
+	 * time function is continuous; see the comment near struct
+	 * cyc2ns_data.
+	 */
+	data->cyc2ns_mul = DIV_ROUND(NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR, cpu_khz);
+	data->cyc2ns_shift = CYC2NS_SCALE_FACTOR;
+	data->cyc2ns_offset = ns_now -
+		mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR);
+
+	cyc2ns_write_end(cpu, data);
 
+done:
 	sched_clock_idle_wakeup_event(0);
 	local_irq_restore(flags);
 }
-
 /*
  * Scheduler clock - returns current time in nanosec units.
  */
 u64 native_sched_clock(void)
 {
-	u64 this_offset;
+	u64 tsc_now;
 
 	/*
 	 * Fall back to jiffies if there's no TSC available:
@@ -119,10 +288,10 @@ u64 native_sched_clock(void)
 	}
 
 	/* read the Time Stamp Counter: */
-	rdtscll(this_offset);
+	rdtscll(tsc_now);
 
 	/* return the value in ns */
-	return cycles_2_ns(this_offset);
+	return cycles_2_ns(tsc_now);
 }
 
 /* We need to define a real function for sched_clock, to override the
@@ -678,11 +847,21 @@ void tsc_restore_sched_clock_state(void)
 
 	local_irq_save(flags);
 
-	__this_cpu_write(cyc2ns_offset, 0);
+	/*
+	 * We're comming out of suspend, there's no concurrency yet; don't
+	 * bother being nice about the RCU stuff, just write to both
+	 * data fields.
+	 */
+
+	this_cpu_write(cyc2ns.data[0].cyc2ns_offset, 0);
+	this_cpu_write(cyc2ns.data[1].cyc2ns_offset, 0);
+
 	offset = cyc2ns_suspend - sched_clock();
 
-	for_each_possible_cpu(cpu)
-		per_cpu(cyc2ns_offset, cpu) = offset;
+	for_each_possible_cpu(cpu) {
+		per_cpu(cyc2ns.data[0].cyc2ns_offset, cpu) = offset;
+		per_cpu(cyc2ns.data[1].cyc2ns_offset, cpu) = offset;
+	}
 
 	local_irq_restore(flags);
 }
@@ -1005,8 +1184,10 @@ void __init tsc_init(void)
 	 * speed as the bootup CPU. (cpufreq notifiers will fix this
 	 * up if their speed diverges)
 	 */
-	for_each_possible_cpu(cpu)
+	for_each_possible_cpu(cpu) {
+		cyc2ns_init(cpu);
 		set_cyc2ns_scale(cpu_khz, cpu);
+	}
 
 	if (tsc_disabled > 0)
 		return;
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index efe4d72..dfe605a 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -433,15 +433,49 @@ static void reset_with_ipi(struct pnmask *distribution, struct bau_control *bcp)
 	return;
 }
 
-static inline unsigned long cycles_2_us(unsigned long long cyc)
+/*
+ * Not to be confused with cycles_2_ns() from tsc.c; this gives a relative
+ * number, not an absolute. It converts a duration in cycles to a duration in
+ * ns.
+ */
+static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 {
+	struct cyc2ns_data *data = cyc2ns_read_begin();
 	unsigned long long ns;
-	unsigned long us;
-	int cpu = smp_processor_id();
 
-	ns =  (cyc * per_cpu(cyc2ns, cpu)) >> CYC2NS_SCALE_FACTOR;
-	us = ns / 1000;
-	return us;
+	ns = mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift);
+
+	cyc2ns_read_end(data);
+	return ns;
+}
+
+/*
+ * The reverse of the above; converts a duration in ns to a duration in cycles.
+ */ 
+static inline unsigned long long ns_2_cycles(unsigned long long ns)
+{
+	struct cyc2ns_data *data = cyc2ns_read_begin();
+	unsigned long long cyc;
+
+	cyc = (ns << data->cyc2ns_shift) / data->cyc2ns_mul;
+
+	cyc2ns_read_end(data);
+	return cyc;
+}
+
+static inline unsigned long cycles_2_us(unsigned long long cyc)
+{
+	return cycles_2_ns(cyc) / NSEC_PER_USEC;
+}
+
+static inline cycles_t sec_2_cycles(unsigned long sec)
+{
+	return ns_2_cycles(sec * NSEC_PER_SEC);
+}
+
+static inline unsigned long long usec_2_cycles(unsigned long usec)
+{
+	return ns_2_cycles(usec * NSEC_PER_USEC);
 }
 
 /*
@@ -668,16 +702,6 @@ static int wait_completion(struct bau_desc *bau_desc,
 								bcp, try);
 }
 
-static inline cycles_t sec_2_cycles(unsigned long sec)
-{
-	unsigned long ns;
-	cycles_t cyc;
-
-	ns = sec * 1000000000;
-	cyc = (ns << CYC2NS_SCALE_FACTOR)/(per_cpu(cyc2ns, smp_processor_id()));
-	return cyc;
-}
-
 /*
  * Our retries are blocked by all destination sw ack resources being
  * in use, and a timeout is pending. In that case hardware immediately
@@ -1327,16 +1351,6 @@ static void ptc_seq_stop(struct seq_file *file, void *data)
 {
 }
 
-static inline unsigned long long usec_2_cycles(unsigned long microsec)
-{
-	unsigned long ns;
-	unsigned long long cyc;
-
-	ns = microsec * 1000;
-	cyc = (ns << CYC2NS_SCALE_FACTOR)/(per_cpu(cyc2ns, smp_processor_id()));
-	return cyc;
-}
-
 /*
  * Display the statistics thru /proc/sgi_uv/ptc_statistics
  * 'data' points to the cpu number
-- 
cgit v0.10.2


From ef08f0fff87630d4f67ceb09514d8b444df833f8 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 28 Nov 2013 19:31:23 +0100
Subject: sched/clock: Remove local_irq_disable() from the clocks

Now that x86 no longer requires IRQs disabled for sched_clock() and
ia64 never had this requirement (it doesn't seem to do cpufreq at
all), we can remove the requirement of disabling IRQs.

                        MAINLINE   PRE        POST

    sched_clock_stable: 1          1          1
    (cold) sched_clock: 329841     257223     221876
    (cold) local_clock: 301773     309889     234692
    (warm) sched_clock: 38375      25280      25602
    (warm) local_clock: 100371     85268      33265
    (warm) rdtsc:       27340      24247      24214
    sched_clock_stable: 0          0          0
    (cold) sched_clock: 382634     301224     235941
    (cold) local_clock: 396890     399870     297017
    (warm) sched_clock: 38194      25630      25233
    (warm) local_clock: 143452     129629     71234
    (warm) rdtsc:       27345      24307      24245

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/n/tip-36e5kohiasnr106d077mgubp@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c3ae144..5937154 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -26,9 +26,10 @@
  * at 0 on boot (but people really shouldn't rely on that).
  *
  * cpu_clock(i)       -- can be used from any context, including NMI.
- * sched_clock_cpu(i) -- must be used with local IRQs disabled (implied by NMI)
  * local_clock()      -- is cpu_clock() on the current cpu.
  *
+ * sched_clock_cpu(i)
+ *
  * How:
  *
  * The implementation either uses sched_clock() when
@@ -50,15 +51,6 @@
  * Furthermore, explicit sleep and wakeup hooks allow us to account for time
  * that is otherwise invisible (TSC gets stopped).
  *
- *
- * Notes:
- *
- * The !IRQ-safetly of sched_clock() and sched_clock_cpu() comes from things
- * like cpufreq interrupts that can change the base clock (TSC) multiplier
- * and cause funny jumps in time -- although the filtering provided by
- * sched_clock_cpu() should mitigate serious artifacts we cannot rely on it
- * in general since for !CONFIG_HAVE_UNSTABLE_SCHED_CLOCK we fully rely on
- * sched_clock().
  */
 #include <linux/spinlock.h>
 #include <linux/hardirq.h>
@@ -242,20 +234,20 @@ u64 sched_clock_cpu(int cpu)
 	struct sched_clock_data *scd;
 	u64 clock;
 
-	WARN_ON_ONCE(!irqs_disabled());
-
 	if (sched_clock_stable)
 		return sched_clock();
 
 	if (unlikely(!sched_clock_running))
 		return 0ull;
 
+	preempt_disable();
 	scd = cpu_sdc(cpu);
 
 	if (cpu != smp_processor_id())
 		clock = sched_clock_remote(scd);
 	else
 		clock = sched_clock_local(scd);
+	preempt_enable();
 
 	return clock;
 }
@@ -316,14 +308,7 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
  */
 u64 cpu_clock(int cpu)
 {
-	u64 clock;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	clock = sched_clock_cpu(cpu);
-	local_irq_restore(flags);
-
-	return clock;
+	return sched_clock_cpu(cpu);
 }
 
 /*
@@ -335,14 +320,7 @@ u64 cpu_clock(int cpu)
  */
 u64 local_clock(void)
 {
-	u64 clock;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	clock = sched_clock_cpu(smp_processor_id());
-	local_irq_restore(flags);
-
-	return clock;
+	return sched_clock_cpu(raw_smp_processor_id());
 }
 
 #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
-- 
cgit v0.10.2


From 35af99e646c7f7ea46dc2977601e9e71a51dadd5 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 28 Nov 2013 19:38:42 +0100
Subject: sched/clock, x86: Use a static_key for sched_clock_stable

In order to avoid the runtime condition and variable load turn
sched_clock_stable into a static_key.

Also provide a shorter implementation of local_clock() and
cpu_clock(int) when sched_clock_stable==1.

                        MAINLINE   PRE       POST

    sched_clock_stable: 1          1         1
    (cold) sched_clock: 329841     221876    215295
    (cold) local_clock: 301773     234692    220773
    (warm) sched_clock: 38375      25602     25659
    (warm) local_clock: 100371     33265     27242
    (warm) rdtsc:       27340      24214     24208
    sched_clock_stable: 0          0         0
    (cold) sched_clock: 382634     235941    237019
    (cold) local_clock: 396890     297017    294819
    (warm) sched_clock: 38194      25233     25609
    (warm) local_clock: 143452     71234     71232
    (warm) rdtsc:       27345      24245     24243

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/n/tip-eummbdechzz37mwmpags1gjr@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index bca023b..8bc79cd 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -487,7 +487,7 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
 		if (!check_tsc_unstable())
-			sched_clock_stable = 1;
+			set_sched_clock_stable();
 	}
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index ea04b34..1a439c0 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -93,7 +93,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
 		if (!check_tsc_unstable())
-			sched_clock_stable = 1;
+			set_sched_clock_stable();
 	}
 
 	/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 9f97bd0..b886451 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1890,7 +1890,7 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
 	userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc;
 	userpg->pmc_width = x86_pmu.cntval_bits;
 
-	if (!sched_clock_stable)
+	if (!sched_clock_stable())
 		return;
 
 	data = cyc2ns_read_begin();
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 92b090b..53c1235 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -822,7 +822,7 @@ static unsigned long long cyc2ns_suspend;
 
 void tsc_save_sched_clock_state(void)
 {
-	if (!sched_clock_stable)
+	if (!sched_clock_stable())
 		return;
 
 	cyc2ns_suspend = sched_clock();
@@ -842,7 +842,7 @@ void tsc_restore_sched_clock_state(void)
 	unsigned long flags;
 	int cpu;
 
-	if (!sched_clock_stable)
+	if (!sched_clock_stable())
 		return;
 
 	local_irq_save(flags);
@@ -984,7 +984,7 @@ void mark_tsc_unstable(char *reason)
 {
 	if (!tsc_unstable) {
 		tsc_unstable = 1;
-		sched_clock_stable = 0;
+		clear_sched_clock_stable();
 		disable_sched_clock_irqtime();
 		pr_info("Marking TSC unstable due to %s\n", reason);
 		/* Change only the rating, when not registered */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a196cb7..a038752 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1994,7 +1994,9 @@ static inline void sched_clock_idle_wakeup_event(u64 delta_ns)
  * but then during bootup it turns out that sched_clock()
  * is reliable after all:
  */
-extern int sched_clock_stable;
+extern int sched_clock_stable(void);
+extern void set_sched_clock_stable(void);
+extern void clear_sched_clock_stable(void);
 
 extern void sched_clock_tick(void);
 extern void sched_clock_idle_sleep_event(void);
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 5937154..c9b34c4 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -58,6 +58,7 @@
 #include <linux/percpu.h>
 #include <linux/ktime.h>
 #include <linux/sched.h>
+#include <linux/static_key.h>
 
 /*
  * Scheduler clock - returns current time in nanosec units.
@@ -74,7 +75,27 @@ EXPORT_SYMBOL_GPL(sched_clock);
 __read_mostly int sched_clock_running;
 
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-__read_mostly int sched_clock_stable;
+static struct static_key __sched_clock_stable = STATIC_KEY_INIT;
+
+int sched_clock_stable(void)
+{
+	if (static_key_false(&__sched_clock_stable))
+		return false;
+	return true;
+}
+
+void set_sched_clock_stable(void)
+{
+	if (!sched_clock_stable())
+		static_key_slow_dec(&__sched_clock_stable);
+}
+
+void clear_sched_clock_stable(void)
+{
+	/* XXX worry about clock continuity */
+	if (sched_clock_stable())
+		static_key_slow_inc(&__sched_clock_stable);
+}
 
 struct sched_clock_data {
 	u64			tick_raw;
@@ -234,7 +255,7 @@ u64 sched_clock_cpu(int cpu)
 	struct sched_clock_data *scd;
 	u64 clock;
 
-	if (sched_clock_stable)
+	if (sched_clock_stable())
 		return sched_clock();
 
 	if (unlikely(!sched_clock_running))
@@ -257,7 +278,7 @@ void sched_clock_tick(void)
 	struct sched_clock_data *scd;
 	u64 now, now_gtod;
 
-	if (sched_clock_stable)
+	if (sched_clock_stable())
 		return;
 
 	if (unlikely(!sched_clock_running))
@@ -308,7 +329,10 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
  */
 u64 cpu_clock(int cpu)
 {
-	return sched_clock_cpu(cpu);
+	if (static_key_false(&__sched_clock_stable))
+		return sched_clock_cpu(cpu);
+
+	return sched_clock();
 }
 
 /*
@@ -320,7 +344,10 @@ u64 cpu_clock(int cpu)
  */
 u64 local_clock(void)
 {
-	return sched_clock_cpu(raw_smp_processor_id());
+	if (static_key_false(&__sched_clock_stable))
+		return sched_clock_cpu(raw_smp_processor_id());
+
+	return sched_clock();
 }
 
 #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
@@ -340,12 +367,12 @@ u64 sched_clock_cpu(int cpu)
 
 u64 cpu_clock(int cpu)
 {
-	return sched_clock_cpu(cpu);
+	return sched_clock();
 }
 
 u64 local_clock(void)
 {
-	return sched_clock_cpu(0);
+	return sched_clock();
 }
 
 #endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 374fe04..dd52e7f 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -371,7 +371,7 @@ static void sched_debug_header(struct seq_file *m)
 	PN(cpu_clk);
 	P(jiffies);
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-	P(sched_clock_stable);
+	P(sched_clock_stable());
 #endif
 #undef PN
 #undef P
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index ea20f7d..c833249 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -177,7 +177,7 @@ static bool can_stop_full_tick(void)
 	 * TODO: kick full dynticks CPUs when
 	 * sched_clock_stable is set.
 	 */
-	if (!sched_clock_stable) {
+	if (!sched_clock_stable()) {
 		trace_tick_stop(0, "unstable sched clock\n");
 		/*
 		 * Don't allow the user to think they can get
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index cc2f66f..294b8a2 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2558,7 +2558,7 @@ rb_reserve_next_event(struct ring_buffer *buffer,
 		if (unlikely(test_time_stamp(delta))) {
 			int local_clock_stable = 1;
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-			local_clock_stable = sched_clock_stable;
+			local_clock_stable = sched_clock_stable();
 #endif
 			WARN_ONCE(delta > (1ULL << 59),
 				  KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n%s",
-- 
cgit v0.10.2


From 6577e42a3e1633afe762f47da9e00061ee4b9a5e Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 11 Dec 2013 18:55:53 +0100
Subject: sched/clock: Fix up clear_sched_clock_stable()

The below tells us the static_key conversion has a problem; since the
exact point of clearing that flag isn't too important, delay the flip
and use a workqueue to process it.

[ ] TSC synchronization [CPU#0 -> CPU#22]:
[ ] Measured 8 cycles TSC warp between CPUs, turning off TSC clock.
[ ]
[ ] ======================================================
[ ] [ INFO: possible circular locking dependency detected ]
[ ] 3.13.0-rc3-01745-g848b0d0322cb-dirty #637 Not tainted
[ ] -------------------------------------------------------
[ ] swapper/0/1 is trying to acquire lock:
[ ]  (jump_label_mutex){+.+...}, at: [<ffffffff8115a637>] jump_label_lock+0x17/0x20
[ ]
[ ] but task is already holding lock:
[ ]  (cpu_hotplug.lock){+.+.+.}, at: [<ffffffff8109408b>] cpu_hotplug_begin+0x2b/0x60
[ ]
[ ] which lock already depends on the new lock.
[ ]
[ ]
[ ] the existing dependency chain (in reverse order) is:
[ ]
[ ] -> #1 (cpu_hotplug.lock){+.+.+.}:
[ ]        [<ffffffff810def00>] lock_acquire+0x90/0x130
[ ]        [<ffffffff81661f83>] mutex_lock_nested+0x63/0x3e0
[ ]        [<ffffffff81093fdc>] get_online_cpus+0x3c/0x60
[ ]        [<ffffffff8104cc67>] arch_jump_label_transform+0x37/0x130
[ ]        [<ffffffff8115a3cf>] __jump_label_update+0x5f/0x80
[ ]        [<ffffffff8115a48d>] jump_label_update+0x9d/0xb0
[ ]        [<ffffffff8115aa6d>] static_key_slow_inc+0x9d/0xb0
[ ]        [<ffffffff810c0f65>] sched_feat_set+0xf5/0x100
[ ]        [<ffffffff810c5bdc>] set_numabalancing_state+0x2c/0x30
[ ]        [<ffffffff81d12f3d>] numa_policy_init+0x1af/0x1b7
[ ]        [<ffffffff81cebdf4>] start_kernel+0x35d/0x41f
[ ]        [<ffffffff81ceb5a5>] x86_64_start_reservations+0x2a/0x2c
[ ]        [<ffffffff81ceb6a2>] x86_64_start_kernel+0xfb/0xfe
[ ]
[ ] -> #0 (jump_label_mutex){+.+...}:
[ ]        [<ffffffff810de141>] __lock_acquire+0x1701/0x1eb0
[ ]        [<ffffffff810def00>] lock_acquire+0x90/0x130
[ ]        [<ffffffff81661f83>] mutex_lock_nested+0x63/0x3e0
[ ]        [<ffffffff8115a637>] jump_label_lock+0x17/0x20
[ ]        [<ffffffff8115aa3b>] static_key_slow_inc+0x6b/0xb0
[ ]        [<ffffffff810ca775>] clear_sched_clock_stable+0x15/0x20
[ ]        [<ffffffff810503b3>] mark_tsc_unstable+0x23/0x70
[ ]        [<ffffffff810772cb>] check_tsc_sync_source+0x14b/0x150
[ ]        [<ffffffff81076612>] native_cpu_up+0x3a2/0x890
[ ]        [<ffffffff810941cb>] _cpu_up+0xdb/0x160
[ ]        [<ffffffff810942c9>] cpu_up+0x79/0x90
[ ]        [<ffffffff81d0af6b>] smp_init+0x60/0x8c
[ ]        [<ffffffff81cebf42>] kernel_init_freeable+0x8c/0x197
[ ]        [<ffffffff8164e32e>] kernel_init+0xe/0x130
[ ]        [<ffffffff8166beec>] ret_from_fork+0x7c/0xb0
[ ]
[ ] other info that might help us debug this:
[ ]
[ ]  Possible unsafe locking scenario:
[ ]
[ ]        CPU0                    CPU1
[ ]        ----                    ----
[ ]   lock(cpu_hotplug.lock);
[ ]                                lock(jump_label_mutex);
[ ]                                lock(cpu_hotplug.lock);
[ ]   lock(jump_label_mutex);
[ ]
[ ]  *** DEADLOCK ***
[ ]
[ ] 2 locks held by swapper/0/1:
[ ]  #0:  (cpu_add_remove_lock){+.+.+.}, at: [<ffffffff81094037>] cpu_maps_update_begin+0x17/0x20
[ ]  #1:  (cpu_hotplug.lock){+.+.+.}, at: [<ffffffff8109408b>] cpu_hotplug_begin+0x2b/0x60
[ ]
[ ] stack backtrace:
[ ] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.13.0-rc3-01745-g848b0d0322cb-dirty #637
[ ] Hardware name: Supermicro X8DTN/X8DTN, BIOS 4.6.3 01/08/2010
[ ]  ffffffff82c9c270 ffff880236843bb8 ffffffff8165c5f5 ffffffff82c9c270
[ ]  ffff880236843bf8 ffffffff81658c02 ffff880236843c80 ffff8802368586a0
[ ]  ffff880236858678 0000000000000001 0000000000000002 ffff880236858000
[ ] Call Trace:
[ ]  [<ffffffff8165c5f5>] dump_stack+0x4e/0x7a
[ ]  [<ffffffff81658c02>] print_circular_bug+0x1f9/0x207
[ ]  [<ffffffff810de141>] __lock_acquire+0x1701/0x1eb0
[ ]  [<ffffffff816680ff>] ? __atomic_notifier_call_chain+0x8f/0xb0
[ ]  [<ffffffff810def00>] lock_acquire+0x90/0x130
[ ]  [<ffffffff8115a637>] ? jump_label_lock+0x17/0x20
[ ]  [<ffffffff8115a637>] ? jump_label_lock+0x17/0x20
[ ]  [<ffffffff81661f83>] mutex_lock_nested+0x63/0x3e0
[ ]  [<ffffffff8115a637>] ? jump_label_lock+0x17/0x20
[ ]  [<ffffffff8115a637>] jump_label_lock+0x17/0x20
[ ]  [<ffffffff8115aa3b>] static_key_slow_inc+0x6b/0xb0
[ ]  [<ffffffff810ca775>] clear_sched_clock_stable+0x15/0x20
[ ]  [<ffffffff810503b3>] mark_tsc_unstable+0x23/0x70
[ ]  [<ffffffff810772cb>] check_tsc_sync_source+0x14b/0x150
[ ]  [<ffffffff81076612>] native_cpu_up+0x3a2/0x890
[ ]  [<ffffffff810941cb>] _cpu_up+0xdb/0x160
[ ]  [<ffffffff810942c9>] cpu_up+0x79/0x90
[ ]  [<ffffffff81d0af6b>] smp_init+0x60/0x8c
[ ]  [<ffffffff81cebf42>] kernel_init_freeable+0x8c/0x197
[ ]  [<ffffffff8164e320>] ? rest_init+0xd0/0xd0
[ ]  [<ffffffff8164e32e>] kernel_init+0xe/0x130
[ ]  [<ffffffff8166beec>] ret_from_fork+0x7c/0xb0
[ ]  [<ffffffff8164e320>] ? rest_init+0xd0/0xd0
[ ] ------------[ cut here ]------------
[ ] WARNING: CPU: 0 PID: 1 at /usr/src/linux-2.6/kernel/smp.c:374 smp_call_function_many+0xad/0x300()
[ ] Modules linked in:
[ ] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.13.0-rc3-01745-g848b0d0322cb-dirty #637
[ ] Hardware name: Supermicro X8DTN/X8DTN, BIOS 4.6.3 01/08/2010
[ ]  0000000000000009 ffff880236843be0 ffffffff8165c5f5 0000000000000000
[ ]  ffff880236843c18 ffffffff81093d8c 0000000000000000 0000000000000000
[ ]  ffffffff81ccd1a0 ffffffff810ca951 0000000000000000 ffff880236843c28
[ ] Call Trace:
[ ]  [<ffffffff8165c5f5>] dump_stack+0x4e/0x7a
[ ]  [<ffffffff81093d8c>] warn_slowpath_common+0x8c/0xc0
[ ]  [<ffffffff810ca951>] ? sched_clock_tick+0x1/0xa0
[ ]  [<ffffffff81093dda>] warn_slowpath_null+0x1a/0x20
[ ]  [<ffffffff8110b72d>] smp_call_function_many+0xad/0x300
[ ]  [<ffffffff8104f200>] ? arch_unregister_cpu+0x30/0x30
[ ]  [<ffffffff8104f200>] ? arch_unregister_cpu+0x30/0x30
[ ]  [<ffffffff810ca951>] ? sched_clock_tick+0x1/0xa0
[ ]  [<ffffffff8110ba96>] smp_call_function+0x46/0x80
[ ]  [<ffffffff8104f200>] ? arch_unregister_cpu+0x30/0x30
[ ]  [<ffffffff8110bb3c>] on_each_cpu+0x3c/0xa0
[ ]  [<ffffffff810ca950>] ? sched_clock_idle_sleep_event+0x20/0x20
[ ]  [<ffffffff810ca951>] ? sched_clock_tick+0x1/0xa0
[ ]  [<ffffffff8104f964>] text_poke_bp+0x64/0xd0
[ ]  [<ffffffff810ca950>] ? sched_clock_idle_sleep_event+0x20/0x20
[ ]  [<ffffffff8104ccde>] arch_jump_label_transform+0xae/0x130
[ ]  [<ffffffff8115a3cf>] __jump_label_update+0x5f/0x80
[ ]  [<ffffffff8115a48d>] jump_label_update+0x9d/0xb0
[ ]  [<ffffffff8115aa6d>] static_key_slow_inc+0x9d/0xb0
[ ]  [<ffffffff810ca775>] clear_sched_clock_stable+0x15/0x20
[ ]  [<ffffffff810503b3>] mark_tsc_unstable+0x23/0x70
[ ]  [<ffffffff810772cb>] check_tsc_sync_source+0x14b/0x150
[ ]  [<ffffffff81076612>] native_cpu_up+0x3a2/0x890
[ ]  [<ffffffff810941cb>] _cpu_up+0xdb/0x160
[ ]  [<ffffffff810942c9>] cpu_up+0x79/0x90
[ ]  [<ffffffff81d0af6b>] smp_init+0x60/0x8c
[ ]  [<ffffffff81cebf42>] kernel_init_freeable+0x8c/0x197
[ ]  [<ffffffff8164e320>] ? rest_init+0xd0/0xd0
[ ]  [<ffffffff8164e32e>] kernel_init+0xe/0x130
[ ]  [<ffffffff8166beec>] ret_from_fork+0x7c/0xb0
[ ]  [<ffffffff8164e320>] ? rest_init+0xd0/0xd0
[ ] ---[ end trace 6ff1df5620c49d26 ]---
[ ] tsc: Marking TSC unstable due to check_tsc_sync_source failed

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-v55fgqj3nnyqnngmvuu8ep6h@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c9b34c4..6bd6a67 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -59,6 +59,7 @@
 #include <linux/ktime.h>
 #include <linux/sched.h>
 #include <linux/static_key.h>
+#include <linux/workqueue.h>
 
 /*
  * Scheduler clock - returns current time in nanosec units.
@@ -90,13 +91,23 @@ void set_sched_clock_stable(void)
 		static_key_slow_dec(&__sched_clock_stable);
 }
 
-void clear_sched_clock_stable(void)
+static void __clear_sched_clock_stable(struct work_struct *work)
 {
 	/* XXX worry about clock continuity */
 	if (sched_clock_stable())
 		static_key_slow_inc(&__sched_clock_stable);
 }
 
+static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable);
+
+void clear_sched_clock_stable(void)
+{
+	if (keventd_up())
+		schedule_work(&sched_clock_work);
+	else
+		__clear_sched_clock_stable(&sched_clock_work);
+}
+
 struct sched_clock_data {
 	u64			tick_raw;
 	u64			tick_gtod;
-- 
cgit v0.10.2


From 10b033d434c25a6c9e0f4f4dc2418af1b8236c63 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 28 Nov 2013 19:01:40 +0100
Subject: sched/clock, x86: Avoid a runtime condition in native_sched_clock()

Use a static_key to avoid touching tsc_disabled and a runtime
condition in native_sched_clock() -- less cachelines touched is always
better.

                        MAINLINE   PRE       POST

    sched_clock_stable: 1          1         1
    (cold) sched_clock: 329841     215295    213039
    (cold) local_clock: 301773     220773    216084
    (warm) sched_clock: 38375      25659     25231
    (warm) local_clock: 100371     27242     27601
    (warm) rdtsc:       27340      24208     24203
    sched_clock_stable: 0          0         0
    (cold) sched_clock: 382634     237019    240055
    (cold) local_clock: 396890     294819    299942
    (warm) sched_clock: 38194      25609     25276
    (warm) local_clock: 143452     71232     73232
    (warm) rdtsc:       27345      24243     24244

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/n/tip-hrz87bo37qke25bty6pnfy4b@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 53c1235..6377fb2 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -11,6 +11,7 @@
 #include <linux/clocksource.h>
 #include <linux/percpu.h>
 #include <linux/timex.h>
+#include <linux/static_key.h>
 
 #include <asm/hpet.h>
 #include <asm/timer.h>
@@ -37,6 +38,8 @@ static int __read_mostly tsc_unstable;
    erroneous rdtsc usage on !cpu_has_tsc processors */
 static int __read_mostly tsc_disabled = -1;
 
+static struct static_key __use_tsc = STATIC_KEY_INIT;
+
 int tsc_clocksource_reliable;
 
 /*
@@ -282,7 +285,7 @@ u64 native_sched_clock(void)
 	 *   very important for it to be as fast as the platform
 	 *   can achieve it. )
 	 */
-	if (unlikely(tsc_disabled)) {
+	if (!static_key_false(&__use_tsc)) {
 		/* No locking but a rare wrong value is not a big deal: */
 		return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ);
 	}
@@ -1193,7 +1196,9 @@ void __init tsc_init(void)
 		return;
 
 	/* now allow native_sched_clock() to use rdtsc */
+
 	tsc_disabled = 0;
+	static_key_slow_inc(&__use_tsc);
 
 	if (!no_sched_irq_time)
 		enable_sched_clock_irqtime();
-- 
cgit v0.10.2


From 01f10bc85f538cd681d0a3338b97a33f308d944b Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <artagnon@gmail.com>
Date: Mon, 30 Dec 2013 13:04:19 +0530
Subject: perf diff: Color the Delta column

Color the numbers in the Delta column using percent_color_snprintf().

Generalize the coloring function so that we can accommodate all three
comparison methods in future patches: delta, ratio, and wdiff.

Signed-off-by: Ramkumar Ramachandra <artagnon@gmail.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1388388861-7931-3-git-send-email-artagnon@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 987cac3..6c3f220 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -770,6 +770,45 @@ static int hpp__entry_baseline(struct hist_entry *he, char *buf, size_t size)
 	return ret;
 }
 
+static int __hpp__color_compare(struct perf_hpp_fmt *fmt,
+				struct perf_hpp *hpp, struct hist_entry *he,
+				int comparison_method)
+{
+	struct diff_hpp_fmt *dfmt =
+		container_of(fmt, struct diff_hpp_fmt, fmt);
+	struct hist_entry *pair = get_pair_fmt(he, dfmt);
+	double diff;
+	char pfmt[20] = " ";
+
+	if (!pair)
+		goto dummy_print;
+
+	switch (comparison_method) {
+	case COMPUTE_DELTA:
+		if (pair->diff.computed)
+			diff = pair->diff.period_ratio_delta;
+		else
+			diff = compute_delta(he, pair);
+
+		if (fabs(diff) < 0.01)
+			goto dummy_print;
+		scnprintf(pfmt, 20, "%%%+d.2f%%%%", dfmt->header_width - 1);
+		return percent_color_snprintf(hpp->buf, hpp->size,
+					pfmt, diff);
+	default:
+		BUG_ON(1);
+	}
+dummy_print:
+	return scnprintf(hpp->buf, hpp->size, "%*s",
+			dfmt->header_width, pfmt);
+}
+
+static int hpp__color_delta(struct perf_hpp_fmt *fmt,
+			struct perf_hpp *hpp, struct hist_entry *he)
+{
+	return __hpp__color_compare(fmt, hpp, he, COMPUTE_DELTA);
+}
+
 static void
 hpp__entry_unpair(struct hist_entry *he, int idx, char *buf, size_t size)
 {
@@ -941,8 +980,16 @@ static void data__hpp_register(struct data__file *d, int idx)
 	fmt->entry  = hpp__entry_global;
 
 	/* TODO more colors */
-	if (idx == PERF_HPP_DIFF__BASELINE)
+	switch (idx) {
+	case PERF_HPP_DIFF__BASELINE:
 		fmt->color = hpp__color_baseline;
+		break;
+	case PERF_HPP_DIFF__DELTA:
+		fmt->color = hpp__color_delta;
+		break;
+	default:
+		break;
+	}
 
 	init_header(d, dfmt);
 	perf_hpp__column_register(fmt);
-- 
cgit v0.10.2


From 1f513b2c1e8a2008b8ab767fdb6fa6c154591ed3 Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <artagnon@gmail.com>
Date: Mon, 30 Dec 2013 13:04:20 +0530
Subject: perf diff: Color the Ratio column

In

  $ perf diff -c ratio

color the Ratio column using value_color_snprintf(), a new function that
operates exactly like percent_color_snprintf().

At first glance, it looks like percent_color_snprintf() can be turned
into a non-variadic function simplifying things; however, 53805ec (perf
tools: Remove cast of non-variadic function to variadic, 2013-10-31)
explains why it needs to be a variadic function.

Signed-off-by: Ramkumar Ramachandra <artagnon@gmail.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1388388861-7931-4-git-send-email-artagnon@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 6c3f220..73d8bff 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -795,6 +795,17 @@ static int __hpp__color_compare(struct perf_hpp_fmt *fmt,
 		scnprintf(pfmt, 20, "%%%+d.2f%%%%", dfmt->header_width - 1);
 		return percent_color_snprintf(hpp->buf, hpp->size,
 					pfmt, diff);
+	case COMPUTE_RATIO:
+		if (he->dummy)
+			goto dummy_print;
+		if (pair->diff.computed)
+			diff = pair->diff.period_ratio;
+		else
+			diff = compute_ratio(he, pair);
+
+		scnprintf(pfmt, 20, "%%%d.6f", dfmt->header_width);
+		return value_color_snprintf(hpp->buf, hpp->size,
+					pfmt, diff);
 	default:
 		BUG_ON(1);
 	}
@@ -809,6 +820,12 @@ static int hpp__color_delta(struct perf_hpp_fmt *fmt,
 	return __hpp__color_compare(fmt, hpp, he, COMPUTE_DELTA);
 }
 
+static int hpp__color_ratio(struct perf_hpp_fmt *fmt,
+			struct perf_hpp *hpp, struct hist_entry *he)
+{
+	return __hpp__color_compare(fmt, hpp, he, COMPUTE_RATIO);
+}
+
 static void
 hpp__entry_unpair(struct hist_entry *he, int idx, char *buf, size_t size)
 {
@@ -987,6 +1004,9 @@ static void data__hpp_register(struct data__file *d, int idx)
 	case PERF_HPP_DIFF__DELTA:
 		fmt->color = hpp__color_delta;
 		break;
+	case PERF_HPP_DIFF__RATIO:
+		fmt->color = hpp__color_ratio;
+		break;
 	default:
 		break;
 	}
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 8cda46c..87b8672 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -319,15 +319,19 @@ int percent_color_fprintf(FILE *fp, const char *fmt, double percent)
 	return r;
 }
 
+int value_color_snprintf(char *bf, size_t size, const char *fmt, double value)
+{
+	const char *color = get_percent_color(value);
+	return color_snprintf(bf, size, color, fmt, value);
+}
+
 int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...)
 {
 	va_list args;
 	double percent;
-	const char *color;
 
 	va_start(args, fmt);
 	percent = va_arg(args, double);
 	va_end(args);
-	color = get_percent_color(percent);
-	return color_snprintf(bf, size, color, fmt, percent);
+	return value_color_snprintf(bf, size, fmt, percent);
 }
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index fced384..7ff30a6 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -39,6 +39,7 @@ int color_fprintf(FILE *fp, const char *color, const char *fmt, ...);
 int color_snprintf(char *bf, size_t size, const char *color, const char *fmt, ...);
 int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...);
 int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf);
+int value_color_snprintf(char *bf, size_t size, const char *fmt, double value);
 int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...);
 int percent_color_fprintf(FILE *fp, const char *fmt, double percent);
 const char *get_percent_color(double percent);
-- 
cgit v0.10.2


From a5846e215bd47f61133383822422c683600efa7a Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <artagnon@gmail.com>
Date: Mon, 30 Dec 2013 13:32:35 +0530
Subject: perf diff: Color the Weighted Diff column

In

  $ perf diff -c wdiff:M,N

color the numbers in the Weighted Diff column using color_snprintf(),
picking the colors using get_percent_color().

Signed-off-by: Ramkumar Ramachandra <artagnon@gmail.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1388390555-10808-1-git-send-email-artagnon@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 73d8bff..a77e312 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -778,6 +778,7 @@ static int __hpp__color_compare(struct perf_hpp_fmt *fmt,
 		container_of(fmt, struct diff_hpp_fmt, fmt);
 	struct hist_entry *pair = get_pair_fmt(he, dfmt);
 	double diff;
+	s64 wdiff;
 	char pfmt[20] = " ";
 
 	if (!pair)
@@ -806,6 +807,18 @@ static int __hpp__color_compare(struct perf_hpp_fmt *fmt,
 		scnprintf(pfmt, 20, "%%%d.6f", dfmt->header_width);
 		return value_color_snprintf(hpp->buf, hpp->size,
 					pfmt, diff);
+	case COMPUTE_WEIGHTED_DIFF:
+		if (he->dummy)
+			goto dummy_print;
+		if (pair->diff.computed)
+			wdiff = pair->diff.wdiff;
+		else
+			wdiff = compute_wdiff(he, pair);
+
+		scnprintf(pfmt, 20, "%%14ld", dfmt->header_width);
+		return color_snprintf(hpp->buf, hpp->size,
+				get_percent_color(wdiff),
+				pfmt, wdiff);
 	default:
 		BUG_ON(1);
 	}
@@ -826,6 +839,12 @@ static int hpp__color_ratio(struct perf_hpp_fmt *fmt,
 	return __hpp__color_compare(fmt, hpp, he, COMPUTE_RATIO);
 }
 
+static int hpp__color_wdiff(struct perf_hpp_fmt *fmt,
+			struct perf_hpp *hpp, struct hist_entry *he)
+{
+	return __hpp__color_compare(fmt, hpp, he, COMPUTE_WEIGHTED_DIFF);
+}
+
 static void
 hpp__entry_unpair(struct hist_entry *he, int idx, char *buf, size_t size)
 {
@@ -1007,6 +1026,9 @@ static void data__hpp_register(struct data__file *d, int idx)
 	case PERF_HPP_DIFF__RATIO:
 		fmt->color = hpp__color_ratio;
 		break;
+	case PERF_HPP_DIFF__WEIGHTED_DIFF:
+		fmt->color = hpp__color_wdiff;
+		break;
 	default:
 		break;
 	}
-- 
cgit v0.10.2


From 075dfd82102d2048e43e1cbf48d558d915c50072 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Mon, 13 Jan 2014 13:35:16 +0100
Subject: s390/compat: fix PSW32_USER_BITS definition

PSW32_USER_BITS should define the primary address space for user space
instead of the home address space.
Symptom of this bug is that gdb doesn't work in compat mode.

The bug was introduced with e258d719ff28 "s390/uaccess: always run the kernel
in home space" and f26946d7ecad "s390/compat: make psw32_user_bits a constant
value again".

Cc: stable@vger.kernel.org # v3.13+
Reported-by: Andreas Arnez <arnez@linux.vnet.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 4bf9da0..5d7e8cf 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -38,7 +38,8 @@
 
 #define PSW32_USER_BITS (PSW32_MASK_DAT | PSW32_MASK_IO | PSW32_MASK_EXT | \
 			 PSW32_DEFAULT_KEY | PSW32_MASK_BASE | \
-			 PSW32_MASK_MCHECK | PSW32_MASK_PSTATE | PSW32_ASC_HOME)
+			 PSW32_MASK_MCHECK | PSW32_MASK_PSTATE | \
+			 PSW32_ASC_PRIMARY)
 
 #define COMPAT_USER_HZ		100
 #define COMPAT_UTS_MACHINE	"s390\0\0\0\0"
-- 
cgit v0.10.2


From 28aa39b853fc889e672b73f69ce591d15e6306b0 Mon Sep 17 00:00:00 2001
From: Paul Gortmaker <paul.gortmaker@windriver.com>
Date: Mon, 13 Jan 2014 16:02:28 +0100
Subject: s390: delete new instances of __cpuinit usage

The patch "s390/perf: add support for the CPU-Measurement Sampling
Facility" added a new instance of the __cpuinit macro usage.

We removed this a couple versions ago; we now want to remove
the compat no-op stubs.  Introducing new users is not what
we want to see at this point in time, as it will break once
the stubs are gone.

Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 3c3bc8d..6c0d298 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1512,8 +1512,8 @@ static void cpumf_measurement_alert(struct ext_code ext_code,
 	}
 }
 
-static int __cpuinit cpumf_pmu_notifier(struct notifier_block *self,
-					unsigned long action, void *hcpu)
+static int cpumf_pmu_notifier(struct notifier_block *self,
+			      unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (long) hcpu;
 	int flags;
-- 
cgit v0.10.2


From 0bd3a173d711857fc9f583eb5825386cc08f3948 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 19 Nov 2013 16:13:38 +0100
Subject: sched/preempt, locking: Rework local_bh_{dis,en}able()

Currently local_bh_disable() is out-of-line for no apparent reason.
So inline it to save a few cycles on call/return nonsense, the
function body is a single add on x86 (a few loads and store extra on
load/store archs).

Also expose two new local_bh functions:

  __local_bh_{dis,en}able_ip(unsigned long ip, unsigned int cnt);

Which implement the actual local_bh_{dis,en}able() behaviour.

The next patch uses the exposed @cnt argument to optimize bh lock
functions.

With build fixes from Jacob Pan.

Cc: rjw@rjwysocki.net
Cc: rui.zhang@intel.com
Cc: jacob.jun.pan@linux.intel.com
Cc: Mike Galbraith <bitbucket@online.de>
Cc: hpa@zytor.com
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: lenb@kernel.org
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20131119151338.GF3694@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h
index 27b1bcf..86c12c9 100644
--- a/include/linux/bottom_half.h
+++ b/include/linux/bottom_half.h
@@ -1,9 +1,35 @@
 #ifndef _LINUX_BH_H
 #define _LINUX_BH_H
 
-extern void local_bh_disable(void);
+#include <linux/preempt.h>
+#include <linux/preempt_mask.h>
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt);
+#else
+static __always_inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
+{
+	preempt_count_add(cnt);
+	barrier();
+}
+#endif
+
+static inline void local_bh_disable(void)
+{
+	__local_bh_disable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET);
+}
+
 extern void _local_bh_enable(void);
-extern void local_bh_enable(void);
-extern void local_bh_enable_ip(unsigned long ip);
+extern void __local_bh_enable_ip(unsigned long ip, unsigned int cnt);
+
+static inline void local_bh_enable_ip(unsigned long ip)
+{
+	__local_bh_enable_ip(ip, SOFTIRQ_DISABLE_OFFSET);
+}
+
+static inline void local_bh_enable(void)
+{
+	__local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET);
+}
 
 #endif /* _LINUX_BH_H */
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index d9cf963..12d5f97 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -5,6 +5,7 @@
 #include <linux/lockdep.h>
 #include <linux/ftrace_irq.h>
 #include <linux/vtime.h>
+#include <asm/hardirq.h>
 
 
 extern void synchronize_irq(unsigned int irq);
diff --git a/include/linux/preempt_mask.h b/include/linux/preempt_mask.h
index b8d96bc..dbeec4d 100644
--- a/include/linux/preempt_mask.h
+++ b/include/linux/preempt_mask.h
@@ -2,7 +2,6 @@
 #define LINUX_PREEMPT_MASK_H
 
 #include <linux/preempt.h>
-#include <asm/hardirq.h>
 
 /*
  * We put the hardirq and softirq counter into the preemption
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 7500cce1..9e368ef 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -89,7 +89,7 @@ static void wakeup_softirqd(void)
  * where hardirqs are disabled legitimately:
  */
 #ifdef CONFIG_TRACE_IRQFLAGS
-static void __local_bh_disable(unsigned long ip, unsigned int cnt)
+void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
 {
 	unsigned long flags;
 
@@ -114,21 +114,9 @@ static void __local_bh_disable(unsigned long ip, unsigned int cnt)
 	if (preempt_count() == cnt)
 		trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
 }
-#else /* !CONFIG_TRACE_IRQFLAGS */
-static inline void __local_bh_disable(unsigned long ip, unsigned int cnt)
-{
-	preempt_count_add(cnt);
-	barrier();
-}
+EXPORT_SYMBOL(__local_bh_disable_ip);
 #endif /* CONFIG_TRACE_IRQFLAGS */
 
-void local_bh_disable(void)
-{
-	__local_bh_disable(_RET_IP_, SOFTIRQ_DISABLE_OFFSET);
-}
-
-EXPORT_SYMBOL(local_bh_disable);
-
 static void __local_bh_enable(unsigned int cnt)
 {
 	WARN_ON_ONCE(!irqs_disabled());
@@ -151,7 +139,7 @@ void _local_bh_enable(void)
 
 EXPORT_SYMBOL(_local_bh_enable);
 
-static inline void _local_bh_enable_ip(unsigned long ip)
+void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
 {
 	WARN_ON_ONCE(in_irq() || irqs_disabled());
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -166,7 +154,7 @@ static inline void _local_bh_enable_ip(unsigned long ip)
 	 * Keep preemption disabled until we are done with
 	 * softirq processing:
  	 */
-	preempt_count_sub(SOFTIRQ_DISABLE_OFFSET - 1);
+	preempt_count_sub(cnt - 1);
 
 	if (unlikely(!in_interrupt() && local_softirq_pending())) {
 		/*
@@ -182,18 +170,7 @@ static inline void _local_bh_enable_ip(unsigned long ip)
 #endif
 	preempt_check_resched();
 }
-
-void local_bh_enable(void)
-{
-	_local_bh_enable_ip(_RET_IP_);
-}
-EXPORT_SYMBOL(local_bh_enable);
-
-void local_bh_enable_ip(unsigned long ip)
-{
-	_local_bh_enable_ip(ip);
-}
-EXPORT_SYMBOL(local_bh_enable_ip);
+EXPORT_SYMBOL(__local_bh_enable_ip);
 
 /*
  * We restart softirq processing for at most MAX_SOFTIRQ_RESTART times,
@@ -230,7 +207,7 @@ asmlinkage void __do_softirq(void)
 	pending = local_softirq_pending();
 	account_irq_enter_time(current);
 
-	__local_bh_disable(_RET_IP_, SOFTIRQ_OFFSET);
+	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
 	lockdep_softirq_enter();
 
 	cpu = smp_processor_id();
-- 
cgit v0.10.2


From 8cb75e0c4ec9786b81439761eac1d18d4a931af3 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 20 Nov 2013 12:22:37 +0100
Subject: sched/preempt: Fix up missed PREEMPT_NEED_RESCHED folding

With various drivers wanting to inject idle time; we get people
calling idle routines outside of the idle loop proper.

Therefore we need to be extra careful about not missing
TIF_NEED_RESCHED -> PREEMPT_NEED_RESCHED propagations.

While looking at this, I also realized there's a small window in the
existing idle loop where we can miss TIF_NEED_RESCHED; when it hits
right after the tif_need_resched() test at the end of the loop but
right before the need_resched() test at the start of the loop.

So move preempt_fold_need_resched() out of the loop where we're
guaranteed to have TIF_NEED_RESCHED set.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-x9jgh45oeayzajz2mjt0y7d6@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 19b71c4..1da25a5 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -53,7 +53,7 @@ static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
 		if (!need_resched())
 			__mwait(eax, ecx);
 	}
-	__current_clr_polling();
+	current_clr_polling();
 }
 
 #endif /* _ASM_X86_MWAIT_H */
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index dd9ddf8..59749fc 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -134,6 +134,21 @@ do { \
 #undef preempt_check_resched
 #endif
 
+#ifdef CONFIG_PREEMPT
+#define preempt_set_need_resched() \
+do { \
+	set_preempt_need_resched(); \
+} while (0)
+#define preempt_fold_need_resched() \
+do { \
+	if (tif_need_resched()) \
+		set_preempt_need_resched(); \
+} while (0)
+#else
+#define preempt_set_need_resched() do { } while (0)
+#define preempt_fold_need_resched() do { } while (0)
+#endif
+
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 
 struct preempt_notifier;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a038752..ffccdad 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2745,6 +2745,21 @@ static inline bool __must_check current_clr_polling_and_test(void)
 }
 #endif
 
+static inline void current_clr_polling(void)
+{
+	__current_clr_polling();
+
+	/*
+	 * Ensure we check TIF_NEED_RESCHED after we clear the polling bit.
+	 * Once the bit is cleared, we'll get IPIs with every new
+	 * TIF_NEED_RESCHED and the IPI handler, scheduler_ipi(), will also
+	 * fold.
+	 */
+	smp_mb(); /* paired with resched_task() */
+
+	preempt_fold_need_resched();
+}
+
 static __always_inline bool need_resched(void)
 {
 	return unlikely(tif_need_resched());
diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c
index 988573a..277f494 100644
--- a/kernel/cpu/idle.c
+++ b/kernel/cpu/idle.c
@@ -105,14 +105,17 @@ static void cpu_idle_loop(void)
 				__current_set_polling();
 			}
 			arch_cpu_idle_exit();
-			/*
-			 * We need to test and propagate the TIF_NEED_RESCHED
-			 * bit here because we might not have send the
-			 * reschedule IPI to idle tasks.
-			 */
-			if (tif_need_resched())
-				set_preempt_need_resched();
 		}
+
+		/*
+		 * Since we fell out of the loop above, we know
+		 * TIF_NEED_RESCHED must be set, propagate it into
+		 * PREEMPT_NEED_RESCHED.
+		 *
+		 * This is required because for polling idle loops we will
+		 * not have had an IPI to fold the state for us.
+		 */
+		preempt_set_need_resched();
 		tick_nohz_idle_exit();
 		schedule_preempt_disabled();
 	}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 392c6f8..0326c06 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1510,8 +1510,7 @@ void scheduler_ipi(void)
 	 * TIF_NEED_RESCHED remotely (for the first time) will also send
 	 * this IPI.
 	 */
-	if (tif_need_resched())
-		set_preempt_need_resched();
+	preempt_fold_need_resched();
 
 	if (llist_empty(&this_rq()->wake_list)
 			&& !tick_nohz_full_cpu(smp_processor_id())
-- 
cgit v0.10.2


From 1774e9f3e5c8b38de3b3bc8bd0eacd280f655baf Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 19 Nov 2013 16:13:38 +0100
Subject: sched, net: Clean up preempt_enable_no_resched() abuse

The only valid use of preempt_enable_no_resched() is if the very next
line is schedule() or if we know preemption cannot actually be enabled
by that statement due to known more preempt_count 'refs'.

Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: rjw@rjwysocki.net
Cc: Eliezer Tamir <eliezer.tamir@linux.intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: rui.zhang@intel.com
Cc: jacob.jun.pan@linux.intel.com
Cc: Mike Galbraith <bitbucket@online.de>
Cc: hpa@zytor.com
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: lenb@kernel.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20131119151338.GF3694@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c4638e6..82de786 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1623,11 +1623,11 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		    (len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) &&
 		    !sysctl_tcp_low_latency &&
 		    net_dma_find_channel()) {
-			preempt_enable_no_resched();
+			preempt_enable();
 			tp->ucopy.pinned_list =
 					dma_pin_iovec_pages(msg->msg_iov, len);
 		} else {
-			preempt_enable_no_resched();
+			preempt_enable();
 		}
 	}
 #endif
-- 
cgit v0.10.2


From 37089834528be3ef8cbf927e47c753b3e272a856 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 19 Nov 2013 16:13:38 +0100
Subject: sched, net: Fixup busy_loop_us_clock()

The only valid use of preempt_enable_no_resched() is if the very next
line is schedule() or if we know preemption cannot actually be enabled
by that statement due to known more preempt_count 'refs'.

This busy_poll stuff looks to be completely and utterly broken,
sched_clock() can return utter garbage with interrupts enabled (rare
but still) and it can drift unbounded between CPUs.

This means that if you get preempted/migrated and your new CPU is
years behind on the previous CPU we get to busy spin for a _very_ long
time.

There is a _REASON_ sched_clock() warns about preemptability -
papering over it with a preempt_disable()/preempt_enable_no_resched()
is just terminal brain damage on so many levels.

Replace sched_clock() usage with local_clock() which has a bounded
drift between CPUs (<2 jiffies).

There is a further problem with the entire busy wait poll thing in
that the spin time is additive to the syscall timeout, not inclusive.

Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: rui.zhang@intel.com
Cc: jacob.jun.pan@linux.intel.com
Cc: Mike Galbraith <bitbucket@online.de>
Cc: hpa@zytor.com
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: lenb@kernel.org
Cc: rjw@rjwysocki.net
Cc: Eliezer Tamir <eliezer.tamir@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20131119151338.GF3694@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 829627d..1d67fb6 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -42,27 +42,10 @@ static inline bool net_busy_loop_on(void)
 	return sysctl_net_busy_poll;
 }
 
-/* a wrapper to make debug_smp_processor_id() happy
- * we can use sched_clock() because we don't care much about precision
- * we only care that the average is bounded
- */
-#ifdef CONFIG_DEBUG_PREEMPT
-static inline u64 busy_loop_us_clock(void)
-{
-	u64 rc;
-
-	preempt_disable_notrace();
-	rc = sched_clock();
-	preempt_enable_no_resched_notrace();
-
-	return rc >> 10;
-}
-#else /* CONFIG_DEBUG_PREEMPT */
 static inline u64 busy_loop_us_clock(void)
 {
-	return sched_clock() >> 10;
+	return local_clock() >> 10;
 }
-#endif /* CONFIG_DEBUG_PREEMPT */
 
 static inline unsigned long sk_busy_loop_end_time(struct sock *sk)
 {
-- 
cgit v0.10.2


From 130816ce4d5f69167324f7272e70aa3d641677c6 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 11 Dec 2013 12:21:17 +0100
Subject: sched, thermal: Clean up preempt_enable_no_resched() abuse

The only valid use of preempt_enable_no_resched() is if the very next
line is schedule() or if we know preemption cannot actually be enabled
by that statement due to known more preempt_count 'refs'.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: rjw@rjwysocki.net
Cc: Eliezer Tamir <eliezer.tamir@linux.intel.com>
Cc: rui.zhang@intel.com
Cc: jacob.jun.pan@linux.intel.com
Cc: Mike Galbraith <bitbucket@online.de>
Cc: hpa@zytor.com
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: lenb@kernel.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/n/tip-zcfvacdlvlr63qmnn5i58vuj@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c
index e8275f2..d833c8f 100644
--- a/drivers/thermal/intel_powerclamp.c
+++ b/drivers/thermal/intel_powerclamp.c
@@ -443,7 +443,7 @@ static int clamp_thread(void *arg)
 			atomic_inc(&idle_wakeup_counter);
 		}
 		tick_nohz_idle_exit();
-		preempt_enable_no_resched();
+		preempt_enable();
 	}
 	del_timer_sync(&wakeup_timer);
 	clear_bit(cpunr, cpu_clamping_mask);
-- 
cgit v0.10.2


From 1d027ee9b80c30e83769ef306ccfafe483dd1672 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 13 Jan 2014 15:15:25 -0300
Subject: perf probe: Fix build when DWARF support libraries not present
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On a freshly installed system, after libelf-dev is installed we get:

    CC       /tmp/build/perf/util/probe-event.o
  util/probe-event.c: In function ‘try_to_find_probe_trace_events’:
  util/probe-event.c:753:46: error: unused parameter ‘target’ [-Werror=unused-parameter]
       int max_tevs __maybe_unused, const char *target)
                                                ^
    CC       /tmp/build/perf/util/cgroup.o
  util/probe-event.c: At top level:
  util/probe-event.c:193:12: error: ‘get_text_start_address’ defined but not used [-Werror=unused-function]
   static int get_text_start_address(const char *exec, unsigned long *address)
            ^
  cc1: all warnings being treated as errors
  make[1]: *** [/tmp/build/perf/util/probe-event.o] Error 1
  make[1]: *** Waiting for unfinished jobs....
  make: *** [install] Error 2

Fix it by enclosing functions only used when those libraries are installed
under the suitable preprocessor define and using __maybe_unused to a function
that is only built when DWARF support is disabled.

Problem introduced in this changeset:

  commit fb7345bbf7fad9bf72ef63a19c707970b9685812
  Author: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
  Date:   Thu Dec 26 05:41:53 2013 +0000

      perf probe: Support basic dwarf-based operations on uprobe events

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-73kc2fopt81517hrdgdra18o@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 86ed858..a4ee6b4 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -172,6 +172,7 @@ const char *kernel_get_module_path(const char *module)
 	return (dso) ? dso->long_name : NULL;
 }
 
+#ifdef HAVE_DWARF_SUPPORT
 /* Copied from unwind.c */
 static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
 				    GElf_Shdr *shp, const char *name)
@@ -217,6 +218,7 @@ out:
 	elf_end(elf);
 	return ret;
 }
+#endif
 
 static int init_user_exec(void)
 {
@@ -750,7 +752,8 @@ static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
 
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 				struct probe_trace_event **tevs __maybe_unused,
-				int max_tevs __maybe_unused, const char *target)
+				int max_tevs __maybe_unused,
+				const char *target __maybe_unused)
 {
 	if (perf_probe_event_need_dwarf(pev)) {
 		pr_warning("Debuginfo-analysis is not supported.\n");
-- 
cgit v0.10.2


From 5aa3d718f259007121b9366d36315fb8a2983d3d Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Wed, 4 Dec 2013 20:50:42 +0100
Subject: x86, ramdisk: Export relocated ramdisk VA

The ramdisk can possibly get relocated if the whole image is not mapped.
And since we're going over it in the microcode loader and fishing out
the relevant microcode patches, we want access it at its new location.
Thus, export it.

Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>

diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 59bcf4e..d62c9f8 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -3,7 +3,6 @@
 
 #include <uapi/asm/setup.h>
 
-
 #define COMMAND_LINE_SIZE 2048
 
 #include <linux/linkage.h>
@@ -29,6 +28,8 @@
 #include <asm/bootparam.h>
 #include <asm/x86_init.h>
 
+extern u64 relocated_ramdisk;
+
 /* Interrupt control for vSMPowered x86_64 systems */
 #ifdef CONFIG_X86_64
 void vsmp_init(void);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index cb233bc..baefc6d 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -295,6 +295,8 @@ static void __init reserve_brk(void)
 	_brk_start = 0;
 }
 
+u64 relocated_ramdisk;
+
 #ifdef CONFIG_BLK_DEV_INITRD
 
 static u64 __init get_ramdisk_image(void)
@@ -321,25 +323,24 @@ static void __init relocate_initrd(void)
 	u64 ramdisk_image = get_ramdisk_image();
 	u64 ramdisk_size  = get_ramdisk_size();
 	u64 area_size     = PAGE_ALIGN(ramdisk_size);
-	u64 ramdisk_here;
 	unsigned long slop, clen, mapaddr;
 	char *p, *q;
 
 	/* We need to move the initrd down into directly mapped mem */
-	ramdisk_here = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
-						 area_size, PAGE_SIZE);
+	relocated_ramdisk = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
+						   area_size, PAGE_SIZE);
 
-	if (!ramdisk_here)
+	if (!relocated_ramdisk)
 		panic("Cannot find place for new RAMDISK of size %lld\n",
-			 ramdisk_size);
+		      ramdisk_size);
 
 	/* Note: this includes all the mem currently occupied by
 	   the initrd, we rely on that fact to keep the data intact. */
-	memblock_reserve(ramdisk_here, area_size);
-	initrd_start = ramdisk_here + PAGE_OFFSET;
+	memblock_reserve(relocated_ramdisk, area_size);
+	initrd_start = relocated_ramdisk + PAGE_OFFSET;
 	initrd_end   = initrd_start + ramdisk_size;
 	printk(KERN_INFO "Allocated new RAMDISK: [mem %#010llx-%#010llx]\n",
-			 ramdisk_here, ramdisk_here + ramdisk_size - 1);
+	       relocated_ramdisk, relocated_ramdisk + ramdisk_size - 1);
 
 	q = (char *)initrd_start;
 
@@ -363,7 +364,7 @@ static void __init relocate_initrd(void)
 	printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to"
 		" [mem %#010llx-%#010llx]\n",
 		ramdisk_image, ramdisk_image + ramdisk_size - 1,
-		ramdisk_here, ramdisk_here + ramdisk_size - 1);
+		relocated_ramdisk, relocated_ramdisk + ramdisk_size - 1);
 }
 
 static void __init early_reserve_initrd(void)
-- 
cgit v0.10.2


From e1b43e3f13f7157249fb962ccf88b84eb0421fb4 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Wed, 4 Dec 2013 12:31:31 +0100
Subject: x86, microcode: Share native MSR accessing variants

We want to use those in AMD's early loading path too. Also, add a
native_wrmsrl variant.

Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>

diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index f98bd66..b59827e 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -1,6 +1,21 @@
 #ifndef _ASM_X86_MICROCODE_H
 #define _ASM_X86_MICROCODE_H
 
+#define native_rdmsr(msr, val1, val2)			\
+do {							\
+	u64 __val = native_read_msr((msr));		\
+	(void)((val1) = (u32)__val);			\
+	(void)((val2) = (u32)(__val >> 32));		\
+} while (0)
+
+#define native_wrmsr(msr, low, high)			\
+	native_write_msr(msr, low, high)
+
+#define native_wrmsrl(msr, val)				\
+	native_write_msr((msr),				\
+			 (u32)((u64)(val)),		\
+			 (u32)((u64)(val) >> 32))
+
 struct cpu_signature {
 	unsigned int sig;
 	unsigned int pf;
diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c
index 1575deb..18f7391 100644
--- a/arch/x86/kernel/microcode_intel_early.c
+++ b/arch/x86/kernel/microcode_intel_early.c
@@ -365,16 +365,6 @@ out:
 	return state;
 }
 
-#define native_rdmsr(msr, val1, val2)		\
-do {						\
-	u64 __val = native_read_msr((msr));	\
-	(void)((val1) = (u32)__val);		\
-	(void)((val2) = (u32)(__val >> 32));	\
-} while (0)
-
-#define native_wrmsr(msr, low, high)		\
-	native_write_msr(msr, low, high);
-
 static int collect_cpu_info_early(struct ucode_cpu_info *uci)
 {
 	unsigned int val[2];
-- 
cgit v0.10.2


From 5335ba5cf475369f88db8e6835764efdcad8ab96 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Fri, 29 Nov 2013 14:58:44 +0100
Subject: x86, microcode, AMD: Fix early ucode loading

The original idea to use the microcode cache for the APs doesn't pan out
because we do memory allocation there very early and with IRQs disabled
and we don't want to involve GFP_ATOMIC allocations. Not if it can be
helped.

Thus, extend the caching of the BSP patch approach to the APs and
iterate over the ucode in the initrd instead of using the cache. We
still save the relevant patches to it but later, right before we
jettison the initrd.

While at it, fix early ucode loading on 32-bit too.

Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>

diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index 4c01917..b7b10b8 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -61,11 +61,10 @@ extern int __apply_microcode_amd(struct microcode_amd *mc_amd);
 extern int apply_microcode_amd(int cpu);
 extern enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size);
 
+#define PATCH_MAX_SIZE PAGE_SIZE
+extern u8 amd_ucode_patch[PATCH_MAX_SIZE];
+
 #ifdef CONFIG_MICROCODE_AMD_EARLY
-#ifdef CONFIG_X86_32
-#define MPB_MAX_SIZE PAGE_SIZE
-extern u8 amd_bsp_mpb[MPB_MAX_SIZE];
-#endif
 extern void __init load_ucode_amd_bsp(void);
 extern void load_ucode_amd_ap(void);
 extern int __init save_microcode_in_initrd_amd(void);
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index c3d4cc9..4a6ff74 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -182,10 +182,10 @@ int __apply_microcode_amd(struct microcode_amd *mc_amd)
 {
 	u32 rev, dummy;
 
-	wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code);
+	native_wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code);
 
 	/* verify patch application was successful */
-	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
+	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
 	if (rev != mc_amd->hdr.patch_id)
 		return -1;
 
@@ -332,6 +332,9 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover)
 	patch->patch_id  = mc_hdr->patch_id;
 	patch->equiv_cpu = proc_id;
 
+	pr_debug("%s: Added patch_id: 0x%08x, proc_id: 0x%04x\n",
+		 __func__, patch->patch_id, proc_id);
+
 	/* ... and add to cache. */
 	update_cache(patch);
 
@@ -390,9 +393,9 @@ enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size)
 	if (cpu_data(smp_processor_id()).cpu_index == boot_cpu_data.cpu_index) {
 		struct ucode_patch *p = find_patch(smp_processor_id());
 		if (p) {
-			memset(amd_bsp_mpb, 0, MPB_MAX_SIZE);
-			memcpy(amd_bsp_mpb, p->data, min_t(u32, ksize(p->data),
-							   MPB_MAX_SIZE));
+			memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
+			memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data),
+							       PATCH_MAX_SIZE));
 		}
 	}
 #endif
diff --git a/arch/x86/kernel/microcode_amd_early.c b/arch/x86/kernel/microcode_amd_early.c
index 6073104..8384c0f 100644
--- a/arch/x86/kernel/microcode_amd_early.c
+++ b/arch/x86/kernel/microcode_amd_early.c
@@ -2,6 +2,7 @@
  * Copyright (C) 2013 Advanced Micro Devices, Inc.
  *
  * Author: Jacob Shin <jacob.shin@amd.com>
+ * Fixes: Borislav Petkov <bp@suse.de>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -15,10 +16,18 @@
 #include <asm/setup.h>
 #include <asm/microcode_amd.h>
 
-static bool ucode_loaded;
+/*
+ * This points to the current valid container of microcode patches which we will
+ * save from the initrd before jettisoning its contents.
+ */
+static u8 *container;
+static size_t container_size;
+
 static u32 ucode_new_rev;
-static unsigned long ucode_offset;
-static size_t ucode_size;
+u8 amd_ucode_patch[PATCH_MAX_SIZE];
+static u16 this_equiv_id;
+
+struct cpio_data ucode_cpio;
 
 /*
  * Microcode patch container file is prepended to the initrd in cpio format.
@@ -32,9 +41,6 @@ static struct cpio_data __init find_ucode_in_initrd(void)
 	char *path;
 	void *start;
 	size_t size;
-	unsigned long *uoffset;
-	size_t *usize;
-	struct cpio_data cd;
 
 #ifdef CONFIG_X86_32
 	struct boot_params *p;
@@ -47,30 +53,50 @@ static struct cpio_data __init find_ucode_in_initrd(void)
 	path    = (char *)__pa_nodebug(ucode_path);
 	start   = (void *)p->hdr.ramdisk_image;
 	size    = p->hdr.ramdisk_size;
-	uoffset = (unsigned long *)__pa_nodebug(&ucode_offset);
-	usize   = (size_t *)__pa_nodebug(&ucode_size);
 #else
 	path    = ucode_path;
 	start   = (void *)(boot_params.hdr.ramdisk_image + PAGE_OFFSET);
 	size    = boot_params.hdr.ramdisk_size;
-	uoffset = &ucode_offset;
-	usize   = &ucode_size;
 #endif
 
-	cd = find_cpio_data(path, start, size, &offset);
-	if (!cd.data)
-		return cd;
+	return find_cpio_data(path, start, size, &offset);
+}
 
-	if (*(u32 *)cd.data != UCODE_MAGIC) {
-		cd.data = NULL;
-		cd.size = 0;
-		return cd;
-	}
+static size_t compute_container_size(u8 *data, u32 total_size)
+{
+	size_t size = 0;
+	u32 *header = (u32 *)data;
 
-	*uoffset = (u8 *)cd.data - (u8 *)start;
-	*usize   = cd.size;
+	if (header[0] != UCODE_MAGIC ||
+	    header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */
+	    header[2] == 0)                            /* size */
+		return size;
 
-	return cd;
+	size = header[2] + CONTAINER_HDR_SZ;
+	total_size -= size;
+	data += size;
+
+	while (total_size) {
+		u16 patch_size;
+
+		header = (u32 *)data;
+
+		if (header[0] != UCODE_UCODE_TYPE)
+			break;
+
+		/*
+		 * Sanity-check patch size.
+		 */
+		patch_size = header[1];
+		if (patch_size > PATCH_MAX_SIZE)
+			break;
+
+		size	   += patch_size + SECTION_HDR_SIZE;
+		data	   += patch_size + SECTION_HDR_SIZE;
+		total_size -= patch_size + SECTION_HDR_SIZE;
+	}
+
+	return size;
 }
 
 /*
@@ -85,23 +111,22 @@ static struct cpio_data __init find_ucode_in_initrd(void)
 static void apply_ucode_in_initrd(void *ucode, size_t size)
 {
 	struct equiv_cpu_entry *eq;
+	size_t *cont_sz;
 	u32 *header;
-	u8  *data;
+	u8  *data, **cont;
 	u16 eq_id = 0;
 	int offset, left;
-	u32 rev, eax;
+	u32 rev, eax, ebx, ecx, edx;
 	u32 *new_rev;
-	unsigned long *uoffset;
-	size_t *usize;
 
 #ifdef CONFIG_X86_32
 	new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
-	uoffset = (unsigned long *)__pa_nodebug(&ucode_offset);
-	usize   = (size_t *)__pa_nodebug(&ucode_size);
+	cont_sz = (size_t *)__pa_nodebug(&container_size);
+	cont	= (u8 **)__pa_nodebug(&container);
 #else
 	new_rev = &ucode_new_rev;
-	uoffset = &ucode_offset;
-	usize   = &ucode_size;
+	cont_sz = &container_size;
+	cont	= &container;
 #endif
 
 	data   = ucode;
@@ -109,23 +134,37 @@ static void apply_ucode_in_initrd(void *ucode, size_t size)
 	header = (u32 *)data;
 
 	/* find equiv cpu table */
-
-	if (header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */
+	if (header[0] != UCODE_MAGIC ||
+	    header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */
 	    header[2] == 0)                            /* size */
 		return;
 
-	eax = cpuid_eax(0x00000001);
+	eax = 0x00000001;
+	ecx = 0;
+	native_cpuid(&eax, &ebx, &ecx, &edx);
 
 	while (left > 0) {
 		eq = (struct equiv_cpu_entry *)(data + CONTAINER_HDR_SZ);
 
+		*cont = data;
+
+		/* Advance past the container header */
 		offset = header[2] + CONTAINER_HDR_SZ;
 		data  += offset;
 		left  -= offset;
 
 		eq_id = find_equiv_id(eq, eax);
-		if (eq_id)
+		if (eq_id) {
+			this_equiv_id = eq_id;
+			*cont_sz = compute_container_size(*cont, left + offset);
+
+			/*
+			 * truncate how much we need to iterate over in the
+			 * ucode update loop below
+			 */
+			left = *cont_sz - offset;
 			break;
+		}
 
 		/*
 		 * support multiple container files appended together. if this
@@ -145,19 +184,18 @@ static void apply_ucode_in_initrd(void *ucode, size_t size)
 
 		/* mark where the next microcode container file starts */
 		offset    = data - (u8 *)ucode;
-		*uoffset += offset;
-		*usize   -= offset;
 		ucode     = data;
 	}
 
 	if (!eq_id) {
-		*usize = 0;
+		*cont = NULL;
+		*cont_sz = 0;
 		return;
 	}
 
 	/* find ucode and update if needed */
 
-	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax);
+	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax);
 
 	while (left > 0) {
 		struct microcode_amd *mc;
@@ -168,73 +206,83 @@ static void apply_ucode_in_initrd(void *ucode, size_t size)
 			break;
 
 		mc = (struct microcode_amd *)(data + SECTION_HDR_SIZE);
-		if (eq_id == mc->hdr.processor_rev_id && rev < mc->hdr.patch_id)
-			if (__apply_microcode_amd(mc) == 0) {
+
+		if (eq_id == mc->hdr.processor_rev_id && rev < mc->hdr.patch_id) {
+
+			if (!__apply_microcode_amd(mc)) {
 				rev = mc->hdr.patch_id;
 				*new_rev = rev;
+
+				/* save ucode patch */
+				memcpy(amd_ucode_patch, mc,
+				       min_t(u32, header[1], PATCH_MAX_SIZE));
 			}
+		}
 
 		offset  = header[1] + SECTION_HDR_SIZE;
 		data   += offset;
 		left   -= offset;
 	}
-
-	/* mark where this microcode container file ends */
-	offset  = *usize - (data - (u8 *)ucode);
-	*usize -= offset;
-
-	if (!(*new_rev))
-		*usize = 0;
 }
 
 void __init load_ucode_amd_bsp(void)
 {
-	struct cpio_data cd = find_ucode_in_initrd();
-	if (!cd.data)
+	struct cpio_data cp;
+	void **data;
+	size_t *size;
+
+#ifdef CONFIG_X86_32
+	data =  (void **)__pa_nodebug(&ucode_cpio.data);
+	size = (size_t *)__pa_nodebug(&ucode_cpio.size);
+#else
+	data = &ucode_cpio.data;
+	size = &ucode_cpio.size;
+#endif
+
+	cp = find_ucode_in_initrd();
+	if (!cp.data)
 		return;
 
-	apply_ucode_in_initrd(cd.data, cd.size);
+	*data = cp.data;
+	*size = cp.size;
+
+	apply_ucode_in_initrd(cp.data, cp.size);
 }
 
 #ifdef CONFIG_X86_32
-u8 amd_bsp_mpb[MPB_MAX_SIZE];
-
 /*
  * On 32-bit, since AP's early load occurs before paging is turned on, we
  * cannot traverse cpu_equiv_table and pcache in kernel heap memory. So during
  * cold boot, AP will apply_ucode_in_initrd() just like the BSP. During
- * save_microcode_in_initrd_amd() BSP's patch is copied to amd_bsp_mpb, which
- * is used upon resume from suspend.
+ * save_microcode_in_initrd_amd() BSP's patch is copied to amd_ucode_patch,
+ * which is used upon resume from suspend.
  */
 void load_ucode_amd_ap(void)
 {
 	struct microcode_amd *mc;
-	unsigned long *initrd;
-	unsigned long *uoffset;
 	size_t *usize;
-	void *ucode;
+	void **ucode;
 
-	mc = (struct microcode_amd *)__pa(amd_bsp_mpb);
+	mc = (struct microcode_amd *)__pa(amd_ucode_patch);
 	if (mc->hdr.patch_id && mc->hdr.processor_rev_id) {
 		__apply_microcode_amd(mc);
 		return;
 	}
 
-	initrd  = (unsigned long *)__pa(&initrd_start);
-	uoffset = (unsigned long *)__pa(&ucode_offset);
-	usize   = (size_t *)__pa(&ucode_size);
+	ucode = (void *)__pa_nodebug(&container);
+	usize = (size_t *)__pa_nodebug(&container_size);
 
-	if (!*usize || !*initrd)
+	if (!*ucode || !*usize)
 		return;
 
-	ucode = (void *)((unsigned long)__pa(*initrd) + *uoffset);
-	apply_ucode_in_initrd(ucode, *usize);
+	apply_ucode_in_initrd(*ucode, *usize);
 }
 
 static void __init collect_cpu_sig_on_bsp(void *arg)
 {
 	unsigned int cpu = smp_processor_id();
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+
 	uci->cpu_sig.sig = cpuid_eax(0x00000001);
 }
 #else
@@ -242,36 +290,54 @@ void load_ucode_amd_ap(void)
 {
 	unsigned int cpu = smp_processor_id();
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+	struct equiv_cpu_entry *eq;
+	struct microcode_amd *mc;
 	u32 rev, eax;
+	u16 eq_id;
+
+	/* Exit if called on the BSP. */
+	if (!cpu)
+		return;
+
+	if (!container)
+		return;
 
 	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax);
-	eax = cpuid_eax(0x00000001);
 
 	uci->cpu_sig.rev = rev;
 	uci->cpu_sig.sig = eax;
 
-	if (cpu && !ucode_loaded) {
-		void *ucode;
+	eax = cpuid_eax(0x00000001);
+	eq  = (struct equiv_cpu_entry *)(container + CONTAINER_HDR_SZ);
 
-		if (!ucode_size || !initrd_start)
-			return;
+	eq_id = find_equiv_id(eq, eax);
+	if (!eq_id)
+		return;
+
+	if (eq_id == this_equiv_id) {
+		mc = (struct microcode_amd *)amd_ucode_patch;
 
-		ucode = (void *)(initrd_start + ucode_offset);
-		eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
-		if (load_microcode_amd(eax, ucode, ucode_size) != UCODE_OK)
+		if (mc && rev < mc->hdr.patch_id) {
+			if (!__apply_microcode_amd(mc))
+				ucode_new_rev = mc->hdr.patch_id;
+		}
+
+	} else {
+		if (!ucode_cpio.data)
 			return;
 
-		ucode_loaded = true;
+		/*
+		 * AP has a different equivalence ID than BSP, looks like
+		 * mixed-steppings silicon so go through the ucode blob anew.
+		 */
+		apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size);
 	}
-
-	apply_microcode_amd(cpu);
 }
 #endif
 
 int __init save_microcode_in_initrd_amd(void)
 {
 	enum ucode_state ret;
-	void *ucode;
 	u32 eax;
 
 #ifdef CONFIG_X86_32
@@ -280,22 +346,35 @@ int __init save_microcode_in_initrd_amd(void)
 
 	if (!uci->cpu_sig.sig)
 		smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1);
+
+	/*
+	 * Take into account the fact that the ramdisk might get relocated
+	 * and therefore we need to recompute the container's position in
+	 * virtual memory space.
+	 */
+	container = (u8 *)(__va((u32)relocated_ramdisk) +
+			   ((u32)container - boot_params.hdr.ramdisk_image));
 #endif
 	if (ucode_new_rev)
 		pr_info("microcode: updated early to new patch_level=0x%08x\n",
 			ucode_new_rev);
 
-	if (ucode_loaded || !ucode_size || !initrd_start)
-		return 0;
+	if (!container)
+		return -EINVAL;
 
-	ucode = (void *)(initrd_start + ucode_offset);
 	eax   = cpuid_eax(0x00000001);
 	eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
 
-	ret = load_microcode_amd(eax, ucode, ucode_size);
+	ret = load_microcode_amd(eax, container, container_size);
 	if (ret != UCODE_OK)
 		return -EINVAL;
 
-	ucode_loaded = true;
+	/*
+	 * This will be freed any msec now, stash patches for the current
+	 * family and switch to patch cache for cpu hotplug, etc later.
+	 */
+	container = NULL;
+	container_size = 0;
+
 	return 0;
 }
-- 
cgit v0.10.2


From bad5fa631fca5466401cd4a48e30cc1f1cb6101e Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Sun, 1 Dec 2013 18:09:58 +0100
Subject: x86, microcode: Move to a proper location

We've grown a bunch of microcode loader files all prefixed with
"microcode_". They should be under cpu/ because this is strictly
CPU-related functionality so do that and drop the prefix since they're
in their own directory now which gives that prefix. :)

While at it, drop MICROCODE_INTEL_LIB config item and stash the
functionality under CONFIG_MICROCODE_INTEL as it was its only user.

Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0952ecd..01bfb9e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1080,10 +1080,6 @@ config MICROCODE_OLD_INTERFACE
 	def_bool y
 	depends on MICROCODE
 
-config MICROCODE_INTEL_LIB
-	def_bool y
-	depends on MICROCODE_INTEL
-
 config MICROCODE_INTEL_EARLY
 	def_bool n
 
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 9b0a34e..4d0094d 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -91,15 +91,6 @@ obj-$(CONFIG_PARAVIRT_CLOCK)	+= pvclock.o
 
 obj-$(CONFIG_PCSPKR_PLATFORM)	+= pcspeaker.o
 
-obj-$(CONFIG_MICROCODE_EARLY)		+= microcode_core_early.o
-obj-$(CONFIG_MICROCODE_INTEL_EARLY)	+= microcode_intel_early.o
-obj-$(CONFIG_MICROCODE_INTEL_LIB)	+= microcode_intel_lib.o
-microcode-y				:= microcode_core.o
-microcode-$(CONFIG_MICROCODE_INTEL)	+= microcode_intel.o
-microcode-$(CONFIG_MICROCODE_AMD)	+= microcode_amd.o
-obj-$(CONFIG_MICROCODE_AMD_EARLY)	+= microcode_amd_early.o
-obj-$(CONFIG_MICROCODE)			+= microcode.o
-
 obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o
 
 obj-$(CONFIG_SWIOTLB)			+= pci-swiotlb.o
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 47b56a7..0710eef 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -42,6 +42,7 @@ endif
 
 obj-$(CONFIG_X86_MCE)			+= mcheck/
 obj-$(CONFIG_MTRR)			+= mtrr/
+obj-$(CONFIG_MICROCODE)			+= microcode/
 
 obj-$(CONFIG_X86_LOCAL_APIC)		+= perfctr-watchdog.o perf_event_amd_ibs.o
 
diff --git a/arch/x86/kernel/cpu/microcode/Makefile b/arch/x86/kernel/cpu/microcode/Makefile
new file mode 100644
index 0000000..285c854
--- /dev/null
+++ b/arch/x86/kernel/cpu/microcode/Makefile
@@ -0,0 +1,7 @@
+microcode-y				:= core.o
+obj-$(CONFIG_MICROCODE)			+= microcode.o
+microcode-$(CONFIG_MICROCODE_INTEL)	+= intel.o intel_lib.o
+microcode-$(CONFIG_MICROCODE_AMD)	+= amd.o
+obj-$(CONFIG_MICROCODE_EARLY)		+= core_early.o
+obj-$(CONFIG_MICROCODE_INTEL_EARLY)	+= intel_early.o
+obj-$(CONFIG_MICROCODE_AMD_EARLY)	+= amd_early.o
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
new file mode 100644
index 0000000..4a6ff74
--- /dev/null
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -0,0 +1,492 @@
+/*
+ *  AMD CPU Microcode Update Driver for Linux
+ *  Copyright (C) 2008-2011 Advanced Micro Devices Inc.
+ *
+ *  Author: Peter Oruba <peter.oruba@amd.com>
+ *
+ *  Based on work by:
+ *  Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ *
+ *  Maintainers:
+ *  Andreas Herrmann <herrmann.der.user@googlemail.com>
+ *  Borislav Petkov <bp@alien8.de>
+ *
+ *  This driver allows to upgrade microcode on F10h AMD
+ *  CPUs and later.
+ *
+ *  Licensed under the terms of the GNU General Public
+ *  License version 2. See file COPYING for details.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/firmware.h>
+#include <linux/pci_ids.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include <asm/microcode.h>
+#include <asm/processor.h>
+#include <asm/msr.h>
+#include <asm/microcode_amd.h>
+
+MODULE_DESCRIPTION("AMD Microcode Update Driver");
+MODULE_AUTHOR("Peter Oruba");
+MODULE_LICENSE("GPL v2");
+
+static struct equiv_cpu_entry *equiv_cpu_table;
+
+struct ucode_patch {
+	struct list_head plist;
+	void *data;
+	u32 patch_id;
+	u16 equiv_cpu;
+};
+
+static LIST_HEAD(pcache);
+
+static u16 __find_equiv_id(unsigned int cpu)
+{
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+	return find_equiv_id(equiv_cpu_table, uci->cpu_sig.sig);
+}
+
+static u32 find_cpu_family_by_equiv_cpu(u16 equiv_cpu)
+{
+	int i = 0;
+
+	BUG_ON(!equiv_cpu_table);
+
+	while (equiv_cpu_table[i].equiv_cpu != 0) {
+		if (equiv_cpu == equiv_cpu_table[i].equiv_cpu)
+			return equiv_cpu_table[i].installed_cpu;
+		i++;
+	}
+	return 0;
+}
+
+/*
+ * a small, trivial cache of per-family ucode patches
+ */
+static struct ucode_patch *cache_find_patch(u16 equiv_cpu)
+{
+	struct ucode_patch *p;
+
+	list_for_each_entry(p, &pcache, plist)
+		if (p->equiv_cpu == equiv_cpu)
+			return p;
+	return NULL;
+}
+
+static void update_cache(struct ucode_patch *new_patch)
+{
+	struct ucode_patch *p;
+
+	list_for_each_entry(p, &pcache, plist) {
+		if (p->equiv_cpu == new_patch->equiv_cpu) {
+			if (p->patch_id >= new_patch->patch_id)
+				/* we already have the latest patch */
+				return;
+
+			list_replace(&p->plist, &new_patch->plist);
+			kfree(p->data);
+			kfree(p);
+			return;
+		}
+	}
+	/* no patch found, add it */
+	list_add_tail(&new_patch->plist, &pcache);
+}
+
+static void free_cache(void)
+{
+	struct ucode_patch *p, *tmp;
+
+	list_for_each_entry_safe(p, tmp, &pcache, plist) {
+		__list_del(p->plist.prev, p->plist.next);
+		kfree(p->data);
+		kfree(p);
+	}
+}
+
+static struct ucode_patch *find_patch(unsigned int cpu)
+{
+	u16 equiv_id;
+
+	equiv_id = __find_equiv_id(cpu);
+	if (!equiv_id)
+		return NULL;
+
+	return cache_find_patch(equiv_id);
+}
+
+static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
+{
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+	struct ucode_patch *p;
+
+	csig->sig = cpuid_eax(0x00000001);
+	csig->rev = c->microcode;
+
+	/*
+	 * a patch could have been loaded early, set uci->mc so that
+	 * mc_bp_resume() can call apply_microcode()
+	 */
+	p = find_patch(cpu);
+	if (p && (p->patch_id == csig->rev))
+		uci->mc = p->data;
+
+	pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev);
+
+	return 0;
+}
+
+static unsigned int verify_patch_size(u8 family, u32 patch_size,
+				      unsigned int size)
+{
+	u32 max_size;
+
+#define F1XH_MPB_MAX_SIZE 2048
+#define F14H_MPB_MAX_SIZE 1824
+#define F15H_MPB_MAX_SIZE 4096
+#define F16H_MPB_MAX_SIZE 3458
+
+	switch (family) {
+	case 0x14:
+		max_size = F14H_MPB_MAX_SIZE;
+		break;
+	case 0x15:
+		max_size = F15H_MPB_MAX_SIZE;
+		break;
+	case 0x16:
+		max_size = F16H_MPB_MAX_SIZE;
+		break;
+	default:
+		max_size = F1XH_MPB_MAX_SIZE;
+		break;
+	}
+
+	if (patch_size > min_t(u32, size, max_size)) {
+		pr_err("patch size mismatch\n");
+		return 0;
+	}
+
+	return patch_size;
+}
+
+int __apply_microcode_amd(struct microcode_amd *mc_amd)
+{
+	u32 rev, dummy;
+
+	native_wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code);
+
+	/* verify patch application was successful */
+	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
+	if (rev != mc_amd->hdr.patch_id)
+		return -1;
+
+	return 0;
+}
+
+int apply_microcode_amd(int cpu)
+{
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	struct microcode_amd *mc_amd;
+	struct ucode_cpu_info *uci;
+	struct ucode_patch *p;
+	u32 rev, dummy;
+
+	BUG_ON(raw_smp_processor_id() != cpu);
+
+	uci = ucode_cpu_info + cpu;
+
+	p = find_patch(cpu);
+	if (!p)
+		return 0;
+
+	mc_amd  = p->data;
+	uci->mc = p->data;
+
+	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
+
+	/* need to apply patch? */
+	if (rev >= mc_amd->hdr.patch_id) {
+		c->microcode = rev;
+		uci->cpu_sig.rev = rev;
+		return 0;
+	}
+
+	if (__apply_microcode_amd(mc_amd)) {
+		pr_err("CPU%d: update failed for patch_level=0x%08x\n",
+			cpu, mc_amd->hdr.patch_id);
+		return -1;
+	}
+	pr_info("CPU%d: new patch_level=0x%08x\n", cpu,
+		mc_amd->hdr.patch_id);
+
+	uci->cpu_sig.rev = mc_amd->hdr.patch_id;
+	c->microcode = mc_amd->hdr.patch_id;
+
+	return 0;
+}
+
+static int install_equiv_cpu_table(const u8 *buf)
+{
+	unsigned int *ibuf = (unsigned int *)buf;
+	unsigned int type = ibuf[1];
+	unsigned int size = ibuf[2];
+
+	if (type != UCODE_EQUIV_CPU_TABLE_TYPE || !size) {
+		pr_err("empty section/"
+		       "invalid type field in container file section header\n");
+		return -EINVAL;
+	}
+
+	equiv_cpu_table = vmalloc(size);
+	if (!equiv_cpu_table) {
+		pr_err("failed to allocate equivalent CPU table\n");
+		return -ENOMEM;
+	}
+
+	memcpy(equiv_cpu_table, buf + CONTAINER_HDR_SZ, size);
+
+	/* add header length */
+	return size + CONTAINER_HDR_SZ;
+}
+
+static void free_equiv_cpu_table(void)
+{
+	vfree(equiv_cpu_table);
+	equiv_cpu_table = NULL;
+}
+
+static void cleanup(void)
+{
+	free_equiv_cpu_table();
+	free_cache();
+}
+
+/*
+ * We return the current size even if some of the checks failed so that
+ * we can skip over the next patch. If we return a negative value, we
+ * signal a grave error like a memory allocation has failed and the
+ * driver cannot continue functioning normally. In such cases, we tear
+ * down everything we've used up so far and exit.
+ */
+static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover)
+{
+	struct microcode_header_amd *mc_hdr;
+	struct ucode_patch *patch;
+	unsigned int patch_size, crnt_size, ret;
+	u32 proc_fam;
+	u16 proc_id;
+
+	patch_size  = *(u32 *)(fw + 4);
+	crnt_size   = patch_size + SECTION_HDR_SIZE;
+	mc_hdr	    = (struct microcode_header_amd *)(fw + SECTION_HDR_SIZE);
+	proc_id	    = mc_hdr->processor_rev_id;
+
+	proc_fam = find_cpu_family_by_equiv_cpu(proc_id);
+	if (!proc_fam) {
+		pr_err("No patch family for equiv ID: 0x%04x\n", proc_id);
+		return crnt_size;
+	}
+
+	/* check if patch is for the current family */
+	proc_fam = ((proc_fam >> 8) & 0xf) + ((proc_fam >> 20) & 0xff);
+	if (proc_fam != family)
+		return crnt_size;
+
+	if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) {
+		pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n",
+			mc_hdr->patch_id);
+		return crnt_size;
+	}
+
+	ret = verify_patch_size(family, patch_size, leftover);
+	if (!ret) {
+		pr_err("Patch-ID 0x%08x: size mismatch.\n", mc_hdr->patch_id);
+		return crnt_size;
+	}
+
+	patch = kzalloc(sizeof(*patch), GFP_KERNEL);
+	if (!patch) {
+		pr_err("Patch allocation failure.\n");
+		return -EINVAL;
+	}
+
+	patch->data = kzalloc(patch_size, GFP_KERNEL);
+	if (!patch->data) {
+		pr_err("Patch data allocation failure.\n");
+		kfree(patch);
+		return -EINVAL;
+	}
+
+	/* All looks ok, copy patch... */
+	memcpy(patch->data, fw + SECTION_HDR_SIZE, patch_size);
+	INIT_LIST_HEAD(&patch->plist);
+	patch->patch_id  = mc_hdr->patch_id;
+	patch->equiv_cpu = proc_id;
+
+	pr_debug("%s: Added patch_id: 0x%08x, proc_id: 0x%04x\n",
+		 __func__, patch->patch_id, proc_id);
+
+	/* ... and add to cache. */
+	update_cache(patch);
+
+	return crnt_size;
+}
+
+static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
+					     size_t size)
+{
+	enum ucode_state ret = UCODE_ERROR;
+	unsigned int leftover;
+	u8 *fw = (u8 *)data;
+	int crnt_size = 0;
+	int offset;
+
+	offset = install_equiv_cpu_table(data);
+	if (offset < 0) {
+		pr_err("failed to create equivalent cpu table\n");
+		return ret;
+	}
+	fw += offset;
+	leftover = size - offset;
+
+	if (*(u32 *)fw != UCODE_UCODE_TYPE) {
+		pr_err("invalid type field in container file section header\n");
+		free_equiv_cpu_table();
+		return ret;
+	}
+
+	while (leftover) {
+		crnt_size = verify_and_add_patch(family, fw, leftover);
+		if (crnt_size < 0)
+			return ret;
+
+		fw	 += crnt_size;
+		leftover -= crnt_size;
+	}
+
+	return UCODE_OK;
+}
+
+enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size)
+{
+	enum ucode_state ret;
+
+	/* free old equiv table */
+	free_equiv_cpu_table();
+
+	ret = __load_microcode_amd(family, data, size);
+
+	if (ret != UCODE_OK)
+		cleanup();
+
+#if defined(CONFIG_MICROCODE_AMD_EARLY) && defined(CONFIG_X86_32)
+	/* save BSP's matching patch for early load */
+	if (cpu_data(smp_processor_id()).cpu_index == boot_cpu_data.cpu_index) {
+		struct ucode_patch *p = find_patch(smp_processor_id());
+		if (p) {
+			memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
+			memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data),
+							       PATCH_MAX_SIZE));
+		}
+	}
+#endif
+	return ret;
+}
+
+/*
+ * AMD microcode firmware naming convention, up to family 15h they are in
+ * the legacy file:
+ *
+ *    amd-ucode/microcode_amd.bin
+ *
+ * This legacy file is always smaller than 2K in size.
+ *
+ * Beginning with family 15h, they are in family-specific firmware files:
+ *
+ *    amd-ucode/microcode_amd_fam15h.bin
+ *    amd-ucode/microcode_amd_fam16h.bin
+ *    ...
+ *
+ * These might be larger than 2K.
+ */
+static enum ucode_state request_microcode_amd(int cpu, struct device *device,
+					      bool refresh_fw)
+{
+	char fw_name[36] = "amd-ucode/microcode_amd.bin";
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	enum ucode_state ret = UCODE_NFOUND;
+	const struct firmware *fw;
+
+	/* reload ucode container only on the boot cpu */
+	if (!refresh_fw || c->cpu_index != boot_cpu_data.cpu_index)
+		return UCODE_OK;
+
+	if (c->x86 >= 0x15)
+		snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86);
+
+	if (request_firmware(&fw, (const char *)fw_name, device)) {
+		pr_debug("failed to load file %s\n", fw_name);
+		goto out;
+	}
+
+	ret = UCODE_ERROR;
+	if (*(u32 *)fw->data != UCODE_MAGIC) {
+		pr_err("invalid magic value (0x%08x)\n", *(u32 *)fw->data);
+		goto fw_release;
+	}
+
+	ret = load_microcode_amd(c->x86, fw->data, fw->size);
+
+ fw_release:
+	release_firmware(fw);
+
+ out:
+	return ret;
+}
+
+static enum ucode_state
+request_microcode_user(int cpu, const void __user *buf, size_t size)
+{
+	return UCODE_ERROR;
+}
+
+static void microcode_fini_cpu_amd(int cpu)
+{
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+
+	uci->mc = NULL;
+}
+
+static struct microcode_ops microcode_amd_ops = {
+	.request_microcode_user           = request_microcode_user,
+	.request_microcode_fw             = request_microcode_amd,
+	.collect_cpu_info                 = collect_cpu_info_amd,
+	.apply_microcode                  = apply_microcode_amd,
+	.microcode_fini_cpu               = microcode_fini_cpu_amd,
+};
+
+struct microcode_ops * __init init_amd_microcode(void)
+{
+	struct cpuinfo_x86 *c = &cpu_data(0);
+
+	if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) {
+		pr_warning("AMD CPU family 0x%x not supported\n", c->x86);
+		return NULL;
+	}
+
+	return &microcode_amd_ops;
+}
+
+void __exit exit_amd_microcode(void)
+{
+	cleanup();
+}
diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c
new file mode 100644
index 0000000..8384c0f
--- /dev/null
+++ b/arch/x86/kernel/cpu/microcode/amd_early.c
@@ -0,0 +1,380 @@
+/*
+ * Copyright (C) 2013 Advanced Micro Devices, Inc.
+ *
+ * Author: Jacob Shin <jacob.shin@amd.com>
+ * Fixes: Borislav Petkov <bp@suse.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/earlycpio.h>
+#include <linux/initrd.h>
+
+#include <asm/cpu.h>
+#include <asm/setup.h>
+#include <asm/microcode_amd.h>
+
+/*
+ * This points to the current valid container of microcode patches which we will
+ * save from the initrd before jettisoning its contents.
+ */
+static u8 *container;
+static size_t container_size;
+
+static u32 ucode_new_rev;
+u8 amd_ucode_patch[PATCH_MAX_SIZE];
+static u16 this_equiv_id;
+
+struct cpio_data ucode_cpio;
+
+/*
+ * Microcode patch container file is prepended to the initrd in cpio format.
+ * See Documentation/x86/early-microcode.txt
+ */
+static __initdata char ucode_path[] = "kernel/x86/microcode/AuthenticAMD.bin";
+
+static struct cpio_data __init find_ucode_in_initrd(void)
+{
+	long offset = 0;
+	char *path;
+	void *start;
+	size_t size;
+
+#ifdef CONFIG_X86_32
+	struct boot_params *p;
+
+	/*
+	 * On 32-bit, early load occurs before paging is turned on so we need
+	 * to use physical addresses.
+	 */
+	p       = (struct boot_params *)__pa_nodebug(&boot_params);
+	path    = (char *)__pa_nodebug(ucode_path);
+	start   = (void *)p->hdr.ramdisk_image;
+	size    = p->hdr.ramdisk_size;
+#else
+	path    = ucode_path;
+	start   = (void *)(boot_params.hdr.ramdisk_image + PAGE_OFFSET);
+	size    = boot_params.hdr.ramdisk_size;
+#endif
+
+	return find_cpio_data(path, start, size, &offset);
+}
+
+static size_t compute_container_size(u8 *data, u32 total_size)
+{
+	size_t size = 0;
+	u32 *header = (u32 *)data;
+
+	if (header[0] != UCODE_MAGIC ||
+	    header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */
+	    header[2] == 0)                            /* size */
+		return size;
+
+	size = header[2] + CONTAINER_HDR_SZ;
+	total_size -= size;
+	data += size;
+
+	while (total_size) {
+		u16 patch_size;
+
+		header = (u32 *)data;
+
+		if (header[0] != UCODE_UCODE_TYPE)
+			break;
+
+		/*
+		 * Sanity-check patch size.
+		 */
+		patch_size = header[1];
+		if (patch_size > PATCH_MAX_SIZE)
+			break;
+
+		size	   += patch_size + SECTION_HDR_SIZE;
+		data	   += patch_size + SECTION_HDR_SIZE;
+		total_size -= patch_size + SECTION_HDR_SIZE;
+	}
+
+	return size;
+}
+
+/*
+ * Early load occurs before we can vmalloc(). So we look for the microcode
+ * patch container file in initrd, traverse equivalent cpu table, look for a
+ * matching microcode patch, and update, all in initrd memory in place.
+ * When vmalloc() is available for use later -- on 64-bit during first AP load,
+ * and on 32-bit during save_microcode_in_initrd_amd() -- we can call
+ * load_microcode_amd() to save equivalent cpu table and microcode patches in
+ * kernel heap memory.
+ */
+static void apply_ucode_in_initrd(void *ucode, size_t size)
+{
+	struct equiv_cpu_entry *eq;
+	size_t *cont_sz;
+	u32 *header;
+	u8  *data, **cont;
+	u16 eq_id = 0;
+	int offset, left;
+	u32 rev, eax, ebx, ecx, edx;
+	u32 *new_rev;
+
+#ifdef CONFIG_X86_32
+	new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
+	cont_sz = (size_t *)__pa_nodebug(&container_size);
+	cont	= (u8 **)__pa_nodebug(&container);
+#else
+	new_rev = &ucode_new_rev;
+	cont_sz = &container_size;
+	cont	= &container;
+#endif
+
+	data   = ucode;
+	left   = size;
+	header = (u32 *)data;
+
+	/* find equiv cpu table */
+	if (header[0] != UCODE_MAGIC ||
+	    header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */
+	    header[2] == 0)                            /* size */
+		return;
+
+	eax = 0x00000001;
+	ecx = 0;
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+
+	while (left > 0) {
+		eq = (struct equiv_cpu_entry *)(data + CONTAINER_HDR_SZ);
+
+		*cont = data;
+
+		/* Advance past the container header */
+		offset = header[2] + CONTAINER_HDR_SZ;
+		data  += offset;
+		left  -= offset;
+
+		eq_id = find_equiv_id(eq, eax);
+		if (eq_id) {
+			this_equiv_id = eq_id;
+			*cont_sz = compute_container_size(*cont, left + offset);
+
+			/*
+			 * truncate how much we need to iterate over in the
+			 * ucode update loop below
+			 */
+			left = *cont_sz - offset;
+			break;
+		}
+
+		/*
+		 * support multiple container files appended together. if this
+		 * one does not have a matching equivalent cpu entry, we fast
+		 * forward to the next container file.
+		 */
+		while (left > 0) {
+			header = (u32 *)data;
+			if (header[0] == UCODE_MAGIC &&
+			    header[1] == UCODE_EQUIV_CPU_TABLE_TYPE)
+				break;
+
+			offset = header[1] + SECTION_HDR_SIZE;
+			data  += offset;
+			left  -= offset;
+		}
+
+		/* mark where the next microcode container file starts */
+		offset    = data - (u8 *)ucode;
+		ucode     = data;
+	}
+
+	if (!eq_id) {
+		*cont = NULL;
+		*cont_sz = 0;
+		return;
+	}
+
+	/* find ucode and update if needed */
+
+	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax);
+
+	while (left > 0) {
+		struct microcode_amd *mc;
+
+		header = (u32 *)data;
+		if (header[0] != UCODE_UCODE_TYPE || /* type */
+		    header[1] == 0)                  /* size */
+			break;
+
+		mc = (struct microcode_amd *)(data + SECTION_HDR_SIZE);
+
+		if (eq_id == mc->hdr.processor_rev_id && rev < mc->hdr.patch_id) {
+
+			if (!__apply_microcode_amd(mc)) {
+				rev = mc->hdr.patch_id;
+				*new_rev = rev;
+
+				/* save ucode patch */
+				memcpy(amd_ucode_patch, mc,
+				       min_t(u32, header[1], PATCH_MAX_SIZE));
+			}
+		}
+
+		offset  = header[1] + SECTION_HDR_SIZE;
+		data   += offset;
+		left   -= offset;
+	}
+}
+
+void __init load_ucode_amd_bsp(void)
+{
+	struct cpio_data cp;
+	void **data;
+	size_t *size;
+
+#ifdef CONFIG_X86_32
+	data =  (void **)__pa_nodebug(&ucode_cpio.data);
+	size = (size_t *)__pa_nodebug(&ucode_cpio.size);
+#else
+	data = &ucode_cpio.data;
+	size = &ucode_cpio.size;
+#endif
+
+	cp = find_ucode_in_initrd();
+	if (!cp.data)
+		return;
+
+	*data = cp.data;
+	*size = cp.size;
+
+	apply_ucode_in_initrd(cp.data, cp.size);
+}
+
+#ifdef CONFIG_X86_32
+/*
+ * On 32-bit, since AP's early load occurs before paging is turned on, we
+ * cannot traverse cpu_equiv_table and pcache in kernel heap memory. So during
+ * cold boot, AP will apply_ucode_in_initrd() just like the BSP. During
+ * save_microcode_in_initrd_amd() BSP's patch is copied to amd_ucode_patch,
+ * which is used upon resume from suspend.
+ */
+void load_ucode_amd_ap(void)
+{
+	struct microcode_amd *mc;
+	size_t *usize;
+	void **ucode;
+
+	mc = (struct microcode_amd *)__pa(amd_ucode_patch);
+	if (mc->hdr.patch_id && mc->hdr.processor_rev_id) {
+		__apply_microcode_amd(mc);
+		return;
+	}
+
+	ucode = (void *)__pa_nodebug(&container);
+	usize = (size_t *)__pa_nodebug(&container_size);
+
+	if (!*ucode || !*usize)
+		return;
+
+	apply_ucode_in_initrd(*ucode, *usize);
+}
+
+static void __init collect_cpu_sig_on_bsp(void *arg)
+{
+	unsigned int cpu = smp_processor_id();
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+
+	uci->cpu_sig.sig = cpuid_eax(0x00000001);
+}
+#else
+void load_ucode_amd_ap(void)
+{
+	unsigned int cpu = smp_processor_id();
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+	struct equiv_cpu_entry *eq;
+	struct microcode_amd *mc;
+	u32 rev, eax;
+	u16 eq_id;
+
+	/* Exit if called on the BSP. */
+	if (!cpu)
+		return;
+
+	if (!container)
+		return;
+
+	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax);
+
+	uci->cpu_sig.rev = rev;
+	uci->cpu_sig.sig = eax;
+
+	eax = cpuid_eax(0x00000001);
+	eq  = (struct equiv_cpu_entry *)(container + CONTAINER_HDR_SZ);
+
+	eq_id = find_equiv_id(eq, eax);
+	if (!eq_id)
+		return;
+
+	if (eq_id == this_equiv_id) {
+		mc = (struct microcode_amd *)amd_ucode_patch;
+
+		if (mc && rev < mc->hdr.patch_id) {
+			if (!__apply_microcode_amd(mc))
+				ucode_new_rev = mc->hdr.patch_id;
+		}
+
+	} else {
+		if (!ucode_cpio.data)
+			return;
+
+		/*
+		 * AP has a different equivalence ID than BSP, looks like
+		 * mixed-steppings silicon so go through the ucode blob anew.
+		 */
+		apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size);
+	}
+}
+#endif
+
+int __init save_microcode_in_initrd_amd(void)
+{
+	enum ucode_state ret;
+	u32 eax;
+
+#ifdef CONFIG_X86_32
+	unsigned int bsp = boot_cpu_data.cpu_index;
+	struct ucode_cpu_info *uci = ucode_cpu_info + bsp;
+
+	if (!uci->cpu_sig.sig)
+		smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1);
+
+	/*
+	 * Take into account the fact that the ramdisk might get relocated
+	 * and therefore we need to recompute the container's position in
+	 * virtual memory space.
+	 */
+	container = (u8 *)(__va((u32)relocated_ramdisk) +
+			   ((u32)container - boot_params.hdr.ramdisk_image));
+#endif
+	if (ucode_new_rev)
+		pr_info("microcode: updated early to new patch_level=0x%08x\n",
+			ucode_new_rev);
+
+	if (!container)
+		return -EINVAL;
+
+	eax   = cpuid_eax(0x00000001);
+	eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
+
+	ret = load_microcode_amd(eax, container, container_size);
+	if (ret != UCODE_OK)
+		return -EINVAL;
+
+	/*
+	 * This will be freed any msec now, stash patches for the current
+	 * family and switch to patch cache for cpu hotplug, etc later.
+	 */
+	container = NULL;
+	container_size = 0;
+
+	return 0;
+}
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
new file mode 100644
index 0000000..15c9876
--- /dev/null
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -0,0 +1,645 @@
+/*
+ *	Intel CPU Microcode Update Driver for Linux
+ *
+ *	Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ *		      2006	Shaohua Li <shaohua.li@intel.com>
+ *
+ *	This driver allows to upgrade microcode on Intel processors
+ *	belonging to IA-32 family - PentiumPro, Pentium II,
+ *	Pentium III, Xeon, Pentium 4, etc.
+ *
+ *	Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
+ *	Software Developer's Manual
+ *	Order Number 253668 or free download from:
+ *
+ *	http://developer.intel.com/Assets/PDF/manual/253668.pdf	
+ *
+ *	For more information, go to http://www.urbanmyth.org/microcode
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ *
+ *	1.0	16 Feb 2000, Tigran Aivazian <tigran@sco.com>
+ *		Initial release.
+ *	1.01	18 Feb 2000, Tigran Aivazian <tigran@sco.com>
+ *		Added read() support + cleanups.
+ *	1.02	21 Feb 2000, Tigran Aivazian <tigran@sco.com>
+ *		Added 'device trimming' support. open(O_WRONLY) zeroes
+ *		and frees the saved copy of applied microcode.
+ *	1.03	29 Feb 2000, Tigran Aivazian <tigran@sco.com>
+ *		Made to use devfs (/dev/cpu/microcode) + cleanups.
+ *	1.04	06 Jun 2000, Simon Trimmer <simon@veritas.com>
+ *		Added misc device support (now uses both devfs and misc).
+ *		Added MICROCODE_IOCFREE ioctl to clear memory.
+ *	1.05	09 Jun 2000, Simon Trimmer <simon@veritas.com>
+ *		Messages for error cases (non Intel & no suitable microcode).
+ *	1.06	03 Aug 2000, Tigran Aivazian <tigran@veritas.com>
+ *		Removed ->release(). Removed exclusive open and status bitmap.
+ *		Added microcode_rwsem to serialize read()/write()/ioctl().
+ *		Removed global kernel lock usage.
+ *	1.07	07 Sep 2000, Tigran Aivazian <tigran@veritas.com>
+ *		Write 0 to 0x8B msr and then cpuid before reading revision,
+ *		so that it works even if there were no update done by the
+ *		BIOS. Otherwise, reading from 0x8B gives junk (which happened
+ *		to be 0 on my machine which is why it worked even when I
+ *		disabled update by the BIOS)
+ *		Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix.
+ *	1.08	11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and
+ *			     Tigran Aivazian <tigran@veritas.com>
+ *		Intel Pentium 4 processor support and bugfixes.
+ *	1.09	30 Oct 2001, Tigran Aivazian <tigran@veritas.com>
+ *		Bugfix for HT (Hyper-Threading) enabled processors
+ *		whereby processor resources are shared by all logical processors
+ *		in a single CPU package.
+ *	1.10	28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and
+ *		Tigran Aivazian <tigran@veritas.com>,
+ *		Serialize updates as required on HT processors due to
+ *		speculative nature of implementation.
+ *	1.11	22 Mar 2002 Tigran Aivazian <tigran@veritas.com>
+ *		Fix the panic when writing zero-length microcode chunk.
+ *	1.12	29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>,
+ *		Jun Nakajima <jun.nakajima@intel.com>
+ *		Support for the microcode updates in the new format.
+ *	1.13	10 Oct 2003 Tigran Aivazian <tigran@veritas.com>
+ *		Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl
+ *		because we no longer hold a copy of applied microcode
+ *		in kernel memory.
+ *	1.14	25 Jun 2004 Tigran Aivazian <tigran@veritas.com>
+ *		Fix sigmatch() macro to handle old CPUs with pf == 0.
+ *		Thanks to Stuart Swales for pointing out this bug.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/platform_device.h>
+#include <linux/miscdevice.h>
+#include <linux/capability.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/cpu.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/syscore_ops.h>
+
+#include <asm/microcode.h>
+#include <asm/processor.h>
+#include <asm/cpu_device_id.h>
+#include <asm/perf_event.h>
+
+MODULE_DESCRIPTION("Microcode Update Driver");
+MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>");
+MODULE_LICENSE("GPL");
+
+#define MICROCODE_VERSION	"2.00"
+
+static struct microcode_ops	*microcode_ops;
+
+/*
+ * Synchronization.
+ *
+ * All non cpu-hotplug-callback call sites use:
+ *
+ * - microcode_mutex to synchronize with each other;
+ * - get/put_online_cpus() to synchronize with
+ *   the cpu-hotplug-callback call sites.
+ *
+ * We guarantee that only a single cpu is being
+ * updated at any particular moment of time.
+ */
+static DEFINE_MUTEX(microcode_mutex);
+
+struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
+EXPORT_SYMBOL_GPL(ucode_cpu_info);
+
+/*
+ * Operations that are run on a target cpu:
+ */
+
+struct cpu_info_ctx {
+	struct cpu_signature	*cpu_sig;
+	int			err;
+};
+
+static void collect_cpu_info_local(void *arg)
+{
+	struct cpu_info_ctx *ctx = arg;
+
+	ctx->err = microcode_ops->collect_cpu_info(smp_processor_id(),
+						   ctx->cpu_sig);
+}
+
+static int collect_cpu_info_on_target(int cpu, struct cpu_signature *cpu_sig)
+{
+	struct cpu_info_ctx ctx = { .cpu_sig = cpu_sig, .err = 0 };
+	int ret;
+
+	ret = smp_call_function_single(cpu, collect_cpu_info_local, &ctx, 1);
+	if (!ret)
+		ret = ctx.err;
+
+	return ret;
+}
+
+static int collect_cpu_info(int cpu)
+{
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+	int ret;
+
+	memset(uci, 0, sizeof(*uci));
+
+	ret = collect_cpu_info_on_target(cpu, &uci->cpu_sig);
+	if (!ret)
+		uci->valid = 1;
+
+	return ret;
+}
+
+struct apply_microcode_ctx {
+	int err;
+};
+
+static void apply_microcode_local(void *arg)
+{
+	struct apply_microcode_ctx *ctx = arg;
+
+	ctx->err = microcode_ops->apply_microcode(smp_processor_id());
+}
+
+static int apply_microcode_on_target(int cpu)
+{
+	struct apply_microcode_ctx ctx = { .err = 0 };
+	int ret;
+
+	ret = smp_call_function_single(cpu, apply_microcode_local, &ctx, 1);
+	if (!ret)
+		ret = ctx.err;
+
+	return ret;
+}
+
+#ifdef CONFIG_MICROCODE_OLD_INTERFACE
+static int do_microcode_update(const void __user *buf, size_t size)
+{
+	int error = 0;
+	int cpu;
+
+	for_each_online_cpu(cpu) {
+		struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+		enum ucode_state ustate;
+
+		if (!uci->valid)
+			continue;
+
+		ustate = microcode_ops->request_microcode_user(cpu, buf, size);
+		if (ustate == UCODE_ERROR) {
+			error = -1;
+			break;
+		} else if (ustate == UCODE_OK)
+			apply_microcode_on_target(cpu);
+	}
+
+	return error;
+}
+
+static int microcode_open(struct inode *inode, struct file *file)
+{
+	return capable(CAP_SYS_RAWIO) ? nonseekable_open(inode, file) : -EPERM;
+}
+
+static ssize_t microcode_write(struct file *file, const char __user *buf,
+			       size_t len, loff_t *ppos)
+{
+	ssize_t ret = -EINVAL;
+
+	if ((len >> PAGE_SHIFT) > totalram_pages) {
+		pr_err("too much data (max %ld pages)\n", totalram_pages);
+		return ret;
+	}
+
+	get_online_cpus();
+	mutex_lock(&microcode_mutex);
+
+	if (do_microcode_update(buf, len) == 0)
+		ret = (ssize_t)len;
+
+	if (ret > 0)
+		perf_check_microcode();
+
+	mutex_unlock(&microcode_mutex);
+	put_online_cpus();
+
+	return ret;
+}
+
+static const struct file_operations microcode_fops = {
+	.owner			= THIS_MODULE,
+	.write			= microcode_write,
+	.open			= microcode_open,
+	.llseek		= no_llseek,
+};
+
+static struct miscdevice microcode_dev = {
+	.minor			= MICROCODE_MINOR,
+	.name			= "microcode",
+	.nodename		= "cpu/microcode",
+	.fops			= &microcode_fops,
+};
+
+static int __init microcode_dev_init(void)
+{
+	int error;
+
+	error = misc_register(&microcode_dev);
+	if (error) {
+		pr_err("can't misc_register on minor=%d\n", MICROCODE_MINOR);
+		return error;
+	}
+
+	return 0;
+}
+
+static void __exit microcode_dev_exit(void)
+{
+	misc_deregister(&microcode_dev);
+}
+
+MODULE_ALIAS_MISCDEV(MICROCODE_MINOR);
+MODULE_ALIAS("devname:cpu/microcode");
+#else
+#define microcode_dev_init()	0
+#define microcode_dev_exit()	do { } while (0)
+#endif
+
+/* fake device for request_firmware */
+static struct platform_device	*microcode_pdev;
+
+static int reload_for_cpu(int cpu)
+{
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+	enum ucode_state ustate;
+	int err = 0;
+
+	if (!uci->valid)
+		return err;
+
+	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev, true);
+	if (ustate == UCODE_OK)
+		apply_microcode_on_target(cpu);
+	else
+		if (ustate == UCODE_ERROR)
+			err = -EINVAL;
+	return err;
+}
+
+static ssize_t reload_store(struct device *dev,
+			    struct device_attribute *attr,
+			    const char *buf, size_t size)
+{
+	unsigned long val;
+	int cpu;
+	ssize_t ret = 0, tmp_ret;
+
+	ret = kstrtoul(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	if (val != 1)
+		return size;
+
+	get_online_cpus();
+	mutex_lock(&microcode_mutex);
+	for_each_online_cpu(cpu) {
+		tmp_ret = reload_for_cpu(cpu);
+		if (tmp_ret != 0)
+			pr_warn("Error reloading microcode on CPU %d\n", cpu);
+
+		/* save retval of the first encountered reload error */
+		if (!ret)
+			ret = tmp_ret;
+	}
+	if (!ret)
+		perf_check_microcode();
+	mutex_unlock(&microcode_mutex);
+	put_online_cpus();
+
+	if (!ret)
+		ret = size;
+
+	return ret;
+}
+
+static ssize_t version_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct ucode_cpu_info *uci = ucode_cpu_info + dev->id;
+
+	return sprintf(buf, "0x%x\n", uci->cpu_sig.rev);
+}
+
+static ssize_t pf_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct ucode_cpu_info *uci = ucode_cpu_info + dev->id;
+
+	return sprintf(buf, "0x%x\n", uci->cpu_sig.pf);
+}
+
+static DEVICE_ATTR(reload, 0200, NULL, reload_store);
+static DEVICE_ATTR(version, 0400, version_show, NULL);
+static DEVICE_ATTR(processor_flags, 0400, pf_show, NULL);
+
+static struct attribute *mc_default_attrs[] = {
+	&dev_attr_version.attr,
+	&dev_attr_processor_flags.attr,
+	NULL
+};
+
+static struct attribute_group mc_attr_group = {
+	.attrs			= mc_default_attrs,
+	.name			= "microcode",
+};
+
+static void microcode_fini_cpu(int cpu)
+{
+	microcode_ops->microcode_fini_cpu(cpu);
+}
+
+static enum ucode_state microcode_resume_cpu(int cpu)
+{
+	pr_debug("CPU%d updated upon resume\n", cpu);
+
+	if (apply_microcode_on_target(cpu))
+		return UCODE_ERROR;
+
+	return UCODE_OK;
+}
+
+static enum ucode_state microcode_init_cpu(int cpu, bool refresh_fw)
+{
+	enum ucode_state ustate;
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+
+	if (uci && uci->valid)
+		return UCODE_OK;
+
+	if (collect_cpu_info(cpu))
+		return UCODE_ERROR;
+
+	/* --dimm. Trigger a delayed update? */
+	if (system_state != SYSTEM_RUNNING)
+		return UCODE_NFOUND;
+
+	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev,
+						     refresh_fw);
+
+	if (ustate == UCODE_OK) {
+		pr_debug("CPU%d updated upon init\n", cpu);
+		apply_microcode_on_target(cpu);
+	}
+
+	return ustate;
+}
+
+static enum ucode_state microcode_update_cpu(int cpu)
+{
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+
+	if (uci->valid)
+		return microcode_resume_cpu(cpu);
+
+	return microcode_init_cpu(cpu, false);
+}
+
+static int mc_device_add(struct device *dev, struct subsys_interface *sif)
+{
+	int err, cpu = dev->id;
+
+	if (!cpu_online(cpu))
+		return 0;
+
+	pr_debug("CPU%d added\n", cpu);
+
+	err = sysfs_create_group(&dev->kobj, &mc_attr_group);
+	if (err)
+		return err;
+
+	if (microcode_init_cpu(cpu, true) == UCODE_ERROR)
+		return -EINVAL;
+
+	return err;
+}
+
+static int mc_device_remove(struct device *dev, struct subsys_interface *sif)
+{
+	int cpu = dev->id;
+
+	if (!cpu_online(cpu))
+		return 0;
+
+	pr_debug("CPU%d removed\n", cpu);
+	microcode_fini_cpu(cpu);
+	sysfs_remove_group(&dev->kobj, &mc_attr_group);
+	return 0;
+}
+
+static struct subsys_interface mc_cpu_interface = {
+	.name			= "microcode",
+	.subsys			= &cpu_subsys,
+	.add_dev		= mc_device_add,
+	.remove_dev		= mc_device_remove,
+};
+
+/**
+ * mc_bp_resume - Update boot CPU microcode during resume.
+ */
+static void mc_bp_resume(void)
+{
+	int cpu = smp_processor_id();
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+
+	if (uci->valid && uci->mc)
+		microcode_ops->apply_microcode(cpu);
+}
+
+static struct syscore_ops mc_syscore_ops = {
+	.resume			= mc_bp_resume,
+};
+
+static int
+mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (unsigned long)hcpu;
+	struct device *dev;
+
+	dev = get_cpu_device(cpu);
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_ONLINE:
+		microcode_update_cpu(cpu);
+		pr_debug("CPU%d added\n", cpu);
+		/*
+		 * "break" is missing on purpose here because we want to fall
+		 * through in order to create the sysfs group.
+		 */
+
+	case CPU_DOWN_FAILED:
+		if (sysfs_create_group(&dev->kobj, &mc_attr_group))
+			pr_err("Failed to create group for CPU%d\n", cpu);
+		break;
+
+	case CPU_DOWN_PREPARE:
+		/* Suspend is in progress, only remove the interface */
+		sysfs_remove_group(&dev->kobj, &mc_attr_group);
+		pr_debug("CPU%d removed\n", cpu);
+		break;
+
+	/*
+	 * case CPU_DEAD:
+	 *
+	 * When a CPU goes offline, don't free up or invalidate the copy of
+	 * the microcode in kernel memory, so that we can reuse it when the
+	 * CPU comes back online without unnecessarily requesting the userspace
+	 * for it again.
+	 */
+	}
+
+	/* The CPU refused to come up during a system resume */
+	if (action == CPU_UP_CANCELED_FROZEN)
+		microcode_fini_cpu(cpu);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __refdata mc_cpu_notifier = {
+	.notifier_call	= mc_cpu_callback,
+};
+
+#ifdef MODULE
+/* Autoload on Intel and AMD systems */
+static const struct x86_cpu_id __initconst microcode_id[] = {
+#ifdef CONFIG_MICROCODE_INTEL
+	{ X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, },
+#endif
+#ifdef CONFIG_MICROCODE_AMD
+	{ X86_VENDOR_AMD, X86_FAMILY_ANY, X86_MODEL_ANY, },
+#endif
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, microcode_id);
+#endif
+
+static struct attribute *cpu_root_microcode_attrs[] = {
+	&dev_attr_reload.attr,
+	NULL
+};
+
+static struct attribute_group cpu_root_microcode_group = {
+	.name  = "microcode",
+	.attrs = cpu_root_microcode_attrs,
+};
+
+static int __init microcode_init(void)
+{
+	struct cpuinfo_x86 *c = &cpu_data(0);
+	int error;
+
+	if (c->x86_vendor == X86_VENDOR_INTEL)
+		microcode_ops = init_intel_microcode();
+	else if (c->x86_vendor == X86_VENDOR_AMD)
+		microcode_ops = init_amd_microcode();
+	else
+		pr_err("no support for this CPU vendor\n");
+
+	if (!microcode_ops)
+		return -ENODEV;
+
+	microcode_pdev = platform_device_register_simple("microcode", -1,
+							 NULL, 0);
+	if (IS_ERR(microcode_pdev))
+		return PTR_ERR(microcode_pdev);
+
+	get_online_cpus();
+	mutex_lock(&microcode_mutex);
+
+	error = subsys_interface_register(&mc_cpu_interface);
+	if (!error)
+		perf_check_microcode();
+	mutex_unlock(&microcode_mutex);
+	put_online_cpus();
+
+	if (error)
+		goto out_pdev;
+
+	error = sysfs_create_group(&cpu_subsys.dev_root->kobj,
+				   &cpu_root_microcode_group);
+
+	if (error) {
+		pr_err("Error creating microcode group!\n");
+		goto out_driver;
+	}
+
+	error = microcode_dev_init();
+	if (error)
+		goto out_ucode_group;
+
+	register_syscore_ops(&mc_syscore_ops);
+	register_hotcpu_notifier(&mc_cpu_notifier);
+
+	pr_info("Microcode Update Driver: v" MICROCODE_VERSION
+		" <tigran@aivazian.fsnet.co.uk>, Peter Oruba\n");
+
+	return 0;
+
+ out_ucode_group:
+	sysfs_remove_group(&cpu_subsys.dev_root->kobj,
+			   &cpu_root_microcode_group);
+
+ out_driver:
+	get_online_cpus();
+	mutex_lock(&microcode_mutex);
+
+	subsys_interface_unregister(&mc_cpu_interface);
+
+	mutex_unlock(&microcode_mutex);
+	put_online_cpus();
+
+ out_pdev:
+	platform_device_unregister(microcode_pdev);
+	return error;
+
+}
+module_init(microcode_init);
+
+static void __exit microcode_exit(void)
+{
+	struct cpuinfo_x86 *c = &cpu_data(0);
+
+	microcode_dev_exit();
+
+	unregister_hotcpu_notifier(&mc_cpu_notifier);
+	unregister_syscore_ops(&mc_syscore_ops);
+
+	sysfs_remove_group(&cpu_subsys.dev_root->kobj,
+			   &cpu_root_microcode_group);
+
+	get_online_cpus();
+	mutex_lock(&microcode_mutex);
+
+	subsys_interface_unregister(&mc_cpu_interface);
+
+	mutex_unlock(&microcode_mutex);
+	put_online_cpus();
+
+	platform_device_unregister(microcode_pdev);
+
+	microcode_ops = NULL;
+
+	if (c->x86_vendor == X86_VENDOR_AMD)
+		exit_amd_microcode();
+
+	pr_info("Microcode Update Driver: v" MICROCODE_VERSION " removed.\n");
+}
+module_exit(microcode_exit);
diff --git a/arch/x86/kernel/cpu/microcode/core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c
new file mode 100644
index 0000000..be7f851
--- /dev/null
+++ b/arch/x86/kernel/cpu/microcode/core_early.c
@@ -0,0 +1,141 @@
+/*
+ *	X86 CPU microcode early update for Linux
+ *
+ *	Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com>
+ *			   H Peter Anvin" <hpa@zytor.com>
+ *
+ *	This driver allows to early upgrade microcode on Intel processors
+ *	belonging to IA-32 family - PentiumPro, Pentium II,
+ *	Pentium III, Xeon, Pentium 4, etc.
+ *
+ *	Reference: Section 9.11 of Volume 3, IA-32 Intel Architecture
+ *	Software Developer's Manual.
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+#include <linux/module.h>
+#include <asm/microcode_intel.h>
+#include <asm/microcode_amd.h>
+#include <asm/processor.h>
+
+#define QCHAR(a, b, c, d) ((a) + ((b) << 8) + ((c) << 16) + ((d) << 24))
+#define CPUID_INTEL1 QCHAR('G', 'e', 'n', 'u')
+#define CPUID_INTEL2 QCHAR('i', 'n', 'e', 'I')
+#define CPUID_INTEL3 QCHAR('n', 't', 'e', 'l')
+#define CPUID_AMD1 QCHAR('A', 'u', 't', 'h')
+#define CPUID_AMD2 QCHAR('e', 'n', 't', 'i')
+#define CPUID_AMD3 QCHAR('c', 'A', 'M', 'D')
+
+#define CPUID_IS(a, b, c, ebx, ecx, edx)	\
+		(!((ebx ^ (a))|(edx ^ (b))|(ecx ^ (c))))
+
+/*
+ * In early loading microcode phase on BSP, boot_cpu_data is not set up yet.
+ * x86_vendor() gets vendor id for BSP.
+ *
+ * In 32 bit AP case, accessing boot_cpu_data needs linear address. To simplify
+ * coding, we still use x86_vendor() to get vendor id for AP.
+ *
+ * x86_vendor() gets vendor information directly through cpuid.
+ */
+static int x86_vendor(void)
+{
+	u32 eax = 0x00000000;
+	u32 ebx, ecx = 0, edx;
+
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+
+	if (CPUID_IS(CPUID_INTEL1, CPUID_INTEL2, CPUID_INTEL3, ebx, ecx, edx))
+		return X86_VENDOR_INTEL;
+
+	if (CPUID_IS(CPUID_AMD1, CPUID_AMD2, CPUID_AMD3, ebx, ecx, edx))
+		return X86_VENDOR_AMD;
+
+	return X86_VENDOR_UNKNOWN;
+}
+
+static int x86_family(void)
+{
+	u32 eax = 0x00000001;
+	u32 ebx, ecx = 0, edx;
+	int x86;
+
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+
+	x86 = (eax >> 8) & 0xf;
+	if (x86 == 15)
+		x86 += (eax >> 20) & 0xff;
+
+	return x86;
+}
+
+void __init load_ucode_bsp(void)
+{
+	int vendor, x86;
+
+	if (!have_cpuid_p())
+		return;
+
+	vendor = x86_vendor();
+	x86 = x86_family();
+
+	switch (vendor) {
+	case X86_VENDOR_INTEL:
+		if (x86 >= 6)
+			load_ucode_intel_bsp();
+		break;
+	case X86_VENDOR_AMD:
+		if (x86 >= 0x10)
+			load_ucode_amd_bsp();
+		break;
+	default:
+		break;
+	}
+}
+
+void load_ucode_ap(void)
+{
+	int vendor, x86;
+
+	if (!have_cpuid_p())
+		return;
+
+	vendor = x86_vendor();
+	x86 = x86_family();
+
+	switch (vendor) {
+	case X86_VENDOR_INTEL:
+		if (x86 >= 6)
+			load_ucode_intel_ap();
+		break;
+	case X86_VENDOR_AMD:
+		if (x86 >= 0x10)
+			load_ucode_amd_ap();
+		break;
+	default:
+		break;
+	}
+}
+
+int __init save_microcode_in_initrd(void)
+{
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+
+	switch (c->x86_vendor) {
+	case X86_VENDOR_INTEL:
+		if (c->x86 >= 6)
+			save_microcode_in_initrd_intel();
+		break;
+	case X86_VENDOR_AMD:
+		if (c->x86 >= 0x10)
+			save_microcode_in_initrd_amd();
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
new file mode 100644
index 0000000..5fb2ceb
--- /dev/null
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -0,0 +1,333 @@
+/*
+ *	Intel CPU Microcode Update Driver for Linux
+ *
+ *	Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ *		      2006	Shaohua Li <shaohua.li@intel.com>
+ *
+ *	This driver allows to upgrade microcode on Intel processors
+ *	belonging to IA-32 family - PentiumPro, Pentium II,
+ *	Pentium III, Xeon, Pentium 4, etc.
+ *
+ *	Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
+ *	Software Developer's Manual
+ *	Order Number 253668 or free download from:
+ *
+ *	http://developer.intel.com/Assets/PDF/manual/253668.pdf	
+ *
+ *	For more information, go to http://www.urbanmyth.org/microcode
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ *
+ *	1.0	16 Feb 2000, Tigran Aivazian <tigran@sco.com>
+ *		Initial release.
+ *	1.01	18 Feb 2000, Tigran Aivazian <tigran@sco.com>
+ *		Added read() support + cleanups.
+ *	1.02	21 Feb 2000, Tigran Aivazian <tigran@sco.com>
+ *		Added 'device trimming' support. open(O_WRONLY) zeroes
+ *		and frees the saved copy of applied microcode.
+ *	1.03	29 Feb 2000, Tigran Aivazian <tigran@sco.com>
+ *		Made to use devfs (/dev/cpu/microcode) + cleanups.
+ *	1.04	06 Jun 2000, Simon Trimmer <simon@veritas.com>
+ *		Added misc device support (now uses both devfs and misc).
+ *		Added MICROCODE_IOCFREE ioctl to clear memory.
+ *	1.05	09 Jun 2000, Simon Trimmer <simon@veritas.com>
+ *		Messages for error cases (non Intel & no suitable microcode).
+ *	1.06	03 Aug 2000, Tigran Aivazian <tigran@veritas.com>
+ *		Removed ->release(). Removed exclusive open and status bitmap.
+ *		Added microcode_rwsem to serialize read()/write()/ioctl().
+ *		Removed global kernel lock usage.
+ *	1.07	07 Sep 2000, Tigran Aivazian <tigran@veritas.com>
+ *		Write 0 to 0x8B msr and then cpuid before reading revision,
+ *		so that it works even if there were no update done by the
+ *		BIOS. Otherwise, reading from 0x8B gives junk (which happened
+ *		to be 0 on my machine which is why it worked even when I
+ *		disabled update by the BIOS)
+ *		Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix.
+ *	1.08	11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and
+ *			     Tigran Aivazian <tigran@veritas.com>
+ *		Intel Pentium 4 processor support and bugfixes.
+ *	1.09	30 Oct 2001, Tigran Aivazian <tigran@veritas.com>
+ *		Bugfix for HT (Hyper-Threading) enabled processors
+ *		whereby processor resources are shared by all logical processors
+ *		in a single CPU package.
+ *	1.10	28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and
+ *		Tigran Aivazian <tigran@veritas.com>,
+ *		Serialize updates as required on HT processors due to
+ *		speculative nature of implementation.
+ *	1.11	22 Mar 2002 Tigran Aivazian <tigran@veritas.com>
+ *		Fix the panic when writing zero-length microcode chunk.
+ *	1.12	29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>,
+ *		Jun Nakajima <jun.nakajima@intel.com>
+ *		Support for the microcode updates in the new format.
+ *	1.13	10 Oct 2003 Tigran Aivazian <tigran@veritas.com>
+ *		Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl
+ *		because we no longer hold a copy of applied microcode
+ *		in kernel memory.
+ *	1.14	25 Jun 2004 Tigran Aivazian <tigran@veritas.com>
+ *		Fix sigmatch() macro to handle old CPUs with pf == 0.
+ *		Thanks to Stuart Swales for pointing out this bug.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/firmware.h>
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+
+#include <asm/microcode_intel.h>
+#include <asm/processor.h>
+#include <asm/msr.h>
+
+MODULE_DESCRIPTION("Microcode Update Driver");
+MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>");
+MODULE_LICENSE("GPL");
+
+static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
+{
+	struct cpuinfo_x86 *c = &cpu_data(cpu_num);
+	unsigned int val[2];
+
+	memset(csig, 0, sizeof(*csig));
+
+	csig->sig = cpuid_eax(0x00000001);
+
+	if ((c->x86_model >= 5) || (c->x86 > 6)) {
+		/* get processor flags from MSR 0x17 */
+		rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]);
+		csig->pf = 1 << ((val[1] >> 18) & 7);
+	}
+
+	csig->rev = c->microcode;
+	pr_info("CPU%d sig=0x%x, pf=0x%x, revision=0x%x\n",
+		cpu_num, csig->sig, csig->pf, csig->rev);
+
+	return 0;
+}
+
+/*
+ * return 0 - no update found
+ * return 1 - found update
+ */
+static int get_matching_mc(struct microcode_intel *mc_intel, int cpu)
+{
+	struct cpu_signature cpu_sig;
+	unsigned int csig, cpf, crev;
+
+	collect_cpu_info(cpu, &cpu_sig);
+
+	csig = cpu_sig.sig;
+	cpf = cpu_sig.pf;
+	crev = cpu_sig.rev;
+
+	return get_matching_microcode(csig, cpf, mc_intel, crev);
+}
+
+int apply_microcode(int cpu)
+{
+	struct microcode_intel *mc_intel;
+	struct ucode_cpu_info *uci;
+	unsigned int val[2];
+	int cpu_num = raw_smp_processor_id();
+	struct cpuinfo_x86 *c = &cpu_data(cpu_num);
+
+	uci = ucode_cpu_info + cpu;
+	mc_intel = uci->mc;
+
+	/* We should bind the task to the CPU */
+	BUG_ON(cpu_num != cpu);
+
+	if (mc_intel == NULL)
+		return 0;
+
+	/*
+	 * Microcode on this CPU could be updated earlier. Only apply the
+	 * microcode patch in mc_intel when it is newer than the one on this
+	 * CPU.
+	 */
+	if (get_matching_mc(mc_intel, cpu) == 0)
+		return 0;
+
+	/* write microcode via MSR 0x79 */
+	wrmsr(MSR_IA32_UCODE_WRITE,
+	      (unsigned long) mc_intel->bits,
+	      (unsigned long) mc_intel->bits >> 16 >> 16);
+	wrmsr(MSR_IA32_UCODE_REV, 0, 0);
+
+	/* As documented in the SDM: Do a CPUID 1 here */
+	sync_core();
+
+	/* get the current revision from MSR 0x8B */
+	rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
+
+	if (val[1] != mc_intel->hdr.rev) {
+		pr_err("CPU%d update to revision 0x%x failed\n",
+		       cpu_num, mc_intel->hdr.rev);
+		return -1;
+	}
+	pr_info("CPU%d updated to revision 0x%x, date = %04x-%02x-%02x\n",
+		cpu_num, val[1],
+		mc_intel->hdr.date & 0xffff,
+		mc_intel->hdr.date >> 24,
+		(mc_intel->hdr.date >> 16) & 0xff);
+
+	uci->cpu_sig.rev = val[1];
+	c->microcode = val[1];
+
+	return 0;
+}
+
+static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
+				int (*get_ucode_data)(void *, const void *, size_t))
+{
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+	u8 *ucode_ptr = data, *new_mc = NULL, *mc = NULL;
+	int new_rev = uci->cpu_sig.rev;
+	unsigned int leftover = size;
+	enum ucode_state state = UCODE_OK;
+	unsigned int curr_mc_size = 0;
+	unsigned int csig, cpf;
+
+	while (leftover) {
+		struct microcode_header_intel mc_header;
+		unsigned int mc_size;
+
+		if (get_ucode_data(&mc_header, ucode_ptr, sizeof(mc_header)))
+			break;
+
+		mc_size = get_totalsize(&mc_header);
+		if (!mc_size || mc_size > leftover) {
+			pr_err("error! Bad data in microcode data file\n");
+			break;
+		}
+
+		/* For performance reasons, reuse mc area when possible */
+		if (!mc || mc_size > curr_mc_size) {
+			vfree(mc);
+			mc = vmalloc(mc_size);
+			if (!mc)
+				break;
+			curr_mc_size = mc_size;
+		}
+
+		if (get_ucode_data(mc, ucode_ptr, mc_size) ||
+		    microcode_sanity_check(mc, 1) < 0) {
+			break;
+		}
+
+		csig = uci->cpu_sig.sig;
+		cpf = uci->cpu_sig.pf;
+		if (get_matching_microcode(csig, cpf, mc, new_rev)) {
+			vfree(new_mc);
+			new_rev = mc_header.rev;
+			new_mc  = mc;
+			mc = NULL;	/* trigger new vmalloc */
+		}
+
+		ucode_ptr += mc_size;
+		leftover  -= mc_size;
+	}
+
+	vfree(mc);
+
+	if (leftover) {
+		vfree(new_mc);
+		state = UCODE_ERROR;
+		goto out;
+	}
+
+	if (!new_mc) {
+		state = UCODE_NFOUND;
+		goto out;
+	}
+
+	vfree(uci->mc);
+	uci->mc = (struct microcode_intel *)new_mc;
+
+	/*
+	 * If early loading microcode is supported, save this mc into
+	 * permanent memory. So it will be loaded early when a CPU is hot added
+	 * or resumes.
+	 */
+	save_mc_for_early(new_mc);
+
+	pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
+		 cpu, new_rev, uci->cpu_sig.rev);
+out:
+	return state;
+}
+
+static int get_ucode_fw(void *to, const void *from, size_t n)
+{
+	memcpy(to, from, n);
+	return 0;
+}
+
+static enum ucode_state request_microcode_fw(int cpu, struct device *device,
+					     bool refresh_fw)
+{
+	char name[30];
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	const struct firmware *firmware;
+	enum ucode_state ret;
+
+	sprintf(name, "intel-ucode/%02x-%02x-%02x",
+		c->x86, c->x86_model, c->x86_mask);
+
+	if (request_firmware(&firmware, name, device)) {
+		pr_debug("data file %s load failed\n", name);
+		return UCODE_NFOUND;
+	}
+
+	ret = generic_load_microcode(cpu, (void *)firmware->data,
+				     firmware->size, &get_ucode_fw);
+
+	release_firmware(firmware);
+
+	return ret;
+}
+
+static int get_ucode_user(void *to, const void *from, size_t n)
+{
+	return copy_from_user(to, from, n);
+}
+
+static enum ucode_state
+request_microcode_user(int cpu, const void __user *buf, size_t size)
+{
+	return generic_load_microcode(cpu, (void *)buf, size, &get_ucode_user);
+}
+
+static void microcode_fini_cpu(int cpu)
+{
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+
+	vfree(uci->mc);
+	uci->mc = NULL;
+}
+
+static struct microcode_ops microcode_intel_ops = {
+	.request_microcode_user		  = request_microcode_user,
+	.request_microcode_fw             = request_microcode_fw,
+	.collect_cpu_info                 = collect_cpu_info,
+	.apply_microcode                  = apply_microcode,
+	.microcode_fini_cpu               = microcode_fini_cpu,
+};
+
+struct microcode_ops * __init init_intel_microcode(void)
+{
+	struct cpuinfo_x86 *c = &cpu_data(0);
+
+	if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 ||
+	    cpu_has(c, X86_FEATURE_IA64)) {
+		pr_err("Intel CPU family 0x%x not supported\n", c->x86);
+		return NULL;
+	}
+
+	return &microcode_intel_ops;
+}
+
diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c
new file mode 100644
index 0000000..18f7391
--- /dev/null
+++ b/arch/x86/kernel/cpu/microcode/intel_early.c
@@ -0,0 +1,787 @@
+/*
+ *	Intel CPU microcode early update for Linux
+ *
+ *	Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com>
+ *			   H Peter Anvin" <hpa@zytor.com>
+ *
+ *	This allows to early upgrade microcode on Intel processors
+ *	belonging to IA-32 family - PentiumPro, Pentium II,
+ *	Pentium III, Xeon, Pentium 4, etc.
+ *
+ *	Reference: Section 9.11 of Volume 3, IA-32 Intel Architecture
+ *	Software Developer's Manual.
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ */
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/earlycpio.h>
+#include <linux/initrd.h>
+#include <linux/cpu.h>
+#include <asm/msr.h>
+#include <asm/microcode_intel.h>
+#include <asm/processor.h>
+#include <asm/tlbflush.h>
+#include <asm/setup.h>
+
+unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT];
+struct mc_saved_data {
+	unsigned int mc_saved_count;
+	struct microcode_intel **mc_saved;
+} mc_saved_data;
+
+static enum ucode_state
+generic_load_microcode_early(struct microcode_intel **mc_saved_p,
+			     unsigned int mc_saved_count,
+			     struct ucode_cpu_info *uci)
+{
+	struct microcode_intel *ucode_ptr, *new_mc = NULL;
+	int new_rev = uci->cpu_sig.rev;
+	enum ucode_state state = UCODE_OK;
+	unsigned int mc_size;
+	struct microcode_header_intel *mc_header;
+	unsigned int csig = uci->cpu_sig.sig;
+	unsigned int cpf = uci->cpu_sig.pf;
+	int i;
+
+	for (i = 0; i < mc_saved_count; i++) {
+		ucode_ptr = mc_saved_p[i];
+
+		mc_header = (struct microcode_header_intel *)ucode_ptr;
+		mc_size = get_totalsize(mc_header);
+		if (get_matching_microcode(csig, cpf, ucode_ptr, new_rev)) {
+			new_rev = mc_header->rev;
+			new_mc  = ucode_ptr;
+		}
+	}
+
+	if (!new_mc) {
+		state = UCODE_NFOUND;
+		goto out;
+	}
+
+	uci->mc = (struct microcode_intel *)new_mc;
+out:
+	return state;
+}
+
+static void
+microcode_pointer(struct microcode_intel **mc_saved,
+		  unsigned long *mc_saved_in_initrd,
+		  unsigned long initrd_start, int mc_saved_count)
+{
+	int i;
+
+	for (i = 0; i < mc_saved_count; i++)
+		mc_saved[i] = (struct microcode_intel *)
+			      (mc_saved_in_initrd[i] + initrd_start);
+}
+
+#ifdef CONFIG_X86_32
+static void
+microcode_phys(struct microcode_intel **mc_saved_tmp,
+	       struct mc_saved_data *mc_saved_data)
+{
+	int i;
+	struct microcode_intel ***mc_saved;
+
+	mc_saved = (struct microcode_intel ***)
+		   __pa_nodebug(&mc_saved_data->mc_saved);
+	for (i = 0; i < mc_saved_data->mc_saved_count; i++) {
+		struct microcode_intel *p;
+
+		p = *(struct microcode_intel **)
+			__pa_nodebug(mc_saved_data->mc_saved + i);
+		mc_saved_tmp[i] = (struct microcode_intel *)__pa_nodebug(p);
+	}
+}
+#endif
+
+static enum ucode_state
+load_microcode(struct mc_saved_data *mc_saved_data,
+	       unsigned long *mc_saved_in_initrd,
+	       unsigned long initrd_start,
+	       struct ucode_cpu_info *uci)
+{
+	struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT];
+	unsigned int count = mc_saved_data->mc_saved_count;
+
+	if (!mc_saved_data->mc_saved) {
+		microcode_pointer(mc_saved_tmp, mc_saved_in_initrd,
+				  initrd_start, count);
+
+		return generic_load_microcode_early(mc_saved_tmp, count, uci);
+	} else {
+#ifdef CONFIG_X86_32
+		microcode_phys(mc_saved_tmp, mc_saved_data);
+		return generic_load_microcode_early(mc_saved_tmp, count, uci);
+#else
+		return generic_load_microcode_early(mc_saved_data->mc_saved,
+						    count, uci);
+#endif
+	}
+}
+
+static u8 get_x86_family(unsigned long sig)
+{
+	u8 x86;
+
+	x86 = (sig >> 8) & 0xf;
+
+	if (x86 == 0xf)
+		x86 += (sig >> 20) & 0xff;
+
+	return x86;
+}
+
+static u8 get_x86_model(unsigned long sig)
+{
+	u8 x86, x86_model;
+
+	x86 = get_x86_family(sig);
+	x86_model = (sig >> 4) & 0xf;
+
+	if (x86 == 0x6 || x86 == 0xf)
+		x86_model += ((sig >> 16) & 0xf) << 4;
+
+	return x86_model;
+}
+
+/*
+ * Given CPU signature and a microcode patch, this function finds if the
+ * microcode patch has matching family and model with the CPU.
+ */
+static enum ucode_state
+matching_model_microcode(struct microcode_header_intel *mc_header,
+			unsigned long sig)
+{
+	u8 x86, x86_model;
+	u8 x86_ucode, x86_model_ucode;
+	struct extended_sigtable *ext_header;
+	unsigned long total_size = get_totalsize(mc_header);
+	unsigned long data_size = get_datasize(mc_header);
+	int ext_sigcount, i;
+	struct extended_signature *ext_sig;
+
+	x86 = get_x86_family(sig);
+	x86_model = get_x86_model(sig);
+
+	x86_ucode = get_x86_family(mc_header->sig);
+	x86_model_ucode = get_x86_model(mc_header->sig);
+
+	if (x86 == x86_ucode && x86_model == x86_model_ucode)
+		return UCODE_OK;
+
+	/* Look for ext. headers: */
+	if (total_size <= data_size + MC_HEADER_SIZE)
+		return UCODE_NFOUND;
+
+	ext_header = (struct extended_sigtable *)
+		     mc_header + data_size + MC_HEADER_SIZE;
+	ext_sigcount = ext_header->count;
+	ext_sig = (void *)ext_header + EXT_HEADER_SIZE;
+
+	for (i = 0; i < ext_sigcount; i++) {
+		x86_ucode = get_x86_family(ext_sig->sig);
+		x86_model_ucode = get_x86_model(ext_sig->sig);
+
+		if (x86 == x86_ucode && x86_model == x86_model_ucode)
+			return UCODE_OK;
+
+		ext_sig++;
+	}
+
+	return UCODE_NFOUND;
+}
+
+static int
+save_microcode(struct mc_saved_data *mc_saved_data,
+	       struct microcode_intel **mc_saved_src,
+	       unsigned int mc_saved_count)
+{
+	int i, j;
+	struct microcode_intel **mc_saved_p;
+	int ret;
+
+	if (!mc_saved_count)
+		return -EINVAL;
+
+	/*
+	 * Copy new microcode data.
+	 */
+	mc_saved_p = kmalloc(mc_saved_count*sizeof(struct microcode_intel *),
+			     GFP_KERNEL);
+	if (!mc_saved_p)
+		return -ENOMEM;
+
+	for (i = 0; i < mc_saved_count; i++) {
+		struct microcode_intel *mc = mc_saved_src[i];
+		struct microcode_header_intel *mc_header = &mc->hdr;
+		unsigned long mc_size = get_totalsize(mc_header);
+		mc_saved_p[i] = kmalloc(mc_size, GFP_KERNEL);
+		if (!mc_saved_p[i]) {
+			ret = -ENOMEM;
+			goto err;
+		}
+		if (!mc_saved_src[i]) {
+			ret = -EINVAL;
+			goto err;
+		}
+		memcpy(mc_saved_p[i], mc, mc_size);
+	}
+
+	/*
+	 * Point to newly saved microcode.
+	 */
+	mc_saved_data->mc_saved = mc_saved_p;
+	mc_saved_data->mc_saved_count = mc_saved_count;
+
+	return 0;
+
+err:
+	for (j = 0; j <= i; j++)
+		kfree(mc_saved_p[j]);
+	kfree(mc_saved_p);
+
+	return ret;
+}
+
+/*
+ * A microcode patch in ucode_ptr is saved into mc_saved
+ * - if it has matching signature and newer revision compared to an existing
+ *   patch mc_saved.
+ * - or if it is a newly discovered microcode patch.
+ *
+ * The microcode patch should have matching model with CPU.
+ */
+static void _save_mc(struct microcode_intel **mc_saved, u8 *ucode_ptr,
+		     unsigned int *mc_saved_count_p)
+{
+	int i;
+	int found = 0;
+	unsigned int mc_saved_count = *mc_saved_count_p;
+	struct microcode_header_intel *mc_header;
+
+	mc_header = (struct microcode_header_intel *)ucode_ptr;
+	for (i = 0; i < mc_saved_count; i++) {
+		unsigned int sig, pf;
+		unsigned int new_rev;
+		struct microcode_header_intel *mc_saved_header =
+			     (struct microcode_header_intel *)mc_saved[i];
+		sig = mc_saved_header->sig;
+		pf = mc_saved_header->pf;
+		new_rev = mc_header->rev;
+
+		if (get_matching_sig(sig, pf, ucode_ptr, new_rev)) {
+			found = 1;
+			if (update_match_revision(mc_header, new_rev)) {
+				/*
+				 * Found an older ucode saved before.
+				 * Replace the older one with this newer
+				 * one.
+				 */
+				mc_saved[i] =
+					(struct microcode_intel *)ucode_ptr;
+				break;
+			}
+		}
+	}
+	if (i >= mc_saved_count && !found)
+		/*
+		 * This ucode is first time discovered in ucode file.
+		 * Save it to memory.
+		 */
+		mc_saved[mc_saved_count++] =
+				 (struct microcode_intel *)ucode_ptr;
+
+	*mc_saved_count_p = mc_saved_count;
+}
+
+/*
+ * Get microcode matching with BSP's model. Only CPUs with the same model as
+ * BSP can stay in the platform.
+ */
+static enum ucode_state __init
+get_matching_model_microcode(int cpu, unsigned long start,
+			     void *data, size_t size,
+			     struct mc_saved_data *mc_saved_data,
+			     unsigned long *mc_saved_in_initrd,
+			     struct ucode_cpu_info *uci)
+{
+	u8 *ucode_ptr = data;
+	unsigned int leftover = size;
+	enum ucode_state state = UCODE_OK;
+	unsigned int mc_size;
+	struct microcode_header_intel *mc_header;
+	struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT];
+	unsigned int mc_saved_count = mc_saved_data->mc_saved_count;
+	int i;
+
+	while (leftover) {
+		mc_header = (struct microcode_header_intel *)ucode_ptr;
+
+		mc_size = get_totalsize(mc_header);
+		if (!mc_size || mc_size > leftover ||
+			microcode_sanity_check(ucode_ptr, 0) < 0)
+			break;
+
+		leftover -= mc_size;
+
+		/*
+		 * Since APs with same family and model as the BSP may boot in
+		 * the platform, we need to find and save microcode patches
+		 * with the same family and model as the BSP.
+		 */
+		if (matching_model_microcode(mc_header, uci->cpu_sig.sig) !=
+			 UCODE_OK) {
+			ucode_ptr += mc_size;
+			continue;
+		}
+
+		_save_mc(mc_saved_tmp, ucode_ptr, &mc_saved_count);
+
+		ucode_ptr += mc_size;
+	}
+
+	if (leftover) {
+		state = UCODE_ERROR;
+		goto out;
+	}
+
+	if (mc_saved_count == 0) {
+		state = UCODE_NFOUND;
+		goto out;
+	}
+
+	for (i = 0; i < mc_saved_count; i++)
+		mc_saved_in_initrd[i] = (unsigned long)mc_saved_tmp[i] - start;
+
+	mc_saved_data->mc_saved_count = mc_saved_count;
+out:
+	return state;
+}
+
+static int collect_cpu_info_early(struct ucode_cpu_info *uci)
+{
+	unsigned int val[2];
+	u8 x86, x86_model;
+	struct cpu_signature csig;
+	unsigned int eax, ebx, ecx, edx;
+
+	csig.sig = 0;
+	csig.pf = 0;
+	csig.rev = 0;
+
+	memset(uci, 0, sizeof(*uci));
+
+	eax = 0x00000001;
+	ecx = 0;
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+	csig.sig = eax;
+
+	x86 = get_x86_family(csig.sig);
+	x86_model = get_x86_model(csig.sig);
+
+	if ((x86_model >= 5) || (x86 > 6)) {
+		/* get processor flags from MSR 0x17 */
+		native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]);
+		csig.pf = 1 << ((val[1] >> 18) & 7);
+	}
+	native_wrmsr(MSR_IA32_UCODE_REV, 0, 0);
+
+	/* As documented in the SDM: Do a CPUID 1 here */
+	sync_core();
+
+	/* get the current revision from MSR 0x8B */
+	native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
+
+	csig.rev = val[1];
+
+	uci->cpu_sig = csig;
+	uci->valid = 1;
+
+	return 0;
+}
+
+#ifdef DEBUG
+static void __ref show_saved_mc(void)
+{
+	int i, j;
+	unsigned int sig, pf, rev, total_size, data_size, date;
+	struct ucode_cpu_info uci;
+
+	if (mc_saved_data.mc_saved_count == 0) {
+		pr_debug("no micorcode data saved.\n");
+		return;
+	}
+	pr_debug("Total microcode saved: %d\n", mc_saved_data.mc_saved_count);
+
+	collect_cpu_info_early(&uci);
+
+	sig = uci.cpu_sig.sig;
+	pf = uci.cpu_sig.pf;
+	rev = uci.cpu_sig.rev;
+	pr_debug("CPU%d: sig=0x%x, pf=0x%x, rev=0x%x\n",
+		 smp_processor_id(), sig, pf, rev);
+
+	for (i = 0; i < mc_saved_data.mc_saved_count; i++) {
+		struct microcode_header_intel *mc_saved_header;
+		struct extended_sigtable *ext_header;
+		int ext_sigcount;
+		struct extended_signature *ext_sig;
+
+		mc_saved_header = (struct microcode_header_intel *)
+				  mc_saved_data.mc_saved[i];
+		sig = mc_saved_header->sig;
+		pf = mc_saved_header->pf;
+		rev = mc_saved_header->rev;
+		total_size = get_totalsize(mc_saved_header);
+		data_size = get_datasize(mc_saved_header);
+		date = mc_saved_header->date;
+
+		pr_debug("mc_saved[%d]: sig=0x%x, pf=0x%x, rev=0x%x, toal size=0x%x, date = %04x-%02x-%02x\n",
+			 i, sig, pf, rev, total_size,
+			 date & 0xffff,
+			 date >> 24,
+			 (date >> 16) & 0xff);
+
+		/* Look for ext. headers: */
+		if (total_size <= data_size + MC_HEADER_SIZE)
+			continue;
+
+		ext_header = (struct extended_sigtable *)
+			     mc_saved_header + data_size + MC_HEADER_SIZE;
+		ext_sigcount = ext_header->count;
+		ext_sig = (void *)ext_header + EXT_HEADER_SIZE;
+
+		for (j = 0; j < ext_sigcount; j++) {
+			sig = ext_sig->sig;
+			pf = ext_sig->pf;
+
+			pr_debug("\tExtended[%d]: sig=0x%x, pf=0x%x\n",
+				 j, sig, pf);
+
+			ext_sig++;
+		}
+
+	}
+}
+#else
+static inline void show_saved_mc(void)
+{
+}
+#endif
+
+#if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU)
+static DEFINE_MUTEX(x86_cpu_microcode_mutex);
+/*
+ * Save this mc into mc_saved_data. So it will be loaded early when a CPU is
+ * hot added or resumes.
+ *
+ * Please make sure this mc should be a valid microcode patch before calling
+ * this function.
+ */
+int save_mc_for_early(u8 *mc)
+{
+	struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT];
+	unsigned int mc_saved_count_init;
+	unsigned int mc_saved_count;
+	struct microcode_intel **mc_saved;
+	int ret = 0;
+	int i;
+
+	/*
+	 * Hold hotplug lock so mc_saved_data is not accessed by a CPU in
+	 * hotplug.
+	 */
+	mutex_lock(&x86_cpu_microcode_mutex);
+
+	mc_saved_count_init = mc_saved_data.mc_saved_count;
+	mc_saved_count = mc_saved_data.mc_saved_count;
+	mc_saved = mc_saved_data.mc_saved;
+
+	if (mc_saved && mc_saved_count)
+		memcpy(mc_saved_tmp, mc_saved,
+		       mc_saved_count * sizeof(struct mirocode_intel *));
+	/*
+	 * Save the microcode patch mc in mc_save_tmp structure if it's a newer
+	 * version.
+	 */
+
+	_save_mc(mc_saved_tmp, mc, &mc_saved_count);
+
+	/*
+	 * Save the mc_save_tmp in global mc_saved_data.
+	 */
+	ret = save_microcode(&mc_saved_data, mc_saved_tmp, mc_saved_count);
+	if (ret) {
+		pr_err("Cannot save microcode patch.\n");
+		goto out;
+	}
+
+	show_saved_mc();
+
+	/*
+	 * Free old saved microcod data.
+	 */
+	if (mc_saved) {
+		for (i = 0; i < mc_saved_count_init; i++)
+			kfree(mc_saved[i]);
+		kfree(mc_saved);
+	}
+
+out:
+	mutex_unlock(&x86_cpu_microcode_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(save_mc_for_early);
+#endif
+
+static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin";
+static __init enum ucode_state
+scan_microcode(unsigned long start, unsigned long end,
+		struct mc_saved_data *mc_saved_data,
+		unsigned long *mc_saved_in_initrd,
+		struct ucode_cpu_info *uci)
+{
+	unsigned int size = end - start + 1;
+	struct cpio_data cd;
+	long offset = 0;
+#ifdef CONFIG_X86_32
+	char *p = (char *)__pa_nodebug(ucode_name);
+#else
+	char *p = ucode_name;
+#endif
+
+	cd.data = NULL;
+	cd.size = 0;
+
+	cd = find_cpio_data(p, (void *)start, size, &offset);
+	if (!cd.data)
+		return UCODE_ERROR;
+
+
+	return get_matching_model_microcode(0, start, cd.data, cd.size,
+					    mc_saved_data, mc_saved_in_initrd,
+					    uci);
+}
+
+/*
+ * Print ucode update info.
+ */
+static void
+print_ucode_info(struct ucode_cpu_info *uci, unsigned int date)
+{
+	int cpu = smp_processor_id();
+
+	pr_info("CPU%d microcode updated early to revision 0x%x, date = %04x-%02x-%02x\n",
+		cpu,
+		uci->cpu_sig.rev,
+		date & 0xffff,
+		date >> 24,
+		(date >> 16) & 0xff);
+}
+
+#ifdef CONFIG_X86_32
+
+static int delay_ucode_info;
+static int current_mc_date;
+
+/*
+ * Print early updated ucode info after printk works. This is delayed info dump.
+ */
+void show_ucode_info_early(void)
+{
+	struct ucode_cpu_info uci;
+
+	if (delay_ucode_info) {
+		collect_cpu_info_early(&uci);
+		print_ucode_info(&uci, current_mc_date);
+		delay_ucode_info = 0;
+	}
+}
+
+/*
+ * At this point, we can not call printk() yet. Keep microcode patch number in
+ * mc_saved_data.mc_saved and delay printing microcode info in
+ * show_ucode_info_early() until printk() works.
+ */
+static void print_ucode(struct ucode_cpu_info *uci)
+{
+	struct microcode_intel *mc_intel;
+	int *delay_ucode_info_p;
+	int *current_mc_date_p;
+
+	mc_intel = uci->mc;
+	if (mc_intel == NULL)
+		return;
+
+	delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info);
+	current_mc_date_p = (int *)__pa_nodebug(&current_mc_date);
+
+	*delay_ucode_info_p = 1;
+	*current_mc_date_p = mc_intel->hdr.date;
+}
+#else
+
+/*
+ * Flush global tlb. We only do this in x86_64 where paging has been enabled
+ * already and PGE should be enabled as well.
+ */
+static inline void flush_tlb_early(void)
+{
+	__native_flush_tlb_global_irq_disabled();
+}
+
+static inline void print_ucode(struct ucode_cpu_info *uci)
+{
+	struct microcode_intel *mc_intel;
+
+	mc_intel = uci->mc;
+	if (mc_intel == NULL)
+		return;
+
+	print_ucode_info(uci, mc_intel->hdr.date);
+}
+#endif
+
+static int apply_microcode_early(struct mc_saved_data *mc_saved_data,
+				 struct ucode_cpu_info *uci)
+{
+	struct microcode_intel *mc_intel;
+	unsigned int val[2];
+
+	mc_intel = uci->mc;
+	if (mc_intel == NULL)
+		return 0;
+
+	/* write microcode via MSR 0x79 */
+	native_wrmsr(MSR_IA32_UCODE_WRITE,
+	      (unsigned long) mc_intel->bits,
+	      (unsigned long) mc_intel->bits >> 16 >> 16);
+	native_wrmsr(MSR_IA32_UCODE_REV, 0, 0);
+
+	/* As documented in the SDM: Do a CPUID 1 here */
+	sync_core();
+
+	/* get the current revision from MSR 0x8B */
+	native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
+	if (val[1] != mc_intel->hdr.rev)
+		return -1;
+
+#ifdef CONFIG_X86_64
+	/* Flush global tlb. This is precaution. */
+	flush_tlb_early();
+#endif
+	uci->cpu_sig.rev = val[1];
+
+	print_ucode(uci);
+
+	return 0;
+}
+
+/*
+ * This function converts microcode patch offsets previously stored in
+ * mc_saved_in_initrd to pointers and stores the pointers in mc_saved_data.
+ */
+int __init save_microcode_in_initrd_intel(void)
+{
+	unsigned int count = mc_saved_data.mc_saved_count;
+	struct microcode_intel *mc_saved[MAX_UCODE_COUNT];
+	int ret = 0;
+
+	if (count == 0)
+		return ret;
+
+	microcode_pointer(mc_saved, mc_saved_in_initrd, initrd_start, count);
+	ret = save_microcode(&mc_saved_data, mc_saved, count);
+	if (ret)
+		pr_err("Cannot save microcode patches from initrd.\n");
+
+	show_saved_mc();
+
+	return ret;
+}
+
+static void __init
+_load_ucode_intel_bsp(struct mc_saved_data *mc_saved_data,
+		      unsigned long *mc_saved_in_initrd,
+		      unsigned long initrd_start_early,
+		      unsigned long initrd_end_early,
+		      struct ucode_cpu_info *uci)
+{
+	collect_cpu_info_early(uci);
+	scan_microcode(initrd_start_early, initrd_end_early, mc_saved_data,
+		       mc_saved_in_initrd, uci);
+	load_microcode(mc_saved_data, mc_saved_in_initrd,
+		       initrd_start_early, uci);
+	apply_microcode_early(mc_saved_data, uci);
+}
+
+void __init
+load_ucode_intel_bsp(void)
+{
+	u64 ramdisk_image, ramdisk_size;
+	unsigned long initrd_start_early, initrd_end_early;
+	struct ucode_cpu_info uci;
+#ifdef CONFIG_X86_32
+	struct boot_params *boot_params_p;
+
+	boot_params_p = (struct boot_params *)__pa_nodebug(&boot_params);
+	ramdisk_image = boot_params_p->hdr.ramdisk_image;
+	ramdisk_size  = boot_params_p->hdr.ramdisk_size;
+	initrd_start_early = ramdisk_image;
+	initrd_end_early = initrd_start_early + ramdisk_size;
+
+	_load_ucode_intel_bsp(
+		(struct mc_saved_data *)__pa_nodebug(&mc_saved_data),
+		(unsigned long *)__pa_nodebug(&mc_saved_in_initrd),
+		initrd_start_early, initrd_end_early, &uci);
+#else
+	ramdisk_image = boot_params.hdr.ramdisk_image;
+	ramdisk_size  = boot_params.hdr.ramdisk_size;
+	initrd_start_early = ramdisk_image + PAGE_OFFSET;
+	initrd_end_early = initrd_start_early + ramdisk_size;
+
+	_load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd,
+			      initrd_start_early, initrd_end_early, &uci);
+#endif
+}
+
+void load_ucode_intel_ap(void)
+{
+	struct mc_saved_data *mc_saved_data_p;
+	struct ucode_cpu_info uci;
+	unsigned long *mc_saved_in_initrd_p;
+	unsigned long initrd_start_addr;
+#ifdef CONFIG_X86_32
+	unsigned long *initrd_start_p;
+
+	mc_saved_in_initrd_p =
+		(unsigned long *)__pa_nodebug(mc_saved_in_initrd);
+	mc_saved_data_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data);
+	initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start);
+	initrd_start_addr = (unsigned long)__pa_nodebug(*initrd_start_p);
+#else
+	mc_saved_data_p = &mc_saved_data;
+	mc_saved_in_initrd_p = mc_saved_in_initrd;
+	initrd_start_addr = initrd_start;
+#endif
+
+	/*
+	 * If there is no valid ucode previously saved in memory, no need to
+	 * update ucode on this AP.
+	 */
+	if (mc_saved_data_p->mc_saved_count == 0)
+		return;
+
+	collect_cpu_info_early(&uci);
+	load_microcode(mc_saved_data_p, mc_saved_in_initrd_p,
+		       initrd_start_addr, &uci);
+	apply_microcode_early(mc_saved_data_p, &uci);
+}
diff --git a/arch/x86/kernel/cpu/microcode/intel_lib.c b/arch/x86/kernel/cpu/microcode/intel_lib.c
new file mode 100644
index 0000000..ce69320
--- /dev/null
+++ b/arch/x86/kernel/cpu/microcode/intel_lib.c
@@ -0,0 +1,174 @@
+/*
+ *	Intel CPU Microcode Update Driver for Linux
+ *
+ *	Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com>
+ *			   H Peter Anvin" <hpa@zytor.com>
+ *
+ *	This driver allows to upgrade microcode on Intel processors
+ *	belonging to IA-32 family - PentiumPro, Pentium II,
+ *	Pentium III, Xeon, Pentium 4, etc.
+ *
+ *	Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
+ *	Software Developer's Manual
+ *	Order Number 253668 or free download from:
+ *
+ *	http://developer.intel.com/Assets/PDF/manual/253668.pdf
+ *
+ *	For more information, go to http://www.urbanmyth.org/microcode
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License
+ *	as published by the Free Software Foundation; either version
+ *	2 of the License, or (at your option) any later version.
+ *
+ */
+#include <linux/firmware.h>
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/microcode_intel.h>
+#include <asm/processor.h>
+#include <asm/msr.h>
+
+static inline int
+update_match_cpu(unsigned int csig, unsigned int cpf,
+		 unsigned int sig, unsigned int pf)
+{
+	return (!sigmatch(sig, csig, pf, cpf)) ? 0 : 1;
+}
+
+int
+update_match_revision(struct microcode_header_intel *mc_header, int rev)
+{
+	return (mc_header->rev <= rev) ? 0 : 1;
+}
+
+int microcode_sanity_check(void *mc, int print_err)
+{
+	unsigned long total_size, data_size, ext_table_size;
+	struct microcode_header_intel *mc_header = mc;
+	struct extended_sigtable *ext_header = NULL;
+	int sum, orig_sum, ext_sigcount = 0, i;
+	struct extended_signature *ext_sig;
+
+	total_size = get_totalsize(mc_header);
+	data_size = get_datasize(mc_header);
+
+	if (data_size + MC_HEADER_SIZE > total_size) {
+		if (print_err)
+			pr_err("error! Bad data size in microcode data file\n");
+		return -EINVAL;
+	}
+
+	if (mc_header->ldrver != 1 || mc_header->hdrver != 1) {
+		if (print_err)
+			pr_err("error! Unknown microcode update format\n");
+		return -EINVAL;
+	}
+	ext_table_size = total_size - (MC_HEADER_SIZE + data_size);
+	if (ext_table_size) {
+		if ((ext_table_size < EXT_HEADER_SIZE)
+		 || ((ext_table_size - EXT_HEADER_SIZE) % EXT_SIGNATURE_SIZE)) {
+			if (print_err)
+				pr_err("error! Small exttable size in microcode data file\n");
+			return -EINVAL;
+		}
+		ext_header = mc + MC_HEADER_SIZE + data_size;
+		if (ext_table_size != exttable_size(ext_header)) {
+			if (print_err)
+				pr_err("error! Bad exttable size in microcode data file\n");
+			return -EFAULT;
+		}
+		ext_sigcount = ext_header->count;
+	}
+
+	/* check extended table checksum */
+	if (ext_table_size) {
+		int ext_table_sum = 0;
+		int *ext_tablep = (int *)ext_header;
+
+		i = ext_table_size / DWSIZE;
+		while (i--)
+			ext_table_sum += ext_tablep[i];
+		if (ext_table_sum) {
+			if (print_err)
+				pr_warn("aborting, bad extended signature table checksum\n");
+			return -EINVAL;
+		}
+	}
+
+	/* calculate the checksum */
+	orig_sum = 0;
+	i = (MC_HEADER_SIZE + data_size) / DWSIZE;
+	while (i--)
+		orig_sum += ((int *)mc)[i];
+	if (orig_sum) {
+		if (print_err)
+			pr_err("aborting, bad checksum\n");
+		return -EINVAL;
+	}
+	if (!ext_table_size)
+		return 0;
+	/* check extended signature checksum */
+	for (i = 0; i < ext_sigcount; i++) {
+		ext_sig = (void *)ext_header + EXT_HEADER_SIZE +
+			  EXT_SIGNATURE_SIZE * i;
+		sum = orig_sum
+			- (mc_header->sig + mc_header->pf + mc_header->cksum)
+			+ (ext_sig->sig + ext_sig->pf + ext_sig->cksum);
+		if (sum) {
+			if (print_err)
+				pr_err("aborting, bad checksum\n");
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(microcode_sanity_check);
+
+/*
+ * return 0 - no update found
+ * return 1 - found update
+ */
+int get_matching_sig(unsigned int csig, int cpf, void *mc, int rev)
+{
+	struct microcode_header_intel *mc_header = mc;
+	struct extended_sigtable *ext_header;
+	unsigned long total_size = get_totalsize(mc_header);
+	int ext_sigcount, i;
+	struct extended_signature *ext_sig;
+
+	if (update_match_cpu(csig, cpf, mc_header->sig, mc_header->pf))
+		return 1;
+
+	/* Look for ext. headers: */
+	if (total_size <= get_datasize(mc_header) + MC_HEADER_SIZE)
+		return 0;
+
+	ext_header = mc + get_datasize(mc_header) + MC_HEADER_SIZE;
+	ext_sigcount = ext_header->count;
+	ext_sig = (void *)ext_header + EXT_HEADER_SIZE;
+
+	for (i = 0; i < ext_sigcount; i++) {
+		if (update_match_cpu(csig, cpf, ext_sig->sig, ext_sig->pf))
+			return 1;
+		ext_sig++;
+	}
+	return 0;
+}
+
+/*
+ * return 0 - no update found
+ * return 1 - found update
+ */
+int get_matching_microcode(unsigned int csig, int cpf, void *mc, int rev)
+{
+	struct microcode_header_intel *mc_header = mc;
+
+	if (!update_match_revision(mc_header, rev))
+		return 0;
+
+	return get_matching_sig(csig, cpf, mc, rev);
+}
+EXPORT_SYMBOL_GPL(get_matching_microcode);
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
deleted file mode 100644
index 4a6ff74..0000000
--- a/arch/x86/kernel/microcode_amd.c
+++ /dev/null
@@ -1,492 +0,0 @@
-/*
- *  AMD CPU Microcode Update Driver for Linux
- *  Copyright (C) 2008-2011 Advanced Micro Devices Inc.
- *
- *  Author: Peter Oruba <peter.oruba@amd.com>
- *
- *  Based on work by:
- *  Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
- *
- *  Maintainers:
- *  Andreas Herrmann <herrmann.der.user@googlemail.com>
- *  Borislav Petkov <bp@alien8.de>
- *
- *  This driver allows to upgrade microcode on F10h AMD
- *  CPUs and later.
- *
- *  Licensed under the terms of the GNU General Public
- *  License version 2. See file COPYING for details.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/firmware.h>
-#include <linux/pci_ids.h>
-#include <linux/uaccess.h>
-#include <linux/vmalloc.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/pci.h>
-
-#include <asm/microcode.h>
-#include <asm/processor.h>
-#include <asm/msr.h>
-#include <asm/microcode_amd.h>
-
-MODULE_DESCRIPTION("AMD Microcode Update Driver");
-MODULE_AUTHOR("Peter Oruba");
-MODULE_LICENSE("GPL v2");
-
-static struct equiv_cpu_entry *equiv_cpu_table;
-
-struct ucode_patch {
-	struct list_head plist;
-	void *data;
-	u32 patch_id;
-	u16 equiv_cpu;
-};
-
-static LIST_HEAD(pcache);
-
-static u16 __find_equiv_id(unsigned int cpu)
-{
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	return find_equiv_id(equiv_cpu_table, uci->cpu_sig.sig);
-}
-
-static u32 find_cpu_family_by_equiv_cpu(u16 equiv_cpu)
-{
-	int i = 0;
-
-	BUG_ON(!equiv_cpu_table);
-
-	while (equiv_cpu_table[i].equiv_cpu != 0) {
-		if (equiv_cpu == equiv_cpu_table[i].equiv_cpu)
-			return equiv_cpu_table[i].installed_cpu;
-		i++;
-	}
-	return 0;
-}
-
-/*
- * a small, trivial cache of per-family ucode patches
- */
-static struct ucode_patch *cache_find_patch(u16 equiv_cpu)
-{
-	struct ucode_patch *p;
-
-	list_for_each_entry(p, &pcache, plist)
-		if (p->equiv_cpu == equiv_cpu)
-			return p;
-	return NULL;
-}
-
-static void update_cache(struct ucode_patch *new_patch)
-{
-	struct ucode_patch *p;
-
-	list_for_each_entry(p, &pcache, plist) {
-		if (p->equiv_cpu == new_patch->equiv_cpu) {
-			if (p->patch_id >= new_patch->patch_id)
-				/* we already have the latest patch */
-				return;
-
-			list_replace(&p->plist, &new_patch->plist);
-			kfree(p->data);
-			kfree(p);
-			return;
-		}
-	}
-	/* no patch found, add it */
-	list_add_tail(&new_patch->plist, &pcache);
-}
-
-static void free_cache(void)
-{
-	struct ucode_patch *p, *tmp;
-
-	list_for_each_entry_safe(p, tmp, &pcache, plist) {
-		__list_del(p->plist.prev, p->plist.next);
-		kfree(p->data);
-		kfree(p);
-	}
-}
-
-static struct ucode_patch *find_patch(unsigned int cpu)
-{
-	u16 equiv_id;
-
-	equiv_id = __find_equiv_id(cpu);
-	if (!equiv_id)
-		return NULL;
-
-	return cache_find_patch(equiv_id);
-}
-
-static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
-{
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	struct ucode_patch *p;
-
-	csig->sig = cpuid_eax(0x00000001);
-	csig->rev = c->microcode;
-
-	/*
-	 * a patch could have been loaded early, set uci->mc so that
-	 * mc_bp_resume() can call apply_microcode()
-	 */
-	p = find_patch(cpu);
-	if (p && (p->patch_id == csig->rev))
-		uci->mc = p->data;
-
-	pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev);
-
-	return 0;
-}
-
-static unsigned int verify_patch_size(u8 family, u32 patch_size,
-				      unsigned int size)
-{
-	u32 max_size;
-
-#define F1XH_MPB_MAX_SIZE 2048
-#define F14H_MPB_MAX_SIZE 1824
-#define F15H_MPB_MAX_SIZE 4096
-#define F16H_MPB_MAX_SIZE 3458
-
-	switch (family) {
-	case 0x14:
-		max_size = F14H_MPB_MAX_SIZE;
-		break;
-	case 0x15:
-		max_size = F15H_MPB_MAX_SIZE;
-		break;
-	case 0x16:
-		max_size = F16H_MPB_MAX_SIZE;
-		break;
-	default:
-		max_size = F1XH_MPB_MAX_SIZE;
-		break;
-	}
-
-	if (patch_size > min_t(u32, size, max_size)) {
-		pr_err("patch size mismatch\n");
-		return 0;
-	}
-
-	return patch_size;
-}
-
-int __apply_microcode_amd(struct microcode_amd *mc_amd)
-{
-	u32 rev, dummy;
-
-	native_wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code);
-
-	/* verify patch application was successful */
-	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-	if (rev != mc_amd->hdr.patch_id)
-		return -1;
-
-	return 0;
-}
-
-int apply_microcode_amd(int cpu)
-{
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
-	struct microcode_amd *mc_amd;
-	struct ucode_cpu_info *uci;
-	struct ucode_patch *p;
-	u32 rev, dummy;
-
-	BUG_ON(raw_smp_processor_id() != cpu);
-
-	uci = ucode_cpu_info + cpu;
-
-	p = find_patch(cpu);
-	if (!p)
-		return 0;
-
-	mc_amd  = p->data;
-	uci->mc = p->data;
-
-	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-
-	/* need to apply patch? */
-	if (rev >= mc_amd->hdr.patch_id) {
-		c->microcode = rev;
-		uci->cpu_sig.rev = rev;
-		return 0;
-	}
-
-	if (__apply_microcode_amd(mc_amd)) {
-		pr_err("CPU%d: update failed for patch_level=0x%08x\n",
-			cpu, mc_amd->hdr.patch_id);
-		return -1;
-	}
-	pr_info("CPU%d: new patch_level=0x%08x\n", cpu,
-		mc_amd->hdr.patch_id);
-
-	uci->cpu_sig.rev = mc_amd->hdr.patch_id;
-	c->microcode = mc_amd->hdr.patch_id;
-
-	return 0;
-}
-
-static int install_equiv_cpu_table(const u8 *buf)
-{
-	unsigned int *ibuf = (unsigned int *)buf;
-	unsigned int type = ibuf[1];
-	unsigned int size = ibuf[2];
-
-	if (type != UCODE_EQUIV_CPU_TABLE_TYPE || !size) {
-		pr_err("empty section/"
-		       "invalid type field in container file section header\n");
-		return -EINVAL;
-	}
-
-	equiv_cpu_table = vmalloc(size);
-	if (!equiv_cpu_table) {
-		pr_err("failed to allocate equivalent CPU table\n");
-		return -ENOMEM;
-	}
-
-	memcpy(equiv_cpu_table, buf + CONTAINER_HDR_SZ, size);
-
-	/* add header length */
-	return size + CONTAINER_HDR_SZ;
-}
-
-static void free_equiv_cpu_table(void)
-{
-	vfree(equiv_cpu_table);
-	equiv_cpu_table = NULL;
-}
-
-static void cleanup(void)
-{
-	free_equiv_cpu_table();
-	free_cache();
-}
-
-/*
- * We return the current size even if some of the checks failed so that
- * we can skip over the next patch. If we return a negative value, we
- * signal a grave error like a memory allocation has failed and the
- * driver cannot continue functioning normally. In such cases, we tear
- * down everything we've used up so far and exit.
- */
-static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover)
-{
-	struct microcode_header_amd *mc_hdr;
-	struct ucode_patch *patch;
-	unsigned int patch_size, crnt_size, ret;
-	u32 proc_fam;
-	u16 proc_id;
-
-	patch_size  = *(u32 *)(fw + 4);
-	crnt_size   = patch_size + SECTION_HDR_SIZE;
-	mc_hdr	    = (struct microcode_header_amd *)(fw + SECTION_HDR_SIZE);
-	proc_id	    = mc_hdr->processor_rev_id;
-
-	proc_fam = find_cpu_family_by_equiv_cpu(proc_id);
-	if (!proc_fam) {
-		pr_err("No patch family for equiv ID: 0x%04x\n", proc_id);
-		return crnt_size;
-	}
-
-	/* check if patch is for the current family */
-	proc_fam = ((proc_fam >> 8) & 0xf) + ((proc_fam >> 20) & 0xff);
-	if (proc_fam != family)
-		return crnt_size;
-
-	if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) {
-		pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n",
-			mc_hdr->patch_id);
-		return crnt_size;
-	}
-
-	ret = verify_patch_size(family, patch_size, leftover);
-	if (!ret) {
-		pr_err("Patch-ID 0x%08x: size mismatch.\n", mc_hdr->patch_id);
-		return crnt_size;
-	}
-
-	patch = kzalloc(sizeof(*patch), GFP_KERNEL);
-	if (!patch) {
-		pr_err("Patch allocation failure.\n");
-		return -EINVAL;
-	}
-
-	patch->data = kzalloc(patch_size, GFP_KERNEL);
-	if (!patch->data) {
-		pr_err("Patch data allocation failure.\n");
-		kfree(patch);
-		return -EINVAL;
-	}
-
-	/* All looks ok, copy patch... */
-	memcpy(patch->data, fw + SECTION_HDR_SIZE, patch_size);
-	INIT_LIST_HEAD(&patch->plist);
-	patch->patch_id  = mc_hdr->patch_id;
-	patch->equiv_cpu = proc_id;
-
-	pr_debug("%s: Added patch_id: 0x%08x, proc_id: 0x%04x\n",
-		 __func__, patch->patch_id, proc_id);
-
-	/* ... and add to cache. */
-	update_cache(patch);
-
-	return crnt_size;
-}
-
-static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
-					     size_t size)
-{
-	enum ucode_state ret = UCODE_ERROR;
-	unsigned int leftover;
-	u8 *fw = (u8 *)data;
-	int crnt_size = 0;
-	int offset;
-
-	offset = install_equiv_cpu_table(data);
-	if (offset < 0) {
-		pr_err("failed to create equivalent cpu table\n");
-		return ret;
-	}
-	fw += offset;
-	leftover = size - offset;
-
-	if (*(u32 *)fw != UCODE_UCODE_TYPE) {
-		pr_err("invalid type field in container file section header\n");
-		free_equiv_cpu_table();
-		return ret;
-	}
-
-	while (leftover) {
-		crnt_size = verify_and_add_patch(family, fw, leftover);
-		if (crnt_size < 0)
-			return ret;
-
-		fw	 += crnt_size;
-		leftover -= crnt_size;
-	}
-
-	return UCODE_OK;
-}
-
-enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size)
-{
-	enum ucode_state ret;
-
-	/* free old equiv table */
-	free_equiv_cpu_table();
-
-	ret = __load_microcode_amd(family, data, size);
-
-	if (ret != UCODE_OK)
-		cleanup();
-
-#if defined(CONFIG_MICROCODE_AMD_EARLY) && defined(CONFIG_X86_32)
-	/* save BSP's matching patch for early load */
-	if (cpu_data(smp_processor_id()).cpu_index == boot_cpu_data.cpu_index) {
-		struct ucode_patch *p = find_patch(smp_processor_id());
-		if (p) {
-			memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
-			memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data),
-							       PATCH_MAX_SIZE));
-		}
-	}
-#endif
-	return ret;
-}
-
-/*
- * AMD microcode firmware naming convention, up to family 15h they are in
- * the legacy file:
- *
- *    amd-ucode/microcode_amd.bin
- *
- * This legacy file is always smaller than 2K in size.
- *
- * Beginning with family 15h, they are in family-specific firmware files:
- *
- *    amd-ucode/microcode_amd_fam15h.bin
- *    amd-ucode/microcode_amd_fam16h.bin
- *    ...
- *
- * These might be larger than 2K.
- */
-static enum ucode_state request_microcode_amd(int cpu, struct device *device,
-					      bool refresh_fw)
-{
-	char fw_name[36] = "amd-ucode/microcode_amd.bin";
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
-	enum ucode_state ret = UCODE_NFOUND;
-	const struct firmware *fw;
-
-	/* reload ucode container only on the boot cpu */
-	if (!refresh_fw || c->cpu_index != boot_cpu_data.cpu_index)
-		return UCODE_OK;
-
-	if (c->x86 >= 0x15)
-		snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86);
-
-	if (request_firmware(&fw, (const char *)fw_name, device)) {
-		pr_debug("failed to load file %s\n", fw_name);
-		goto out;
-	}
-
-	ret = UCODE_ERROR;
-	if (*(u32 *)fw->data != UCODE_MAGIC) {
-		pr_err("invalid magic value (0x%08x)\n", *(u32 *)fw->data);
-		goto fw_release;
-	}
-
-	ret = load_microcode_amd(c->x86, fw->data, fw->size);
-
- fw_release:
-	release_firmware(fw);
-
- out:
-	return ret;
-}
-
-static enum ucode_state
-request_microcode_user(int cpu, const void __user *buf, size_t size)
-{
-	return UCODE_ERROR;
-}
-
-static void microcode_fini_cpu_amd(int cpu)
-{
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-
-	uci->mc = NULL;
-}
-
-static struct microcode_ops microcode_amd_ops = {
-	.request_microcode_user           = request_microcode_user,
-	.request_microcode_fw             = request_microcode_amd,
-	.collect_cpu_info                 = collect_cpu_info_amd,
-	.apply_microcode                  = apply_microcode_amd,
-	.microcode_fini_cpu               = microcode_fini_cpu_amd,
-};
-
-struct microcode_ops * __init init_amd_microcode(void)
-{
-	struct cpuinfo_x86 *c = &cpu_data(0);
-
-	if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) {
-		pr_warning("AMD CPU family 0x%x not supported\n", c->x86);
-		return NULL;
-	}
-
-	return &microcode_amd_ops;
-}
-
-void __exit exit_amd_microcode(void)
-{
-	cleanup();
-}
diff --git a/arch/x86/kernel/microcode_amd_early.c b/arch/x86/kernel/microcode_amd_early.c
deleted file mode 100644
index 8384c0f..0000000
--- a/arch/x86/kernel/microcode_amd_early.c
+++ /dev/null
@@ -1,380 +0,0 @@
-/*
- * Copyright (C) 2013 Advanced Micro Devices, Inc.
- *
- * Author: Jacob Shin <jacob.shin@amd.com>
- * Fixes: Borislav Petkov <bp@suse.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/earlycpio.h>
-#include <linux/initrd.h>
-
-#include <asm/cpu.h>
-#include <asm/setup.h>
-#include <asm/microcode_amd.h>
-
-/*
- * This points to the current valid container of microcode patches which we will
- * save from the initrd before jettisoning its contents.
- */
-static u8 *container;
-static size_t container_size;
-
-static u32 ucode_new_rev;
-u8 amd_ucode_patch[PATCH_MAX_SIZE];
-static u16 this_equiv_id;
-
-struct cpio_data ucode_cpio;
-
-/*
- * Microcode patch container file is prepended to the initrd in cpio format.
- * See Documentation/x86/early-microcode.txt
- */
-static __initdata char ucode_path[] = "kernel/x86/microcode/AuthenticAMD.bin";
-
-static struct cpio_data __init find_ucode_in_initrd(void)
-{
-	long offset = 0;
-	char *path;
-	void *start;
-	size_t size;
-
-#ifdef CONFIG_X86_32
-	struct boot_params *p;
-
-	/*
-	 * On 32-bit, early load occurs before paging is turned on so we need
-	 * to use physical addresses.
-	 */
-	p       = (struct boot_params *)__pa_nodebug(&boot_params);
-	path    = (char *)__pa_nodebug(ucode_path);
-	start   = (void *)p->hdr.ramdisk_image;
-	size    = p->hdr.ramdisk_size;
-#else
-	path    = ucode_path;
-	start   = (void *)(boot_params.hdr.ramdisk_image + PAGE_OFFSET);
-	size    = boot_params.hdr.ramdisk_size;
-#endif
-
-	return find_cpio_data(path, start, size, &offset);
-}
-
-static size_t compute_container_size(u8 *data, u32 total_size)
-{
-	size_t size = 0;
-	u32 *header = (u32 *)data;
-
-	if (header[0] != UCODE_MAGIC ||
-	    header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */
-	    header[2] == 0)                            /* size */
-		return size;
-
-	size = header[2] + CONTAINER_HDR_SZ;
-	total_size -= size;
-	data += size;
-
-	while (total_size) {
-		u16 patch_size;
-
-		header = (u32 *)data;
-
-		if (header[0] != UCODE_UCODE_TYPE)
-			break;
-
-		/*
-		 * Sanity-check patch size.
-		 */
-		patch_size = header[1];
-		if (patch_size > PATCH_MAX_SIZE)
-			break;
-
-		size	   += patch_size + SECTION_HDR_SIZE;
-		data	   += patch_size + SECTION_HDR_SIZE;
-		total_size -= patch_size + SECTION_HDR_SIZE;
-	}
-
-	return size;
-}
-
-/*
- * Early load occurs before we can vmalloc(). So we look for the microcode
- * patch container file in initrd, traverse equivalent cpu table, look for a
- * matching microcode patch, and update, all in initrd memory in place.
- * When vmalloc() is available for use later -- on 64-bit during first AP load,
- * and on 32-bit during save_microcode_in_initrd_amd() -- we can call
- * load_microcode_amd() to save equivalent cpu table and microcode patches in
- * kernel heap memory.
- */
-static void apply_ucode_in_initrd(void *ucode, size_t size)
-{
-	struct equiv_cpu_entry *eq;
-	size_t *cont_sz;
-	u32 *header;
-	u8  *data, **cont;
-	u16 eq_id = 0;
-	int offset, left;
-	u32 rev, eax, ebx, ecx, edx;
-	u32 *new_rev;
-
-#ifdef CONFIG_X86_32
-	new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
-	cont_sz = (size_t *)__pa_nodebug(&container_size);
-	cont	= (u8 **)__pa_nodebug(&container);
-#else
-	new_rev = &ucode_new_rev;
-	cont_sz = &container_size;
-	cont	= &container;
-#endif
-
-	data   = ucode;
-	left   = size;
-	header = (u32 *)data;
-
-	/* find equiv cpu table */
-	if (header[0] != UCODE_MAGIC ||
-	    header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */
-	    header[2] == 0)                            /* size */
-		return;
-
-	eax = 0x00000001;
-	ecx = 0;
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-
-	while (left > 0) {
-		eq = (struct equiv_cpu_entry *)(data + CONTAINER_HDR_SZ);
-
-		*cont = data;
-
-		/* Advance past the container header */
-		offset = header[2] + CONTAINER_HDR_SZ;
-		data  += offset;
-		left  -= offset;
-
-		eq_id = find_equiv_id(eq, eax);
-		if (eq_id) {
-			this_equiv_id = eq_id;
-			*cont_sz = compute_container_size(*cont, left + offset);
-
-			/*
-			 * truncate how much we need to iterate over in the
-			 * ucode update loop below
-			 */
-			left = *cont_sz - offset;
-			break;
-		}
-
-		/*
-		 * support multiple container files appended together. if this
-		 * one does not have a matching equivalent cpu entry, we fast
-		 * forward to the next container file.
-		 */
-		while (left > 0) {
-			header = (u32 *)data;
-			if (header[0] == UCODE_MAGIC &&
-			    header[1] == UCODE_EQUIV_CPU_TABLE_TYPE)
-				break;
-
-			offset = header[1] + SECTION_HDR_SIZE;
-			data  += offset;
-			left  -= offset;
-		}
-
-		/* mark where the next microcode container file starts */
-		offset    = data - (u8 *)ucode;
-		ucode     = data;
-	}
-
-	if (!eq_id) {
-		*cont = NULL;
-		*cont_sz = 0;
-		return;
-	}
-
-	/* find ucode and update if needed */
-
-	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax);
-
-	while (left > 0) {
-		struct microcode_amd *mc;
-
-		header = (u32 *)data;
-		if (header[0] != UCODE_UCODE_TYPE || /* type */
-		    header[1] == 0)                  /* size */
-			break;
-
-		mc = (struct microcode_amd *)(data + SECTION_HDR_SIZE);
-
-		if (eq_id == mc->hdr.processor_rev_id && rev < mc->hdr.patch_id) {
-
-			if (!__apply_microcode_amd(mc)) {
-				rev = mc->hdr.patch_id;
-				*new_rev = rev;
-
-				/* save ucode patch */
-				memcpy(amd_ucode_patch, mc,
-				       min_t(u32, header[1], PATCH_MAX_SIZE));
-			}
-		}
-
-		offset  = header[1] + SECTION_HDR_SIZE;
-		data   += offset;
-		left   -= offset;
-	}
-}
-
-void __init load_ucode_amd_bsp(void)
-{
-	struct cpio_data cp;
-	void **data;
-	size_t *size;
-
-#ifdef CONFIG_X86_32
-	data =  (void **)__pa_nodebug(&ucode_cpio.data);
-	size = (size_t *)__pa_nodebug(&ucode_cpio.size);
-#else
-	data = &ucode_cpio.data;
-	size = &ucode_cpio.size;
-#endif
-
-	cp = find_ucode_in_initrd();
-	if (!cp.data)
-		return;
-
-	*data = cp.data;
-	*size = cp.size;
-
-	apply_ucode_in_initrd(cp.data, cp.size);
-}
-
-#ifdef CONFIG_X86_32
-/*
- * On 32-bit, since AP's early load occurs before paging is turned on, we
- * cannot traverse cpu_equiv_table and pcache in kernel heap memory. So during
- * cold boot, AP will apply_ucode_in_initrd() just like the BSP. During
- * save_microcode_in_initrd_amd() BSP's patch is copied to amd_ucode_patch,
- * which is used upon resume from suspend.
- */
-void load_ucode_amd_ap(void)
-{
-	struct microcode_amd *mc;
-	size_t *usize;
-	void **ucode;
-
-	mc = (struct microcode_amd *)__pa(amd_ucode_patch);
-	if (mc->hdr.patch_id && mc->hdr.processor_rev_id) {
-		__apply_microcode_amd(mc);
-		return;
-	}
-
-	ucode = (void *)__pa_nodebug(&container);
-	usize = (size_t *)__pa_nodebug(&container_size);
-
-	if (!*ucode || !*usize)
-		return;
-
-	apply_ucode_in_initrd(*ucode, *usize);
-}
-
-static void __init collect_cpu_sig_on_bsp(void *arg)
-{
-	unsigned int cpu = smp_processor_id();
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-
-	uci->cpu_sig.sig = cpuid_eax(0x00000001);
-}
-#else
-void load_ucode_amd_ap(void)
-{
-	unsigned int cpu = smp_processor_id();
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	struct equiv_cpu_entry *eq;
-	struct microcode_amd *mc;
-	u32 rev, eax;
-	u16 eq_id;
-
-	/* Exit if called on the BSP. */
-	if (!cpu)
-		return;
-
-	if (!container)
-		return;
-
-	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax);
-
-	uci->cpu_sig.rev = rev;
-	uci->cpu_sig.sig = eax;
-
-	eax = cpuid_eax(0x00000001);
-	eq  = (struct equiv_cpu_entry *)(container + CONTAINER_HDR_SZ);
-
-	eq_id = find_equiv_id(eq, eax);
-	if (!eq_id)
-		return;
-
-	if (eq_id == this_equiv_id) {
-		mc = (struct microcode_amd *)amd_ucode_patch;
-
-		if (mc && rev < mc->hdr.patch_id) {
-			if (!__apply_microcode_amd(mc))
-				ucode_new_rev = mc->hdr.patch_id;
-		}
-
-	} else {
-		if (!ucode_cpio.data)
-			return;
-
-		/*
-		 * AP has a different equivalence ID than BSP, looks like
-		 * mixed-steppings silicon so go through the ucode blob anew.
-		 */
-		apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size);
-	}
-}
-#endif
-
-int __init save_microcode_in_initrd_amd(void)
-{
-	enum ucode_state ret;
-	u32 eax;
-
-#ifdef CONFIG_X86_32
-	unsigned int bsp = boot_cpu_data.cpu_index;
-	struct ucode_cpu_info *uci = ucode_cpu_info + bsp;
-
-	if (!uci->cpu_sig.sig)
-		smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1);
-
-	/*
-	 * Take into account the fact that the ramdisk might get relocated
-	 * and therefore we need to recompute the container's position in
-	 * virtual memory space.
-	 */
-	container = (u8 *)(__va((u32)relocated_ramdisk) +
-			   ((u32)container - boot_params.hdr.ramdisk_image));
-#endif
-	if (ucode_new_rev)
-		pr_info("microcode: updated early to new patch_level=0x%08x\n",
-			ucode_new_rev);
-
-	if (!container)
-		return -EINVAL;
-
-	eax   = cpuid_eax(0x00000001);
-	eax   = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
-
-	ret = load_microcode_amd(eax, container, container_size);
-	if (ret != UCODE_OK)
-		return -EINVAL;
-
-	/*
-	 * This will be freed any msec now, stash patches for the current
-	 * family and switch to patch cache for cpu hotplug, etc later.
-	 */
-	container = NULL;
-	container_size = 0;
-
-	return 0;
-}
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
deleted file mode 100644
index 15c9876..0000000
--- a/arch/x86/kernel/microcode_core.c
+++ /dev/null
@@ -1,645 +0,0 @@
-/*
- *	Intel CPU Microcode Update Driver for Linux
- *
- *	Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
- *		      2006	Shaohua Li <shaohua.li@intel.com>
- *
- *	This driver allows to upgrade microcode on Intel processors
- *	belonging to IA-32 family - PentiumPro, Pentium II,
- *	Pentium III, Xeon, Pentium 4, etc.
- *
- *	Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
- *	Software Developer's Manual
- *	Order Number 253668 or free download from:
- *
- *	http://developer.intel.com/Assets/PDF/manual/253668.pdf	
- *
- *	For more information, go to http://www.urbanmyth.org/microcode
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- *
- *	1.0	16 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Initial release.
- *	1.01	18 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Added read() support + cleanups.
- *	1.02	21 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Added 'device trimming' support. open(O_WRONLY) zeroes
- *		and frees the saved copy of applied microcode.
- *	1.03	29 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Made to use devfs (/dev/cpu/microcode) + cleanups.
- *	1.04	06 Jun 2000, Simon Trimmer <simon@veritas.com>
- *		Added misc device support (now uses both devfs and misc).
- *		Added MICROCODE_IOCFREE ioctl to clear memory.
- *	1.05	09 Jun 2000, Simon Trimmer <simon@veritas.com>
- *		Messages for error cases (non Intel & no suitable microcode).
- *	1.06	03 Aug 2000, Tigran Aivazian <tigran@veritas.com>
- *		Removed ->release(). Removed exclusive open and status bitmap.
- *		Added microcode_rwsem to serialize read()/write()/ioctl().
- *		Removed global kernel lock usage.
- *	1.07	07 Sep 2000, Tigran Aivazian <tigran@veritas.com>
- *		Write 0 to 0x8B msr and then cpuid before reading revision,
- *		so that it works even if there were no update done by the
- *		BIOS. Otherwise, reading from 0x8B gives junk (which happened
- *		to be 0 on my machine which is why it worked even when I
- *		disabled update by the BIOS)
- *		Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix.
- *	1.08	11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and
- *			     Tigran Aivazian <tigran@veritas.com>
- *		Intel Pentium 4 processor support and bugfixes.
- *	1.09	30 Oct 2001, Tigran Aivazian <tigran@veritas.com>
- *		Bugfix for HT (Hyper-Threading) enabled processors
- *		whereby processor resources are shared by all logical processors
- *		in a single CPU package.
- *	1.10	28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and
- *		Tigran Aivazian <tigran@veritas.com>,
- *		Serialize updates as required on HT processors due to
- *		speculative nature of implementation.
- *	1.11	22 Mar 2002 Tigran Aivazian <tigran@veritas.com>
- *		Fix the panic when writing zero-length microcode chunk.
- *	1.12	29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>,
- *		Jun Nakajima <jun.nakajima@intel.com>
- *		Support for the microcode updates in the new format.
- *	1.13	10 Oct 2003 Tigran Aivazian <tigran@veritas.com>
- *		Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl
- *		because we no longer hold a copy of applied microcode
- *		in kernel memory.
- *	1.14	25 Jun 2004 Tigran Aivazian <tigran@veritas.com>
- *		Fix sigmatch() macro to handle old CPUs with pf == 0.
- *		Thanks to Stuart Swales for pointing out this bug.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/platform_device.h>
-#include <linux/miscdevice.h>
-#include <linux/capability.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/cpu.h>
-#include <linux/fs.h>
-#include <linux/mm.h>
-#include <linux/syscore_ops.h>
-
-#include <asm/microcode.h>
-#include <asm/processor.h>
-#include <asm/cpu_device_id.h>
-#include <asm/perf_event.h>
-
-MODULE_DESCRIPTION("Microcode Update Driver");
-MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>");
-MODULE_LICENSE("GPL");
-
-#define MICROCODE_VERSION	"2.00"
-
-static struct microcode_ops	*microcode_ops;
-
-/*
- * Synchronization.
- *
- * All non cpu-hotplug-callback call sites use:
- *
- * - microcode_mutex to synchronize with each other;
- * - get/put_online_cpus() to synchronize with
- *   the cpu-hotplug-callback call sites.
- *
- * We guarantee that only a single cpu is being
- * updated at any particular moment of time.
- */
-static DEFINE_MUTEX(microcode_mutex);
-
-struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
-EXPORT_SYMBOL_GPL(ucode_cpu_info);
-
-/*
- * Operations that are run on a target cpu:
- */
-
-struct cpu_info_ctx {
-	struct cpu_signature	*cpu_sig;
-	int			err;
-};
-
-static void collect_cpu_info_local(void *arg)
-{
-	struct cpu_info_ctx *ctx = arg;
-
-	ctx->err = microcode_ops->collect_cpu_info(smp_processor_id(),
-						   ctx->cpu_sig);
-}
-
-static int collect_cpu_info_on_target(int cpu, struct cpu_signature *cpu_sig)
-{
-	struct cpu_info_ctx ctx = { .cpu_sig = cpu_sig, .err = 0 };
-	int ret;
-
-	ret = smp_call_function_single(cpu, collect_cpu_info_local, &ctx, 1);
-	if (!ret)
-		ret = ctx.err;
-
-	return ret;
-}
-
-static int collect_cpu_info(int cpu)
-{
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	int ret;
-
-	memset(uci, 0, sizeof(*uci));
-
-	ret = collect_cpu_info_on_target(cpu, &uci->cpu_sig);
-	if (!ret)
-		uci->valid = 1;
-
-	return ret;
-}
-
-struct apply_microcode_ctx {
-	int err;
-};
-
-static void apply_microcode_local(void *arg)
-{
-	struct apply_microcode_ctx *ctx = arg;
-
-	ctx->err = microcode_ops->apply_microcode(smp_processor_id());
-}
-
-static int apply_microcode_on_target(int cpu)
-{
-	struct apply_microcode_ctx ctx = { .err = 0 };
-	int ret;
-
-	ret = smp_call_function_single(cpu, apply_microcode_local, &ctx, 1);
-	if (!ret)
-		ret = ctx.err;
-
-	return ret;
-}
-
-#ifdef CONFIG_MICROCODE_OLD_INTERFACE
-static int do_microcode_update(const void __user *buf, size_t size)
-{
-	int error = 0;
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-		enum ucode_state ustate;
-
-		if (!uci->valid)
-			continue;
-
-		ustate = microcode_ops->request_microcode_user(cpu, buf, size);
-		if (ustate == UCODE_ERROR) {
-			error = -1;
-			break;
-		} else if (ustate == UCODE_OK)
-			apply_microcode_on_target(cpu);
-	}
-
-	return error;
-}
-
-static int microcode_open(struct inode *inode, struct file *file)
-{
-	return capable(CAP_SYS_RAWIO) ? nonseekable_open(inode, file) : -EPERM;
-}
-
-static ssize_t microcode_write(struct file *file, const char __user *buf,
-			       size_t len, loff_t *ppos)
-{
-	ssize_t ret = -EINVAL;
-
-	if ((len >> PAGE_SHIFT) > totalram_pages) {
-		pr_err("too much data (max %ld pages)\n", totalram_pages);
-		return ret;
-	}
-
-	get_online_cpus();
-	mutex_lock(&microcode_mutex);
-
-	if (do_microcode_update(buf, len) == 0)
-		ret = (ssize_t)len;
-
-	if (ret > 0)
-		perf_check_microcode();
-
-	mutex_unlock(&microcode_mutex);
-	put_online_cpus();
-
-	return ret;
-}
-
-static const struct file_operations microcode_fops = {
-	.owner			= THIS_MODULE,
-	.write			= microcode_write,
-	.open			= microcode_open,
-	.llseek		= no_llseek,
-};
-
-static struct miscdevice microcode_dev = {
-	.minor			= MICROCODE_MINOR,
-	.name			= "microcode",
-	.nodename		= "cpu/microcode",
-	.fops			= &microcode_fops,
-};
-
-static int __init microcode_dev_init(void)
-{
-	int error;
-
-	error = misc_register(&microcode_dev);
-	if (error) {
-		pr_err("can't misc_register on minor=%d\n", MICROCODE_MINOR);
-		return error;
-	}
-
-	return 0;
-}
-
-static void __exit microcode_dev_exit(void)
-{
-	misc_deregister(&microcode_dev);
-}
-
-MODULE_ALIAS_MISCDEV(MICROCODE_MINOR);
-MODULE_ALIAS("devname:cpu/microcode");
-#else
-#define microcode_dev_init()	0
-#define microcode_dev_exit()	do { } while (0)
-#endif
-
-/* fake device for request_firmware */
-static struct platform_device	*microcode_pdev;
-
-static int reload_for_cpu(int cpu)
-{
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	enum ucode_state ustate;
-	int err = 0;
-
-	if (!uci->valid)
-		return err;
-
-	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev, true);
-	if (ustate == UCODE_OK)
-		apply_microcode_on_target(cpu);
-	else
-		if (ustate == UCODE_ERROR)
-			err = -EINVAL;
-	return err;
-}
-
-static ssize_t reload_store(struct device *dev,
-			    struct device_attribute *attr,
-			    const char *buf, size_t size)
-{
-	unsigned long val;
-	int cpu;
-	ssize_t ret = 0, tmp_ret;
-
-	ret = kstrtoul(buf, 0, &val);
-	if (ret)
-		return ret;
-
-	if (val != 1)
-		return size;
-
-	get_online_cpus();
-	mutex_lock(&microcode_mutex);
-	for_each_online_cpu(cpu) {
-		tmp_ret = reload_for_cpu(cpu);
-		if (tmp_ret != 0)
-			pr_warn("Error reloading microcode on CPU %d\n", cpu);
-
-		/* save retval of the first encountered reload error */
-		if (!ret)
-			ret = tmp_ret;
-	}
-	if (!ret)
-		perf_check_microcode();
-	mutex_unlock(&microcode_mutex);
-	put_online_cpus();
-
-	if (!ret)
-		ret = size;
-
-	return ret;
-}
-
-static ssize_t version_show(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	struct ucode_cpu_info *uci = ucode_cpu_info + dev->id;
-
-	return sprintf(buf, "0x%x\n", uci->cpu_sig.rev);
-}
-
-static ssize_t pf_show(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	struct ucode_cpu_info *uci = ucode_cpu_info + dev->id;
-
-	return sprintf(buf, "0x%x\n", uci->cpu_sig.pf);
-}
-
-static DEVICE_ATTR(reload, 0200, NULL, reload_store);
-static DEVICE_ATTR(version, 0400, version_show, NULL);
-static DEVICE_ATTR(processor_flags, 0400, pf_show, NULL);
-
-static struct attribute *mc_default_attrs[] = {
-	&dev_attr_version.attr,
-	&dev_attr_processor_flags.attr,
-	NULL
-};
-
-static struct attribute_group mc_attr_group = {
-	.attrs			= mc_default_attrs,
-	.name			= "microcode",
-};
-
-static void microcode_fini_cpu(int cpu)
-{
-	microcode_ops->microcode_fini_cpu(cpu);
-}
-
-static enum ucode_state microcode_resume_cpu(int cpu)
-{
-	pr_debug("CPU%d updated upon resume\n", cpu);
-
-	if (apply_microcode_on_target(cpu))
-		return UCODE_ERROR;
-
-	return UCODE_OK;
-}
-
-static enum ucode_state microcode_init_cpu(int cpu, bool refresh_fw)
-{
-	enum ucode_state ustate;
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-
-	if (uci && uci->valid)
-		return UCODE_OK;
-
-	if (collect_cpu_info(cpu))
-		return UCODE_ERROR;
-
-	/* --dimm. Trigger a delayed update? */
-	if (system_state != SYSTEM_RUNNING)
-		return UCODE_NFOUND;
-
-	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev,
-						     refresh_fw);
-
-	if (ustate == UCODE_OK) {
-		pr_debug("CPU%d updated upon init\n", cpu);
-		apply_microcode_on_target(cpu);
-	}
-
-	return ustate;
-}
-
-static enum ucode_state microcode_update_cpu(int cpu)
-{
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-
-	if (uci->valid)
-		return microcode_resume_cpu(cpu);
-
-	return microcode_init_cpu(cpu, false);
-}
-
-static int mc_device_add(struct device *dev, struct subsys_interface *sif)
-{
-	int err, cpu = dev->id;
-
-	if (!cpu_online(cpu))
-		return 0;
-
-	pr_debug("CPU%d added\n", cpu);
-
-	err = sysfs_create_group(&dev->kobj, &mc_attr_group);
-	if (err)
-		return err;
-
-	if (microcode_init_cpu(cpu, true) == UCODE_ERROR)
-		return -EINVAL;
-
-	return err;
-}
-
-static int mc_device_remove(struct device *dev, struct subsys_interface *sif)
-{
-	int cpu = dev->id;
-
-	if (!cpu_online(cpu))
-		return 0;
-
-	pr_debug("CPU%d removed\n", cpu);
-	microcode_fini_cpu(cpu);
-	sysfs_remove_group(&dev->kobj, &mc_attr_group);
-	return 0;
-}
-
-static struct subsys_interface mc_cpu_interface = {
-	.name			= "microcode",
-	.subsys			= &cpu_subsys,
-	.add_dev		= mc_device_add,
-	.remove_dev		= mc_device_remove,
-};
-
-/**
- * mc_bp_resume - Update boot CPU microcode during resume.
- */
-static void mc_bp_resume(void)
-{
-	int cpu = smp_processor_id();
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-
-	if (uci->valid && uci->mc)
-		microcode_ops->apply_microcode(cpu);
-}
-
-static struct syscore_ops mc_syscore_ops = {
-	.resume			= mc_bp_resume,
-};
-
-static int
-mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (unsigned long)hcpu;
-	struct device *dev;
-
-	dev = get_cpu_device(cpu);
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_ONLINE:
-		microcode_update_cpu(cpu);
-		pr_debug("CPU%d added\n", cpu);
-		/*
-		 * "break" is missing on purpose here because we want to fall
-		 * through in order to create the sysfs group.
-		 */
-
-	case CPU_DOWN_FAILED:
-		if (sysfs_create_group(&dev->kobj, &mc_attr_group))
-			pr_err("Failed to create group for CPU%d\n", cpu);
-		break;
-
-	case CPU_DOWN_PREPARE:
-		/* Suspend is in progress, only remove the interface */
-		sysfs_remove_group(&dev->kobj, &mc_attr_group);
-		pr_debug("CPU%d removed\n", cpu);
-		break;
-
-	/*
-	 * case CPU_DEAD:
-	 *
-	 * When a CPU goes offline, don't free up or invalidate the copy of
-	 * the microcode in kernel memory, so that we can reuse it when the
-	 * CPU comes back online without unnecessarily requesting the userspace
-	 * for it again.
-	 */
-	}
-
-	/* The CPU refused to come up during a system resume */
-	if (action == CPU_UP_CANCELED_FROZEN)
-		microcode_fini_cpu(cpu);
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block __refdata mc_cpu_notifier = {
-	.notifier_call	= mc_cpu_callback,
-};
-
-#ifdef MODULE
-/* Autoload on Intel and AMD systems */
-static const struct x86_cpu_id __initconst microcode_id[] = {
-#ifdef CONFIG_MICROCODE_INTEL
-	{ X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, },
-#endif
-#ifdef CONFIG_MICROCODE_AMD
-	{ X86_VENDOR_AMD, X86_FAMILY_ANY, X86_MODEL_ANY, },
-#endif
-	{}
-};
-MODULE_DEVICE_TABLE(x86cpu, microcode_id);
-#endif
-
-static struct attribute *cpu_root_microcode_attrs[] = {
-	&dev_attr_reload.attr,
-	NULL
-};
-
-static struct attribute_group cpu_root_microcode_group = {
-	.name  = "microcode",
-	.attrs = cpu_root_microcode_attrs,
-};
-
-static int __init microcode_init(void)
-{
-	struct cpuinfo_x86 *c = &cpu_data(0);
-	int error;
-
-	if (c->x86_vendor == X86_VENDOR_INTEL)
-		microcode_ops = init_intel_microcode();
-	else if (c->x86_vendor == X86_VENDOR_AMD)
-		microcode_ops = init_amd_microcode();
-	else
-		pr_err("no support for this CPU vendor\n");
-
-	if (!microcode_ops)
-		return -ENODEV;
-
-	microcode_pdev = platform_device_register_simple("microcode", -1,
-							 NULL, 0);
-	if (IS_ERR(microcode_pdev))
-		return PTR_ERR(microcode_pdev);
-
-	get_online_cpus();
-	mutex_lock(&microcode_mutex);
-
-	error = subsys_interface_register(&mc_cpu_interface);
-	if (!error)
-		perf_check_microcode();
-	mutex_unlock(&microcode_mutex);
-	put_online_cpus();
-
-	if (error)
-		goto out_pdev;
-
-	error = sysfs_create_group(&cpu_subsys.dev_root->kobj,
-				   &cpu_root_microcode_group);
-
-	if (error) {
-		pr_err("Error creating microcode group!\n");
-		goto out_driver;
-	}
-
-	error = microcode_dev_init();
-	if (error)
-		goto out_ucode_group;
-
-	register_syscore_ops(&mc_syscore_ops);
-	register_hotcpu_notifier(&mc_cpu_notifier);
-
-	pr_info("Microcode Update Driver: v" MICROCODE_VERSION
-		" <tigran@aivazian.fsnet.co.uk>, Peter Oruba\n");
-
-	return 0;
-
- out_ucode_group:
-	sysfs_remove_group(&cpu_subsys.dev_root->kobj,
-			   &cpu_root_microcode_group);
-
- out_driver:
-	get_online_cpus();
-	mutex_lock(&microcode_mutex);
-
-	subsys_interface_unregister(&mc_cpu_interface);
-
-	mutex_unlock(&microcode_mutex);
-	put_online_cpus();
-
- out_pdev:
-	platform_device_unregister(microcode_pdev);
-	return error;
-
-}
-module_init(microcode_init);
-
-static void __exit microcode_exit(void)
-{
-	struct cpuinfo_x86 *c = &cpu_data(0);
-
-	microcode_dev_exit();
-
-	unregister_hotcpu_notifier(&mc_cpu_notifier);
-	unregister_syscore_ops(&mc_syscore_ops);
-
-	sysfs_remove_group(&cpu_subsys.dev_root->kobj,
-			   &cpu_root_microcode_group);
-
-	get_online_cpus();
-	mutex_lock(&microcode_mutex);
-
-	subsys_interface_unregister(&mc_cpu_interface);
-
-	mutex_unlock(&microcode_mutex);
-	put_online_cpus();
-
-	platform_device_unregister(microcode_pdev);
-
-	microcode_ops = NULL;
-
-	if (c->x86_vendor == X86_VENDOR_AMD)
-		exit_amd_microcode();
-
-	pr_info("Microcode Update Driver: v" MICROCODE_VERSION " removed.\n");
-}
-module_exit(microcode_exit);
diff --git a/arch/x86/kernel/microcode_core_early.c b/arch/x86/kernel/microcode_core_early.c
deleted file mode 100644
index be7f851..0000000
--- a/arch/x86/kernel/microcode_core_early.c
+++ /dev/null
@@ -1,141 +0,0 @@
-/*
- *	X86 CPU microcode early update for Linux
- *
- *	Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com>
- *			   H Peter Anvin" <hpa@zytor.com>
- *
- *	This driver allows to early upgrade microcode on Intel processors
- *	belonging to IA-32 family - PentiumPro, Pentium II,
- *	Pentium III, Xeon, Pentium 4, etc.
- *
- *	Reference: Section 9.11 of Volume 3, IA-32 Intel Architecture
- *	Software Developer's Manual.
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- */
-#include <linux/module.h>
-#include <asm/microcode_intel.h>
-#include <asm/microcode_amd.h>
-#include <asm/processor.h>
-
-#define QCHAR(a, b, c, d) ((a) + ((b) << 8) + ((c) << 16) + ((d) << 24))
-#define CPUID_INTEL1 QCHAR('G', 'e', 'n', 'u')
-#define CPUID_INTEL2 QCHAR('i', 'n', 'e', 'I')
-#define CPUID_INTEL3 QCHAR('n', 't', 'e', 'l')
-#define CPUID_AMD1 QCHAR('A', 'u', 't', 'h')
-#define CPUID_AMD2 QCHAR('e', 'n', 't', 'i')
-#define CPUID_AMD3 QCHAR('c', 'A', 'M', 'D')
-
-#define CPUID_IS(a, b, c, ebx, ecx, edx)	\
-		(!((ebx ^ (a))|(edx ^ (b))|(ecx ^ (c))))
-
-/*
- * In early loading microcode phase on BSP, boot_cpu_data is not set up yet.
- * x86_vendor() gets vendor id for BSP.
- *
- * In 32 bit AP case, accessing boot_cpu_data needs linear address. To simplify
- * coding, we still use x86_vendor() to get vendor id for AP.
- *
- * x86_vendor() gets vendor information directly through cpuid.
- */
-static int x86_vendor(void)
-{
-	u32 eax = 0x00000000;
-	u32 ebx, ecx = 0, edx;
-
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-
-	if (CPUID_IS(CPUID_INTEL1, CPUID_INTEL2, CPUID_INTEL3, ebx, ecx, edx))
-		return X86_VENDOR_INTEL;
-
-	if (CPUID_IS(CPUID_AMD1, CPUID_AMD2, CPUID_AMD3, ebx, ecx, edx))
-		return X86_VENDOR_AMD;
-
-	return X86_VENDOR_UNKNOWN;
-}
-
-static int x86_family(void)
-{
-	u32 eax = 0x00000001;
-	u32 ebx, ecx = 0, edx;
-	int x86;
-
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-
-	x86 = (eax >> 8) & 0xf;
-	if (x86 == 15)
-		x86 += (eax >> 20) & 0xff;
-
-	return x86;
-}
-
-void __init load_ucode_bsp(void)
-{
-	int vendor, x86;
-
-	if (!have_cpuid_p())
-		return;
-
-	vendor = x86_vendor();
-	x86 = x86_family();
-
-	switch (vendor) {
-	case X86_VENDOR_INTEL:
-		if (x86 >= 6)
-			load_ucode_intel_bsp();
-		break;
-	case X86_VENDOR_AMD:
-		if (x86 >= 0x10)
-			load_ucode_amd_bsp();
-		break;
-	default:
-		break;
-	}
-}
-
-void load_ucode_ap(void)
-{
-	int vendor, x86;
-
-	if (!have_cpuid_p())
-		return;
-
-	vendor = x86_vendor();
-	x86 = x86_family();
-
-	switch (vendor) {
-	case X86_VENDOR_INTEL:
-		if (x86 >= 6)
-			load_ucode_intel_ap();
-		break;
-	case X86_VENDOR_AMD:
-		if (x86 >= 0x10)
-			load_ucode_amd_ap();
-		break;
-	default:
-		break;
-	}
-}
-
-int __init save_microcode_in_initrd(void)
-{
-	struct cpuinfo_x86 *c = &boot_cpu_data;
-
-	switch (c->x86_vendor) {
-	case X86_VENDOR_INTEL:
-		if (c->x86 >= 6)
-			save_microcode_in_initrd_intel();
-		break;
-	case X86_VENDOR_AMD:
-		if (c->x86 >= 0x10)
-			save_microcode_in_initrd_amd();
-		break;
-	default:
-		break;
-	}
-
-	return 0;
-}
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
deleted file mode 100644
index 5fb2ceb..0000000
--- a/arch/x86/kernel/microcode_intel.c
+++ /dev/null
@@ -1,333 +0,0 @@
-/*
- *	Intel CPU Microcode Update Driver for Linux
- *
- *	Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
- *		      2006	Shaohua Li <shaohua.li@intel.com>
- *
- *	This driver allows to upgrade microcode on Intel processors
- *	belonging to IA-32 family - PentiumPro, Pentium II,
- *	Pentium III, Xeon, Pentium 4, etc.
- *
- *	Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
- *	Software Developer's Manual
- *	Order Number 253668 or free download from:
- *
- *	http://developer.intel.com/Assets/PDF/manual/253668.pdf	
- *
- *	For more information, go to http://www.urbanmyth.org/microcode
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- *
- *	1.0	16 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Initial release.
- *	1.01	18 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Added read() support + cleanups.
- *	1.02	21 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Added 'device trimming' support. open(O_WRONLY) zeroes
- *		and frees the saved copy of applied microcode.
- *	1.03	29 Feb 2000, Tigran Aivazian <tigran@sco.com>
- *		Made to use devfs (/dev/cpu/microcode) + cleanups.
- *	1.04	06 Jun 2000, Simon Trimmer <simon@veritas.com>
- *		Added misc device support (now uses both devfs and misc).
- *		Added MICROCODE_IOCFREE ioctl to clear memory.
- *	1.05	09 Jun 2000, Simon Trimmer <simon@veritas.com>
- *		Messages for error cases (non Intel & no suitable microcode).
- *	1.06	03 Aug 2000, Tigran Aivazian <tigran@veritas.com>
- *		Removed ->release(). Removed exclusive open and status bitmap.
- *		Added microcode_rwsem to serialize read()/write()/ioctl().
- *		Removed global kernel lock usage.
- *	1.07	07 Sep 2000, Tigran Aivazian <tigran@veritas.com>
- *		Write 0 to 0x8B msr and then cpuid before reading revision,
- *		so that it works even if there were no update done by the
- *		BIOS. Otherwise, reading from 0x8B gives junk (which happened
- *		to be 0 on my machine which is why it worked even when I
- *		disabled update by the BIOS)
- *		Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix.
- *	1.08	11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and
- *			     Tigran Aivazian <tigran@veritas.com>
- *		Intel Pentium 4 processor support and bugfixes.
- *	1.09	30 Oct 2001, Tigran Aivazian <tigran@veritas.com>
- *		Bugfix for HT (Hyper-Threading) enabled processors
- *		whereby processor resources are shared by all logical processors
- *		in a single CPU package.
- *	1.10	28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and
- *		Tigran Aivazian <tigran@veritas.com>,
- *		Serialize updates as required on HT processors due to
- *		speculative nature of implementation.
- *	1.11	22 Mar 2002 Tigran Aivazian <tigran@veritas.com>
- *		Fix the panic when writing zero-length microcode chunk.
- *	1.12	29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>,
- *		Jun Nakajima <jun.nakajima@intel.com>
- *		Support for the microcode updates in the new format.
- *	1.13	10 Oct 2003 Tigran Aivazian <tigran@veritas.com>
- *		Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl
- *		because we no longer hold a copy of applied microcode
- *		in kernel memory.
- *	1.14	25 Jun 2004 Tigran Aivazian <tigran@veritas.com>
- *		Fix sigmatch() macro to handle old CPUs with pf == 0.
- *		Thanks to Stuart Swales for pointing out this bug.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/firmware.h>
-#include <linux/uaccess.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/vmalloc.h>
-
-#include <asm/microcode_intel.h>
-#include <asm/processor.h>
-#include <asm/msr.h>
-
-MODULE_DESCRIPTION("Microcode Update Driver");
-MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>");
-MODULE_LICENSE("GPL");
-
-static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
-{
-	struct cpuinfo_x86 *c = &cpu_data(cpu_num);
-	unsigned int val[2];
-
-	memset(csig, 0, sizeof(*csig));
-
-	csig->sig = cpuid_eax(0x00000001);
-
-	if ((c->x86_model >= 5) || (c->x86 > 6)) {
-		/* get processor flags from MSR 0x17 */
-		rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]);
-		csig->pf = 1 << ((val[1] >> 18) & 7);
-	}
-
-	csig->rev = c->microcode;
-	pr_info("CPU%d sig=0x%x, pf=0x%x, revision=0x%x\n",
-		cpu_num, csig->sig, csig->pf, csig->rev);
-
-	return 0;
-}
-
-/*
- * return 0 - no update found
- * return 1 - found update
- */
-static int get_matching_mc(struct microcode_intel *mc_intel, int cpu)
-{
-	struct cpu_signature cpu_sig;
-	unsigned int csig, cpf, crev;
-
-	collect_cpu_info(cpu, &cpu_sig);
-
-	csig = cpu_sig.sig;
-	cpf = cpu_sig.pf;
-	crev = cpu_sig.rev;
-
-	return get_matching_microcode(csig, cpf, mc_intel, crev);
-}
-
-int apply_microcode(int cpu)
-{
-	struct microcode_intel *mc_intel;
-	struct ucode_cpu_info *uci;
-	unsigned int val[2];
-	int cpu_num = raw_smp_processor_id();
-	struct cpuinfo_x86 *c = &cpu_data(cpu_num);
-
-	uci = ucode_cpu_info + cpu;
-	mc_intel = uci->mc;
-
-	/* We should bind the task to the CPU */
-	BUG_ON(cpu_num != cpu);
-
-	if (mc_intel == NULL)
-		return 0;
-
-	/*
-	 * Microcode on this CPU could be updated earlier. Only apply the
-	 * microcode patch in mc_intel when it is newer than the one on this
-	 * CPU.
-	 */
-	if (get_matching_mc(mc_intel, cpu) == 0)
-		return 0;
-
-	/* write microcode via MSR 0x79 */
-	wrmsr(MSR_IA32_UCODE_WRITE,
-	      (unsigned long) mc_intel->bits,
-	      (unsigned long) mc_intel->bits >> 16 >> 16);
-	wrmsr(MSR_IA32_UCODE_REV, 0, 0);
-
-	/* As documented in the SDM: Do a CPUID 1 here */
-	sync_core();
-
-	/* get the current revision from MSR 0x8B */
-	rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
-
-	if (val[1] != mc_intel->hdr.rev) {
-		pr_err("CPU%d update to revision 0x%x failed\n",
-		       cpu_num, mc_intel->hdr.rev);
-		return -1;
-	}
-	pr_info("CPU%d updated to revision 0x%x, date = %04x-%02x-%02x\n",
-		cpu_num, val[1],
-		mc_intel->hdr.date & 0xffff,
-		mc_intel->hdr.date >> 24,
-		(mc_intel->hdr.date >> 16) & 0xff);
-
-	uci->cpu_sig.rev = val[1];
-	c->microcode = val[1];
-
-	return 0;
-}
-
-static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
-				int (*get_ucode_data)(void *, const void *, size_t))
-{
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	u8 *ucode_ptr = data, *new_mc = NULL, *mc = NULL;
-	int new_rev = uci->cpu_sig.rev;
-	unsigned int leftover = size;
-	enum ucode_state state = UCODE_OK;
-	unsigned int curr_mc_size = 0;
-	unsigned int csig, cpf;
-
-	while (leftover) {
-		struct microcode_header_intel mc_header;
-		unsigned int mc_size;
-
-		if (get_ucode_data(&mc_header, ucode_ptr, sizeof(mc_header)))
-			break;
-
-		mc_size = get_totalsize(&mc_header);
-		if (!mc_size || mc_size > leftover) {
-			pr_err("error! Bad data in microcode data file\n");
-			break;
-		}
-
-		/* For performance reasons, reuse mc area when possible */
-		if (!mc || mc_size > curr_mc_size) {
-			vfree(mc);
-			mc = vmalloc(mc_size);
-			if (!mc)
-				break;
-			curr_mc_size = mc_size;
-		}
-
-		if (get_ucode_data(mc, ucode_ptr, mc_size) ||
-		    microcode_sanity_check(mc, 1) < 0) {
-			break;
-		}
-
-		csig = uci->cpu_sig.sig;
-		cpf = uci->cpu_sig.pf;
-		if (get_matching_microcode(csig, cpf, mc, new_rev)) {
-			vfree(new_mc);
-			new_rev = mc_header.rev;
-			new_mc  = mc;
-			mc = NULL;	/* trigger new vmalloc */
-		}
-
-		ucode_ptr += mc_size;
-		leftover  -= mc_size;
-	}
-
-	vfree(mc);
-
-	if (leftover) {
-		vfree(new_mc);
-		state = UCODE_ERROR;
-		goto out;
-	}
-
-	if (!new_mc) {
-		state = UCODE_NFOUND;
-		goto out;
-	}
-
-	vfree(uci->mc);
-	uci->mc = (struct microcode_intel *)new_mc;
-
-	/*
-	 * If early loading microcode is supported, save this mc into
-	 * permanent memory. So it will be loaded early when a CPU is hot added
-	 * or resumes.
-	 */
-	save_mc_for_early(new_mc);
-
-	pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
-		 cpu, new_rev, uci->cpu_sig.rev);
-out:
-	return state;
-}
-
-static int get_ucode_fw(void *to, const void *from, size_t n)
-{
-	memcpy(to, from, n);
-	return 0;
-}
-
-static enum ucode_state request_microcode_fw(int cpu, struct device *device,
-					     bool refresh_fw)
-{
-	char name[30];
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
-	const struct firmware *firmware;
-	enum ucode_state ret;
-
-	sprintf(name, "intel-ucode/%02x-%02x-%02x",
-		c->x86, c->x86_model, c->x86_mask);
-
-	if (request_firmware(&firmware, name, device)) {
-		pr_debug("data file %s load failed\n", name);
-		return UCODE_NFOUND;
-	}
-
-	ret = generic_load_microcode(cpu, (void *)firmware->data,
-				     firmware->size, &get_ucode_fw);
-
-	release_firmware(firmware);
-
-	return ret;
-}
-
-static int get_ucode_user(void *to, const void *from, size_t n)
-{
-	return copy_from_user(to, from, n);
-}
-
-static enum ucode_state
-request_microcode_user(int cpu, const void __user *buf, size_t size)
-{
-	return generic_load_microcode(cpu, (void *)buf, size, &get_ucode_user);
-}
-
-static void microcode_fini_cpu(int cpu)
-{
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-
-	vfree(uci->mc);
-	uci->mc = NULL;
-}
-
-static struct microcode_ops microcode_intel_ops = {
-	.request_microcode_user		  = request_microcode_user,
-	.request_microcode_fw             = request_microcode_fw,
-	.collect_cpu_info                 = collect_cpu_info,
-	.apply_microcode                  = apply_microcode,
-	.microcode_fini_cpu               = microcode_fini_cpu,
-};
-
-struct microcode_ops * __init init_intel_microcode(void)
-{
-	struct cpuinfo_x86 *c = &cpu_data(0);
-
-	if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 ||
-	    cpu_has(c, X86_FEATURE_IA64)) {
-		pr_err("Intel CPU family 0x%x not supported\n", c->x86);
-		return NULL;
-	}
-
-	return &microcode_intel_ops;
-}
-
diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c
deleted file mode 100644
index 18f7391..0000000
--- a/arch/x86/kernel/microcode_intel_early.c
+++ /dev/null
@@ -1,787 +0,0 @@
-/*
- *	Intel CPU microcode early update for Linux
- *
- *	Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com>
- *			   H Peter Anvin" <hpa@zytor.com>
- *
- *	This allows to early upgrade microcode on Intel processors
- *	belonging to IA-32 family - PentiumPro, Pentium II,
- *	Pentium III, Xeon, Pentium 4, etc.
- *
- *	Reference: Section 9.11 of Volume 3, IA-32 Intel Architecture
- *	Software Developer's Manual.
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- */
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/slab.h>
-#include <linux/earlycpio.h>
-#include <linux/initrd.h>
-#include <linux/cpu.h>
-#include <asm/msr.h>
-#include <asm/microcode_intel.h>
-#include <asm/processor.h>
-#include <asm/tlbflush.h>
-#include <asm/setup.h>
-
-unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT];
-struct mc_saved_data {
-	unsigned int mc_saved_count;
-	struct microcode_intel **mc_saved;
-} mc_saved_data;
-
-static enum ucode_state
-generic_load_microcode_early(struct microcode_intel **mc_saved_p,
-			     unsigned int mc_saved_count,
-			     struct ucode_cpu_info *uci)
-{
-	struct microcode_intel *ucode_ptr, *new_mc = NULL;
-	int new_rev = uci->cpu_sig.rev;
-	enum ucode_state state = UCODE_OK;
-	unsigned int mc_size;
-	struct microcode_header_intel *mc_header;
-	unsigned int csig = uci->cpu_sig.sig;
-	unsigned int cpf = uci->cpu_sig.pf;
-	int i;
-
-	for (i = 0; i < mc_saved_count; i++) {
-		ucode_ptr = mc_saved_p[i];
-
-		mc_header = (struct microcode_header_intel *)ucode_ptr;
-		mc_size = get_totalsize(mc_header);
-		if (get_matching_microcode(csig, cpf, ucode_ptr, new_rev)) {
-			new_rev = mc_header->rev;
-			new_mc  = ucode_ptr;
-		}
-	}
-
-	if (!new_mc) {
-		state = UCODE_NFOUND;
-		goto out;
-	}
-
-	uci->mc = (struct microcode_intel *)new_mc;
-out:
-	return state;
-}
-
-static void
-microcode_pointer(struct microcode_intel **mc_saved,
-		  unsigned long *mc_saved_in_initrd,
-		  unsigned long initrd_start, int mc_saved_count)
-{
-	int i;
-
-	for (i = 0; i < mc_saved_count; i++)
-		mc_saved[i] = (struct microcode_intel *)
-			      (mc_saved_in_initrd[i] + initrd_start);
-}
-
-#ifdef CONFIG_X86_32
-static void
-microcode_phys(struct microcode_intel **mc_saved_tmp,
-	       struct mc_saved_data *mc_saved_data)
-{
-	int i;
-	struct microcode_intel ***mc_saved;
-
-	mc_saved = (struct microcode_intel ***)
-		   __pa_nodebug(&mc_saved_data->mc_saved);
-	for (i = 0; i < mc_saved_data->mc_saved_count; i++) {
-		struct microcode_intel *p;
-
-		p = *(struct microcode_intel **)
-			__pa_nodebug(mc_saved_data->mc_saved + i);
-		mc_saved_tmp[i] = (struct microcode_intel *)__pa_nodebug(p);
-	}
-}
-#endif
-
-static enum ucode_state
-load_microcode(struct mc_saved_data *mc_saved_data,
-	       unsigned long *mc_saved_in_initrd,
-	       unsigned long initrd_start,
-	       struct ucode_cpu_info *uci)
-{
-	struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT];
-	unsigned int count = mc_saved_data->mc_saved_count;
-
-	if (!mc_saved_data->mc_saved) {
-		microcode_pointer(mc_saved_tmp, mc_saved_in_initrd,
-				  initrd_start, count);
-
-		return generic_load_microcode_early(mc_saved_tmp, count, uci);
-	} else {
-#ifdef CONFIG_X86_32
-		microcode_phys(mc_saved_tmp, mc_saved_data);
-		return generic_load_microcode_early(mc_saved_tmp, count, uci);
-#else
-		return generic_load_microcode_early(mc_saved_data->mc_saved,
-						    count, uci);
-#endif
-	}
-}
-
-static u8 get_x86_family(unsigned long sig)
-{
-	u8 x86;
-
-	x86 = (sig >> 8) & 0xf;
-
-	if (x86 == 0xf)
-		x86 += (sig >> 20) & 0xff;
-
-	return x86;
-}
-
-static u8 get_x86_model(unsigned long sig)
-{
-	u8 x86, x86_model;
-
-	x86 = get_x86_family(sig);
-	x86_model = (sig >> 4) & 0xf;
-
-	if (x86 == 0x6 || x86 == 0xf)
-		x86_model += ((sig >> 16) & 0xf) << 4;
-
-	return x86_model;
-}
-
-/*
- * Given CPU signature and a microcode patch, this function finds if the
- * microcode patch has matching family and model with the CPU.
- */
-static enum ucode_state
-matching_model_microcode(struct microcode_header_intel *mc_header,
-			unsigned long sig)
-{
-	u8 x86, x86_model;
-	u8 x86_ucode, x86_model_ucode;
-	struct extended_sigtable *ext_header;
-	unsigned long total_size = get_totalsize(mc_header);
-	unsigned long data_size = get_datasize(mc_header);
-	int ext_sigcount, i;
-	struct extended_signature *ext_sig;
-
-	x86 = get_x86_family(sig);
-	x86_model = get_x86_model(sig);
-
-	x86_ucode = get_x86_family(mc_header->sig);
-	x86_model_ucode = get_x86_model(mc_header->sig);
-
-	if (x86 == x86_ucode && x86_model == x86_model_ucode)
-		return UCODE_OK;
-
-	/* Look for ext. headers: */
-	if (total_size <= data_size + MC_HEADER_SIZE)
-		return UCODE_NFOUND;
-
-	ext_header = (struct extended_sigtable *)
-		     mc_header + data_size + MC_HEADER_SIZE;
-	ext_sigcount = ext_header->count;
-	ext_sig = (void *)ext_header + EXT_HEADER_SIZE;
-
-	for (i = 0; i < ext_sigcount; i++) {
-		x86_ucode = get_x86_family(ext_sig->sig);
-		x86_model_ucode = get_x86_model(ext_sig->sig);
-
-		if (x86 == x86_ucode && x86_model == x86_model_ucode)
-			return UCODE_OK;
-
-		ext_sig++;
-	}
-
-	return UCODE_NFOUND;
-}
-
-static int
-save_microcode(struct mc_saved_data *mc_saved_data,
-	       struct microcode_intel **mc_saved_src,
-	       unsigned int mc_saved_count)
-{
-	int i, j;
-	struct microcode_intel **mc_saved_p;
-	int ret;
-
-	if (!mc_saved_count)
-		return -EINVAL;
-
-	/*
-	 * Copy new microcode data.
-	 */
-	mc_saved_p = kmalloc(mc_saved_count*sizeof(struct microcode_intel *),
-			     GFP_KERNEL);
-	if (!mc_saved_p)
-		return -ENOMEM;
-
-	for (i = 0; i < mc_saved_count; i++) {
-		struct microcode_intel *mc = mc_saved_src[i];
-		struct microcode_header_intel *mc_header = &mc->hdr;
-		unsigned long mc_size = get_totalsize(mc_header);
-		mc_saved_p[i] = kmalloc(mc_size, GFP_KERNEL);
-		if (!mc_saved_p[i]) {
-			ret = -ENOMEM;
-			goto err;
-		}
-		if (!mc_saved_src[i]) {
-			ret = -EINVAL;
-			goto err;
-		}
-		memcpy(mc_saved_p[i], mc, mc_size);
-	}
-
-	/*
-	 * Point to newly saved microcode.
-	 */
-	mc_saved_data->mc_saved = mc_saved_p;
-	mc_saved_data->mc_saved_count = mc_saved_count;
-
-	return 0;
-
-err:
-	for (j = 0; j <= i; j++)
-		kfree(mc_saved_p[j]);
-	kfree(mc_saved_p);
-
-	return ret;
-}
-
-/*
- * A microcode patch in ucode_ptr is saved into mc_saved
- * - if it has matching signature and newer revision compared to an existing
- *   patch mc_saved.
- * - or if it is a newly discovered microcode patch.
- *
- * The microcode patch should have matching model with CPU.
- */
-static void _save_mc(struct microcode_intel **mc_saved, u8 *ucode_ptr,
-		     unsigned int *mc_saved_count_p)
-{
-	int i;
-	int found = 0;
-	unsigned int mc_saved_count = *mc_saved_count_p;
-	struct microcode_header_intel *mc_header;
-
-	mc_header = (struct microcode_header_intel *)ucode_ptr;
-	for (i = 0; i < mc_saved_count; i++) {
-		unsigned int sig, pf;
-		unsigned int new_rev;
-		struct microcode_header_intel *mc_saved_header =
-			     (struct microcode_header_intel *)mc_saved[i];
-		sig = mc_saved_header->sig;
-		pf = mc_saved_header->pf;
-		new_rev = mc_header->rev;
-
-		if (get_matching_sig(sig, pf, ucode_ptr, new_rev)) {
-			found = 1;
-			if (update_match_revision(mc_header, new_rev)) {
-				/*
-				 * Found an older ucode saved before.
-				 * Replace the older one with this newer
-				 * one.
-				 */
-				mc_saved[i] =
-					(struct microcode_intel *)ucode_ptr;
-				break;
-			}
-		}
-	}
-	if (i >= mc_saved_count && !found)
-		/*
-		 * This ucode is first time discovered in ucode file.
-		 * Save it to memory.
-		 */
-		mc_saved[mc_saved_count++] =
-				 (struct microcode_intel *)ucode_ptr;
-
-	*mc_saved_count_p = mc_saved_count;
-}
-
-/*
- * Get microcode matching with BSP's model. Only CPUs with the same model as
- * BSP can stay in the platform.
- */
-static enum ucode_state __init
-get_matching_model_microcode(int cpu, unsigned long start,
-			     void *data, size_t size,
-			     struct mc_saved_data *mc_saved_data,
-			     unsigned long *mc_saved_in_initrd,
-			     struct ucode_cpu_info *uci)
-{
-	u8 *ucode_ptr = data;
-	unsigned int leftover = size;
-	enum ucode_state state = UCODE_OK;
-	unsigned int mc_size;
-	struct microcode_header_intel *mc_header;
-	struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT];
-	unsigned int mc_saved_count = mc_saved_data->mc_saved_count;
-	int i;
-
-	while (leftover) {
-		mc_header = (struct microcode_header_intel *)ucode_ptr;
-
-		mc_size = get_totalsize(mc_header);
-		if (!mc_size || mc_size > leftover ||
-			microcode_sanity_check(ucode_ptr, 0) < 0)
-			break;
-
-		leftover -= mc_size;
-
-		/*
-		 * Since APs with same family and model as the BSP may boot in
-		 * the platform, we need to find and save microcode patches
-		 * with the same family and model as the BSP.
-		 */
-		if (matching_model_microcode(mc_header, uci->cpu_sig.sig) !=
-			 UCODE_OK) {
-			ucode_ptr += mc_size;
-			continue;
-		}
-
-		_save_mc(mc_saved_tmp, ucode_ptr, &mc_saved_count);
-
-		ucode_ptr += mc_size;
-	}
-
-	if (leftover) {
-		state = UCODE_ERROR;
-		goto out;
-	}
-
-	if (mc_saved_count == 0) {
-		state = UCODE_NFOUND;
-		goto out;
-	}
-
-	for (i = 0; i < mc_saved_count; i++)
-		mc_saved_in_initrd[i] = (unsigned long)mc_saved_tmp[i] - start;
-
-	mc_saved_data->mc_saved_count = mc_saved_count;
-out:
-	return state;
-}
-
-static int collect_cpu_info_early(struct ucode_cpu_info *uci)
-{
-	unsigned int val[2];
-	u8 x86, x86_model;
-	struct cpu_signature csig;
-	unsigned int eax, ebx, ecx, edx;
-
-	csig.sig = 0;
-	csig.pf = 0;
-	csig.rev = 0;
-
-	memset(uci, 0, sizeof(*uci));
-
-	eax = 0x00000001;
-	ecx = 0;
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-	csig.sig = eax;
-
-	x86 = get_x86_family(csig.sig);
-	x86_model = get_x86_model(csig.sig);
-
-	if ((x86_model >= 5) || (x86 > 6)) {
-		/* get processor flags from MSR 0x17 */
-		native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]);
-		csig.pf = 1 << ((val[1] >> 18) & 7);
-	}
-	native_wrmsr(MSR_IA32_UCODE_REV, 0, 0);
-
-	/* As documented in the SDM: Do a CPUID 1 here */
-	sync_core();
-
-	/* get the current revision from MSR 0x8B */
-	native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
-
-	csig.rev = val[1];
-
-	uci->cpu_sig = csig;
-	uci->valid = 1;
-
-	return 0;
-}
-
-#ifdef DEBUG
-static void __ref show_saved_mc(void)
-{
-	int i, j;
-	unsigned int sig, pf, rev, total_size, data_size, date;
-	struct ucode_cpu_info uci;
-
-	if (mc_saved_data.mc_saved_count == 0) {
-		pr_debug("no micorcode data saved.\n");
-		return;
-	}
-	pr_debug("Total microcode saved: %d\n", mc_saved_data.mc_saved_count);
-
-	collect_cpu_info_early(&uci);
-
-	sig = uci.cpu_sig.sig;
-	pf = uci.cpu_sig.pf;
-	rev = uci.cpu_sig.rev;
-	pr_debug("CPU%d: sig=0x%x, pf=0x%x, rev=0x%x\n",
-		 smp_processor_id(), sig, pf, rev);
-
-	for (i = 0; i < mc_saved_data.mc_saved_count; i++) {
-		struct microcode_header_intel *mc_saved_header;
-		struct extended_sigtable *ext_header;
-		int ext_sigcount;
-		struct extended_signature *ext_sig;
-
-		mc_saved_header = (struct microcode_header_intel *)
-				  mc_saved_data.mc_saved[i];
-		sig = mc_saved_header->sig;
-		pf = mc_saved_header->pf;
-		rev = mc_saved_header->rev;
-		total_size = get_totalsize(mc_saved_header);
-		data_size = get_datasize(mc_saved_header);
-		date = mc_saved_header->date;
-
-		pr_debug("mc_saved[%d]: sig=0x%x, pf=0x%x, rev=0x%x, toal size=0x%x, date = %04x-%02x-%02x\n",
-			 i, sig, pf, rev, total_size,
-			 date & 0xffff,
-			 date >> 24,
-			 (date >> 16) & 0xff);
-
-		/* Look for ext. headers: */
-		if (total_size <= data_size + MC_HEADER_SIZE)
-			continue;
-
-		ext_header = (struct extended_sigtable *)
-			     mc_saved_header + data_size + MC_HEADER_SIZE;
-		ext_sigcount = ext_header->count;
-		ext_sig = (void *)ext_header + EXT_HEADER_SIZE;
-
-		for (j = 0; j < ext_sigcount; j++) {
-			sig = ext_sig->sig;
-			pf = ext_sig->pf;
-
-			pr_debug("\tExtended[%d]: sig=0x%x, pf=0x%x\n",
-				 j, sig, pf);
-
-			ext_sig++;
-		}
-
-	}
-}
-#else
-static inline void show_saved_mc(void)
-{
-}
-#endif
-
-#if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU)
-static DEFINE_MUTEX(x86_cpu_microcode_mutex);
-/*
- * Save this mc into mc_saved_data. So it will be loaded early when a CPU is
- * hot added or resumes.
- *
- * Please make sure this mc should be a valid microcode patch before calling
- * this function.
- */
-int save_mc_for_early(u8 *mc)
-{
-	struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT];
-	unsigned int mc_saved_count_init;
-	unsigned int mc_saved_count;
-	struct microcode_intel **mc_saved;
-	int ret = 0;
-	int i;
-
-	/*
-	 * Hold hotplug lock so mc_saved_data is not accessed by a CPU in
-	 * hotplug.
-	 */
-	mutex_lock(&x86_cpu_microcode_mutex);
-
-	mc_saved_count_init = mc_saved_data.mc_saved_count;
-	mc_saved_count = mc_saved_data.mc_saved_count;
-	mc_saved = mc_saved_data.mc_saved;
-
-	if (mc_saved && mc_saved_count)
-		memcpy(mc_saved_tmp, mc_saved,
-		       mc_saved_count * sizeof(struct mirocode_intel *));
-	/*
-	 * Save the microcode patch mc in mc_save_tmp structure if it's a newer
-	 * version.
-	 */
-
-	_save_mc(mc_saved_tmp, mc, &mc_saved_count);
-
-	/*
-	 * Save the mc_save_tmp in global mc_saved_data.
-	 */
-	ret = save_microcode(&mc_saved_data, mc_saved_tmp, mc_saved_count);
-	if (ret) {
-		pr_err("Cannot save microcode patch.\n");
-		goto out;
-	}
-
-	show_saved_mc();
-
-	/*
-	 * Free old saved microcod data.
-	 */
-	if (mc_saved) {
-		for (i = 0; i < mc_saved_count_init; i++)
-			kfree(mc_saved[i]);
-		kfree(mc_saved);
-	}
-
-out:
-	mutex_unlock(&x86_cpu_microcode_mutex);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(save_mc_for_early);
-#endif
-
-static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin";
-static __init enum ucode_state
-scan_microcode(unsigned long start, unsigned long end,
-		struct mc_saved_data *mc_saved_data,
-		unsigned long *mc_saved_in_initrd,
-		struct ucode_cpu_info *uci)
-{
-	unsigned int size = end - start + 1;
-	struct cpio_data cd;
-	long offset = 0;
-#ifdef CONFIG_X86_32
-	char *p = (char *)__pa_nodebug(ucode_name);
-#else
-	char *p = ucode_name;
-#endif
-
-	cd.data = NULL;
-	cd.size = 0;
-
-	cd = find_cpio_data(p, (void *)start, size, &offset);
-	if (!cd.data)
-		return UCODE_ERROR;
-
-
-	return get_matching_model_microcode(0, start, cd.data, cd.size,
-					    mc_saved_data, mc_saved_in_initrd,
-					    uci);
-}
-
-/*
- * Print ucode update info.
- */
-static void
-print_ucode_info(struct ucode_cpu_info *uci, unsigned int date)
-{
-	int cpu = smp_processor_id();
-
-	pr_info("CPU%d microcode updated early to revision 0x%x, date = %04x-%02x-%02x\n",
-		cpu,
-		uci->cpu_sig.rev,
-		date & 0xffff,
-		date >> 24,
-		(date >> 16) & 0xff);
-}
-
-#ifdef CONFIG_X86_32
-
-static int delay_ucode_info;
-static int current_mc_date;
-
-/*
- * Print early updated ucode info after printk works. This is delayed info dump.
- */
-void show_ucode_info_early(void)
-{
-	struct ucode_cpu_info uci;
-
-	if (delay_ucode_info) {
-		collect_cpu_info_early(&uci);
-		print_ucode_info(&uci, current_mc_date);
-		delay_ucode_info = 0;
-	}
-}
-
-/*
- * At this point, we can not call printk() yet. Keep microcode patch number in
- * mc_saved_data.mc_saved and delay printing microcode info in
- * show_ucode_info_early() until printk() works.
- */
-static void print_ucode(struct ucode_cpu_info *uci)
-{
-	struct microcode_intel *mc_intel;
-	int *delay_ucode_info_p;
-	int *current_mc_date_p;
-
-	mc_intel = uci->mc;
-	if (mc_intel == NULL)
-		return;
-
-	delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info);
-	current_mc_date_p = (int *)__pa_nodebug(&current_mc_date);
-
-	*delay_ucode_info_p = 1;
-	*current_mc_date_p = mc_intel->hdr.date;
-}
-#else
-
-/*
- * Flush global tlb. We only do this in x86_64 where paging has been enabled
- * already and PGE should be enabled as well.
- */
-static inline void flush_tlb_early(void)
-{
-	__native_flush_tlb_global_irq_disabled();
-}
-
-static inline void print_ucode(struct ucode_cpu_info *uci)
-{
-	struct microcode_intel *mc_intel;
-
-	mc_intel = uci->mc;
-	if (mc_intel == NULL)
-		return;
-
-	print_ucode_info(uci, mc_intel->hdr.date);
-}
-#endif
-
-static int apply_microcode_early(struct mc_saved_data *mc_saved_data,
-				 struct ucode_cpu_info *uci)
-{
-	struct microcode_intel *mc_intel;
-	unsigned int val[2];
-
-	mc_intel = uci->mc;
-	if (mc_intel == NULL)
-		return 0;
-
-	/* write microcode via MSR 0x79 */
-	native_wrmsr(MSR_IA32_UCODE_WRITE,
-	      (unsigned long) mc_intel->bits,
-	      (unsigned long) mc_intel->bits >> 16 >> 16);
-	native_wrmsr(MSR_IA32_UCODE_REV, 0, 0);
-
-	/* As documented in the SDM: Do a CPUID 1 here */
-	sync_core();
-
-	/* get the current revision from MSR 0x8B */
-	native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
-	if (val[1] != mc_intel->hdr.rev)
-		return -1;
-
-#ifdef CONFIG_X86_64
-	/* Flush global tlb. This is precaution. */
-	flush_tlb_early();
-#endif
-	uci->cpu_sig.rev = val[1];
-
-	print_ucode(uci);
-
-	return 0;
-}
-
-/*
- * This function converts microcode patch offsets previously stored in
- * mc_saved_in_initrd to pointers and stores the pointers in mc_saved_data.
- */
-int __init save_microcode_in_initrd_intel(void)
-{
-	unsigned int count = mc_saved_data.mc_saved_count;
-	struct microcode_intel *mc_saved[MAX_UCODE_COUNT];
-	int ret = 0;
-
-	if (count == 0)
-		return ret;
-
-	microcode_pointer(mc_saved, mc_saved_in_initrd, initrd_start, count);
-	ret = save_microcode(&mc_saved_data, mc_saved, count);
-	if (ret)
-		pr_err("Cannot save microcode patches from initrd.\n");
-
-	show_saved_mc();
-
-	return ret;
-}
-
-static void __init
-_load_ucode_intel_bsp(struct mc_saved_data *mc_saved_data,
-		      unsigned long *mc_saved_in_initrd,
-		      unsigned long initrd_start_early,
-		      unsigned long initrd_end_early,
-		      struct ucode_cpu_info *uci)
-{
-	collect_cpu_info_early(uci);
-	scan_microcode(initrd_start_early, initrd_end_early, mc_saved_data,
-		       mc_saved_in_initrd, uci);
-	load_microcode(mc_saved_data, mc_saved_in_initrd,
-		       initrd_start_early, uci);
-	apply_microcode_early(mc_saved_data, uci);
-}
-
-void __init
-load_ucode_intel_bsp(void)
-{
-	u64 ramdisk_image, ramdisk_size;
-	unsigned long initrd_start_early, initrd_end_early;
-	struct ucode_cpu_info uci;
-#ifdef CONFIG_X86_32
-	struct boot_params *boot_params_p;
-
-	boot_params_p = (struct boot_params *)__pa_nodebug(&boot_params);
-	ramdisk_image = boot_params_p->hdr.ramdisk_image;
-	ramdisk_size  = boot_params_p->hdr.ramdisk_size;
-	initrd_start_early = ramdisk_image;
-	initrd_end_early = initrd_start_early + ramdisk_size;
-
-	_load_ucode_intel_bsp(
-		(struct mc_saved_data *)__pa_nodebug(&mc_saved_data),
-		(unsigned long *)__pa_nodebug(&mc_saved_in_initrd),
-		initrd_start_early, initrd_end_early, &uci);
-#else
-	ramdisk_image = boot_params.hdr.ramdisk_image;
-	ramdisk_size  = boot_params.hdr.ramdisk_size;
-	initrd_start_early = ramdisk_image + PAGE_OFFSET;
-	initrd_end_early = initrd_start_early + ramdisk_size;
-
-	_load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd,
-			      initrd_start_early, initrd_end_early, &uci);
-#endif
-}
-
-void load_ucode_intel_ap(void)
-{
-	struct mc_saved_data *mc_saved_data_p;
-	struct ucode_cpu_info uci;
-	unsigned long *mc_saved_in_initrd_p;
-	unsigned long initrd_start_addr;
-#ifdef CONFIG_X86_32
-	unsigned long *initrd_start_p;
-
-	mc_saved_in_initrd_p =
-		(unsigned long *)__pa_nodebug(mc_saved_in_initrd);
-	mc_saved_data_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data);
-	initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start);
-	initrd_start_addr = (unsigned long)__pa_nodebug(*initrd_start_p);
-#else
-	mc_saved_data_p = &mc_saved_data;
-	mc_saved_in_initrd_p = mc_saved_in_initrd;
-	initrd_start_addr = initrd_start;
-#endif
-
-	/*
-	 * If there is no valid ucode previously saved in memory, no need to
-	 * update ucode on this AP.
-	 */
-	if (mc_saved_data_p->mc_saved_count == 0)
-		return;
-
-	collect_cpu_info_early(&uci);
-	load_microcode(mc_saved_data_p, mc_saved_in_initrd_p,
-		       initrd_start_addr, &uci);
-	apply_microcode_early(mc_saved_data_p, &uci);
-}
diff --git a/arch/x86/kernel/microcode_intel_lib.c b/arch/x86/kernel/microcode_intel_lib.c
deleted file mode 100644
index ce69320..0000000
--- a/arch/x86/kernel/microcode_intel_lib.c
+++ /dev/null
@@ -1,174 +0,0 @@
-/*
- *	Intel CPU Microcode Update Driver for Linux
- *
- *	Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com>
- *			   H Peter Anvin" <hpa@zytor.com>
- *
- *	This driver allows to upgrade microcode on Intel processors
- *	belonging to IA-32 family - PentiumPro, Pentium II,
- *	Pentium III, Xeon, Pentium 4, etc.
- *
- *	Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture
- *	Software Developer's Manual
- *	Order Number 253668 or free download from:
- *
- *	http://developer.intel.com/Assets/PDF/manual/253668.pdf
- *
- *	For more information, go to http://www.urbanmyth.org/microcode
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- *
- */
-#include <linux/firmware.h>
-#include <linux/uaccess.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-#include <asm/microcode_intel.h>
-#include <asm/processor.h>
-#include <asm/msr.h>
-
-static inline int
-update_match_cpu(unsigned int csig, unsigned int cpf,
-		 unsigned int sig, unsigned int pf)
-{
-	return (!sigmatch(sig, csig, pf, cpf)) ? 0 : 1;
-}
-
-int
-update_match_revision(struct microcode_header_intel *mc_header, int rev)
-{
-	return (mc_header->rev <= rev) ? 0 : 1;
-}
-
-int microcode_sanity_check(void *mc, int print_err)
-{
-	unsigned long total_size, data_size, ext_table_size;
-	struct microcode_header_intel *mc_header = mc;
-	struct extended_sigtable *ext_header = NULL;
-	int sum, orig_sum, ext_sigcount = 0, i;
-	struct extended_signature *ext_sig;
-
-	total_size = get_totalsize(mc_header);
-	data_size = get_datasize(mc_header);
-
-	if (data_size + MC_HEADER_SIZE > total_size) {
-		if (print_err)
-			pr_err("error! Bad data size in microcode data file\n");
-		return -EINVAL;
-	}
-
-	if (mc_header->ldrver != 1 || mc_header->hdrver != 1) {
-		if (print_err)
-			pr_err("error! Unknown microcode update format\n");
-		return -EINVAL;
-	}
-	ext_table_size = total_size - (MC_HEADER_SIZE + data_size);
-	if (ext_table_size) {
-		if ((ext_table_size < EXT_HEADER_SIZE)
-		 || ((ext_table_size - EXT_HEADER_SIZE) % EXT_SIGNATURE_SIZE)) {
-			if (print_err)
-				pr_err("error! Small exttable size in microcode data file\n");
-			return -EINVAL;
-		}
-		ext_header = mc + MC_HEADER_SIZE + data_size;
-		if (ext_table_size != exttable_size(ext_header)) {
-			if (print_err)
-				pr_err("error! Bad exttable size in microcode data file\n");
-			return -EFAULT;
-		}
-		ext_sigcount = ext_header->count;
-	}
-
-	/* check extended table checksum */
-	if (ext_table_size) {
-		int ext_table_sum = 0;
-		int *ext_tablep = (int *)ext_header;
-
-		i = ext_table_size / DWSIZE;
-		while (i--)
-			ext_table_sum += ext_tablep[i];
-		if (ext_table_sum) {
-			if (print_err)
-				pr_warn("aborting, bad extended signature table checksum\n");
-			return -EINVAL;
-		}
-	}
-
-	/* calculate the checksum */
-	orig_sum = 0;
-	i = (MC_HEADER_SIZE + data_size) / DWSIZE;
-	while (i--)
-		orig_sum += ((int *)mc)[i];
-	if (orig_sum) {
-		if (print_err)
-			pr_err("aborting, bad checksum\n");
-		return -EINVAL;
-	}
-	if (!ext_table_size)
-		return 0;
-	/* check extended signature checksum */
-	for (i = 0; i < ext_sigcount; i++) {
-		ext_sig = (void *)ext_header + EXT_HEADER_SIZE +
-			  EXT_SIGNATURE_SIZE * i;
-		sum = orig_sum
-			- (mc_header->sig + mc_header->pf + mc_header->cksum)
-			+ (ext_sig->sig + ext_sig->pf + ext_sig->cksum);
-		if (sum) {
-			if (print_err)
-				pr_err("aborting, bad checksum\n");
-			return -EINVAL;
-		}
-	}
-	return 0;
-}
-EXPORT_SYMBOL_GPL(microcode_sanity_check);
-
-/*
- * return 0 - no update found
- * return 1 - found update
- */
-int get_matching_sig(unsigned int csig, int cpf, void *mc, int rev)
-{
-	struct microcode_header_intel *mc_header = mc;
-	struct extended_sigtable *ext_header;
-	unsigned long total_size = get_totalsize(mc_header);
-	int ext_sigcount, i;
-	struct extended_signature *ext_sig;
-
-	if (update_match_cpu(csig, cpf, mc_header->sig, mc_header->pf))
-		return 1;
-
-	/* Look for ext. headers: */
-	if (total_size <= get_datasize(mc_header) + MC_HEADER_SIZE)
-		return 0;
-
-	ext_header = mc + get_datasize(mc_header) + MC_HEADER_SIZE;
-	ext_sigcount = ext_header->count;
-	ext_sig = (void *)ext_header + EXT_HEADER_SIZE;
-
-	for (i = 0; i < ext_sigcount; i++) {
-		if (update_match_cpu(csig, cpf, ext_sig->sig, ext_sig->pf))
-			return 1;
-		ext_sig++;
-	}
-	return 0;
-}
-
-/*
- * return 0 - no update found
- * return 1 - found update
- */
-int get_matching_microcode(unsigned int csig, int cpf, void *mc, int rev)
-{
-	struct microcode_header_intel *mc_header = mc;
-
-	if (!update_match_revision(mc_header, rev))
-		return 0;
-
-	return get_matching_sig(csig, cpf, mc, rev);
-}
-EXPORT_SYMBOL_GPL(get_matching_microcode);
-- 
cgit v0.10.2


From 9ef9730ba84d4021a27d3a1679fd50f9bac0e0e7 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Thu, 9 Jan 2014 08:34:00 +0300
Subject: cxgb4: silence shift wrapping static checker warning

I don't know how large "tp->vlan_shift" is but static checkers worry
about shift wrapping bugs here.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Dimitris Michailidis <dm@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
index cb05be9..81e8402 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
@@ -423,7 +423,7 @@ u64 cxgb4_select_ntuple(struct net_device *dev,
 	 * in the Compressed Filter Tuple.
 	 */
 	if (tp->vlan_shift >= 0 && l2t->vlan != VLAN_NONE)
-		ntuple |= (F_FT_VLAN_VLD | l2t->vlan) << tp->vlan_shift;
+		ntuple |= (u64)(F_FT_VLAN_VLD | l2t->vlan) << tp->vlan_shift;
 
 	if (tp->port_shift >= 0)
 		ntuple |= (u64)l2t->lport << tp->port_shift;
-- 
cgit v0.10.2


From 26f7f9877234e6b9ed87eff4ca450631bafe0182 Mon Sep 17 00:00:00 2001
From: Yann Droneaud <ydroneaud@opteya.com>
Date: Sat, 11 Jan 2014 18:48:15 +0100
Subject: perf tools: Remove unused test-volatile-register-var.c

Since commit 01287e2cb7ad, test-volatile-register-var.c is no more built
as part of the automatic feature check.

This patch remove the unneeded file.

Signed-off-by: Yann Droneaud <ydroneaud@opteya.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/339d86ad76741ed929defd18541f774b404003b4.1389461371.git.ydroneaud@opteya.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/config/feature-checks/test-volatile-register-var.c b/tools/perf/config/feature-checks/test-volatile-register-var.c
deleted file mode 100644
index c9f398d..0000000
--- a/tools/perf/config/feature-checks/test-volatile-register-var.c
+++ /dev/null
@@ -1,6 +0,0 @@
-#include <stdio.h>
-
-int main(void)
-{
-	return puts("hi");
-}
-- 
cgit v0.10.2


From abce1ec9b08a4f318f431e6b9a12524227ae7109 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Tue, 14 Jan 2014 12:50:49 +1000
Subject: Revert "drm: copy mode type in drm_mode_connector_list_update()"

This reverts commit 3fbd6439e4639ecaeaae6c079e0aa497a1ac3482.

This caused some strange booting lockup issues on an Intel G33
belonging to Daniel Vetter, very unusual, I was hoping Daniel
would track this down, but it looks like instead I'll have to hack
a different fix for -next.

Signed-off-by: Dave Airlie <airlied@redhat.com>

diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index 85071a1..b073315 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1041,7 +1041,7 @@ void drm_mode_connector_list_update(struct drm_connector *connector)
 				/* if equal delete the probed mode */
 				mode->status = pmode->status;
 				/* Merge type bits together */
-				mode->type = pmode->type;
+				mode->type |= pmode->type;
 				list_del(&pmode->head);
 				drm_mode_destroy(connector->dev, pmode);
 				break;
-- 
cgit v0.10.2


From 1cc03eb93245e63b0b7a7832165efdc52e25b4e6 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Mon, 6 Jan 2014 13:19:42 +1100
Subject: md/raid5: Fix possible confusion when multiple write errors occur.

commit 5d8c71f9e5fbdd95650be00294d238e27a363b5c
    md: raid5 crash during degradation

Fixed a crash in an overly simplistic way which could leave
R5_WriteError or R5_MadeGood set in the stripe cache for devices
for which it is no longer relevant.
When those devices are removed and spares added the flags are still
set and can cause incorrect behaviour.

commit 14a75d3e07c784c004b4b44b34af996b8e4ac453
    md/raid5: preferentially read from replacement device if possible.

Fixed the same bug if a more effective way, so we can now revert
the original commit.

Reported-and-tested-by: Alexander Lyakas <alex.bolshoy@gmail.com>
Cc: stable@vger.kernel.org (3.2+ - 3.2 will need a different fix though)
Fixes: 5d8c71f9e5fbdd95650be00294d238e27a363b5c
Signed-off-by: NeilBrown <neilb@suse.de>

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index cc055da..9168173 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3608,7 +3608,7 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 			 */
 			set_bit(R5_Insync, &dev->flags);
 
-		if (rdev && test_bit(R5_WriteError, &dev->flags)) {
+		if (test_bit(R5_WriteError, &dev->flags)) {
 			/* This flag does not apply to '.replacement'
 			 * only to .rdev, so make sure to check that*/
 			struct md_rdev *rdev2 = rcu_dereference(
@@ -3621,7 +3621,7 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 			} else
 				clear_bit(R5_WriteError, &dev->flags);
 		}
-		if (rdev && test_bit(R5_MadeGood, &dev->flags)) {
+		if (test_bit(R5_MadeGood, &dev->flags)) {
 			/* This flag does not apply to '.replacement'
 			 * only to .rdev, so make sure to check that*/
 			struct md_rdev *rdev2 = rcu_dereference(
-- 
cgit v0.10.2


From b50c259e25d9260b9108dc0c2964c26e5ecbe1c1 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Tue, 14 Jan 2014 10:38:09 +1100
Subject: md/raid10: fix two bugs in handling of known-bad-blocks.

If we discover a bad block when reading we split the request and
potentially read some of it from a different device.

The code path of this has two bugs in RAID10.
1/ we get a spin_lock with _irq, but unlock without _irq!!
2/ The calculation of 'sectors_handled' is wrong, as can be clearly
   seen by comparison with raid1.c

This leads to at least 2 warnings and a probable crash is a RAID10
ever had known bad blocks.

Cc: stable@vger.kernel.org (v3.1+)
Fixes: 856e08e23762dfb92ffc68fd0a8d228f9e152160
Reported-by: Damian Nowak <spam@nowaker.net>
URL: https://bugzilla.kernel.org/show_bug.cgi?id=68181
Signed-off-by: NeilBrown <neilb@suse.de>

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index c504e83..6528521 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1319,7 +1319,7 @@ read_again:
 			/* Could not read all from this device, so we will
 			 * need another r10_bio.
 			 */
-			sectors_handled = (r10_bio->sectors + max_sectors
+			sectors_handled = (r10_bio->sector + max_sectors
 					   - bio->bi_sector);
 			r10_bio->sectors = max_sectors;
 			spin_lock_irq(&conf->device_lock);
@@ -1327,7 +1327,7 @@ read_again:
 				bio->bi_phys_segments = 2;
 			else
 				bio->bi_phys_segments++;
-			spin_unlock(&conf->device_lock);
+			spin_unlock_irq(&conf->device_lock);
 			/* Cannot call generic_make_request directly
 			 * as that will be queued in __generic_make_request
 			 * and subsequent mempool_alloc might block
-- 
cgit v0.10.2


From 41a336e011887f73e7c879b60e1e3544045435cb Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Tue, 14 Jan 2014 11:56:14 +1100
Subject: md/raid1: fix request counting bug in new 'barrier' code.

The new iobarrier implementation in raid1 (which keeps normal writes
and resync activity separate) counts every request what is not before
the current resync point in either next_window_requests or
current_window_requests.
It flags that the request is counted by setting ->start_next_window.

allow_barrier follows this model exactly and decrements one of the
*_window_requests if and only if ->start_next_window is set.

However wait_barrier(), which increments *_window_requests uses a
slightly different test for setting -.start_next_window (which is set
from the return value of this function).
So there is a possibility of the counts getting out of sync, and this
leads to the resync hanging.

So change wait_barrier() to return a non-zero value in exactly the
same cases that it increments *_window_requests.

But was introduced in 3.13-rc1.

Reported-by: Bruno Wolff III <bruno@wolff.to>
URL: https://bugzilla.kernel.org/show_bug.cgi?id=68061
Fixes: 79ef3a8aa1cb1523cc231c9a90a278333c21f761
Cc: majianpeng <majianpeng@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 1e5a540..a49cfcc 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -924,9 +924,8 @@ static sector_t wait_barrier(struct r1conf *conf, struct bio *bio)
 				conf->next_window_requests++;
 			else
 				conf->current_window_requests++;
-		}
-		if (bio->bi_sector >= conf->start_next_window)
 			sector = conf->start_next_window;
+		}
 	}
 
 	conf->nr_pending++;
-- 
cgit v0.10.2


From 5af9bef72c074dbe946da8b74eabd79cd5a9ff19 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Tue, 14 Jan 2014 15:16:10 +1100
Subject: md/raid5: fix a recently broken BUG_ON().

commit 6d183de4077191d1201283a9035ce57a9b05254d
    md/raid5: fix newly-broken locking in get_active_stripe.

simplified a BUG_ON, but removed too much so now it sometimes fires
when it shouldn't.

When the STRIPE_EXPANDING flag is set, the stripe_head might be on a
special list while multiple stripe_heads are collected, or it might
not be on any list, even a 'free' list when the refcount is zero.  As
long as STRIPE_EXPANDING is set, it will be found and added back to a
list eventually.

So both of the BUG_ONs which test for the ->lru being empty or not
need to avoid the case where STRIPE_EXPANDING is set.

The patch which broke this was marked for -stable, so this patch needs
to be applied to any branch that received 6d183de4

Fixes: 6d183de4077191d1201283a9035ce57a9b05254d
Cc: stable@vger.kernel.org (any release to which above was applied)
Signed-off-by: NeilBrown <neilb@suse.de>

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 9168173..cbb1571 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -687,7 +687,8 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
 			} else {
 				if (!test_bit(STRIPE_HANDLE, &sh->state))
 					atomic_inc(&conf->active_stripes);
-				BUG_ON(list_empty(&sh->lru));
+				BUG_ON(list_empty(&sh->lru) &&
+				       !test_bit(STRIPE_EXPANDING, &sh->state));
 				list_del_init(&sh->lru);
 				if (sh->group) {
 					sh->group->stripes_cnt--;
-- 
cgit v0.10.2


From e8b849158508565e0cd6bc80061124afc5879160 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Mon, 6 Jan 2014 10:35:34 +1100
Subject: md/raid10: fix bug when raid10 recovery fails to recover a block.

commit e875ecea266a543e643b19e44cf472f1412708f9
    md/raid10 record bad blocks as needed during recovery.

added code to the "cannot recover this block" path to record a bad
block rather than fail the whole recovery.
Unfortunately this new case was placed *after* r10bio was freed rather
than *before*, yet it still uses r10bio.
This is will crash with a null dereference.

So move the freeing of r10bio down where it is safe.

Cc: stable@vger.kernel.org (v3.1+)
Fixes: e875ecea266a543e643b19e44cf472f1412708f9
Reported-by: Damian Nowak <spam@nowaker.net>
URL: https://bugzilla.kernel.org/show_bug.cgi?id=68181
Signed-off-by: NeilBrown <neilb@suse.de>

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 6528521..06eeb99 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3218,10 +3218,6 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 			if (j == conf->copies) {
 				/* Cannot recover, so abort the recovery or
 				 * record a bad block */
-				put_buf(r10_bio);
-				if (rb2)
-					atomic_dec(&rb2->remaining);
-				r10_bio = rb2;
 				if (any_working) {
 					/* problem is that there are bad blocks
 					 * on other device(s)
@@ -3253,6 +3249,10 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 					mirror->recovery_disabled
 						= mddev->recovery_disabled;
 				}
+				put_buf(r10_bio);
+				if (rb2)
+					atomic_dec(&rb2->remaining);
+				r10_bio = rb2;
 				break;
 			}
 		}
-- 
cgit v0.10.2


From 8313b8e57f55b15e5b7f7fc5d1630bbf686a9a97 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Thu, 12 Dec 2013 10:13:33 +1100
Subject: md: fix problem when adding device to read-only array with bitmap.

If an array is started degraded, and then the missing device
is found it can be re-added and a minimal bitmap-based recovery
will bring it fully up-to-date.

If the array is read-only a recovery would not be allowed.
But also if the array is read-only and the missing device was
present very recently, then there could be no need for any
recovery at all, so we simply include the device in the read-only
array without any recovery.

However... if the missing device was removed a little longer ago
it could be missing some updates, but if a bitmap is present it will
be conditionally accepted pending a bitmap-based update.  We don't
currently detect this case properly and will include that old
device into the read-only array with no recovery even though it really
needs a recovery.

This patch keeps track of whether a bitmap-based-recovery is really
needed or not in the new Bitmap_sync rdev flag.  If that is set,
then the device will not be added to a read-only array.

Cc: Andrei Warkentin <andreiw@vmware.com>
Fixes: d70ed2e4fafdbef0800e73942482bb075c21578b
Cc: stable@vger.kernel.org (3.2+)
Signed-off-by: NeilBrown <neilb@suse.de>

diff --git a/drivers/md/md.c b/drivers/md/md.c
index e60cebf..2a456a5 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1087,6 +1087,7 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
 	rdev->raid_disk = -1;
 	clear_bit(Faulty, &rdev->flags);
 	clear_bit(In_sync, &rdev->flags);
+	clear_bit(Bitmap_sync, &rdev->flags);
 	clear_bit(WriteMostly, &rdev->flags);
 
 	if (mddev->raid_disks == 0) {
@@ -1165,6 +1166,8 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
 		 */
 		if (ev1 < mddev->bitmap->events_cleared)
 			return 0;
+		if (ev1 < mddev->events)
+			set_bit(Bitmap_sync, &rdev->flags);
 	} else {
 		if (ev1 < mddev->events)
 			/* just a hot-add of a new device, leave raid_disk at -1 */
@@ -1573,6 +1576,7 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
 	rdev->raid_disk = -1;
 	clear_bit(Faulty, &rdev->flags);
 	clear_bit(In_sync, &rdev->flags);
+	clear_bit(Bitmap_sync, &rdev->flags);
 	clear_bit(WriteMostly, &rdev->flags);
 
 	if (mddev->raid_disks == 0) {
@@ -1655,6 +1659,8 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
 		 */
 		if (ev1 < mddev->bitmap->events_cleared)
 			return 0;
+		if (ev1 < mddev->events)
+			set_bit(Bitmap_sync, &rdev->flags);
 	} else {
 		if (ev1 < mddev->events)
 			/* just a hot-add of a new device, leave raid_disk at -1 */
@@ -2798,6 +2804,7 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len)
 		else
 			rdev->saved_raid_disk = -1;
 		clear_bit(In_sync, &rdev->flags);
+		clear_bit(Bitmap_sync, &rdev->flags);
 		err = rdev->mddev->pers->
 			hot_add_disk(rdev->mddev, rdev);
 		if (err) {
@@ -5770,6 +5777,7 @@ static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info)
 			    info->raid_disk < mddev->raid_disks) {
 				rdev->raid_disk = info->raid_disk;
 				set_bit(In_sync, &rdev->flags);
+				clear_bit(Bitmap_sync, &rdev->flags);
 			} else
 				rdev->raid_disk = -1;
 		} else
@@ -7716,7 +7724,8 @@ static int remove_and_add_spares(struct mddev *mddev,
 		if (test_bit(Faulty, &rdev->flags))
 			continue;
 		if (mddev->ro &&
-		    rdev->saved_raid_disk < 0)
+		    ! (rdev->saved_raid_disk >= 0 &&
+		       !test_bit(Bitmap_sync, &rdev->flags)))
 			continue;
 
 		rdev->recovery_offset = 0;
@@ -7797,9 +7806,12 @@ void md_check_recovery(struct mddev *mddev)
 			 * As we only add devices that are already in-sync,
 			 * we can activate the spares immediately.
 			 */
-			clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			remove_and_add_spares(mddev, NULL);
-			mddev->pers->spare_active(mddev);
+			/* There is no thread, but we need to call
+			 * ->spare_active and clear saved_raid_disk
+			 */
+			md_reap_sync_thread(mddev);
+			clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			goto unlock;
 		}
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 2f5cc8a..0095ec8 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -129,6 +129,9 @@ struct md_rdev {
 enum flag_bits {
 	Faulty,			/* device is known to have a fault */
 	In_sync,		/* device is in_sync with rest of array */
+	Bitmap_sync,		/* ..actually, not quite In_sync.  Need a
+				 * bitmap-based recovery to get fully in sync
+				 */
 	Unmerged,		/* device is being added to array and should
 				 * be considerred for bvec_merge_fn but not
 				 * yet for actual IO
-- 
cgit v0.10.2


From f549ed1abc7e4f0292ce08c4143c64a610c8b2cb Mon Sep 17 00:00:00 2001
From: Stephen Rothwell <sfr@canb.auug.org.au>
Date: Tue, 14 Jan 2014 16:36:10 +1100
Subject: arch: Re-sort some Kbuild files to hopefully help avoid some
 conflicts

Checkin:

    93ea02bb8435 arch: Clean up asm/barrier.h implementations using asm-generic/barrier.h

... unfortunately left some Kbuild files out of order, which caused
unnecessary merge conflicts, in particular with checkin:

    e3fec2f74f7f lib: Add missing arch generic-y entries for asm-generic/hash.h

Put them back in order to make the upcoming merges cleaner.

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Link: http://lkml.kernel.org/r/20140114164420.d296fbcc4be3a5f126c86069@canb.auug.org.au
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: David Miller <davem@davemloft.net>

diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index e07c786..9ae21c1 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -1,4 +1,5 @@
 generic-y += auxvec.h
+generic-y += barrier.h
 generic-y += bugs.h
 generic-y += bitsperlong.h
 generic-y += clkdev.h
@@ -47,4 +48,3 @@ generic-y += user.h
 generic-y += vga.h
 generic-y += xor.h
 generic-y += preempt.h
-generic-y += barrier.h
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index 35ec2e5..199b1a9 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -3,6 +3,7 @@ header-y += arch-v10/
 header-y += arch-v32/
 
 
+generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += kvm_para.h
@@ -12,4 +13,3 @@ generic-y += trace_clock.h
 generic-y += vga.h
 generic-y += xor.h
 generic-y += preempt.h
-generic-y += barrier.h
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index a614ec9..ada843c 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -2,6 +2,7 @@
 header-y += ucontext.h
 
 generic-y += auxvec.h
+generic-y += barrier.h
 generic-y += bug.h
 generic-y += bugs.h
 generic-y += clkdev.h
@@ -54,4 +55,3 @@ generic-y += ucontext.h
 generic-y += unaligned.h
 generic-y += xor.h
 generic-y += preempt.h
-generic-y += barrier.h
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index f77fb66..a824265 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -1,7 +1,7 @@
 
+generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += trace_clock.h
 generic-y += syscalls.h
 generic-y += preempt.h
-generic-y += barrier.h
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index 367ef39..032143e 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -1,6 +1,6 @@
 
+generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += trace_clock.h
 generic-y += preempt.h
-generic-y += barrier.h
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index 8df06d0..34b0be4 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -1,8 +1,8 @@
 
+generic-y += barrier.h
 generic-y += word-at-a-time.h auxvec.h user.h cputime.h emergency-restart.h \
 	  segment.h topology.h vga.h device.h percpu.h hw_irq.h mutex.h \
 	  div64.h irq_regs.h kdebug.h kvm_para.h local64.h local.h param.h \
 	  poll.h xor.h clkdev.h exec.h
 generic-y += trace_clock.h
 generic-y += preempt.h
-generic-y += barrier.h
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index ee2993b..fe7471e 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -1,8 +1,8 @@
 
 header-y +=
 
+generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += trace_clock.h
 generic-y += xor.h
 generic-y += preempt.h
-generic-y += barrier.h
-- 
cgit v0.10.2


From 70315d22d3c7383f9a508d0aab21e2eb35b2303a Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 10 Jan 2014 15:34:45 -0500
Subject: inet_diag: fix inet_diag_dump_icsk() to use correct state for
 timewait sockets

Fix inet_diag_dump_icsk() to reflect the fact that both TCP_TIME_WAIT
and TCP_FIN_WAIT2 connections are represented by inet_timewait_sock
(not just TIME_WAIT), and for such sockets the tw_substate field holds
the real state, which can be either TCP_TIME_WAIT or TCP_FIN_WAIT2.

This brings the inet_diag state-matching code in line with the field
it uses to populate idiag_state. This is also analogous to the info
exported in /proc/net/tcp, where get_tcp4_sock() exports sk->sk_state
and get_timewait4_sock() exports tw->tw_substate.

Before fixing this, (a) neither "ss -nemoi" nor "ss -nemoi state
fin-wait-2" would return a socket in TCP_FIN_WAIT2; and (b) "ss -nemoi
state time-wait" would also return sockets in state TCP_FIN_WAIT2.

This is an old bug that predates 05dbc7b ("tcp/dccp: remove twchain").

Signed-off-by: Neal Cardwell <ncardwell@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index a0f52da..e34dccb 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -930,12 +930,15 @@ skip_listen_ht:
 		spin_lock_bh(lock);
 		sk_nulls_for_each(sk, node, &head->chain) {
 			int res;
+			int state;
 
 			if (!net_eq(sock_net(sk), net))
 				continue;
 			if (num < s_num)
 				goto next_normal;
-			if (!(r->idiag_states & (1 << sk->sk_state)))
+			state = (sk->sk_state == TCP_TIME_WAIT) ?
+				inet_twsk(sk)->tw_substate : sk->sk_state;
+			if (!(r->idiag_states & (1 << state)))
 				goto next_normal;
 			if (r->sdiag_family != AF_UNSPEC &&
 			    sk->sk_family != r->sdiag_family)
-- 
cgit v0.10.2


From fdc3452cd2c7b2bfe0f378f92123f4f9a98fa2bd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= <bjorn@mork.no>
Date: Fri, 10 Jan 2014 23:10:17 +0100
Subject: net: usbnet: fix SG initialisation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 60e453a940ac ("USBNET: fix handling padding packet")
added an extra SG entry in case padding is necessary, but
failed to update the initialisation of the list. This can
cause list traversal to fall off the end of the list,
resulting in an oops.

Fixes: 60e453a940ac ("USBNET: fix handling padding packet")
Reported-by: Thomas Kear <thomas@kear.co.nz>
Cc: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Tested-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 8494bb5..aba04f5 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1245,7 +1245,7 @@ static int build_dma_sg(const struct sk_buff *skb, struct urb *urb)
 		return -ENOMEM;
 
 	urb->num_sgs = num_sgs;
-	sg_init_table(urb->sg, urb->num_sgs);
+	sg_init_table(urb->sg, urb->num_sgs + 1);
 
 	sg_set_buf(&urb->sg[s++], skb->data, skb_headlen(skb));
 	total_len += skb_headlen(skb);
-- 
cgit v0.10.2


From 60283df7ac26a4fe2d56631ca2946e04725e7eaf Mon Sep 17 00:00:00 2001
From: Richard Weinberger <richard@nod.at>
Date: Tue, 14 Jan 2014 08:44:47 +0100
Subject: x86/apic: Read Error Status Register correctly

Currently we do a read, a dummy write and a final read to fetch
the error code. The value from the final read is taken.
This is not the recommended way and leads to corrupted/lost ESR
values.

Intel(c) 64 and IA-32 Architectures Software Developer's Manual,
Combined Volumes 1, 2ABC, 3ABC, Section 10.5.3 states:

  Before attempt to read from the ESR, software should first
  write to it. (The value written does not affect the values read
  subsequently; only zero may be written in x2APIC mode.) This
  write clears any previously logged errors and updates the ESR
  with any errors detected since the last write to the ESR.
  This write also rearms the APIC error interrupt triggering
  mechanism.

This patch removes the first read such that we are conform with
the manual.

On my (very old) Pentium MMX SMP system this patch fixes the
issue that APIC errors:

  a) are not always reported and
  b) are reported with false error numbers.

Signed-off-by: Richard Weinberger <richard@nod.at>
Cc: seiji.aguchi@hds.com
Cc: rientjes@google.com
Cc: konrad.wilk@oracle.com
Cc: bp@alien8.de
Cc: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/1389685487-20872-1-git-send-email-richard@nod.at
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index d278736..4ec1dd6 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1968,7 +1968,7 @@ __visible void smp_trace_spurious_interrupt(struct pt_regs *regs)
  */
 static inline void __smp_error_interrupt(struct pt_regs *regs)
 {
-	u32 v0, v1;
+	u32 v;
 	u32 i = 0;
 	static const char * const error_interrupt_reason[] = {
 		"Send CS error",		/* APIC Error Bit 0 */
@@ -1982,21 +1982,20 @@ static inline void __smp_error_interrupt(struct pt_regs *regs)
 	};
 
 	/* First tickle the hardware, only then report what went on. -- REW */
-	v0 = apic_read(APIC_ESR);
 	apic_write(APIC_ESR, 0);
-	v1 = apic_read(APIC_ESR);
+	v = apic_read(APIC_ESR);
 	ack_APIC_irq();
 	atomic_inc(&irq_err_count);
 
-	apic_printk(APIC_DEBUG, KERN_DEBUG "APIC error on CPU%d: %02x(%02x)",
-		    smp_processor_id(), v0 , v1);
+	apic_printk(APIC_DEBUG, KERN_DEBUG "APIC error on CPU%d: %02x",
+		    smp_processor_id(), v);
 
-	v1 = v1 & 0xff;
-	while (v1) {
-		if (v1 & 0x1)
+	v &= 0xff;
+	while (v) {
+		if (v & 0x1)
 			apic_printk(APIC_DEBUG, KERN_CONT " : %s", error_interrupt_reason[i]);
 		i++;
-		v1 >>= 1;
+		v >>= 1;
 	}
 
 	apic_printk(APIC_DEBUG, KERN_CONT "\n");
-- 
cgit v0.10.2


From 1c59a861d6982edf3f9905ad2098575336ae904d Mon Sep 17 00:00:00 2001
From: Eugene Crosser <Eugene.Crosser@ru.ibm.com>
Date: Wed, 24 Apr 2013 12:00:23 +0200
Subject: s390/qdio: bridgeport support - CHSC part

Introduce function for the "Perform network-subchannel operation"
CHSC command with operation code "bridgeport information",
and bit definitions for "characteristics" pertaning to this command.

Signed-off-by: Eugene Crosser <eugene.crosser@ru.ibm.com>
Reviewed-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/include/asm/css_chars.h b/arch/s390/include/asm/css_chars.h
index 7e1c917..09d1dd4 100644
--- a/arch/s390/include/asm/css_chars.h
+++ b/arch/s390/include/asm/css_chars.h
@@ -29,6 +29,8 @@ struct css_general_char {
 	u32 fcx : 1;	 /* bit 88 */
 	u32 : 19;
 	u32 alt_ssi : 1; /* bit 108 */
+	u32:1;
+	u32 narf:1;	 /* bit 110 */
 } __packed;
 
 extern struct css_general_char css_general_characteristics;
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index 57d0d7e..0a1abf1 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -378,6 +378,34 @@ struct qdio_initialize {
 	struct qdio_outbuf_state *output_sbal_state_array;
 };
 
+/**
+ * enum qdio_brinfo_entry_type - type of address entry for qdio_brinfo_desc()
+ * @l3_ipv6_addr: entry contains IPv6 address
+ * @l3_ipv4_addr: entry contains IPv4 address
+ * @l2_addr_lnid: entry contains MAC address and VLAN ID
+ */
+enum qdio_brinfo_entry_type {l3_ipv6_addr, l3_ipv4_addr, l2_addr_lnid};
+
+/**
+ * struct qdio_brinfo_entry_XXX - Address entry for qdio_brinfo_desc()
+ * @nit:  Network interface token
+ * @addr: Address of one of the three types
+ *
+ * The struct is passed to the callback function by qdio_brinfo_desc()
+ */
+struct qdio_brinfo_entry_l3_ipv6 {
+	u64 nit;
+	struct { unsigned char _s6_addr[16]; } addr;
+} __packed;
+struct qdio_brinfo_entry_l3_ipv4 {
+	u64 nit;
+	struct { uint32_t _s_addr; } addr;
+} __packed;
+struct qdio_brinfo_entry_l2 {
+	u64 nit;
+	struct { u8 mac[6]; u16 lnid; } addr_lnid;
+} __packed;
+
 #define QDIO_STATE_INACTIVE		0x00000002 /* after qdio_cleanup */
 #define QDIO_STATE_ESTABLISHED		0x00000004 /* after qdio_establish */
 #define QDIO_STATE_ACTIVE		0x00000008 /* after qdio_activate */
@@ -399,5 +427,10 @@ extern int qdio_get_next_buffers(struct ccw_device *, int, int *, int *);
 extern int qdio_shutdown(struct ccw_device *, int);
 extern int qdio_free(struct ccw_device *);
 extern int qdio_get_ssqd_desc(struct ccw_device *, struct qdio_ssqd_desc *);
+extern int qdio_pnso_brinfo(struct subchannel_id schid,
+		int cnc, u16 *response,
+		void (*cb)(void *priv, enum qdio_brinfo_entry_type type,
+				void *entry),
+		void *priv);
 
 #endif /* __QDIO_H__ */
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index eee70cb..f6b9188 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -55,6 +55,7 @@ int chsc_error_from_response(int response)
 	case 0x0004:
 		return -EOPNOTSUPP;
 	case 0x000b:
+	case 0x0107:		/* "Channel busy" for the op 0x003d */
 		return -EBUSY;
 	case 0x0100:
 	case 0x0102:
@@ -1202,3 +1203,35 @@ out:
 	return ret;
 }
 EXPORT_SYMBOL_GPL(chsc_scm_info);
+
+/**
+ * chsc_pnso_brinfo() - Perform Network-Subchannel Operation, Bridge Info.
+ * @schid:		id of the subchannel on which PNSO is performed
+ * @brinfo_area:	request and response block for the operation
+ * @resume_token:	resume token for multiblock response
+ * @cnc:		Boolean change-notification control
+ *
+ * brinfo_area must be allocated by the caller with get_zeroed_page(GFP_KERNEL)
+ *
+ * Returns 0 on success.
+ */
+int chsc_pnso_brinfo(struct subchannel_id schid,
+		struct chsc_pnso_area *brinfo_area,
+		struct chsc_brinfo_resume_token resume_token,
+		int cnc)
+{
+	memset(brinfo_area, 0, sizeof(*brinfo_area));
+	brinfo_area->request.length = 0x0030;
+	brinfo_area->request.code = 0x003d; /* network-subchannel operation */
+	brinfo_area->m	   = schid.m;
+	brinfo_area->ssid  = schid.ssid;
+	brinfo_area->sch   = schid.sch_no;
+	brinfo_area->cssid = schid.cssid;
+	brinfo_area->oc    = 0; /* Store-network-bridging-information list */
+	brinfo_area->resume_token = resume_token;
+	brinfo_area->n	   = (cnc != 0);
+	if (chsc(brinfo_area))
+		return -EIO;
+	return chsc_error_from_response(brinfo_area->response.code);
+}
+EXPORT_SYMBOL_GPL(chsc_pnso_brinfo);
diff --git a/drivers/s390/cio/chsc.h b/drivers/s390/cio/chsc.h
index 23d072e..7e53a9c 100644
--- a/drivers/s390/cio/chsc.h
+++ b/drivers/s390/cio/chsc.h
@@ -61,7 +61,9 @@ struct css_chsc_char {
 	u32 : 20;
 	u32 scssc : 1;  /* bit 107 */
 	u32 scsscf : 1; /* bit 108 */
-	u32 : 19;
+	u32:7;
+	u32 pnso:1; /* bit 116 */
+	u32:11;
 }__attribute__((packed));
 
 extern struct css_chsc_char css_chsc_characteristics;
@@ -188,6 +190,53 @@ struct chsc_scm_info {
 
 int chsc_scm_info(struct chsc_scm_info *scm_area, u64 token);
 
+struct chsc_brinfo_resume_token {
+	u64 t1;
+	u64 t2;
+} __packed;
+
+struct chsc_brinfo_naihdr {
+	struct chsc_brinfo_resume_token resume_token;
+	u32:32;
+	u32 instance;
+	u32:24;
+	u8 naids;
+	u32 reserved[3];
+} __packed;
+
+struct chsc_pnso_area {
+	struct chsc_header request;
+	u8:2;
+	u8 m:1;
+	u8:5;
+	u8:2;
+	u8 ssid:2;
+	u8 fmt:4;
+	u16 sch;
+	u8:8;
+	u8 cssid;
+	u16:16;
+	u8 oc;
+	u32:24;
+	struct chsc_brinfo_resume_token resume_token;
+	u32 n:1;
+	u32:31;
+	u32 reserved[3];
+	struct chsc_header response;
+	u32:32;
+	struct chsc_brinfo_naihdr naihdr;
+	union {
+		struct qdio_brinfo_entry_l3_ipv6 l3_ipv6[0];
+		struct qdio_brinfo_entry_l3_ipv4 l3_ipv4[0];
+		struct qdio_brinfo_entry_l2	 l2[0];
+	} entries;
+} __packed;
+
+int chsc_pnso_brinfo(struct subchannel_id schid,
+		struct chsc_pnso_area *brinfo_area,
+		struct chsc_brinfo_resume_token resume_token,
+		int cnc);
+
 #ifdef CONFIG_SCM_BUS
 int scm_update_information(void);
 int scm_process_availability_information(void);
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index 3e602e8..c883a08 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -1752,6 +1752,97 @@ int qdio_stop_irq(struct ccw_device *cdev, int nr)
 }
 EXPORT_SYMBOL(qdio_stop_irq);
 
+/**
+ * qdio_pnso_brinfo() - perform network subchannel op #0 - bridge info.
+ * @schid:		Subchannel ID.
+ * @cnc:		Boolean Change-Notification Control
+ * @response:		Response code will be stored at this address
+ * @cb: 		Callback function will be executed for each element
+ *			of the address list
+ * @priv:		Pointer passed from the caller to qdio_pnso_brinfo()
+ * @type:		Type of the address entry passed to the callback
+ * @entry:		Entry containg the address of the specified type
+ * @priv:		Pointer to pass to the callback function.
+ *
+ * Performs "Store-network-bridging-information list" operation and calls
+ * the callback function for every entry in the list. If "change-
+ * notification-control" is set, further changes in the address list
+ * will be reported via the IPA command.
+ */
+int qdio_pnso_brinfo(struct subchannel_id schid,
+		int cnc, u16 *response,
+		void (*cb)(void *priv, enum qdio_brinfo_entry_type type,
+				void *entry),
+		void *priv)
+{
+	struct chsc_pnso_area *rr;
+	int rc;
+	u32 prev_instance = 0;
+	int isfirstblock = 1;
+	int i, size, elems;
+
+	rr = (struct chsc_pnso_area *)get_zeroed_page(GFP_KERNEL);
+	if (rr == NULL)
+		return -ENOMEM;
+	do {
+		/* on the first iteration, naihdr.resume_token will be zero */
+		rc = chsc_pnso_brinfo(schid, rr, rr->naihdr.resume_token, cnc);
+		if (rc != 0 && rc != -EBUSY)
+			goto out;
+		if (rr->response.code != 1) {
+			rc = -EIO;
+			continue;
+		} else
+			rc = 0;
+
+		if (cb == NULL)
+			continue;
+
+		size = rr->naihdr.naids;
+		elems = (rr->response.length -
+				sizeof(struct chsc_header) -
+				sizeof(struct chsc_brinfo_naihdr)) /
+				size;
+
+		if (!isfirstblock && (rr->naihdr.instance != prev_instance)) {
+			/* Inform the caller that they need to scrap */
+			/* the data that was already reported via cb */
+				rc = -EAGAIN;
+				break;
+		}
+		isfirstblock = 0;
+		prev_instance = rr->naihdr.instance;
+		for (i = 0; i < elems; i++)
+			switch (size) {
+			case sizeof(struct qdio_brinfo_entry_l3_ipv6):
+				(*cb)(priv, l3_ipv6_addr,
+						&rr->entries.l3_ipv6[i]);
+				break;
+			case sizeof(struct qdio_brinfo_entry_l3_ipv4):
+				(*cb)(priv, l3_ipv4_addr,
+						&rr->entries.l3_ipv4[i]);
+				break;
+			case sizeof(struct qdio_brinfo_entry_l2):
+				(*cb)(priv, l2_addr_lnid,
+						&rr->entries.l2[i]);
+				break;
+			default:
+				WARN_ON_ONCE(1);
+				rc = -EIO;
+				goto out;
+			}
+	} while (rr->response.code == 0x0107 ||  /* channel busy */
+		  (rr->response.code == 1 && /* list stored */
+		   /* resume token is non-zero => list incomplete */
+		   (rr->naihdr.resume_token.t1 || rr->naihdr.resume_token.t2)));
+	(*response) = rr->response.code;
+
+out:
+	free_page((unsigned long)rr);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(qdio_pnso_brinfo);
+
 static int __init init_QDIO(void)
 {
 	int rc;
-- 
cgit v0.10.2


From 2fac2b891f287691c27ee8d2eeecf39571b27fea Mon Sep 17 00:00:00 2001
From: Stephen Warren <swarren@nvidia.com>
Date: Mon, 13 Jan 2014 14:29:04 -0700
Subject: i2c: Re-instate body of i2c_parent_is_i2c_adapter()

The body of i2c_parent_is_i2c_adapter() is currently guarded by
I2C_MUX. It should be CONFIG_I2C_MUX instead.

Among potentially other problems, this resulted in i2c_lock_adapter()
only locking I2C mux child adapters, and not the parent adapter. In
turn, this could allow inter-mingling of mux child selection and I2C
transactions, which could result in I2C transactions being directed to
the wrong I2C bus, and possibly even switching between busses in the
middle of a transaction.

One concrete issue caused by this bug was corrupted HDMI EDID reads
during boot on the NVIDIA Tegra Seaboard system, although this only
became apparent in recent linux-next, when the boot timing was changed
just enough to trigger the race condition.

Fixes: 3923172b3d70 ("i2c: reduce parent checking to a NOOP in non-I2C_MUX case")
Cc: Phil Carmody <phil.carmody@partner.samsung.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Stephen Warren <swarren@nvidia.com>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>

diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index eff50e0..d9c8dbd3 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -445,7 +445,7 @@ static inline void i2c_set_adapdata(struct i2c_adapter *dev, void *data)
 static inline struct i2c_adapter *
 i2c_parent_is_i2c_adapter(const struct i2c_adapter *adapter)
 {
-#if IS_ENABLED(I2C_MUX)
+#if IS_ENABLED(CONFIG_I2C_MUX)
 	struct device *parent = adapter->dev.parent;
 
 	if (parent != NULL && parent->type == &i2c_adapter_type)
-- 
cgit v0.10.2


From 3f9aec7610b39521c7c69d754de7265f6994c194 Mon Sep 17 00:00:00 2001
From: Jean Delvare <khali@linux-fr.org>
Date: Tue, 14 Jan 2014 15:59:55 +0100
Subject: hwmon: (coretemp) Fix truncated name of alarm attributes

When the core number exceeds 9, the size of the buffer storing the
alarm attribute name is insufficient and the attribute name is
truncated. This causes libsensors to skip these attributes as the
truncated name is not recognized.

Reported-by: Andreas Hollmann <hollmann@in.tum.de>
Signed-off-by: Jean Delvare <khali@linux-fr.org>
Cc: stable@vger.kernel.org
Signed-off-by: Guenter Roeck <linux@roeck-us.net>

diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index 78be661..9425098 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -52,7 +52,7 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
 
 #define BASE_SYSFS_ATTR_NO	2	/* Sysfs Base attr no for coretemp */
 #define NUM_REAL_CORES		32	/* Number of Real cores per cpu */
-#define CORETEMP_NAME_LENGTH	17	/* String Length of attrs */
+#define CORETEMP_NAME_LENGTH	19	/* String Length of attrs */
 #define MAX_CORE_ATTRS		4	/* Maximum no of basic attrs */
 #define TOTAL_ATTRS		(MAX_CORE_ATTRS + 1)
 #define MAX_CORE_DATA		(NUM_REAL_CORES + BASE_SYSFS_ATTR_NO)
-- 
cgit v0.10.2


From 19259943f0954dcd1817f94776376bf51c6a46d5 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Date: Sat, 7 Dec 2013 21:02:36 +0800
Subject: x86, kaslr: Remove unused including <linux/version.h>

Remove including <linux/version.h> that don't need it.

Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Link: http://lkml.kernel.org/r/CAPgLHd-Fjx1RybjWFAu1vHRfTvhWwMLL3x46BouC5uNxHPjy1A@mail.gmail.com
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 84be175..90a21f4 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -10,7 +10,6 @@
 #include <linux/uts.h>
 #include <linux/utsname.h>
 #include <generated/utsrelease.h>
-#include <linux/version.h>
 
 /* Simplified build-specific string for starting entropy. */
 static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
-- 
cgit v0.10.2


From da2b6fb990cf782b18952f534ec7323453bc4fc9 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 10 Dec 2013 12:27:45 -0800
Subject: x86, kaslr: Clarify RANDOMIZE_BASE_MAX_OFFSET

The help text for RANDOMIZE_BASE_MAX_OFFSET was confusing. This has been
clarified, and updated to be an export-only tunable.

Signed-off-by: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/20131210202745.GA2961@www.outflux.net
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 596cd9e..5c9e19d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1747,26 +1747,33 @@ config RANDOMIZE_BASE
 	   possible. At best, due to page table layouts, 64-bit can use
 	   9 bits of entropy and 32-bit uses 8 bits.
 
+	   If unsure, say N.
+
 config RANDOMIZE_BASE_MAX_OFFSET
-	hex "Maximum ASLR offset allowed"
+	hex "Maximum kASLR offset allowed" if EXPERT
 	depends on RANDOMIZE_BASE
 	range 0x0 0x20000000 if X86_32
 	default "0x20000000" if X86_32
 	range 0x0 0x40000000 if X86_64
 	default "0x40000000" if X86_64
 	---help---
-	 Determines the maximal offset in bytes that will be applied to the
-	 kernel when Address Space Layout Randomization (ASLR) is active.
-	 Must be less than or equal to the actual physical memory on the
-	 system. This must be a multiple of CONFIG_PHYSICAL_ALIGN.
+	  The lesser of RANDOMIZE_BASE_MAX_OFFSET and available physical
+	  memory is used to determine the maximal offset in bytes that will
+	  be applied to the kernel when kernel Address Space Layout
+	  Randomization (kASLR) is active. This must be a multiple of
+	  PHYSICAL_ALIGN.
+
+	  On 32-bit this is limited to 512MiB by page table layouts. The
+	  default is 512MiB.
 
-	 On 32-bit this is limited to 512MiB.
+	  On 64-bit this is limited by how the kernel fixmap page table is
+	  positioned, so this cannot be larger than 1GiB currently. Without
+	  RANDOMIZE_BASE, there is a 512MiB to 1.5GiB split between kernel
+	  and modules. When RANDOMIZE_BASE_MAX_OFFSET is above 512MiB, the
+	  modules area will shrink to compensate, up to the current maximum
+	  1GiB to 1GiB split. The default is 1GiB.
 
-	 On 64-bit this is limited by how the kernel fixmap page table is
-	 positioned, so this cannot be larger that 1GiB currently. Normally
-	 there is a 512MiB to 1.5GiB split between kernel and modules. When
-	 this is raised above the 512MiB default, the modules area will
-	 shrink to compensate, up to the current maximum 1GiB to 1GiB split.
+	  If unsure, leave at the default value.
 
 # Relocation on x86 needs some additional build support
 config X86_NEED_RELOCS
-- 
cgit v0.10.2


From 509051ea8427b2f73f065a1b0a1ef871727c9cb2 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 14 Jan 2014 17:52:14 -0300
Subject: perf record: Rename --no-delay to --no-buffering

That is how the option summary describes it and so that we can free
--delay to replace --initial-delay and then be consistent with stat's
--delay equivalent option.

Suggested-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-f8hd2010uhjl2zzb34hepbmi@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 82bffac..3a35a85 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -68,8 +68,7 @@ OPTIONS
 --realtime=::
 	Collect data with this RT SCHED_FIFO priority.
 
--D::
---no-delay::
+--no-buffering::
 	Collect data without buffering.
 
 -c::
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 07d4cf8..78e790f 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -838,7 +838,7 @@ const struct option record_options[] = {
 		    "record events on existing thread id"),
 	OPT_INTEGER('r', "realtime", &record.realtime_prio,
 		    "collect data with this RT SCHED_FIFO priority"),
-	OPT_BOOLEAN('D', "no-delay", &record.opts.no_delay,
+	OPT_BOOLEAN(0, "no-buffering", &record.opts.no_buffering,
 		    "collect data without buffering"),
 	OPT_BOOLEAN('R', "raw-samples", &record.opts.raw_samples,
 		    "collect raw sample records from all opened counters"),
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 4bd44ab..896f270 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2258,7 +2258,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 			},
 			.user_freq     = UINT_MAX,
 			.user_interval = ULLONG_MAX,
-			.no_delay      = true,
+			.no_buffering  = true,
 			.mmap_pages    = 1024,
 		},
 		.output = stdout,
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index af1ce6e..3c2f213 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -252,7 +252,7 @@ struct record_opts {
 	int	     call_graph;
 	bool	     group;
 	bool	     inherit_stat;
-	bool	     no_delay;
+	bool	     no_buffering;
 	bool	     no_inherit;
 	bool	     no_inherit_set;
 	bool	     no_samples;
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
index 5a016f6..c505ef2 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -11,10 +11,10 @@ int test__syscall_open_tp_fields(void)
 			.uid = UINT_MAX,
 			.uses_mmap = true,
 		},
-		.no_delay   = true,
-		.freq	    = 1,
-		.mmap_pages = 256,
-		.raw_samples = true,
+		.no_buffering = true,
+		.freq	      = 1,
+		.mmap_pages   = 256,
+		.raw_samples  = true,
 	};
 	const char *filename = "/etc/passwd";
 	int flags = O_RDONLY | O_DIRECTORY;
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 39cc7c3..aca1a83 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -39,9 +39,9 @@ int test__PERF_RECORD(void)
 			.uid = UINT_MAX,
 			.uses_mmap = true,
 		},
-		.no_delay   = true,
-		.freq	    = 10,
-		.mmap_pages = 256,
+		.no_buffering = true,
+		.freq	      = 10,
+		.mmap_pages   = 256,
 	};
 	cpu_set_t cpu_mask;
 	size_t cpu_mask_size = sizeof(cpu_mask);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index cd4630a..22e18a2 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -627,7 +627,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	if (opts->sample_address)
 		perf_evsel__set_sample_bit(evsel, DATA_SRC);
 
-	if (opts->no_delay) {
+	if (opts->no_buffering) {
 		attr->watermark = 0;
 		attr->wakeup_events = 1;
 	}
-- 
cgit v0.10.2


From a6205a35ba2d56dcfb79b08cc11b8c7d549826aa Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 14 Jan 2014 17:58:12 -0300
Subject: perf record: Rename --initial-delay to --delay

To be consistent with the equivalent option in 'stat', also, for the
same reason, use -D as the one letter alias.

Suggested-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-p5yjnopajb3a8x0xha7yl5w8@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 3a35a85..c71b0f3 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -208,7 +208,8 @@ overrides that and uses per-thread mmaps.  A side-effect of that is that
 inheritance is automatically disabled.  --per-thread is ignored with a warning
 if combined with -a or -C options.
 
---initial-delay msecs::
+-D::
+--delay=::
 After starting the program, wait msecs before measuring. This is useful to
 filter out the startup phase of the program, which is often very different.
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 78e790f..3c394bf 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -882,7 +882,7 @@ const struct option record_options[] = {
 	OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
 		     "monitor event in cgroup name only",
 		     parse_cgroups),
-	OPT_UINTEGER(0, "initial-delay", &record.opts.initial_delay,
+	OPT_UINTEGER('D', "delay", &record.opts.initial_delay,
 		  "ms to wait before starting measurement after program start"),
 	OPT_STRING('u', "uid", &record.opts.target.uid_str, "user",
 		   "user to profile"),
-- 
cgit v0.10.2


From 267d29a69c6af39445f36102a832b25ed483f299 Mon Sep 17 00:00:00 2001
From: Christian Engelmayer <cengelma@gmx.at>
Date: Sat, 11 Jan 2014 22:19:30 +0100
Subject: ieee802154: Fix memory leak in ieee802154_add_iface()

Fix a memory leak in the ieee802154_add_iface() error handling path.
Detected by Coverity: CID 710490.

Signed-off-by: Christian Engelmayer <cengelma@gmx.at>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index d08c7a4..89b265a 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -221,8 +221,10 @@ int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info)
 
 	if (info->attrs[IEEE802154_ATTR_DEV_TYPE]) {
 		type = nla_get_u8(info->attrs[IEEE802154_ATTR_DEV_TYPE]);
-		if (type >= __IEEE802154_DEV_MAX)
-			return -EINVAL;
+		if (type >= __IEEE802154_DEV_MAX) {
+			rc = -EINVAL;
+			goto nla_put_failure;
+		}
 	}
 
 	dev = phy->add_iface(phy, devname, type);
-- 
cgit v0.10.2


From 3b56496865f9f7d9bcb2f93b44c63f274f08e3b6 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Wed, 15 Jan 2014 00:07:11 +0100
Subject: x86, cpu, amd: Add workaround for family 16h, erratum 793

This adds the workaround for erratum 793 as a precaution in case not
every BIOS implements it.  This addresses CVE-2013-6885.

Erratum text:

[Revision Guide for AMD Family 16h Models 00h-0Fh Processors,
document 51810 Rev. 3.04 November 2013]

793 Specific Combination of Writes to Write Combined Memory Types and
Locked Instructions May Cause Core Hang

Description

Under a highly specific and detailed set of internal timing
conditions, a locked instruction may trigger a timing sequence whereby
the write to a write combined memory type is not flushed, causing the
locked instruction to stall indefinitely.

Potential Effect on System

Processor core hang.

Suggested Workaround

BIOS should set MSR
C001_1020[15] = 1b.

Fix Planned

No fix planned

[ hpa: updated description, fixed typo in MSR name ]

Signed-off-by: Borislav Petkov <bp@suse.de>
Link: http://lkml.kernel.org/r/20140114230711.GS29865@pd.tnic
Tested-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@amd.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index 37813b5..59cea18 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -184,6 +184,7 @@
 #define MSR_AMD64_PATCH_LOADER		0xc0010020
 #define MSR_AMD64_OSVW_ID_LENGTH	0xc0010140
 #define MSR_AMD64_OSVW_STATUS		0xc0010141
+#define MSR_AMD64_LS_CFG		0xc0011020
 #define MSR_AMD64_DC_CFG		0xc0011022
 #define MSR_AMD64_BU_CFG2		0xc001102a
 #define MSR_AMD64_IBSFETCHCTL		0xc0011030
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index bca023b..59bfebc 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -508,6 +508,16 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
 	}
 #endif
+
+	/* F16h erratum 793, CVE-2013-6885 */
+	if (c->x86 == 0x16 && c->x86_model <= 0xf) {
+		u64 val;
+
+		rdmsrl(MSR_AMD64_LS_CFG, val);
+		if (!(val & BIT(15)))
+			wrmsrl(MSR_AMD64_LS_CFG, val | BIT(15));
+	}
+
 }
 
 static const int amd_erratum_383[];
-- 
cgit v0.10.2


From a02bbb1ccfe81d3e859ab2ddde6a2eff9c8b39fd Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Sun, 12 Jan 2014 13:37:56 +0200
Subject: MAINTAINERS: add virtio-dev ML for virtio

Since virtio is an OASIS standard draft now, virtio implementation
discussions are taking place on the virtio-dev OASIS mailing list.
Update MAINTAINERS.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/MAINTAINERS b/MAINTAINERS
index 31a0462..6a6e4ac 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9231,6 +9231,7 @@ F:	include/media/videobuf2-*
 
 VIRTIO CONSOLE DRIVER
 M:	Amit Shah <amit.shah@redhat.com>
+L:	virtio-dev@lists.oasis-open.org
 L:	virtualization@lists.linux-foundation.org
 S:	Maintained
 F:	drivers/char/virtio_console.c
@@ -9240,6 +9241,7 @@ F:	include/uapi/linux/virtio_console.h
 VIRTIO CORE, NET AND BLOCK DRIVERS
 M:	Rusty Russell <rusty@rustcorp.com.au>
 M:	"Michael S. Tsirkin" <mst@redhat.com>
+L:	virtio-dev@lists.oasis-open.org
 L:	virtualization@lists.linux-foundation.org
 S:	Maintained
 F:	drivers/virtio/
@@ -9252,6 +9254,7 @@ F:	include/uapi/linux/virtio_*.h
 VIRTIO HOST (VHOST)
 M:	"Michael S. Tsirkin" <mst@redhat.com>
 L:	kvm@vger.kernel.org
+L:	virtio-dev@lists.oasis-open.org
 L:	virtualization@lists.linux-foundation.org
 L:	netdev@vger.kernel.org
 S:	Maintained
-- 
cgit v0.10.2


From 7c4b5175f65f31e0cd9867a6ddc3171007dfc110 Mon Sep 17 00:00:00 2001
From: Peter Korsgaard <peter@korsgaard.com>
Date: Sun, 12 Jan 2014 23:15:51 +0100
Subject: dm9601: add USB IDs for new dm96xx variants

A number of new dm96xx variants now exist.

Reported-by: Joseph Chang <joseph_chang@davicom.com.tw>
Signed-off-by: Peter Korsgaard <peter@korsgaard.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c
index 14aa48f..e802198 100644
--- a/drivers/net/usb/dm9601.c
+++ b/drivers/net/usb/dm9601.c
@@ -614,6 +614,18 @@ static const struct usb_device_id products[] = {
 	 USB_DEVICE(0x0a46, 0x9621),	/* DM9621A USB to Fast Ethernet Adapter */
 	 .driver_info = (unsigned long)&dm9601_info,
 	},
+	{
+	 USB_DEVICE(0x0a46, 0x9622),	/* DM9622 USB to Fast Ethernet Adapter */
+	 .driver_info = (unsigned long)&dm9601_info,
+	},
+	{
+	 USB_DEVICE(0x0a46, 0x0269),	/* DM962OA USB to Fast Ethernet Adapter */
+	 .driver_info = (unsigned long)&dm9601_info,
+	},
+	{
+	 USB_DEVICE(0x0a46, 0x1269),	/* DM9621A USB to Fast Ethernet Adapter */
+	 .driver_info = (unsigned long)&dm9601_info,
+	},
 	{},			// END
 };
 
-- 
cgit v0.10.2


From 95f4a45de1a0f172b35451fc52283290adb21f6e Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Mon, 13 Jan 2014 02:45:22 +0100
Subject: net: avoid reference counter overflows on fib_rules in multicast
 forwarding

Bob Falken reported that after 4G packets, multicast forwarding stopped
working. This was because of a rule reference counter overflow which
freed the rule as soon as the overflow happend.

This patch solves this by adding the FIB_LOOKUP_NOREF flag to
fib_rules_lookup calls. This is safe even from non-rcu locked sections
as in this case the flag only implies not taking a reference to the rule,
which we don't need at all.

Rules only hold references to the namespace, which are guaranteed to be
available during the call of the non-rcu protected function reg_vif_xmit
because of the interface reference which itself holds a reference to
the net namespace.

Fixes: f0ad0860d01e47 ("ipv4: ipmr: support multiple tables")
Fixes: d1db275dd3f6e4 ("ipv6: ip6mr: support multiple tables")
Reported-by: Bob Falken <NetFestivalHaveFun@gmx.com>
Cc: Patrick McHardy <kaber@trash.net>
Cc: Thomas Graf <tgraf@suug.ch>
Cc: Julian Anastasov <ja@ssi.bg>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 62212c7..1672409 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -157,9 +157,12 @@ static struct mr_table *ipmr_get_table(struct net *net, u32 id)
 static int ipmr_fib_lookup(struct net *net, struct flowi4 *flp4,
 			   struct mr_table **mrt)
 {
-	struct ipmr_result res;
-	struct fib_lookup_arg arg = { .result = &res, };
 	int err;
+	struct ipmr_result res;
+	struct fib_lookup_arg arg = {
+		.result = &res,
+		.flags = FIB_LOOKUP_NOREF,
+	};
 
 	err = fib_rules_lookup(net->ipv4.mr_rules_ops,
 			       flowi4_to_flowi(flp4), 0, &arg);
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index f365310..0eb4038 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -141,9 +141,12 @@ static struct mr6_table *ip6mr_get_table(struct net *net, u32 id)
 static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
 			    struct mr6_table **mrt)
 {
-	struct ip6mr_result res;
-	struct fib_lookup_arg arg = { .result = &res, };
 	int err;
+	struct ip6mr_result res;
+	struct fib_lookup_arg arg = {
+		.result = &res,
+		.flags = FIB_LOOKUP_NOREF,
+	};
 
 	err = fib_rules_lookup(net->ipv6.mr6_rules_ops,
 			       flowi6_to_flowi(flp6), 0, &arg);
-- 
cgit v0.10.2


From 51bb352f15595f2dee42b599680809de3d08999d Mon Sep 17 00:00:00 2001
From: Jitendra Kalsaria <jitendra.kalsaria@qlogic.com>
Date: Tue, 14 Jan 2014 13:57:25 -0500
Subject: qlge: Fix vlan netdev features.

vlan gets the same netdev features except vlan filter.

Signed-off-by: Jitendra Kalsaria <jitendra.kalsaria@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 449f506..f705aee 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -4765,6 +4765,8 @@ static int qlge_probe(struct pci_dev *pdev,
 			    NETIF_F_RXCSUM;
 	ndev->features = ndev->hw_features;
 	ndev->vlan_features = ndev->hw_features;
+	/* vlan gets same features (except vlan filter) */
+	ndev->vlan_features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
 
 	if (test_bit(QL_DMA64, &qdev->flags))
 		ndev->features |= NETIF_F_HIGHDMA;
-- 
cgit v0.10.2


From fdd239ac99a0cc298b382c5ab5e7bcd09e8933d7 Mon Sep 17 00:00:00 2001
From: Ben Skeggs <bskeggs@redhat.com>
Date: Tue, 14 Jan 2014 14:56:22 +1000
Subject: drm/nouveau: fix null ptr dereferences on some boards

Regression from "device: populate master subdev pointer only when fully
constructed"

Reported-by: Bob Gleitsmann <rjgleits@bellsouth.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>

diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/i2c.h b/drivers/gpu/drm/nouveau/core/include/subdev/i2c.h
index 9fa5da7..7f50a85 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/i2c.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/i2c.h
@@ -73,7 +73,7 @@ struct nouveau_i2c {
 	int (*identify)(struct nouveau_i2c *, int index,
 			const char *what, struct nouveau_i2c_board_info *,
 			bool (*match)(struct nouveau_i2c_port *,
-				      struct i2c_board_info *));
+				      struct i2c_board_info *, void *), void *);
 	struct list_head ports;
 };
 
diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/instmem.h b/drivers/gpu/drm/nouveau/core/include/subdev/instmem.h
index ec7a54e..4aca338 100644
--- a/drivers/gpu/drm/nouveau/core/include/subdev/instmem.h
+++ b/drivers/gpu/drm/nouveau/core/include/subdev/instmem.h
@@ -50,6 +50,13 @@ struct nouveau_instmem {
 static inline struct nouveau_instmem *
 nouveau_instmem(void *obj)
 {
+	/* nv04/nv40 impls need to create objects in their constructor,
+	 * which is before the subdev pointer is valid
+	 */
+	if (nv_iclass(obj, NV_SUBDEV_CLASS) &&
+	    nv_subidx(obj) == NVDEV_SUBDEV_INSTMEM)
+		return obj;
+
 	return (void *)nv_device(obj)->subdev[NVDEV_SUBDEV_INSTMEM];
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/i2c/base.c b/drivers/gpu/drm/nouveau/core/subdev/i2c/base.c
index 041fd5e..c33c03d 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/i2c/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/i2c/base.c
@@ -197,7 +197,7 @@ static int
 nouveau_i2c_identify(struct nouveau_i2c *i2c, int index, const char *what,
 		     struct nouveau_i2c_board_info *info,
 		     bool (*match)(struct nouveau_i2c_port *,
-				   struct i2c_board_info *))
+				   struct i2c_board_info *, void *), void *data)
 {
 	struct nouveau_i2c_port *port = nouveau_i2c_find(i2c, index);
 	int i;
@@ -221,7 +221,7 @@ nouveau_i2c_identify(struct nouveau_i2c *i2c, int index, const char *what,
 		}
 
 		if (nv_probe_i2c(port, info[i].dev.addr) &&
-		    (!match || match(port, &info[i].dev))) {
+		    (!match || match(port, &info[i].dev, data))) {
 			nv_info(i2c, "detected %s: %s\n", what,
 				info[i].dev.type);
 			return i;
diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/ic.c b/drivers/gpu/drm/nouveau/core/subdev/therm/ic.c
index 13b8500..30c384e 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/therm/ic.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/therm/ic.c
@@ -29,9 +29,9 @@
 
 static bool
 probe_monitoring_device(struct nouveau_i2c_port *i2c,
-			struct i2c_board_info *info)
+			struct i2c_board_info *info, void *data)
 {
-	struct nouveau_therm_priv *priv = (void *)nouveau_therm(i2c);
+	struct nouveau_therm_priv *priv = data;
 	struct nvbios_therm_sensor *sensor = &priv->bios_sensor;
 	struct i2c_client *client;
 
@@ -95,7 +95,7 @@ nouveau_therm_ic_ctor(struct nouveau_therm *therm)
 		};
 
 		i2c->identify(i2c, NV_I2C_DEFAULT(0), "monitoring device",
-				  board, probe_monitoring_device);
+			      board, probe_monitoring_device, therm);
 		if (priv->ic)
 			return;
 	}
@@ -107,7 +107,7 @@ nouveau_therm_ic_ctor(struct nouveau_therm *therm)
 		};
 
 		i2c->identify(i2c, NV_I2C_DEFAULT(0), "monitoring device",
-				  board, probe_monitoring_device);
+			      board, probe_monitoring_device, therm);
 		if (priv->ic)
 			return;
 	}
@@ -116,5 +116,5 @@ nouveau_therm_ic_ctor(struct nouveau_therm *therm)
 	   device. Let's try our static list.
 	 */
 	i2c->identify(i2c, NV_I2C_DEFAULT(0), "monitoring device",
-		      nv_board_infos, probe_monitoring_device);
+		      nv_board_infos, probe_monitoring_device, therm);
 }
diff --git a/drivers/gpu/drm/nouveau/dispnv04/dfp.c b/drivers/gpu/drm/nouveau/dispnv04/dfp.c
index 936a71c..7fdc51e 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/dfp.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/dfp.c
@@ -643,7 +643,7 @@ static void nv04_tmds_slave_init(struct drm_encoder *encoder)
 	    get_tmds_slave(encoder))
 		return;
 
-	type = i2c->identify(i2c, 2, "TMDS transmitter", info, NULL);
+	type = i2c->identify(i2c, 2, "TMDS transmitter", info, NULL, NULL);
 	if (type < 0)
 		return;
 
diff --git a/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c b/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c
index cc4b208..244822d 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c
@@ -59,7 +59,7 @@ int nv04_tv_identify(struct drm_device *dev, int i2c_index)
 	struct nouveau_i2c *i2c = nouveau_i2c(drm->device);
 
 	return i2c->identify(i2c, i2c_index, "TV encoder",
-			     nv04_tv_encoder_info, NULL);
+			     nv04_tv_encoder_info, NULL, NULL);
 }
 
 
-- 
cgit v0.10.2


From cd9bb0564c551f8a72763dd45590e9ea6787811e Mon Sep 17 00:00:00 2001
From: Jingoo Han <jg1.han@samsung.com>
Date: Tue, 3 Dec 2013 07:10:29 +0000
Subject: hwmon: remove DEFINE_PCI_DEVICE_TABLE macro

Don't use DEFINE_PCI_DEVICE_TABLE macro, because this macro
is not preferred.

Signed-off-by: Jingoo Han <jg1.han@samsung.com>
Acked-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>

diff --git a/drivers/hwmon/fam15h_power.c b/drivers/hwmon/fam15h_power.c
index dff8410..6040121 100644
--- a/drivers/hwmon/fam15h_power.c
+++ b/drivers/hwmon/fam15h_power.c
@@ -249,7 +249,7 @@ static void fam15h_power_remove(struct pci_dev *pdev)
 	sysfs_remove_group(&dev->kobj, &fam15h_power_attr_group);
 }
 
-static DEFINE_PCI_DEVICE_TABLE(fam15h_power_id_table) = {
+static const struct pci_device_id fam15h_power_id_table[] = {
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) },
 	{}
diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index d65f3fd..e375e9f 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -204,7 +204,7 @@ static void k10temp_remove(struct pci_dev *pdev)
 			   &sensor_dev_attr_temp1_crit_hyst.dev_attr);
 }
 
-static DEFINE_PCI_DEVICE_TABLE(k10temp_id_table) = {
+static const struct pci_device_id k10temp_id_table[] = {
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_11H_NB_MISC) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
diff --git a/drivers/hwmon/k8temp.c b/drivers/hwmon/k8temp.c
index 5b50e9e..734d55d 100644
--- a/drivers/hwmon/k8temp.c
+++ b/drivers/hwmon/k8temp.c
@@ -135,7 +135,7 @@ static SENSOR_DEVICE_ATTR_2(temp3_input, S_IRUGO, show_temp, NULL, 1, 0);
 static SENSOR_DEVICE_ATTR_2(temp4_input, S_IRUGO, show_temp, NULL, 1, 1);
 static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
 
-static DEFINE_PCI_DEVICE_TABLE(k8temp_ids) = {
+static const struct pci_device_id k8temp_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) },
 	{ 0 },
 };
diff --git a/drivers/hwmon/sis5595.c b/drivers/hwmon/sis5595.c
index 72a8897..e74bd7e 100644
--- a/drivers/hwmon/sis5595.c
+++ b/drivers/hwmon/sis5595.c
@@ -754,7 +754,7 @@ static struct sis5595_data *sis5595_update_device(struct device *dev)
 	return data;
 }
 
-static DEFINE_PCI_DEVICE_TABLE(sis5595_pci_ids) = {
+static const struct pci_device_id sis5595_pci_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_SI, PCI_DEVICE_ID_SI_503) },
 	{ 0, }
 };
diff --git a/drivers/hwmon/via686a.c b/drivers/hwmon/via686a.c
index c9dcce8..babd732 100644
--- a/drivers/hwmon/via686a.c
+++ b/drivers/hwmon/via686a.c
@@ -824,7 +824,7 @@ static struct via686a_data *via686a_update_device(struct device *dev)
 	return data;
 }
 
-static DEFINE_PCI_DEVICE_TABLE(via686a_pci_ids) = {
+static const struct pci_device_id via686a_pci_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_82C686_4) },
 	{ }
 };
diff --git a/drivers/hwmon/vt8231.c b/drivers/hwmon/vt8231.c
index aee14e2..b3babe3 100644
--- a/drivers/hwmon/vt8231.c
+++ b/drivers/hwmon/vt8231.c
@@ -766,7 +766,7 @@ static struct platform_driver vt8231_driver = {
 	.remove	= vt8231_remove,
 };
 
-static DEFINE_PCI_DEVICE_TABLE(vt8231_pci_ids) = {
+static const struct pci_device_id vt8231_pci_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8231_4) },
 	{ 0, }
 };
-- 
cgit v0.10.2


From 14513ee696a0cd12a19318e433b75a786808adc3 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Mon, 27 May 2013 12:20:19 -0700
Subject: hwmon: (coretemp) Use PCI host bridge ID to identify CPU if necessary

Atom S12x0 CPUs are identified by the CPU host bridge ID. Add an override
table based on PCI IDs as well as code to detect it.

PCI access functions can now be called with PCI disabled, so unlike previous
attempts to use PCI IDs, the code no longer depends on it. If PCI is disabled,
the CPU will not be identified correctly. Since it is unlikely that anything
will work in this case, this is an acceptable limitation.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>

diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index 9425098..d84dae7 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -36,6 +36,7 @@
 #include <linux/cpu.h>
 #include <linux/smp.h>
 #include <linux/moduleparam.h>
+#include <linux/pci.h>
 #include <asm/msr.h>
 #include <asm/processor.h>
 #include <asm/cpu_device_id.h>
@@ -190,6 +191,17 @@ static ssize_t show_temp(struct device *dev,
 	return tdata->valid ? sprintf(buf, "%d\n", tdata->temp) : -EAGAIN;
 }
 
+struct tjmax_pci {
+	unsigned int device;
+	int tjmax;
+};
+
+static const struct tjmax_pci tjmax_pci_table[] = {
+	{ 0x0c72, 102000 },	/* Atom S1240 (Centerton) */
+	{ 0x0c73, 95000 },	/* Atom S1220 (Centerton) */
+	{ 0x0c75, 95000 },	/* Atom S1260 (Centerton) */
+};
+
 struct tjmax {
 	char const *id;
 	int tjmax;
@@ -222,8 +234,11 @@ static const struct tjmax_model tjmax_model_table[] = {
 				 * is undetectable by software
 				 */
 	{ 0x27, ANY, 90000 },	/* Atom Medfield (Z2460) */
-	{ 0x35, ANY, 90000 },	/* Atom Clover Trail/Cloverview (Z2760) */
-	{ 0x36, ANY, 100000 },	/* Atom Cedar Trail/Cedarview (N2xxx, D2xxx) */
+	{ 0x35, ANY, 90000 },	/* Atom Clover Trail/Cloverview (Z27x0) */
+	{ 0x36, ANY, 100000 },	/* Atom Cedar Trail/Cedarview (N2xxx, D2xxx)
+				 * Also matches S12x0 (stepping 9), covered by
+				 * PCI table
+				 */
 };
 
 static int adjust_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
@@ -236,8 +251,20 @@ static int adjust_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
 	int err;
 	u32 eax, edx;
 	int i;
+	struct pci_dev *host_bridge = pci_get_bus_and_slot(0, PCI_DEVFN(0, 0));
+
+	/*
+	 * Explicit tjmax table entries override heuristics.
+	 * First try PCI host bridge IDs, followed by model ID strings
+	 * and model/stepping information.
+	 */
+	if (host_bridge && host_bridge->vendor == PCI_VENDOR_ID_INTEL) {
+		for (i = 0; i < ARRAY_SIZE(tjmax_pci_table); i++) {
+			if (host_bridge->device == tjmax_pci_table[i].device)
+				return tjmax_pci_table[i].tjmax;
+		}
+	}
 
-	/* explicit tjmax table entries override heuristics */
 	for (i = 0; i < ARRAY_SIZE(tjmax_table); i++) {
 		if (strstr(c->x86_model_id, tjmax_table[i].id))
 			return tjmax_table[i].tjmax;
-- 
cgit v0.10.2


From 347c16cfdecf9b4cfb94137b47bf6a05b3ff57d5 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Mon, 27 May 2013 14:17:27 -0700
Subject: hwmon: (coretemp) Add PCI device ID for CE41x0 CPUs

Since we now have to use PCI IDs to detect CPU types anyway, use this mechanism
to detect CE41x0 CPUs. Advantage is that it only requires a single entry and
covers all variants of CE41x0, including those unknown to us.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>

diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index d84dae7..7eed10e 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -197,6 +197,7 @@ struct tjmax_pci {
 };
 
 static const struct tjmax_pci tjmax_pci_table[] = {
+	{ 0x0708, 110000 },	/* CE41x0 (Sodaville ) */
 	{ 0x0c72, 102000 },	/* Atom S1240 (Centerton) */
 	{ 0x0c73, 95000 },	/* Atom S1220 (Centerton) */
 	{ 0x0c75, 95000 },	/* Atom S1260 (Centerton) */
@@ -210,9 +211,6 @@ struct tjmax {
 static const struct tjmax tjmax_table[] = {
 	{ "CPU  230", 100000 },		/* Model 0x1c, stepping 2	*/
 	{ "CPU  330", 125000 },		/* Model 0x1c, stepping 2	*/
-	{ "CPU CE4110", 110000 },	/* Model 0x1c, stepping 10 Sodaville */
-	{ "CPU CE4150", 110000 },	/* Model 0x1c, stepping 10	*/
-	{ "CPU CE4170", 110000 },	/* Model 0x1c, stepping 10	*/
 };
 
 struct tjmax_model {
-- 
cgit v0.10.2


From 9fb6c9c73b11bef65ba80a362547fd116c1e1c9d Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Sat, 9 Nov 2013 09:38:14 -0800
Subject: hwmon: (coretemp) Refine TjMax detection

Intel's turbostat code uses only 7 bits from MSR_IA32_TEMPERATURE_TARGET to
read TjMax, and also only accepts it if the reported temperature is at least
85 degrees C. Play safe and do the same.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>

diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index 7eed10e..b2e59b3 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -368,12 +368,12 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
 		if (cpu_has_tjmax(c))
 			dev_warn(dev, "Unable to read TjMax from CPU %u\n", id);
 	} else {
-		val = (eax >> 16) & 0xff;
+		val = (eax >> 16) & 0x7f;
 		/*
 		 * If the TjMax is not plausible, an assumption
 		 * will be used
 		 */
-		if (val) {
+		if (val >= 85) {
 			dev_dbg(dev, "TjMax is %d degrees C\n", val);
 			return val * 1000;
 		}
-- 
cgit v0.10.2


From c09088d934c1e1672be8b3cfe3ba4f40ab2bf13e Mon Sep 17 00:00:00 2001
From: Anthony Olech <anthony.olech.opensource@diasemi.com>
Date: Wed, 18 Dec 2013 15:15:31 +0000
Subject: hwmon: (da9052) Fix adc to voltage calculation

The ADC resolution of the PMIC is 10-bits, this means that the maximum
possible value is 1023 and not the 1024 as originally in the code.

Signed-off-by: Anthony Olech <anthony.olech.opensource@diasemi.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>

diff --git a/drivers/hwmon/da9052-hwmon.c b/drivers/hwmon/da9052-hwmon.c
index 960fac3..afd3104 100644
--- a/drivers/hwmon/da9052-hwmon.c
+++ b/drivers/hwmon/da9052-hwmon.c
@@ -45,7 +45,7 @@ static const char * const input_names[] = {
 /* Conversion function for VDDOUT and VBAT */
 static inline int volt_reg_to_mv(int value)
 {
-	return DIV_ROUND_CLOSEST(value * 1000, 512) + 2500;
+	return DIV_ROUND_CLOSEST(value * 2000, 1023) + 2500;
 }
 
 /* Conversion function for ADC channels 4, 5 and 6 */
@@ -57,7 +57,7 @@ static inline int input_reg_to_mv(int value)
 /* Conversion function for VBBAT */
 static inline int vbbat_reg_to_mv(int value)
 {
-	return DIV_ROUND_CLOSEST(value * 2500, 512);
+	return DIV_ROUND_CLOSEST(value * 5000, 1023);
 }
 
 static inline int da9052_enable_vddout_channel(struct da9052 *da9052)
-- 
cgit v0.10.2


From bf6ea084ebb54cf8e1d6e60aac3c727cf45bf6c7 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Wed, 20 Nov 2013 10:25:17 -0800
Subject: hwmon: (coretemp) Do not return -EAGAIN for low temperatures

Some Intel CPUs do not set the 'valid' bit in IA32_THERM_STATUS if the
temperature is too low to be measured. This condition will not change until
the CPU is hot enough for its temperature to be measured. Returning an error
in such conditions is not very useful. Drop checking the valid bit and just
return the reported temperature instead.

Reviewed-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>

diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index b2e59b3..bbb0b0d 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -177,18 +177,19 @@ static ssize_t show_temp(struct device *dev,
 	/* Check whether the time interval has elapsed */
 	if (!tdata->valid || time_after(jiffies, tdata->last_updated + HZ)) {
 		rdmsr_on_cpu(tdata->cpu, tdata->status_reg, &eax, &edx);
-		tdata->valid = 0;
-		/* Check whether the data is valid */
-		if (eax & 0x80000000) {
-			tdata->temp = tdata->tjmax -
-					((eax >> 16) & 0x7f) * 1000;
-			tdata->valid = 1;
-		}
+		/*
+		 * Ignore the valid bit. In all observed cases the register
+		 * value is either low or zero if the valid bit is 0.
+		 * Return it instead of reporting an error which doesn't
+		 * really help at all.
+		 */
+		tdata->temp = tdata->tjmax - ((eax >> 16) & 0x7f) * 1000;
+		tdata->valid = 1;
 		tdata->last_updated = jiffies;
 	}
 
 	mutex_unlock(&tdata->update_lock);
-	return tdata->valid ? sprintf(buf, "%d\n", tdata->temp) : -EAGAIN;
+	return sprintf(buf, "%d\n", tdata->temp);
 }
 
 struct tjmax_pci {
-- 
cgit v0.10.2


From 2ac1dfc52dc862eabf30d5ece51f3422e6df561a Mon Sep 17 00:00:00 2001
From: Sachin Kamat <sachin.kamat@linaro.org>
Date: Fri, 27 Dec 2013 11:40:13 +0530
Subject: hwmon: (s3c) Trivial cleanup in hwmon-s3c.h

Commit 436d42c61c3e ("ARM: samsung: move platform_data definitions")
moved the file to the current location but forgot to remove the pointer
to its previous location. Clean it up. While at it also change the header
file protection macros appropriately.

Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>

diff --git a/include/linux/platform_data/hwmon-s3c.h b/include/linux/platform_data/hwmon-s3c.h
index c167e44..0e3cce1 100644
--- a/include/linux/platform_data/hwmon-s3c.h
+++ b/include/linux/platform_data/hwmon-s3c.h
@@ -1,5 +1,4 @@
-/* linux/arch/arm/plat-s3c/include/plat/hwmon.h
- *
+/*
  * Copyright 2005 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *	http://armlinux.simtec.co.uk/
@@ -11,8 +10,8 @@
  * published by the Free Software Foundation.
 */
 
-#ifndef __ASM_ARCH_ADC_HWMON_H
-#define __ASM_ARCH_ADC_HWMON_H __FILE__
+#ifndef __HWMON_S3C_H__
+#define __HWMON_S3C_H__
 
 /**
  * s3c_hwmon_chcfg - channel configuration
@@ -47,5 +46,4 @@ struct s3c_hwmon_pdata {
  */
 extern void __init s3c_hwmon_set_platdata(struct s3c_hwmon_pdata *pd);
 
-#endif /* __ASM_ARCH_ADC_HWMON_H */
-
+#endif /* __HWMON_S3C_H__ */
-- 
cgit v0.10.2


From f5776cc3b55b9b2412df5008bfd7a98075a4891d Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Wed, 25 Dec 2013 07:25:59 -0800
Subject: hwmon: (nct6775) Re-enable logical device mapping for NCT6791 during
 resume

After a suspend/resume cycle, the NCT6791 is back to its original BIOS
programming. In this state, HWMON IO access may be locked.
Re-enable it during resume.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>

diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index cf811c1..8686e96 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -3936,6 +3936,18 @@ static int nct6775_probe(struct platform_device *pdev)
 	return PTR_ERR_OR_ZERO(hwmon_dev);
 }
 
+static void nct6791_enable_io_mapping(int sioaddr)
+{
+	int val;
+
+	val = superio_inb(sioaddr, NCT6791_REG_HM_IO_SPACE_LOCK_ENABLE);
+	if (val & 0x10) {
+		pr_info("Enabling hardware monitor logical device mappings.\n");
+		superio_outb(sioaddr, NCT6791_REG_HM_IO_SPACE_LOCK_ENABLE,
+			     val & ~0x10);
+	}
+}
+
 #ifdef CONFIG_PM
 static int nct6775_suspend(struct device *dev)
 {
@@ -3955,11 +3967,20 @@ static int nct6775_suspend(struct device *dev)
 static int nct6775_resume(struct device *dev)
 {
 	struct nct6775_data *data = dev_get_drvdata(dev);
-	int i, j;
+	int i, j, err = 0;
 
 	mutex_lock(&data->update_lock);
 	data->bank = 0xff;		/* Force initial bank selection */
 
+	if (data->kind == nct6791) {
+		err = superio_enter(data->sioreg);
+		if (err)
+			goto abort;
+
+		nct6791_enable_io_mapping(data->sioreg);
+		superio_exit(data->sioreg);
+	}
+
 	/* Restore limits */
 	for (i = 0; i < data->in_num; i++) {
 		if (!(data->have_in & (1 << i)))
@@ -3996,11 +4017,12 @@ static int nct6775_resume(struct device *dev)
 		nct6775_write_value(data, NCT6775_REG_FANDIV2, data->fandiv2);
 	}
 
+abort:
 	/* Force re-reading all values */
 	data->valid = false;
 	mutex_unlock(&data->update_lock);
 
-	return 0;
+	return err;
 }
 
 static const struct dev_pm_ops nct6775_dev_pm_ops = {
@@ -4088,15 +4110,9 @@ static int __init nct6775_find(int sioaddr, struct nct6775_sio_data *sio_data)
 		pr_warn("Forcibly enabling Super-I/O. Sensor is probably unusable.\n");
 		superio_outb(sioaddr, SIO_REG_ENABLE, val | 0x01);
 	}
-	if (sio_data->kind == nct6791) {
-		val = superio_inb(sioaddr, NCT6791_REG_HM_IO_SPACE_LOCK_ENABLE);
-		if (val & 0x10) {
-			pr_info("Enabling hardware monitor logical device mappings.\n");
-			superio_outb(sioaddr,
-				     NCT6791_REG_HM_IO_SPACE_LOCK_ENABLE,
-				     val & ~0x10);
-		}
-	}
+
+	if (sio_data->kind == nct6791)
+		nct6791_enable_io_mapping(sioaddr);
 
 	superio_exit(sioaddr);
 	pr_info("Found %s or compatible chip at %#x:%#x\n",
-- 
cgit v0.10.2


From 4cb6409bbe05c236fb7b9c67d273067ac1786267 Mon Sep 17 00:00:00 2001
From: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Date: Fri, 10 Jan 2014 16:44:45 -0500
Subject: hwmon: (max197) add include guard

Add include guard to include/linux/platform_data/max197.h to prevent
multiple inclusion.

Signed-off-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>

diff --git a/include/linux/platform_data/max197.h b/include/linux/platform_data/max197.h
index e2a41dd..8da8f94 100644
--- a/include/linux/platform_data/max197.h
+++ b/include/linux/platform_data/max197.h
@@ -11,6 +11,9 @@
  * For further information, see the Documentation/hwmon/max197 file.
  */
 
+#ifndef _PDATA_MAX197_H
+#define _PDATA_MAX197_H
+
 /**
  * struct max197_platform_data - MAX197 connectivity info
  * @convert:	Function used to start a conversion with control byte ctrl.
@@ -19,3 +22,5 @@
 struct max197_platform_data {
 	int (*convert)(u8 ctrl);
 };
+
+#endif /* _PDATA_MAX197_H */
-- 
cgit v0.10.2


From ffcc3b2aa183b85cd5b5d5313a3bc6243daf0e04 Mon Sep 17 00:00:00 2001
From: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Date: Fri, 10 Jan 2014 16:44:46 -0500
Subject: hwmon: (sht15) add include guard

Add include guard to include/linux/platform_data/sht15.h to prevent
multiple inclusion.

Signed-off-by: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>

diff --git a/include/linux/platform_data/sht15.h b/include/linux/platform_data/sht15.h
index 33e0fd2..12289c1 100644
--- a/include/linux/platform_data/sht15.h
+++ b/include/linux/platform_data/sht15.h
@@ -12,6 +12,9 @@
  * For further information, see the Documentation/hwmon/sht15 file.
  */
 
+#ifndef _PDATA_SHT15_H
+#define _PDATA_SHT15_H
+
 /**
  * struct sht15_platform_data - sht15 connectivity info
  * @gpio_data:		no. of gpio to which bidirectional data line is
@@ -31,3 +34,5 @@ struct sht15_platform_data {
 	bool no_otp_reload;
 	bool low_resolution;
 };
+
+#endif /* _PDATA_SHT15_H */
-- 
cgit v0.10.2


From d303b1b5fbb688282bbf72a534b9dfed7af9fe4f Mon Sep 17 00:00:00 2001
From: Phil Pokorny <ppokorny@penguincomputing.com>
Date: Tue, 14 Jan 2014 10:46:46 -0800
Subject: hwmon: (k10temp) Add support for Kaveri CPUs

Add new PCI ID to support new model "Kaveri" family.

Signed-off-by: Philip Pokorny <ppokorny@penguincomputing.com>
Cc: stable@vger.kernel.org
Signed-off-by: Guenter Roeck <linux@roeck-us.net>

diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index e375e9f..baf375b 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -210,6 +210,7 @@ static const struct pci_device_id k10temp_id_table[] = {
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) },
+	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) },
 	{ PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
 	{}
 };
-- 
cgit v0.10.2


From 70f2fe3a26248724d8a5019681a869abdaf3e89a Mon Sep 17 00:00:00 2001
From: Andreas Rohner <andreas.rohner@gmx.net>
Date: Tue, 14 Jan 2014 17:56:36 -0800
Subject: nilfs2: fix segctor bug that causes file system corruption

There is a bug in the function nilfs_segctor_collect, which results in
active data being written to a segment, that is marked as clean.  It is
possible, that this segment is selected for a later segment
construction, whereby the old data is overwritten.

The problem shows itself with the following kernel log message:

  nilfs_sufile_do_cancel_free: segment 6533 must be clean

Usually a few hours later the file system gets corrupted:

  NILFS: bad btree node (blocknr=8748107): level = 0, flags = 0x0, nchildren = 0
  NILFS error (device sdc1): nilfs_bmap_last_key: broken bmap (inode number=114660)

The issue can be reproduced with a file system that is nearly full and
with the cleaner running, while some IO intensive task is running.
Although it is quite hard to reproduce.

This is what happens:

 1. The cleaner starts the segment construction
 2. nilfs_segctor_collect is called
 3. sc_stage is on NILFS_ST_SUFILE and segments are freed
 4. sc_stage is on NILFS_ST_DAT current segment is full
 5. nilfs_segctor_extend_segments is called, which
    allocates a new segment
 6. The new segment is one of the segments freed in step 3
 7. nilfs_sufile_cancel_freev is called and produces an error message
 8. Loop around and the collection starts again
 9. sc_stage is on NILFS_ST_SUFILE and segments are freed
    including the newly allocated segment, which will contain active
    data and can be allocated at a later time
10. A few hours later another segment construction allocates the
    segment and causes file system corruption

This can be prevented by simply reordering the statements.  If
nilfs_sufile_cancel_freev is called before nilfs_segctor_extend_segments
the freed segments are marked as dirty and cannot be allocated any more.

Signed-off-by: Andreas Rohner <andreas.rohner@gmx.net>
Reviewed-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Tested-by: Andreas Rohner <andreas.rohner@gmx.net>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 9f6b486..a1a1916 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -1440,17 +1440,19 @@ static int nilfs_segctor_collect(struct nilfs_sc_info *sci,
 
 		nilfs_clear_logs(&sci->sc_segbufs);
 
-		err = nilfs_segctor_extend_segments(sci, nilfs, nadd);
-		if (unlikely(err))
-			return err;
-
 		if (sci->sc_stage.flags & NILFS_CF_SUFREED) {
 			err = nilfs_sufile_cancel_freev(nilfs->ns_sufile,
 							sci->sc_freesegs,
 							sci->sc_nfreesegs,
 							NULL);
 			WARN_ON(err); /* do not happen */
+			sci->sc_stage.flags &= ~NILFS_CF_SUFREED;
 		}
+
+		err = nilfs_segctor_extend_segments(sci, nilfs, nadd);
+		if (unlikely(err))
+			return err;
+
 		nadd = min_t(int, nadd << 1, SC_MAX_SEGDELTA);
 		sci->sc_stage = prev_stage;
 	}
-- 
cgit v0.10.2


From bad009fe354a00e6b2bf87328995ec76e59ab970 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhc@lemote.com>
Date: Tue, 14 Jan 2014 17:56:37 -0800
Subject: MIPS: fix case mismatch in local_r4k_flush_icache_range()

Currently, Loongson-2 call protected_blast_icache_range() and others
call protected_loongson23_blast_icache_range(), but I think the correct
behavior should be the opposite.  BTW, Loongson-3's cache-ops is
compatible with MIPS64, but not compatible with Loongson-2.  So, rename
xxx_loongson23_yyy things to xxx_loongson2_yyy.

The patch fixes early boot hang with 3.13-rc1, introduced in commit
14bd8c082016 ("MIPS: Loongson: Get rid of Loongson 2 #ifdefery all over
arch/mips").

Signed-off-by: Huacai Chen <chenhc@lemote.com>
Signed-off-by: Aaro Koskinen <aaro.koskinen@iki.fi>
Reviewed-by: Aurelien Jarno <aurelien@aurel32.net>
Acked-by: John Crispin <blogic@openwrt.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/mips/include/asm/cacheops.h b/arch/mips/include/asm/cacheops.h
index c75025f..06b9bc7 100644
--- a/arch/mips/include/asm/cacheops.h
+++ b/arch/mips/include/asm/cacheops.h
@@ -83,6 +83,6 @@
 /*
  * Loongson2-specific cacheops
  */
-#define Hit_Invalidate_I_Loongson23	0x00
+#define Hit_Invalidate_I_Loongson2	0x00
 
 #endif	/* __ASM_CACHEOPS_H */
diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h
index 34d1a19..91d20b0 100644
--- a/arch/mips/include/asm/r4kcache.h
+++ b/arch/mips/include/asm/r4kcache.h
@@ -165,7 +165,7 @@ static inline void flush_icache_line(unsigned long addr)
 	__iflush_prologue
 	switch (boot_cpu_type()) {
 	case CPU_LOONGSON2:
-		cache_op(Hit_Invalidate_I_Loongson23, addr);
+		cache_op(Hit_Invalidate_I_Loongson2, addr);
 		break;
 
 	default:
@@ -219,7 +219,7 @@ static inline void protected_flush_icache_line(unsigned long addr)
 {
 	switch (boot_cpu_type()) {
 	case CPU_LOONGSON2:
-		protected_cache_op(Hit_Invalidate_I_Loongson23, addr);
+		protected_cache_op(Hit_Invalidate_I_Loongson2, addr);
 		break;
 
 	default:
@@ -452,8 +452,8 @@ static inline void prot##extra##blast_##pfx##cache##_range(unsigned long start,
 __BUILD_BLAST_CACHE_RANGE(d, dcache, Hit_Writeback_Inv_D, protected_, )
 __BUILD_BLAST_CACHE_RANGE(s, scache, Hit_Writeback_Inv_SD, protected_, )
 __BUILD_BLAST_CACHE_RANGE(i, icache, Hit_Invalidate_I, protected_, )
-__BUILD_BLAST_CACHE_RANGE(i, icache, Hit_Invalidate_I_Loongson23, \
-	protected_, loongson23_)
+__BUILD_BLAST_CACHE_RANGE(i, icache, Hit_Invalidate_I_Loongson2, \
+	protected_, loongson2_)
 __BUILD_BLAST_CACHE_RANGE(d, dcache, Hit_Writeback_Inv_D, , )
 __BUILD_BLAST_CACHE_RANGE(s, scache, Hit_Writeback_Inv_SD, , )
 /* blast_inv_dcache_range */
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 62ffd20..73f02da6 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -580,11 +580,11 @@ static inline void local_r4k_flush_icache_range(unsigned long start, unsigned lo
 	else {
 		switch (boot_cpu_type()) {
 		case CPU_LOONGSON2:
-			protected_blast_icache_range(start, end);
+			protected_loongson2_blast_icache_range(start, end);
 			break;
 
 		default:
-			protected_loongson23_blast_icache_range(start, end);
+			protected_blast_icache_range(start, end);
 			break;
 		}
 	}
-- 
cgit v0.10.2


From 43a06847b9d277e9f2c3bf8052b44b74e17526c7 Mon Sep 17 00:00:00 2001
From: Aaro Koskinen <aaro.koskinen@iki.fi>
Date: Tue, 14 Jan 2014 17:56:38 -0800
Subject: MIPS: fix blast_icache32 on loongson2

Commit 14bd8c082016 ("MIPS: Loongson: Get rid of Loongson 2 #ifdefery
all over arch/mips") failed to add Loongson2 specific blast_icache32
functions.  Fix that.

The patch fixes the following crash seen with 3.13-rc1:

  Reserved instruction in kernel code[#1]:
  [...]
  Call Trace:
    blast_icache32_page+0x8/0xb0
    r4k_flush_cache_page+0x19c/0x200
    do_wp_page.isra.97+0x47c/0xe08
    handle_mm_fault+0x938/0x1118
    __do_page_fault+0x140/0x540
    resume_userspace_check+0x0/0x10
  Code: 00200825  64834000  00200825 <bc900000> bc900020  bc900040  bc900060  bc900080  bc9000a0

Signed-off-by: Aaro Koskinen <aaro.koskinen@iki.fi>
Reviewed-by: Aurelien Jarno <aurelien@aurel32.net>
Acked-by: John Crispin <blogic@openwrt.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h
index 91d20b0..c84cadd 100644
--- a/arch/mips/include/asm/r4kcache.h
+++ b/arch/mips/include/asm/r4kcache.h
@@ -357,8 +357,8 @@ static inline void invalidate_tcache_page(unsigned long addr)
 		  "i" (op));
 
 /* build blast_xxx, blast_xxx_page, blast_xxx_page_indexed */
-#define __BUILD_BLAST_CACHE(pfx, desc, indexop, hitop, lsize) \
-static inline void blast_##pfx##cache##lsize(void)			\
+#define __BUILD_BLAST_CACHE(pfx, desc, indexop, hitop, lsize, extra)	\
+static inline void extra##blast_##pfx##cache##lsize(void)		\
 {									\
 	unsigned long start = INDEX_BASE;				\
 	unsigned long end = start + current_cpu_data.desc.waysize;	\
@@ -376,7 +376,7 @@ static inline void blast_##pfx##cache##lsize(void)			\
 	__##pfx##flush_epilogue						\
 }									\
 									\
-static inline void blast_##pfx##cache##lsize##_page(unsigned long page) \
+static inline void extra##blast_##pfx##cache##lsize##_page(unsigned long page) \
 {									\
 	unsigned long start = page;					\
 	unsigned long end = page + PAGE_SIZE;				\
@@ -391,7 +391,7 @@ static inline void blast_##pfx##cache##lsize##_page(unsigned long page) \
 	__##pfx##flush_epilogue						\
 }									\
 									\
-static inline void blast_##pfx##cache##lsize##_page_indexed(unsigned long page) \
+static inline void extra##blast_##pfx##cache##lsize##_page_indexed(unsigned long page) \
 {									\
 	unsigned long indexmask = current_cpu_data.desc.waysize - 1;	\
 	unsigned long start = INDEX_BASE + (page & indexmask);		\
@@ -410,23 +410,24 @@ static inline void blast_##pfx##cache##lsize##_page_indexed(unsigned long page)
 	__##pfx##flush_epilogue						\
 }
 
-__BUILD_BLAST_CACHE(d, dcache, Index_Writeback_Inv_D, Hit_Writeback_Inv_D, 16)
-__BUILD_BLAST_CACHE(i, icache, Index_Invalidate_I, Hit_Invalidate_I, 16)
-__BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 16)
-__BUILD_BLAST_CACHE(d, dcache, Index_Writeback_Inv_D, Hit_Writeback_Inv_D, 32)
-__BUILD_BLAST_CACHE(i, icache, Index_Invalidate_I, Hit_Invalidate_I, 32)
-__BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 32)
-__BUILD_BLAST_CACHE(d, dcache, Index_Writeback_Inv_D, Hit_Writeback_Inv_D, 64)
-__BUILD_BLAST_CACHE(i, icache, Index_Invalidate_I, Hit_Invalidate_I, 64)
-__BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 64)
-__BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 128)
-
-__BUILD_BLAST_CACHE(inv_d, dcache, Index_Writeback_Inv_D, Hit_Invalidate_D, 16)
-__BUILD_BLAST_CACHE(inv_d, dcache, Index_Writeback_Inv_D, Hit_Invalidate_D, 32)
-__BUILD_BLAST_CACHE(inv_s, scache, Index_Writeback_Inv_SD, Hit_Invalidate_SD, 16)
-__BUILD_BLAST_CACHE(inv_s, scache, Index_Writeback_Inv_SD, Hit_Invalidate_SD, 32)
-__BUILD_BLAST_CACHE(inv_s, scache, Index_Writeback_Inv_SD, Hit_Invalidate_SD, 64)
-__BUILD_BLAST_CACHE(inv_s, scache, Index_Writeback_Inv_SD, Hit_Invalidate_SD, 128)
+__BUILD_BLAST_CACHE(d, dcache, Index_Writeback_Inv_D, Hit_Writeback_Inv_D, 16, )
+__BUILD_BLAST_CACHE(i, icache, Index_Invalidate_I, Hit_Invalidate_I, 16, )
+__BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 16, )
+__BUILD_BLAST_CACHE(d, dcache, Index_Writeback_Inv_D, Hit_Writeback_Inv_D, 32, )
+__BUILD_BLAST_CACHE(i, icache, Index_Invalidate_I, Hit_Invalidate_I, 32, )
+__BUILD_BLAST_CACHE(i, icache, Index_Invalidate_I, Hit_Invalidate_I_Loongson2, 32, loongson2_)
+__BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 32, )
+__BUILD_BLAST_CACHE(d, dcache, Index_Writeback_Inv_D, Hit_Writeback_Inv_D, 64, )
+__BUILD_BLAST_CACHE(i, icache, Index_Invalidate_I, Hit_Invalidate_I, 64, )
+__BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 64, )
+__BUILD_BLAST_CACHE(s, scache, Index_Writeback_Inv_SD, Hit_Writeback_Inv_SD, 128, )
+
+__BUILD_BLAST_CACHE(inv_d, dcache, Index_Writeback_Inv_D, Hit_Invalidate_D, 16, )
+__BUILD_BLAST_CACHE(inv_d, dcache, Index_Writeback_Inv_D, Hit_Invalidate_D, 32, )
+__BUILD_BLAST_CACHE(inv_s, scache, Index_Writeback_Inv_SD, Hit_Invalidate_SD, 16, )
+__BUILD_BLAST_CACHE(inv_s, scache, Index_Writeback_Inv_SD, Hit_Invalidate_SD, 32, )
+__BUILD_BLAST_CACHE(inv_s, scache, Index_Writeback_Inv_SD, Hit_Invalidate_SD, 64, )
+__BUILD_BLAST_CACHE(inv_s, scache, Index_Writeback_Inv_SD, Hit_Invalidate_SD, 128, )
 
 /* build blast_xxx_range, protected_blast_xxx_range */
 #define __BUILD_BLAST_CACHE_RANGE(pfx, desc, hitop, prot, extra)	\
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 73f02da6..49e572d 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -237,6 +237,8 @@ static void r4k_blast_icache_page_setup(void)
 		r4k_blast_icache_page = (void *)cache_noop;
 	else if (ic_lsize == 16)
 		r4k_blast_icache_page = blast_icache16_page;
+	else if (ic_lsize == 32 && current_cpu_type() == CPU_LOONGSON2)
+		r4k_blast_icache_page = loongson2_blast_icache32_page;
 	else if (ic_lsize == 32)
 		r4k_blast_icache_page = blast_icache32_page;
 	else if (ic_lsize == 64)
@@ -261,6 +263,9 @@ static void r4k_blast_icache_page_indexed_setup(void)
 		else if (TX49XX_ICACHE_INDEX_INV_WAR)
 			r4k_blast_icache_page_indexed =
 				tx49_blast_icache32_page_indexed;
+		else if (current_cpu_type() == CPU_LOONGSON2)
+			r4k_blast_icache_page_indexed =
+				loongson2_blast_icache32_page_indexed;
 		else
 			r4k_blast_icache_page_indexed =
 				blast_icache32_page_indexed;
@@ -284,6 +289,8 @@ static void r4k_blast_icache_setup(void)
 			r4k_blast_icache = blast_r4600_v1_icache32;
 		else if (TX49XX_ICACHE_INDEX_INV_WAR)
 			r4k_blast_icache = tx49_blast_icache32;
+		else if (current_cpu_type() == CPU_LOONGSON2)
+			r4k_blast_icache = loongson2_blast_icache32;
 		else
 			r4k_blast_icache = blast_icache32;
 	} else if (ic_lsize == 64)
-- 
cgit v0.10.2


From 03e5ac2fc3bf6f4140db0371e8bb4243b24e3e02 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Tue, 14 Jan 2014 17:56:40 -0800
Subject: mm: fix crash when using XFS on loopback

Commit 8456a648cf44 ("slab: use struct page for slab management") causes
a crash in the LVM2 testsuite on PA-RISC (the crashing test is
fsadm.sh).  The testsuite doesn't crash on 3.12, crashes on 3.13-rc1 and
later.

 Bad Address (null pointer deref?): Code=15 regs=000000413edd89a0 (Addr=000006202224647d)
 CPU: 3 PID: 24008 Comm: loop0 Not tainted 3.13.0-rc6 #5
 task: 00000001bf3c0048 ti: 000000413edd8000 task.ti: 000000413edd8000

      YZrvWESTHLNXBCVMcbcbcbcbOGFRQPDI
 PSW: 00001000000001101111100100001110 Not tainted
 r00-03  000000ff0806f90e 00000000405c8de0 000000004013e6c0 000000413edd83f0
 r04-07  00000000405a95e0 0000000000000200 00000001414735f0 00000001bf349e40
 r08-11  0000000010fe3d10 0000000000000001 00000040829c7778 000000413efd9000
 r12-15  0000000000000000 000000004060d800 0000000010fe3000 0000000010fe3000
 r16-19  000000413edd82a0 00000041078ddbc0 0000000000000010 0000000000000001
 r20-23  0008f3d0d83a8000 0000000000000000 00000040829c7778 0000000000000080
 r24-27  00000001bf349e40 00000001bf349e40 202d66202224640d 00000000405a95e0
 r28-31  202d662022246465 000000413edd88f0 000000413edd89a0 0000000000000001
 sr00-03  000000000532c000 0000000000000000 0000000000000000 000000000532c000
 sr04-07  0000000000000000 0000000000000000 0000000000000000 0000000000000000

 IASQ: 0000000000000000 0000000000000000 IAOQ: 00000000401fe42c 00000000401fe430
  IIR: 539c0030    ISR: 00000000202d6000  IOR: 000006202224647d
  CPU:        3   CR30: 000000413edd8000 CR31: 0000000000000000
  ORIG_R28: 00000000405a95e0
  IAOQ[0]: vma_interval_tree_iter_first+0x14/0x48
  IAOQ[1]: vma_interval_tree_iter_first+0x18/0x48
  RP(r2): flush_dcache_page+0x128/0x388
 Backtrace:
   flush_dcache_page+0x128/0x388
   lo_splice_actor+0x90/0x148 [loop]
   splice_from_pipe_feed+0xc0/0x1d0
   __splice_from_pipe+0xac/0xc0
   lo_direct_splice_actor+0x1c/0x70 [loop]
   splice_direct_to_actor+0xec/0x228
   lo_receive+0xe4/0x298 [loop]
   loop_thread+0x478/0x640 [loop]
   kthread+0x134/0x168
   end_fault_vector+0x20/0x28
   xfs_setsize_buftarg+0x0/0x90 [xfs]

 Kernel panic - not syncing: Bad Address (null pointer deref?)

Commit 8456a648cf44 changes the page structure so that the slab
subsystem reuses the page->mapping field.

The crash happens in the following way:
 * XFS allocates some memory from slab and issues a bio to read data
   into it.
 * the bio is sent to the loopback device.
 * lo_receive creates an actor and calls splice_direct_to_actor.
 * lo_splice_actor copies data to the target page.
 * lo_splice_actor calls flush_dcache_page because the page may be
   mapped by userspace.  In that case we need to flush the kernel cache.
 * flush_dcache_page asks for the list of userspace mappings, however
   that page->mapping field is reused by the slab subsystem for a
   different purpose.  This causes the crash.

Note that other architectures without coherent caches (sparc, arm, mips)
also call page_mapping from flush_dcache_page, so they may crash in the
same way.

This patch fixes this bug by testing if the page is a slab page in
page_mapping and returning NULL if it is.

The patch also fixes VM_BUG_ON(PageSlab(page)) that could happen in
earlier kernels in the same scenario on architectures without cache
coherence when CONFIG_DEBUG_VM is enabled - so it should be backported
to stable kernels.

In the old kernels, the function page_mapping is placed in
include/linux/mm.h, so you should modify the patch accordingly when
backporting it.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: John David Anglin <dave.anglin@bell.net>]
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Christoph Lameter <cl@linux.com>
Acked-by: Pekka Enberg <penberg@kernel.org>
Reviewed-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Helge Deller <deller@gmx.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/util.c b/mm/util.c
index f7bc209..808f375 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -390,7 +390,10 @@ struct address_space *page_mapping(struct page *page)
 {
 	struct address_space *mapping = page->mapping;
 
-	VM_BUG_ON(PageSlab(page));
+	/* This happens if someone calls flush_dcache_page on slab page */
+	if (unlikely(PageSlab(page)))
+		return NULL;
+
 	if (unlikely(PageSwapCache(page))) {
 		swp_entry_t entry;
 
-- 
cgit v0.10.2


From 5a610fcc7390ee60308deaf09426ada87a1eeec2 Mon Sep 17 00:00:00 2001
From: Qais Yousef <qais.yousef@imgtec.com>
Date: Tue, 14 Jan 2014 17:56:41 -0800
Subject: crash_dump: fix compilation error (on MIPS at least)

  In file included from kernel/crash_dump.c:2:0:
  include/linux/crash_dump.h:22:27: error: unknown type name `pgprot_t'

when CONFIG_CRASH_DUMP=y

The error was traced back to commit 9cb218131de1 ("vmcore: introduce
remap_oldmem_pfn_range()")

include <asm/pgtable.h> to get the missing definition

Signed-off-by: Qais Yousef <qais.yousef@imgtec.com>
Reviewed-by: James Hogan <james.hogan@imgtec.com>
Cc: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Cc: <stable@vger.kernel.org>	[3.12+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index fe68a5a..7032518 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -6,6 +6,8 @@
 #include <linux/proc_fs.h>
 #include <linux/elf.h>
 
+#include <asm/pgtable.h> /* for pgprot_t */
+
 #define ELFCORE_ADDR_MAX	(-1ULL)
 #define ELFCORE_ADDR_ERR	(-2ULL)
 
-- 
cgit v0.10.2


From 74e72f894d56eb9d2e1218530c658e7d297e002b Mon Sep 17 00:00:00 2001
From: Ming Lei <tom.leiming@gmail.com>
Date: Tue, 14 Jan 2014 17:56:42 -0800
Subject: lib/percpu_counter.c: fix __percpu_counter_add()

__percpu_counter_add() may be called in softirq/hardirq handler (such
as, blk_mq_queue_exit() is typically called in hardirq/softirq handler),
so we need to call this_cpu_add()(irq safe helper) to update percpu
counter, otherwise counts may be lost.

This fixes the problem that 'rmmod null_blk' hangs in blk_cleanup_queue()
because of miscounting of request_queue->mq_usage_counter.

This patch is the v1 of previous one of "lib/percpu_counter.c:
disable local irq when updating percpu couter", and takes Andrew's
approach which may be more efficient for ARCHs(x86, s390) that
have optimized this_cpu_add().

Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Shaohua Li <shli@fusionio.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Fan Du <fan.du@windriver.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 7473ee3..1da85bb 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -82,10 +82,10 @@ void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch)
 		unsigned long flags;
 		raw_spin_lock_irqsave(&fbc->lock, flags);
 		fbc->count += count;
+		 __this_cpu_sub(*fbc->counters, count);
 		raw_spin_unlock_irqrestore(&fbc->lock, flags);
-		__this_cpu_write(*fbc->counters, 0);
 	} else {
-		__this_cpu_write(*fbc->counters, count);
+		this_cpu_add(*fbc->counters, amount);
 	}
 	preempt_enable();
 }
-- 
cgit v0.10.2


From d139336700a5f3a560da235e4dfcd286773025d4 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Wed, 15 Jan 2014 12:52:15 +0100
Subject: x86, cpu, amd: Fix a shadowed variable situation

Having u32 and struct cpuinfo_x86 * by the same name is not very smart,
although it was ok in this case due to the limited scope of u32 c and it
being used only once in there.

Fix this.

Signed-off-by: Borislav Petkov <bp@suse.de>
Link: http://lkml.kernel.org/r/1389786735-16751-1-git-send-email-bp@alien8.de
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 39bc78d..e5647ab 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -789,14 +789,10 @@ static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
 	}
 
 	/* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
-	if (!((eax >> 16) & mask)) {
-		u32 a, b, c, d;
-
-		cpuid(0x80000005, &a, &b, &c, &d);
-		tlb_lld_2m[ENTRIES] = (a >> 16) & 0xff;
-	} else {
+	if (!((eax >> 16) & mask))
+		tlb_lld_2m[ENTRIES] = (cpuid_eax(0x80000005) >> 16) & 0xff;
+	else
 		tlb_lld_2m[ENTRIES] = (eax >> 16) & mask;
-	}
 
 	/* a 4M entry uses two 2M entries */
 	tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1;
-- 
cgit v0.10.2


From 0dce7cd67fd9055c4a2ff278f8af1431e646d346 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Wed, 15 Jan 2014 13:39:59 +0100
Subject: kvm: x86: fix apic_base enable check

Commit e66d2ae7c67bd moved the assignment
vcpu->arch.apic_base = value above a condition with
(vcpu->arch.apic_base ^ value), causing that check
to always fail. Use old_value, vcpu->arch.apic_base's
old value, in the condition instead.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 1673940..775702f 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1355,7 +1355,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 	vcpu->arch.apic_base = value;
 
 	/* update jump label if enable bit changes */
-	if ((vcpu->arch.apic_base ^ value) & MSR_IA32_APICBASE_ENABLE) {
+	if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE) {
 		if (value & MSR_IA32_APICBASE_ENABLE)
 			static_key_slow_dec_deferred(&apic_hw_disabled);
 		else
-- 
cgit v0.10.2


From 151e0c7de616310f95393d9306903900fcd8b277 Mon Sep 17 00:00:00 2001
From: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>
Date: Wed, 15 Jan 2014 15:44:58 +0900
Subject: x86, apic, kexec: Add disable_cpu_apicid kernel parameter

Add disable_cpu_apicid kernel parameter. To use this kernel parameter,
specify an initial APIC ID of the corresponding CPU you want to
disable.

This is mostly used for the kdump 2nd kernel to disable BSP to wake up
multiple CPUs without causing system reset or hang due to sending INIT
from AP to BSP.

Kdump users first figure out initial APIC ID of the BSP, CPU0 in the
1st kernel, for example from /proc/cpuinfo and then set up this kernel
parameter for the 2nd kernel using the obtained APIC ID.

However, doing this procedure at each boot time manually is awkward,
which should be automatically done by user-land service scripts, for
example, kexec-tools on fedora/RHEL distributions.

This design is more flexible than disabling BSP in kernel boot time
automatically in that in kernel boot time we have no choice but
referring to ACPI/MP table to obtain initial APIC ID for BSP, meaning
that the method is not applicable to the systems without such BIOS
tables.

One assumption behind this design is that users get initial APIC ID of
the BSP in still healthy state and so BSP is uniquely kept in
CPU0. Thus, through the kernel parameter, only one initial APIC ID can
be specified.

In a comparison with disabled_cpu_apicid, we use read_apic_id(), not
boot_cpu_physical_apicid, because on some platforms, the variable is
modified to the apicid reported as BSP through MP table and this
function is executed with the temporarily modified
boot_cpu_physical_apicid. As a result, disabled_cpu_apicid kernel
parameter doesn't work well for apicids of APs.

Fixing the wrong handling of boot_cpu_physical_apicid requires some
reviews and tests beyond some platforms and it could take some
time. The fix here is a kind of workaround to focus on the main topic
of this patch.

Signed-off-by: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>
Link: http://lkml.kernel.org/r/20140115064458.1545.38775.stgit@localhost6.localdomain6
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index b9e9bd8..6fdbf8c 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -774,6 +774,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	disable=	[IPV6]
 			See Documentation/networking/ipv6.txt.
 
+	disable_cpu_apicid= [X86,APIC,SMP]
+			Format: <int>
+			The number of initial APIC ID for the
+			corresponding CPU to be disabled at boot,
+			mostly used for the kdump 2nd kernel to
+			disable BSP to wake up multiple CPUs without
+			causing system reset or hang due to sending
+			INIT from AP to BSP.
+
 	disable_ddw     [PPC/PSERIES]
 			Disable Dynamic DMA Window support. Use this if
 			to workaround buggy firmware.
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 4ec1dd6..e78ab8c 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -75,6 +75,13 @@ unsigned int max_physical_apicid;
 physid_mask_t phys_cpu_present_map;
 
 /*
+ * Processor to be disabled specified by kernel parameter
+ * disable_cpu_apicid=<int>, mostly used for the kdump 2nd kernel to
+ * avoid undefined behaviour caused by sending INIT from AP to BSP.
+ */
+unsigned int disabled_cpu_apicid = BAD_APICID;
+
+/*
  * Map cpu index to physical APIC ID
  */
 DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID);
@@ -2114,6 +2121,39 @@ int generic_processor_info(int apicid, int version)
 				phys_cpu_present_map);
 
 	/*
+	 * boot_cpu_physical_apicid is designed to have the apicid
+	 * returned by read_apic_id(), i.e, the apicid of the
+	 * currently booting-up processor. However, on some platforms,
+	 * it is temporarilly modified by the apicid reported as BSP
+	 * through MP table. Concretely:
+	 *
+	 * - arch/x86/kernel/mpparse.c: MP_processor_info()
+	 * - arch/x86/mm/amdtopology.c: amd_numa_init()
+	 * - arch/x86/platform/visws/visws_quirks.c: MP_processor_info()
+	 *
+	 * This function is executed with the modified
+	 * boot_cpu_physical_apicid. So, disabled_cpu_apicid kernel
+	 * parameter doesn't work to disable APs on kdump 2nd kernel.
+	 *
+	 * Since fixing handling of boot_cpu_physical_apicid requires
+	 * another discussion and tests on each platform, we leave it
+	 * for now and here we use read_apic_id() directly in this
+	 * function, generic_processor_info().
+	 */
+	if (disabled_cpu_apicid != BAD_APICID &&
+	    disabled_cpu_apicid != read_apic_id() &&
+	    disabled_cpu_apicid == apicid) {
+		int thiscpu = num_processors + disabled_cpus;
+
+		pr_warning("ACPI: Disabling requested cpu."
+			   " Processor %d/0x%x ignored.\n",
+			   thiscpu, apicid);
+
+		disabled_cpus++;
+		return -ENODEV;
+	}
+
+	/*
 	 * If boot cpu has not been detected yet, then only allow upto
 	 * nr_cpu_ids - 1 processors and keep one slot free for boot cpu
 	 */
@@ -2591,3 +2631,12 @@ static int __init lapic_insert_resource(void)
  * that is using request_resource
  */
 late_initcall(lapic_insert_resource);
+
+static int __init apic_set_disabled_cpu_apicid(char *arg)
+{
+	if (!arg || !get_option(&arg, &disabled_cpu_apicid))
+		return -EINVAL;
+
+	return 0;
+}
+early_param("disable_cpu_apicid", apic_set_disabled_cpu_apicid);
-- 
cgit v0.10.2


From 7d16c634233c411f54b89d0f1d51750dc85c5f7e Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 9 Jan 2014 23:07:59 +0900
Subject: perf tools: Fix build error due to zfree() cast
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It failed to build perf on my ubuntu 10.04 box (gcc 4.4.3):

    CC       util/strlist.o
  cc1: warnings being treated as errors
  util/strlist.c: In function ‘str_node__delete’:
  util/strlist.c:42: error: dereferencing type-punned pointer will break strict-aliasing rules
  util/strlist.c:42: error: dereferencing type-punned pointer will break strict-aliasing rules
    CC       util/strfilter.o
  make: *** [util/strlist.o] Error 1

    CC       util/srcline.o
  cc1: warnings being treated as errors
  util/srcline.c: In function ‘addr2line_init’:
  util/srcline.c:132: error: dereferencing type-punned pointer will break strict-aliasing rules
  util/srcline.c:132: error: dereferencing type-punned pointer will break strict-aliasing rules
  util/srcline.c: In function ‘addr2line_cleanup’:
  util/srcline.c:143: error: dereferencing type-punned pointer will break strict-aliasing rules
  util/srcline.c:143: error: dereferencing type-punned pointer will break strict-aliasing rules
  make: *** [util/srcline.o] Error 1

It seems it only allows to remove 'const' qualifier.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1389276479-9047-1-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 7e67879..f3e4bc5 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -129,7 +129,7 @@ static struct a2l_data *addr2line_init(const char *path)
 
 out:
 	if (a2l) {
-		zfree((void **)&a2l->input);
+		zfree((char **)&a2l->input);
 		free(a2l);
 	}
 	bfd_close(abfd);
@@ -140,7 +140,7 @@ static void addr2line_cleanup(struct a2l_data *a2l)
 {
 	if (a2l->abfd)
 		bfd_close(a2l->abfd);
-	zfree((void **)&a2l->input);
+	zfree((char **)&a2l->input);
 	zfree(&a2l->syms);
 	free(a2l);
 }
diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c
index 61a90bf..71f9d10 100644
--- a/tools/perf/util/strlist.c
+++ b/tools/perf/util/strlist.c
@@ -39,7 +39,7 @@ out_delete:
 static void str_node__delete(struct str_node *snode, bool dupstr)
 {
 	if (dupstr)
-		zfree((void **)&snode->s);
+		zfree((char **)&snode->s);
 	free(snode);
 }
 
-- 
cgit v0.10.2


From 3c6d8d84423932f1d9949179c6acdf2405515ee4 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 19 Dec 2013 18:17:44 +0900
Subject: tools lib traceevent: Add state member to struct trace_seq

The trace_seq->state is for tracking errors during the use of trace_seq
APIs and getting rid of die() in it.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/87fvopalbb.fsf@sejong.aot.lge.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index f778d48..56d52a3 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -136,7 +136,7 @@ export Q VERBOSE
 
 EVENT_PARSE_VERSION = $(EP_VERSION).$(EP_PATCHLEVEL).$(EP_EXTRAVERSION)
 
-INCLUDES = -I. $(CONFIG_INCLUDES)
+INCLUDES = -I. -I $(srctree)/../../include $(CONFIG_INCLUDES)
 
 # Set compile option CFLAGS if not set elsewhere
 CFLAGS ?= -g -Wall
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index cf5db90..3c890cb 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -58,6 +58,12 @@ struct pevent_record {
 #endif
 };
 
+enum trace_seq_fail {
+	TRACE_SEQ__GOOD,
+	TRACE_SEQ__BUFFER_POISONED,
+	TRACE_SEQ__MEM_ALLOC_FAILED,
+};
+
 /*
  * Trace sequences are used to allow a function to call several other functions
  * to create a string of data to use (up to a max of PAGE_SIZE).
@@ -68,6 +74,7 @@ struct trace_seq {
 	unsigned int		buffer_size;
 	unsigned int		len;
 	unsigned int		readpos;
+	enum trace_seq_fail	state;
 };
 
 void trace_seq_init(struct trace_seq *s);
diff --git a/tools/lib/traceevent/trace-seq.c b/tools/lib/traceevent/trace-seq.c
index d7f2e68..f711213 100644
--- a/tools/lib/traceevent/trace-seq.c
+++ b/tools/lib/traceevent/trace-seq.c
@@ -22,6 +22,7 @@
 #include <string.h>
 #include <stdarg.h>
 
+#include <asm/bug.h>
 #include "event-parse.h"
 #include "event-utils.h"
 
@@ -32,10 +33,21 @@
 #define TRACE_SEQ_POISON	((void *)0xdeadbeef)
 #define TRACE_SEQ_CHECK(s)						\
 do {									\
-	if ((s)->buffer == TRACE_SEQ_POISON)			\
-		die("Usage of trace_seq after it was destroyed");	\
+	if (WARN_ONCE((s)->buffer == TRACE_SEQ_POISON,			\
+		      "Usage of trace_seq after it was destroyed"))	\
+		(s)->state = TRACE_SEQ__BUFFER_POISONED;		\
 } while (0)
 
+#define TRACE_SEQ_CHECK_RET_N(s, n)		\
+do {						\
+	TRACE_SEQ_CHECK(s);			\
+	if ((s)->state != TRACE_SEQ__GOOD)	\
+		return n; 			\
+} while (0)
+
+#define TRACE_SEQ_CHECK_RET(s)   TRACE_SEQ_CHECK_RET_N(s, )
+#define TRACE_SEQ_CHECK_RET0(s)  TRACE_SEQ_CHECK_RET_N(s, 0)
+
 /**
  * trace_seq_init - initialize the trace_seq structure
  * @s: a pointer to the trace_seq structure to initialize
@@ -46,6 +58,7 @@ void trace_seq_init(struct trace_seq *s)
 	s->readpos = 0;
 	s->buffer_size = TRACE_SEQ_BUF_SIZE;
 	s->buffer = malloc_or_die(s->buffer_size);
+	s->state = TRACE_SEQ__GOOD;
 }
 
 /**
@@ -71,7 +84,7 @@ void trace_seq_destroy(struct trace_seq *s)
 {
 	if (!s)
 		return;
-	TRACE_SEQ_CHECK(s);
+	TRACE_SEQ_CHECK_RET(s);
 	free(s->buffer);
 	s->buffer = TRACE_SEQ_POISON;
 }
@@ -80,8 +93,9 @@ static void expand_buffer(struct trace_seq *s)
 {
 	s->buffer_size += TRACE_SEQ_BUF_SIZE;
 	s->buffer = realloc(s->buffer, s->buffer_size);
-	if (!s->buffer)
-		die("Can't allocate trace_seq buffer memory");
+	if (WARN_ONCE(!s->buffer,
+		      "Can't allocate trace_seq buffer memory"))
+		s->state = TRACE_SEQ__MEM_ALLOC_FAILED;
 }
 
 /**
@@ -105,9 +119,9 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 	int len;
 	int ret;
 
-	TRACE_SEQ_CHECK(s);
-
  try_again:
+	TRACE_SEQ_CHECK_RET0(s);
+
 	len = (s->buffer_size - 1) - s->len;
 
 	va_start(ap, fmt);
@@ -141,9 +155,9 @@ trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
 	int len;
 	int ret;
 
-	TRACE_SEQ_CHECK(s);
-
  try_again:
+	TRACE_SEQ_CHECK_RET0(s);
+
 	len = (s->buffer_size - 1) - s->len;
 
 	ret = vsnprintf(s->buffer + s->len, len, fmt, args);
@@ -172,13 +186,15 @@ int trace_seq_puts(struct trace_seq *s, const char *str)
 {
 	int len;
 
-	TRACE_SEQ_CHECK(s);
+	TRACE_SEQ_CHECK_RET0(s);
 
 	len = strlen(str);
 
 	while (len > ((s->buffer_size - 1) - s->len))
 		expand_buffer(s);
 
+	TRACE_SEQ_CHECK_RET0(s);
+
 	memcpy(s->buffer + s->len, str, len);
 	s->len += len;
 
@@ -187,11 +203,13 @@ int trace_seq_puts(struct trace_seq *s, const char *str)
 
 int trace_seq_putc(struct trace_seq *s, unsigned char c)
 {
-	TRACE_SEQ_CHECK(s);
+	TRACE_SEQ_CHECK_RET0(s);
 
 	while (s->len >= (s->buffer_size - 1))
 		expand_buffer(s);
 
+	TRACE_SEQ_CHECK_RET0(s);
+
 	s->buffer[s->len++] = c;
 
 	return 1;
@@ -199,7 +217,7 @@ int trace_seq_putc(struct trace_seq *s, unsigned char c)
 
 void trace_seq_terminate(struct trace_seq *s)
 {
-	TRACE_SEQ_CHECK(s);
+	TRACE_SEQ_CHECK_RET(s);
 
 	/* There's always one character left on the buffer */
 	s->buffer[s->len] = 0;
@@ -208,5 +226,16 @@ void trace_seq_terminate(struct trace_seq *s)
 int trace_seq_do_printf(struct trace_seq *s)
 {
 	TRACE_SEQ_CHECK(s);
-	return printf("%.*s", s->len, s->buffer);
+
+	switch (s->state) {
+	case TRACE_SEQ__GOOD:
+		return printf("%.*s", s->len, s->buffer);
+	case TRACE_SEQ__BUFFER_POISONED:
+		puts("Usage of trace_seq after it was destroyed");
+		break;
+	case TRACE_SEQ__MEM_ALLOC_FAILED:
+		puts("Can't allocate trace_seq buffer memory");
+		break;
+	}
+	return -1;
 }
-- 
cgit v0.10.2


From 3026bba3c37711234771349ca020d9a85e572f60 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Wed, 15 Jan 2014 10:45:25 +0900
Subject: tools lib traceevent: Check return value of realloc()

If realloc() fails, it'll leak the buffer.  Also increate buffer size
only if the allocation succeeded.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389750340-15965-3-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/trace-seq.c b/tools/lib/traceevent/trace-seq.c
index f711213..e454a2c 100644
--- a/tools/lib/traceevent/trace-seq.c
+++ b/tools/lib/traceevent/trace-seq.c
@@ -91,11 +91,16 @@ void trace_seq_destroy(struct trace_seq *s)
 
 static void expand_buffer(struct trace_seq *s)
 {
-	s->buffer_size += TRACE_SEQ_BUF_SIZE;
-	s->buffer = realloc(s->buffer, s->buffer_size);
-	if (WARN_ONCE(!s->buffer,
-		      "Can't allocate trace_seq buffer memory"))
+	char *buf;
+
+	buf = realloc(s->buffer, s->buffer_size + TRACE_SEQ_BUF_SIZE);
+	if (WARN_ONCE(!buf, "Can't allocate trace_seq buffer memory")) {
 		s->state = TRACE_SEQ__MEM_ALLOC_FAILED;
+		return;
+	}
+
+	s->buffer = buf;
+	s->buffer_size += TRACE_SEQ_BUF_SIZE;
 }
 
 /**
-- 
cgit v0.10.2


From 504586e0954bcf9550dfdea37d3234174ed1d68f Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Wed, 15 Jan 2014 10:45:26 +0900
Subject: tools lib traceevent: Get rid of malloc_or_die() in trace_seq_init()

Use plain malloc() and check its return value.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389750340-15965-4-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/trace-seq.c b/tools/lib/traceevent/trace-seq.c
index e454a2c..ec3bd16 100644
--- a/tools/lib/traceevent/trace-seq.c
+++ b/tools/lib/traceevent/trace-seq.c
@@ -57,8 +57,11 @@ void trace_seq_init(struct trace_seq *s)
 	s->len = 0;
 	s->readpos = 0;
 	s->buffer_size = TRACE_SEQ_BUF_SIZE;
-	s->buffer = malloc_or_die(s->buffer_size);
-	s->state = TRACE_SEQ__GOOD;
+	s->buffer = malloc(s->buffer_size);
+	if (s->buffer != NULL)
+		s->state = TRACE_SEQ__GOOD;
+	else
+		s->state = TRACE_SEQ__MEM_ALLOC_FAILED;
 }
 
 /**
-- 
cgit v0.10.2


From e825e756f84eab0e68d7d6644c018c3412748406 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Wed, 15 Jan 2014 10:45:27 +0900
Subject: tools lib traceevent: Get rid of die() finally!!

Now all of its users were gone. :)

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389750340-15965-5-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/event-utils.h b/tools/lib/traceevent/event-utils.h
index e76c9ac..d1dc217 100644
--- a/tools/lib/traceevent/event-utils.h
+++ b/tools/lib/traceevent/event-utils.h
@@ -23,18 +23,14 @@
 #include <ctype.h>
 
 /* Can be overridden */
-void die(const char *fmt, ...);
-void *malloc_or_die(unsigned int size);
 void warning(const char *fmt, ...);
 void pr_stat(const char *fmt, ...);
 void vpr_stat(const char *fmt, va_list ap);
 
 /* Always available */
-void __die(const char *fmt, ...);
 void __warning(const char *fmt, ...);
 void __pr_stat(const char *fmt, ...);
 
-void __vdie(const char *fmt, ...);
 void __vwarning(const char *fmt, ...);
 void __vpr_stat(const char *fmt, ...);
 
diff --git a/tools/lib/traceevent/parse-utils.c b/tools/lib/traceevent/parse-utils.c
index bba701c..eda07fa 100644
--- a/tools/lib/traceevent/parse-utils.c
+++ b/tools/lib/traceevent/parse-utils.c
@@ -25,40 +25,6 @@
 
 #define __weak __attribute__((weak))
 
-void __vdie(const char *fmt, va_list ap)
-{
-	int ret = errno;
-
-	if (errno)
-		perror("trace-cmd");
-	else
-		ret = -1;
-
-	fprintf(stderr, "  ");
-	vfprintf(stderr, fmt, ap);
-
-	fprintf(stderr, "\n");
-	exit(ret);
-}
-
-void __die(const char *fmt, ...)
-{
-	va_list ap;
-
-	va_start(ap, fmt);
-	__vdie(fmt, ap);
-	va_end(ap);
-}
-
-void __weak die(const char *fmt, ...)
-{
-	va_list ap;
-
-	va_start(ap, fmt);
-	__vdie(fmt, ap);
-	va_end(ap);
-}
-
 void __vwarning(const char *fmt, va_list ap)
 {
 	if (errno)
@@ -117,13 +83,3 @@ void __weak pr_stat(const char *fmt, ...)
 	__vpr_stat(fmt, ap);
 	va_end(ap);
 }
-
-void __weak *malloc_or_die(unsigned int size)
-{
-	void *data;
-
-	data = malloc(size);
-	if (!data)
-		die("malloc");
-	return data;
-}
-- 
cgit v0.10.2


From 8d0c2224ca6e04ba51c403805e7e1e2ca536520b Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Wed, 15 Jan 2014 10:45:28 +0900
Subject: tools lib traceevent: Make plugin unload function receive pevent

The PEVENT_PLUGIN_UNLOADER function might need some cleanup using pevent
like unregister some handlers.  So pass pevent as argument.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389750340-15965-6-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 3c890cb..a3beca5 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -105,7 +105,7 @@ typedef int (*pevent_event_handler_func)(struct trace_seq *s,
 					 void *context);
 
 typedef int (*pevent_plugin_load_func)(struct pevent *pevent);
-typedef int (*pevent_plugin_unload_func)(void);
+typedef int (*pevent_plugin_unload_func)(struct pevent *pevent);
 
 struct plugin_option {
 	struct plugin_option		*next;
@@ -130,7 +130,7 @@ struct plugin_option {
  * PEVENT_PLUGIN_UNLOADER:  (optional)
  *   The function called just before unloading
  *
- *   int PEVENT_PLUGIN_UNLOADER(void)
+ *   int PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
  *
  * PEVENT_PLUGIN_OPTIONS:  (optional)
  *   Plugin options that can be set before loading
@@ -411,7 +411,8 @@ enum pevent_errno {
 struct plugin_list;
 
 struct plugin_list *traceevent_load_plugins(struct pevent *pevent);
-void traceevent_unload_plugins(struct plugin_list *plugin_list);
+void traceevent_unload_plugins(struct plugin_list *plugin_list,
+			       struct pevent *pevent);
 
 struct cmdline;
 struct cmdline_list;
diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c
index 125f567..0c8bf67 100644
--- a/tools/lib/traceevent/event-plugin.c
+++ b/tools/lib/traceevent/event-plugin.c
@@ -197,7 +197,7 @@ traceevent_load_plugins(struct pevent *pevent)
 }
 
 void
-traceevent_unload_plugins(struct plugin_list *plugin_list)
+traceevent_unload_plugins(struct plugin_list *plugin_list, struct pevent *pevent)
 {
 	pevent_plugin_unload_func func;
 	struct plugin_list *list;
@@ -207,7 +207,7 @@ traceevent_unload_plugins(struct plugin_list *plugin_list)
 		plugin_list = list->next;
 		func = dlsym(list->handle, PEVENT_PLUGIN_UNLOADER_NAME);
 		if (func)
-			func();
+			func(pevent);
 		dlclose(list->handle);
 		free(list->name);
 		free(list);
diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c
index aad92ad..3946148 100644
--- a/tools/lib/traceevent/plugin_function.c
+++ b/tools/lib/traceevent/plugin_function.c
@@ -144,7 +144,7 @@ int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
 	return 0;
 }
 
-void PEVENT_PLUGIN_UNLOADER(void)
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
 {
 	int i, x;
 
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index d9f5f61..6322d37 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -34,8 +34,8 @@ int trace_event__init(struct trace_event *t)
 
 void trace_event__cleanup(struct trace_event *t)
 {
+	traceevent_unload_plugins(t->plugin_list, t->pevent);
 	pevent_free(t->pevent);
-	traceevent_unload_plugins(t->plugin_list);
 }
 
 static struct event_format*
-- 
cgit v0.10.2


From a8a5cd8b472ca20e5b8fa649c43b3756867322f8 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 15 Jan 2014 10:44:08 +0000
Subject: perf: tools: Fix cross building

Currently the feature-checks Makefile does not inherit $(CC), and calls
cc rather than $(CROSS_COMPILE)gcc. Thus the feature checks invoke the
native toolchain rather than the cross toolchain, and can identify
features as available when they are not. This can break the build.

Additionally the native pkg-config is always called as opposed to
$(CROSS_COMPILE)pkg-config, so the wrong flags and paths may be passed
to the cross compiler.

This patch passes CROSS_COMPILE down to the feature-checks Makefile, and
forces its use. Additionally pkg-config is replaced with
$(CROSS_COMPILE)pkg-config via a new $(PKG_CONFIG) variable. This patch
has been build tested on x86_64 and arm.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Will Deacon <will.deacon@arm.com>
Link: http://lkml.kernel.org/r/1389782648-4417-4-git-send-email-mark.rutland@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 87d7726..7257e7e 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -76,6 +76,7 @@ $(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD
 
 CC = $(CROSS_COMPILE)gcc
 AR = $(CROSS_COMPILE)ar
+PKG_CONFIG = $(CROSS_COMPILE)pkg-config
 
 RM      = rm -f
 LN      = ln -f
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 01dd43d..d604e50 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -372,7 +372,7 @@ ifndef NO_SLANG
 endif
 
 ifndef NO_GTK2
-  FLAGS_GTK2=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null)
+  FLAGS_GTK2=$(CFLAGS) $(LDFLAGS) $(EXTLIBS) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null)
   ifneq ($(feature-gtk2), 1)
     msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev);
     NO_GTK2 := 1
@@ -381,8 +381,8 @@ ifndef NO_GTK2
       GTK_CFLAGS := -DHAVE_GTK_INFO_BAR_SUPPORT
     endif
     CFLAGS += -DHAVE_GTK2_SUPPORT
-    GTK_CFLAGS += $(shell pkg-config --cflags gtk+-2.0 2>/dev/null)
-    GTK_LIBS := $(shell pkg-config --libs gtk+-2.0 2>/dev/null)
+    GTK_CFLAGS += $(shell $(PKG_CONFIG) --cflags gtk+-2.0 2>/dev/null)
+    GTK_LIBS := $(shell $(PKG_CONFIG) --libs gtk+-2.0 2>/dev/null)
     EXTLIBS += -ldl
   endif
 endif
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 7cf6fcd..12e5513 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -28,7 +28,8 @@ FILES=					\
 	test-stackprotector-all.bin	\
 	test-timerfd.bin
 
-CC := $(CC) -MD
+CC := $(CROSS_COMPILE)gcc -MD
+PKG_CONFIG := $(CROSS_COMPILE)pkg-config
 
 all: $(FILES)
 
@@ -37,7 +38,7 @@ BUILD = $(CC) $(CFLAGS) -o $(OUTPUT)$@ $(patsubst %.bin,%.c,$@) $(LDFLAGS)
 ###############################
 
 test-all.bin:
-	$(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl
+	$(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl
 
 test-hello.bin:
 	$(BUILD)
@@ -82,10 +83,10 @@ test-libslang.bin:
 	$(BUILD) -I/usr/include/slang -lslang
 
 test-gtk2.bin:
-	$(BUILD) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null)
+	$(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null)
 
 test-gtk2-infobar.bin:
-	$(BUILD) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null)
+	$(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null)
 
 grep-libs  = $(filter -l%,$(1))
 strip-libs = $(filter-out -l%,$(1))
-- 
cgit v0.10.2


From 540476de74c9b11403656791838ede91405d3859 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 14 Jan 2014 14:25:34 +0900
Subject: perf tools: Remove symbol_conf.use_callchain check

The machine__resolve_callchain() is called only if symbol_conf.
use_callchain is set so no need to check it again.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Rodrigo Campos <rodrigo@sdfg.com.ar>
Link: http://lkml.kernel.org/r/1389677157-30513-2-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 0130279..ded7459 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1314,8 +1314,6 @@ static int machine__resolve_callchain_sample(struct machine *machine,
 				*root_al = al;
 				callchain_cursor_reset(&callchain_cursor);
 			}
-			if (!symbol_conf.use_callchain)
-				break;
 		}
 
 		err = callchain_cursor_append(&callchain_cursor,
-- 
cgit v0.10.2


From 2dc9fb1a7bf013ce24dd34bc25283b60b966f015 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 14 Jan 2014 14:25:35 +0900
Subject: perf tools: Factor out sample__resolve_callchain()

The report__resolve_callchain() can be shared with perf top code as it
doesn't really depend on the perf report code.  Factor it out as
sample__resolve_callchain().  The same goes to the hist_entry__append_
callchain() too.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Arun Sharma <asharma@fb.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Rodrigo Campos <rodrigo@sdfg.com.ar>
Link: http://lkml.kernel.org/r/1389677157-30513-3-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 46864dd..3c53ec2 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -75,24 +75,6 @@ static int report__config(const char *var, const char *value, void *cb)
 	return perf_default_config(var, value, cb);
 }
 
-static int report__resolve_callchain(struct report *rep, struct symbol **parent,
-				     struct perf_evsel *evsel, struct addr_location *al,
-				     struct perf_sample *sample)
-{
-	if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
-		return machine__resolve_callchain(al->machine, evsel, al->thread, sample,
-						  parent, al, rep->max_stack);
-	}
-	return 0;
-}
-
-static int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample)
-{
-	if (!symbol_conf.use_callchain)
-		return 0;
-	return callchain_append(he->callchain, &callchain_cursor, sample->period);
-}
-
 static int report__add_mem_hist_entry(struct perf_tool *tool, struct addr_location *al,
 				      struct perf_sample *sample, struct perf_evsel *evsel,
 				      union perf_event *event)
@@ -103,7 +85,7 @@ static int report__add_mem_hist_entry(struct perf_tool *tool, struct addr_locati
 	struct hist_entry *he;
 	struct mem_info *mi, *mx;
 	uint64_t cost;
-	int err = report__resolve_callchain(rep, &parent, evsel, al, sample);
+	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
 
 	if (err)
 		return err;
@@ -155,7 +137,7 @@ static int report__add_branch_hist_entry(struct perf_tool *tool, struct addr_loc
 	unsigned i;
 	struct hist_entry *he;
 	struct branch_info *bi, *bx;
-	int err = report__resolve_callchain(rep, &parent, evsel, al, sample);
+	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
 
 	if (err)
 		return err;
@@ -208,7 +190,7 @@ static int report__add_hist_entry(struct perf_tool *tool, struct perf_evsel *evs
 	struct report *rep = container_of(tool, struct report, tool);
 	struct symbol *parent = NULL;
 	struct hist_entry *he;
-	int err = report__resolve_callchain(rep, &parent, evsel, al, sample);
+	int err = sample__resolve_callchain(sample, &parent, evsel, al, rep->max_stack);
 
 	if (err)
 		return err;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 569dd87..76cd510 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -743,15 +743,10 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	if (al.sym == NULL || !al.sym->ignore) {
 		struct hist_entry *he;
 
-		if ((sort__has_parent || symbol_conf.use_callchain) &&
-		    sample->callchain) {
-			err = machine__resolve_callchain(machine, evsel,
-							 al.thread, sample,
-							 &parent, &al,
-							 top->max_stack);
-			if (err)
-				return;
-		}
+		err = sample__resolve_callchain(sample, &parent, evsel, &al,
+						top->max_stack);
+		if (err)
+			return;
 
 		he = perf_evsel__add_hist_entry(evsel, &al, sample);
 		if (he == NULL) {
@@ -759,12 +754,9 @@ static void perf_event__process_sample(struct perf_tool *tool,
 			return;
 		}
 
-		if (symbol_conf.use_callchain) {
-			err = callchain_append(he->callchain, &callchain_cursor,
-					       sample->period);
-			if (err)
-				return;
-		}
+		err = hist_entry__append_callchain(he, sample);
+		if (err)
+			return;
 
 		if (sort__has_sym)
 			perf_top__record_precise_ip(top, he, evsel->idx, ip);
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index e3970e3..9eb4f57 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -17,6 +17,8 @@
 
 #include "hist.h"
 #include "util.h"
+#include "sort.h"
+#include "machine.h"
 #include "callchain.h"
 
 __thread struct callchain_cursor callchain_cursor;
@@ -531,3 +533,24 @@ int callchain_cursor_append(struct callchain_cursor *cursor,
 
 	return 0;
 }
+
+int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent,
+			      struct perf_evsel *evsel, struct addr_location *al,
+			      int max_stack)
+{
+	if (sample->callchain == NULL)
+		return 0;
+
+	if (symbol_conf.use_callchain || sort__has_parent) {
+		return machine__resolve_callchain(al->machine, evsel, al->thread,
+						  sample, parent, al, max_stack);
+	}
+	return 0;
+}
+
+int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample)
+{
+	if (!symbol_conf.use_callchain)
+		return 0;
+	return callchain_append(he->callchain, &callchain_cursor, sample->period);
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 08b25af..8ad97e9 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -145,10 +145,16 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor)
 }
 
 struct option;
+struct hist_entry;
 
 int record_parse_callchain(const char *arg, struct record_opts *opts);
 int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset);
 int record_callchain_opt(const struct option *opt, const char *arg, int unset);
 
+int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent,
+			      struct perf_evsel *evsel, struct addr_location *al,
+			      int max_stack);
+int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample);
+
 extern const char record_callchain_help[];
 #endif	/* __PERF_CALLCHAIN_H */
-- 
cgit v0.10.2


From f39056f9c3275e648e2fb353561aeb377dd351f7 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Tue, 14 Jan 2014 14:25:37 +0900
Subject: perf hists: Convert hist entry functions to use struct he_stat

The hist_entry__add_cpumode_period() and hist_entry__decay() functions
are dealing with hist_entry's stat fields only.

Make them he_stat methods then.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Arun Sharma <asharma@fb.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Rodrigo Campos <rodrigo@sdfg.com.ar>
Link: http://lkml.kernel.org/r/1389677157-30513-5-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 4ed3e88..e4e6249 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -181,21 +181,21 @@ void hists__output_recalc_col_len(struct hists *hists, int max_rows)
 	}
 }
 
-static void hist_entry__add_cpumode_period(struct hist_entry *he,
-					   unsigned int cpumode, u64 period)
+static void he_stat__add_cpumode_period(struct he_stat *he_stat,
+					unsigned int cpumode, u64 period)
 {
 	switch (cpumode) {
 	case PERF_RECORD_MISC_KERNEL:
-		he->stat.period_sys += period;
+		he_stat->period_sys += period;
 		break;
 	case PERF_RECORD_MISC_USER:
-		he->stat.period_us += period;
+		he_stat->period_us += period;
 		break;
 	case PERF_RECORD_MISC_GUEST_KERNEL:
-		he->stat.period_guest_sys += period;
+		he_stat->period_guest_sys += period;
 		break;
 	case PERF_RECORD_MISC_GUEST_USER:
-		he->stat.period_guest_us += period;
+		he_stat->period_guest_us += period;
 		break;
 	default:
 		break;
@@ -222,10 +222,10 @@ static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src)
 	dest->weight		+= src->weight;
 }
 
-static void hist_entry__decay(struct hist_entry *he)
+static void he_stat__decay(struct he_stat *he_stat)
 {
-	he->stat.period = (he->stat.period * 7) / 8;
-	he->stat.nr_events = (he->stat.nr_events * 7) / 8;
+	he_stat->period = (he_stat->period * 7) / 8;
+	he_stat->nr_events = (he_stat->nr_events * 7) / 8;
 	/* XXX need decay for weight too? */
 }
 
@@ -236,7 +236,7 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 	if (prev_period == 0)
 		return true;
 
-	hist_entry__decay(he);
+	he_stat__decay(&he->stat);
 
 	if (!he->filtered)
 		hists->stats.total_period -= prev_period - he->stat.period;
@@ -402,7 +402,7 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 	rb_link_node(&he->rb_node_in, parent, p);
 	rb_insert_color(&he->rb_node_in, hists->entries_in);
 out:
-	hist_entry__add_cpumode_period(he, al->cpumode, period);
+	he_stat__add_cpumode_period(&he->stat, al->cpumode, period);
 	return he;
 }
 
-- 
cgit v0.10.2


From 0e9e79a13ab9d56b86db6538305babc23b1445cc Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 15 Jan 2014 10:44:07 +0000
Subject: tools lib traceevent: fix pointer-integer size mismatch
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The scsi and cfg80211 plugins cast between unsigned long long and
pointers, which is problematic for architectures where unsigned long
long is wider than the native pointer size:

  linux/tools/lib/traceevent/plugin_scsi.c: In function ‘process_scsi_trace_parse_cdb’:
  linux/tools/lib/traceevent/plugin_scsi.c:408:26: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
    scsi_trace_parse_cdb(s, (unsigned char *) args[1], args[2]);

  linux/tools/lib/traceevent/plugin_cfg80211.c: In function ‘process___le16_to_cpup’:
  linux/tools/lib/traceevent/plugin_cfg80211.c:11:18: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
    uint16_t *val = (uint16_t *) args[0];

This patch adds an intermediate cast to unsigned long, silencing the
warning.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Will Deacon <will.deacon@arm.com>
Link: http://lkml.kernel.org/r/1389782648-4417-3-git-send-email-mark.rutland@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugin_cfg80211.c
index dcab8e8..57e9822 100644
--- a/tools/lib/traceevent/plugin_cfg80211.c
+++ b/tools/lib/traceevent/plugin_cfg80211.c
@@ -8,7 +8,7 @@ static unsigned long long
 process___le16_to_cpup(struct trace_seq *s,
 		       unsigned long long *args)
 {
-	uint16_t *val = (uint16_t *) args[0];
+	uint16_t *val = (uint16_t *) (unsigned long) args[0];
 	return val ? (long long) le16toh(*val) : 0;
 }
 
diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugin_scsi.c
index 6fb8e3e..7ef16cc 100644
--- a/tools/lib/traceevent/plugin_scsi.c
+++ b/tools/lib/traceevent/plugin_scsi.c
@@ -405,7 +405,7 @@ scsi_trace_parse_cdb(struct trace_seq *p, unsigned char *cdb, int len)
 unsigned long long process_scsi_trace_parse_cdb(struct trace_seq *s,
 						unsigned long long *args)
 {
-	scsi_trace_parse_cdb(s, (unsigned char *) args[1], args[2]);
+	scsi_trace_parse_cdb(s, (unsigned char *) (unsigned long) args[1], args[2]);
 	return 0;
 }
 
-- 
cgit v0.10.2


From 5b4d1dbc24bb6fd7179ada0f47be34e27e64decb Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@zytor.com>
Date: Wed, 15 Jan 2014 13:02:08 -0800
Subject: x86, apic: Make disabled_cpu_apicid static read_mostly, fix typos

Make disabled_cpu_apicid static and read_mostly, and fix a couple of
typos.

Reported-by: Ingo Molnar <mingo@kernel.org>
Link: http://lkml.kernel.org/r/20140115182511.GA22737@gmail.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index e78ab8c..7f26c9a 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -79,7 +79,7 @@ physid_mask_t phys_cpu_present_map;
  * disable_cpu_apicid=<int>, mostly used for the kdump 2nd kernel to
  * avoid undefined behaviour caused by sending INIT from AP to BSP.
  */
-unsigned int disabled_cpu_apicid = BAD_APICID;
+static unsigned int disabled_cpu_apicid __read_mostly = BAD_APICID;
 
 /*
  * Map cpu index to physical APIC ID
@@ -2124,7 +2124,7 @@ int generic_processor_info(int apicid, int version)
 	 * boot_cpu_physical_apicid is designed to have the apicid
 	 * returned by read_apic_id(), i.e, the apicid of the
 	 * currently booting-up processor. However, on some platforms,
-	 * it is temporarilly modified by the apicid reported as BSP
+	 * it is temporarily modified by the apicid reported as BSP
 	 * through MP table. Concretely:
 	 *
 	 * - arch/x86/kernel/mpparse.c: MP_processor_info()
@@ -2145,7 +2145,7 @@ int generic_processor_info(int apicid, int version)
 	    disabled_cpu_apicid == apicid) {
 		int thiscpu = num_processors + disabled_cpus;
 
-		pr_warning("ACPI: Disabling requested cpu."
+		pr_warning("APIC: Disabling requested cpu."
 			   " Processor %d/0x%x ignored.\n",
 			   thiscpu, apicid);
 
-- 
cgit v0.10.2


From ecd6910db979bc40ac19f0e71e027132fc906068 Mon Sep 17 00:00:00 2001
From: David Cohen <david.a.cohen@linux.intel.com>
Date: Mon, 16 Dec 2013 12:07:36 -0800
Subject: x86, intel-mid: Move Medfield code out of intel-mid.c core file

In order make the driver more portable and support other Intel MID
(Mobile Internet Device) platforms we need to move Medfield code from
intel-mid.c core to its own mfld.c file.

This patch contains no functional changes.

Signed-off-by: David Cohen <david.a.cohen@linux.intel.com>
Link: http://lkml.kernel.org/r/1387224459-25746-2-git-send-email-david.a.cohen@linux.intel.com
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/platform/intel-mid/Makefile b/arch/x86/platform/intel-mid/Makefile
index 01cc29e..78a14ba 100644
--- a/arch/x86/platform/intel-mid/Makefile
+++ b/arch/x86/platform/intel-mid/Makefile
@@ -1,6 +1,6 @@
-obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o
-obj-$(CONFIG_X86_INTEL_MID) += intel_mid_vrtc.o
+obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o intel_mid_vrtc.o mfld.o
 obj-$(CONFIG_EARLY_PRINTK_INTEL_MID) += early_printk_intel_mid.o
+
 # SFI specific code
 ifdef CONFIG_X86_INTEL_MID
 obj-$(CONFIG_SFI) += sfi.o device_libs/
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index f90e290..527d6d5 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -35,6 +35,8 @@
 #include <asm/apb_timer.h>
 #include <asm/reboot.h>
 
+#include "intel_mid_weak_decls.h"
+
 /*
  * the clockevent devices on Moorestown/Medfield can be APBT or LAPIC clock,
  * cmdline option x86_intel_mid_timer can be used to override the configuration
@@ -61,46 +63,11 @@ enum intel_mid_timer_options intel_mid_timer_options;
 enum intel_mid_cpu_type __intel_mid_cpu_chip;
 EXPORT_SYMBOL_GPL(__intel_mid_cpu_chip);
 
-static void intel_mid_power_off(void)
-{
-}
-
 static void intel_mid_reboot(void)
 {
 	intel_scu_ipc_simple_command(IPCMSG_COLD_BOOT, 0);
 }
 
-static unsigned long __init intel_mid_calibrate_tsc(void)
-{
-	unsigned long fast_calibrate;
-	u32 lo, hi, ratio, fsb;
-
-	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
-	pr_debug("IA32 perf status is 0x%x, 0x%0x\n", lo, hi);
-	ratio = (hi >> 8) & 0x1f;
-	pr_debug("ratio is %d\n", ratio);
-	if (!ratio) {
-		pr_err("read a zero ratio, should be incorrect!\n");
-		pr_err("force tsc ratio to 16 ...\n");
-		ratio = 16;
-	}
-	rdmsr(MSR_FSB_FREQ, lo, hi);
-	if ((lo & 0x7) == 0x7)
-		fsb = PENWELL_FSB_FREQ_83SKU;
-	else
-		fsb = PENWELL_FSB_FREQ_100SKU;
-	fast_calibrate = ratio * fsb;
-	pr_debug("read penwell tsc %lu khz\n", fast_calibrate);
-	lapic_timer_frequency = fsb * 1000 / HZ;
-	/* mark tsc clocksource as reliable */
-	set_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC_RELIABLE);
-
-	if (fast_calibrate)
-		return fast_calibrate;
-
-	return 0;
-}
-
 static void __init intel_mid_time_init(void)
 {
 	sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr);
diff --git a/arch/x86/platform/intel-mid/intel_mid_weak_decls.h b/arch/x86/platform/intel-mid/intel_mid_weak_decls.h
new file mode 100644
index 0000000..519beb7
--- /dev/null
+++ b/arch/x86/platform/intel-mid/intel_mid_weak_decls.h
@@ -0,0 +1,15 @@
+/*
+ * intel_mid_weak_decls.h: Weak declarations of intel-mid.c
+ *
+ * (C) Copyright 2013 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+
+/* __attribute__((weak)) makes these declarations overridable */
+extern void intel_mid_power_off(void) __attribute__((weak));
+extern unsigned long __init intel_mid_calibrate_tsc(void) __attribute__((weak));
diff --git a/arch/x86/platform/intel-mid/mfld.c b/arch/x86/platform/intel-mid/mfld.c
new file mode 100644
index 0000000..c7ff83c
--- /dev/null
+++ b/arch/x86/platform/intel-mid/mfld.c
@@ -0,0 +1,51 @@
+/*
+ * mfld.c: Intel Medfield platform setup code
+ *
+ * (C) Copyright 2013 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/init.h>
+
+#include <asm/apic.h>
+#include <asm/intel-mid.h>
+#include <asm/intel_mid_vrtc.h>
+
+void intel_mid_power_off(void)
+{
+}
+
+unsigned long __init intel_mid_calibrate_tsc(void)
+{
+	unsigned long fast_calibrate;
+	u32 lo, hi, ratio, fsb;
+
+	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+	pr_debug("IA32 perf status is 0x%x, 0x%0x\n", lo, hi);
+	ratio = (hi >> 8) & 0x1f;
+	pr_debug("ratio is %d\n", ratio);
+	if (!ratio) {
+		pr_err("read a zero ratio, should be incorrect!\n");
+		pr_err("force tsc ratio to 16 ...\n");
+		ratio = 16;
+	}
+	rdmsr(MSR_FSB_FREQ, lo, hi);
+	if ((lo & 0x7) == 0x7)
+		fsb = PENWELL_FSB_FREQ_83SKU;
+	else
+		fsb = PENWELL_FSB_FREQ_100SKU;
+	fast_calibrate = ratio * fsb;
+	pr_debug("read penwell tsc %lu khz\n", fast_calibrate);
+	lapic_timer_frequency = fsb * 1000 / HZ;
+	/* mark tsc clocksource as reliable */
+	set_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC_RELIABLE);
+
+	if (fast_calibrate)
+		return fast_calibrate;
+
+	return 0;
+}
-- 
cgit v0.10.2


From 85611e3febe78955a519f5f9eb47b941525c8c76 Mon Sep 17 00:00:00 2001
From: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Date: Mon, 16 Dec 2013 12:07:37 -0800
Subject: x86, intel-mid: Add Clovertrail platform support

This patch adds Clovertrail support on intel-mid and makes it more
flexible to support other SoCs.

Signed-off-by: David Cohen <david.a.cohen@linux.intel.com>
Link: http://lkml.kernel.org/r/1387224459-25746-3-git-send-email-david.a.cohen@linux.intel.com
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Fei Yang <fei.yang@intel.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h
index 459769d..f8a8314 100644
--- a/arch/x86/include/asm/intel-mid.h
+++ b/arch/x86/include/asm/intel-mid.h
@@ -51,10 +51,39 @@ struct devs_id {
 enum intel_mid_cpu_type {
 	/* 1 was Moorestown */
 	INTEL_MID_CPU_CHIP_PENWELL = 2,
+	INTEL_MID_CPU_CHIP_CLOVERVIEW,
 };
 
 extern enum intel_mid_cpu_type __intel_mid_cpu_chip;
 
+/**
+ * struct intel_mid_ops - Interface between intel-mid & sub archs
+ * @arch_setup: arch_setup function to re-initialize platform
+ *             structures (x86_init, x86_platform_init)
+ *
+ * This structure can be extended if any new interface is required
+ * between intel-mid & its sub arch files.
+ */
+struct intel_mid_ops {
+	void (*arch_setup)(void);
+};
+
+/* Helper API's for INTEL_MID_OPS_INIT */
+#define DECLARE_INTEL_MID_OPS_INIT(cpuname, cpuid)	\
+				[cpuid] = get_##cpuname##_ops
+
+/* Maximum number of CPU ops */
+#define MAX_CPU_OPS(a) (sizeof(a)/sizeof(void *))
+
+/*
+ * For every new cpu addition, a weak get_<cpuname>_ops() function needs be
+ * declared in arch/x86/platform/intel_mid/intel_mid_weak_decls.h.
+ */
+#define INTEL_MID_OPS_INIT {\
+	DECLARE_INTEL_MID_OPS_INIT(penwell, INTEL_MID_CPU_CHIP_PENWELL), \
+	DECLARE_INTEL_MID_OPS_INIT(cloverview, INTEL_MID_CPU_CHIP_CLOVERVIEW), \
+};
+
 #ifdef CONFIG_X86_INTEL_MID
 
 static inline enum intel_mid_cpu_type intel_mid_identify_cpu(void)
@@ -86,8 +115,21 @@ extern enum intel_mid_timer_options intel_mid_timer_options;
  * Penwell uses spread spectrum clock, so the freq number is not exactly
  * the same as reported by MSR based on SDM.
  */
-#define PENWELL_FSB_FREQ_83SKU         83200
-#define PENWELL_FSB_FREQ_100SKU        99840
+#define FSB_FREQ_83SKU	83200
+#define FSB_FREQ_100SKU	99840
+#define FSB_FREQ_133SKU	133000
+
+#define FSB_FREQ_167SKU	167000
+#define FSB_FREQ_200SKU	200000
+#define FSB_FREQ_267SKU	267000
+#define FSB_FREQ_333SKU	333000
+#define FSB_FREQ_400SKU	400000
+
+/* Bus Select SoC Fuse value */
+#define BSEL_SOC_FUSE_MASK	0x7
+#define BSEL_SOC_FUSE_001	0x1 /* FSB 133MHz */
+#define BSEL_SOC_FUSE_101	0x5 /* FSB 100MHz */
+#define BSEL_SOC_FUSE_111	0x7 /* FSB 83MHz */
 
 #define SFI_MTMR_MAX_NUM 8
 #define SFI_MRTC_MAX	8
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 527d6d5..4095584 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -60,14 +60,27 @@
 
 enum intel_mid_timer_options intel_mid_timer_options;
 
+/* intel_mid_ops to store sub arch ops */
+struct intel_mid_ops *intel_mid_ops;
+/* getter function for sub arch ops*/
+static void *(*get_intel_mid_ops[])(void) = INTEL_MID_OPS_INIT;
 enum intel_mid_cpu_type __intel_mid_cpu_chip;
 EXPORT_SYMBOL_GPL(__intel_mid_cpu_chip);
 
+static void intel_mid_power_off(void)
+{
+};
+
 static void intel_mid_reboot(void)
 {
 	intel_scu_ipc_simple_command(IPCMSG_COLD_BOOT, 0);
 }
 
+static unsigned long __init intel_mid_calibrate_tsc(void)
+{
+	return 0;
+}
+
 static void __init intel_mid_time_init(void)
 {
 	sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr);
@@ -92,13 +105,33 @@ static void __init intel_mid_time_init(void)
 
 static void intel_mid_arch_setup(void)
 {
-	if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x27)
-		__intel_mid_cpu_chip = INTEL_MID_CPU_CHIP_PENWELL;
-	else {
+	if (boot_cpu_data.x86 != 6) {
 		pr_err("Unknown Intel MID CPU (%d:%d), default to Penwell\n",
 			boot_cpu_data.x86, boot_cpu_data.x86_model);
 		__intel_mid_cpu_chip = INTEL_MID_CPU_CHIP_PENWELL;
+		goto out;
+	}
+
+	switch (boot_cpu_data.x86_model) {
+	case 0x35:
+		__intel_mid_cpu_chip = INTEL_MID_CPU_CHIP_CLOVERVIEW;
+		break;
+	case 0x27:
+	default:
+		__intel_mid_cpu_chip = INTEL_MID_CPU_CHIP_PENWELL;
+		break;
 	}
+
+	if (__intel_mid_cpu_chip < MAX_CPU_OPS(get_intel_mid_ops))
+		intel_mid_ops = get_intel_mid_ops[__intel_mid_cpu_chip]();
+	else {
+		intel_mid_ops = get_intel_mid_ops[INTEL_MID_CPU_CHIP_PENWELL]();
+		pr_info("ARCH: Uknown SoC, assuming PENWELL!\n");
+	}
+
+out:
+	if (intel_mid_ops->arch_setup)
+		intel_mid_ops->arch_setup();
 }
 
 /* MID systems don't have i8042 controller */
diff --git a/arch/x86/platform/intel-mid/intel_mid_weak_decls.h b/arch/x86/platform/intel-mid/intel_mid_weak_decls.h
index 519beb7..9ebce044 100644
--- a/arch/x86/platform/intel-mid/intel_mid_weak_decls.h
+++ b/arch/x86/platform/intel-mid/intel_mid_weak_decls.h
@@ -11,5 +11,8 @@
 
 
 /* __attribute__((weak)) makes these declarations overridable */
-extern void intel_mid_power_off(void) __attribute__((weak));
-extern unsigned long __init intel_mid_calibrate_tsc(void) __attribute__((weak));
+/* For every CPU addition a new get_<cpuname>_ops interface needs
+ * to be added.
+ */
+extern void * __cpuinit get_penwell_ops(void) __attribute__((weak));
+extern void * __cpuinit get_cloverview_ops(void) __attribute__((weak));
diff --git a/arch/x86/platform/intel-mid/mfld.c b/arch/x86/platform/intel-mid/mfld.c
index c7ff83c..4f7884e 100644
--- a/arch/x86/platform/intel-mid/mfld.c
+++ b/arch/x86/platform/intel-mid/mfld.c
@@ -15,11 +15,19 @@
 #include <asm/intel-mid.h>
 #include <asm/intel_mid_vrtc.h>
 
-void intel_mid_power_off(void)
+#include "intel_mid_weak_decls.h"
+
+static void penwell_arch_setup(void);
+/* penwell arch ops */
+static struct intel_mid_ops penwell_ops = {
+	.arch_setup = penwell_arch_setup,
+};
+
+static void mfld_power_off(void)
 {
 }
 
-unsigned long __init intel_mid_calibrate_tsc(void)
+static unsigned long __init mfld_calibrate_tsc(void)
 {
 	unsigned long fast_calibrate;
 	u32 lo, hi, ratio, fsb;
@@ -35,9 +43,9 @@ unsigned long __init intel_mid_calibrate_tsc(void)
 	}
 	rdmsr(MSR_FSB_FREQ, lo, hi);
 	if ((lo & 0x7) == 0x7)
-		fsb = PENWELL_FSB_FREQ_83SKU;
+		fsb = FSB_FREQ_83SKU;
 	else
-		fsb = PENWELL_FSB_FREQ_100SKU;
+		fsb = FSB_FREQ_100SKU;
 	fast_calibrate = ratio * fsb;
 	pr_debug("read penwell tsc %lu khz\n", fast_calibrate);
 	lapic_timer_frequency = fsb * 1000 / HZ;
@@ -49,3 +57,19 @@ unsigned long __init intel_mid_calibrate_tsc(void)
 
 	return 0;
 }
+
+static void __init penwell_arch_setup()
+{
+	x86_platform.calibrate_tsc = mfld_calibrate_tsc;
+	pm_power_off = mfld_power_off;
+}
+
+void * __cpuinit get_penwell_ops()
+{
+	return &penwell_ops;
+}
+
+void * __cpuinit get_cloverview_ops()
+{
+	return &penwell_ops;
+}
-- 
cgit v0.10.2


From bc20aa48bbb3068224a1c91f8332971fdb689fad Mon Sep 17 00:00:00 2001
From: David Cohen <david.a.cohen@linux.intel.com>
Date: Mon, 16 Dec 2013 12:07:38 -0800
Subject: x86, intel-mid: Add Merrifield platform support

This code was partially based on Mark Brown's previous work.

Signed-off-by: David Cohen <david.a.cohen@linux.intel.com>
Link: http://lkml.kernel.org/r/1387224459-25746-4-git-send-email-david.a.cohen@linux.intel.com
Signed-off-by: Fei Yang <fei.yang@intel.com>
Cc: Mark F. Brown <mark.f.brown@intel.com>
Cc: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h
index f8a8314..e34e097 100644
--- a/arch/x86/include/asm/intel-mid.h
+++ b/arch/x86/include/asm/intel-mid.h
@@ -52,6 +52,7 @@ enum intel_mid_cpu_type {
 	/* 1 was Moorestown */
 	INTEL_MID_CPU_CHIP_PENWELL = 2,
 	INTEL_MID_CPU_CHIP_CLOVERVIEW,
+	INTEL_MID_CPU_CHIP_TANGIER,
 };
 
 extern enum intel_mid_cpu_type __intel_mid_cpu_chip;
@@ -82,6 +83,7 @@ struct intel_mid_ops {
 #define INTEL_MID_OPS_INIT {\
 	DECLARE_INTEL_MID_OPS_INIT(penwell, INTEL_MID_CPU_CHIP_PENWELL), \
 	DECLARE_INTEL_MID_OPS_INIT(cloverview, INTEL_MID_CPU_CHIP_CLOVERVIEW), \
+	DECLARE_INTEL_MID_OPS_INIT(tangier, INTEL_MID_CPU_CHIP_TANGIER) \
 };
 
 #ifdef CONFIG_X86_INTEL_MID
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 51384ca..84b9d67 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -31,6 +31,7 @@
 #include <asm/pci_x86.h>
 #include <asm/hw_irq.h>
 #include <asm/io_apic.h>
+#include <asm/intel-mid.h>
 
 #define PCIE_CAP_OFFSET	0x100
 
@@ -219,7 +220,10 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 	irq_attr.ioapic = mp_find_ioapic(dev->irq);
 	irq_attr.ioapic_pin = dev->irq;
 	irq_attr.trigger = 1; /* level */
-	irq_attr.polarity = 1; /* active low */
+	if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER)
+		irq_attr.polarity = 0; /* active high */
+	else
+		irq_attr.polarity = 1; /* active low */
 	io_apic_set_pci_routing(&dev->dev, dev->irq, &irq_attr);
 
 	return 0;
diff --git a/arch/x86/platform/intel-mid/Makefile b/arch/x86/platform/intel-mid/Makefile
index 78a14ba..0a8ee70 100644
--- a/arch/x86/platform/intel-mid/Makefile
+++ b/arch/x86/platform/intel-mid/Makefile
@@ -1,4 +1,4 @@
-obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o intel_mid_vrtc.o mfld.o
+obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o intel_mid_vrtc.o mfld.o mrfl.o
 obj-$(CONFIG_EARLY_PRINTK_INTEL_MID) += early_printk_intel_mid.o
 
 # SFI specific code
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 4095584..1bbedc4 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -116,6 +116,10 @@ static void intel_mid_arch_setup(void)
 	case 0x35:
 		__intel_mid_cpu_chip = INTEL_MID_CPU_CHIP_CLOVERVIEW;
 		break;
+	case 0x3C:
+	case 0x4A:
+		__intel_mid_cpu_chip = INTEL_MID_CPU_CHIP_TANGIER;
+		break;
 	case 0x27:
 	default:
 		__intel_mid_cpu_chip = INTEL_MID_CPU_CHIP_PENWELL;
diff --git a/arch/x86/platform/intel-mid/intel_mid_weak_decls.h b/arch/x86/platform/intel-mid/intel_mid_weak_decls.h
index 9ebce044..a537ffc 100644
--- a/arch/x86/platform/intel-mid/intel_mid_weak_decls.h
+++ b/arch/x86/platform/intel-mid/intel_mid_weak_decls.h
@@ -16,3 +16,4 @@
  */
 extern void * __cpuinit get_penwell_ops(void) __attribute__((weak));
 extern void * __cpuinit get_cloverview_ops(void) __attribute__((weak));
+extern void * __init get_tangier_ops(void) __attribute__((weak));
diff --git a/arch/x86/platform/intel-mid/mrfl.c b/arch/x86/platform/intel-mid/mrfl.c
new file mode 100644
index 0000000..09d1015
--- /dev/null
+++ b/arch/x86/platform/intel-mid/mrfl.c
@@ -0,0 +1,103 @@
+/*
+ * mrfl.c: Intel Merrifield platform specific setup code
+ *
+ * (C) Copyright 2013 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/init.h>
+
+#include <asm/apic.h>
+#include <asm/intel-mid.h>
+
+#include "intel_mid_weak_decls.h"
+
+static unsigned long __init tangier_calibrate_tsc(void)
+{
+	unsigned long fast_calibrate;
+	u32 lo, hi, ratio, fsb, bus_freq;
+
+	/* *********************** */
+	/* Compute TSC:Ratio * FSB */
+	/* *********************** */
+
+	/* Compute Ratio */
+	rdmsr(MSR_PLATFORM_INFO, lo, hi);
+	pr_debug("IA32 PLATFORM_INFO is 0x%x : %x\n", hi, lo);
+
+	ratio = (lo >> 8) & 0xFF;
+	pr_debug("ratio is %d\n", ratio);
+	if (!ratio) {
+		pr_err("Read a zero ratio, force tsc ratio to 4 ...\n");
+		ratio = 4;
+	}
+
+	/* Compute FSB */
+	rdmsr(MSR_FSB_FREQ, lo, hi);
+	pr_debug("Actual FSB frequency detected by SOC 0x%x : %x\n",
+			hi, lo);
+
+	bus_freq = lo & 0x7;
+	pr_debug("bus_freq = 0x%x\n", bus_freq);
+
+	if (bus_freq == 0)
+		fsb = FSB_FREQ_100SKU;
+	else if (bus_freq == 1)
+		fsb = FSB_FREQ_100SKU;
+	else if (bus_freq == 2)
+		fsb = FSB_FREQ_133SKU;
+	else if (bus_freq == 3)
+		fsb = FSB_FREQ_167SKU;
+	else if (bus_freq == 4)
+		fsb = FSB_FREQ_83SKU;
+	else if (bus_freq == 5)
+		fsb = FSB_FREQ_400SKU;
+	else if (bus_freq == 6)
+		fsb = FSB_FREQ_267SKU;
+	else if (bus_freq == 7)
+		fsb = FSB_FREQ_333SKU;
+	else {
+		BUG();
+		pr_err("Invalid bus_freq! Setting to minimal value!\n");
+		fsb = FSB_FREQ_100SKU;
+	}
+
+	/* TSC = FSB Freq * Resolved HFM Ratio */
+	fast_calibrate = ratio * fsb;
+	pr_debug("calculate tangier tsc %lu KHz\n", fast_calibrate);
+
+	/* ************************************ */
+	/* Calculate Local APIC Timer Frequency */
+	/* ************************************ */
+	lapic_timer_frequency = (fsb * 1000) / HZ;
+
+	pr_debug("Setting lapic_timer_frequency = %d\n",
+			lapic_timer_frequency);
+
+	/* mark tsc clocksource as reliable */
+	set_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC_RELIABLE);
+
+	if (fast_calibrate)
+		return fast_calibrate;
+
+	return 0;
+}
+
+static void __init tangier_arch_setup(void)
+{
+	x86_platform.calibrate_tsc = tangier_calibrate_tsc;
+}
+
+/* tangier arch ops */
+static struct intel_mid_ops tangier_ops = {
+	.arch_setup = tangier_arch_setup,
+};
+
+void * __cpuinit get_tangier_ops()
+{
+	return &tangier_ops;
+}
diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c
index c84c1ca..80a5228 100644
--- a/arch/x86/platform/intel-mid/sfi.c
+++ b/arch/x86/platform/intel-mid/sfi.c
@@ -443,13 +443,35 @@ static int __init sfi_parse_devs(struct sfi_table_header *table)
 			 * so we have to enable them one by one here
 			 */
 			ioapic = mp_find_ioapic(irq);
-			irq_attr.ioapic = ioapic;
-			irq_attr.ioapic_pin = irq;
-			irq_attr.trigger = 1;
-			irq_attr.polarity = 1;
-			io_apic_set_pci_routing(NULL, irq, &irq_attr);
-		} else
+			if (ioapic >= 0) {
+				irq_attr.ioapic = ioapic;
+				irq_attr.ioapic_pin = irq;
+				irq_attr.trigger = 1;
+				if (intel_mid_identify_cpu() ==
+						INTEL_MID_CPU_CHIP_TANGIER) {
+					if (!strncmp(pentry->name,
+							"r69001-ts-i2c", 13))
+						/* active low */
+						irq_attr.polarity = 1;
+					else if (!strncmp(pentry->name,
+							"synaptics_3202", 14))
+						/* active low */
+						irq_attr.polarity = 1;
+					else if (irq == 41)
+						/* fast_int_1 */
+						irq_attr.polarity = 1;
+					else
+						/* active high */
+						irq_attr.polarity = 0;
+				} else {
+					/* PNW and CLV go with active low */
+					irq_attr.polarity = 1;
+				}
+				io_apic_set_pci_routing(NULL, irq, &irq_attr);
+			}
+		} else {
 			irq = 0; /* No irq */
+		}
 
 		dev = get_device_id(pentry->type, pentry->name);
 
-- 
cgit v0.10.2


From 4cb9b00f42e07830310319a07e6c91413ee8153e Mon Sep 17 00:00:00 2001
From: David Cohen <david.a.cohen@linux.intel.com>
Date: Mon, 16 Dec 2013 17:37:26 -0800
Subject: x86, intel-mid: Remove deprecated X86_MDFLD and X86_WANT_INTEL_MID
 configs

We want to support all Intel MID (Mobile Internet Device) platforms
with a single config selection. This patch removes deprecated
CONFIG_X86_MDFLD and X86_WANT_INTEL_MID options in favor of having
CONFIG_X86_INTEL_MID only.

Signed-off-by: David Cohen <david.a.cohen@linux.intel.com>
Link: http://lkml.kernel.org/r/1387244246-20714-1-git-send-email-david.a.cohen@linux.intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0952ecd..edcf80e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -438,42 +438,26 @@ config X86_INTEL_CE
 	  This option compiles in support for the CE4100 SOC for settop
 	  boxes and media devices.
 
-config X86_WANT_INTEL_MID
+config X86_INTEL_MID
 	bool "Intel MID platform support"
 	depends on X86_32
 	depends on X86_EXTENDED_PLATFORM
-	---help---
-	  Select to build a kernel capable of supporting Intel MID platform
-	  systems which do not have the PCI legacy interfaces (Moorestown,
-	  Medfield). If you are building for a PC class system say N here.
-
-if X86_WANT_INTEL_MID
-
-config X86_INTEL_MID
-	bool
-
-config X86_MDFLD
-       bool "Medfield MID platform"
 	depends on PCI
 	depends on PCI_GOANY
 	depends on X86_IO_APIC
-	select X86_INTEL_MID
 	select SFI
+	select I2C
 	select DW_APB_TIMER
 	select APB_TIMER
-	select I2C
-	select SPI
 	select INTEL_SCU_IPC
-	select X86_PLATFORM_DEVICES
 	select MFD_INTEL_MSIC
 	---help---
-	  Medfield is Intel's Low Power Intel Architecture (LPIA) based Moblin
-	  Internet Device(MID) platform. 
-	  Unlike standard x86 PCs, Medfield does not have many legacy devices
-	  nor standard legacy replacement devices/features. e.g. Medfield does
-	  not contain i8259, i8254, HPET, legacy BIOS, most of the io ports.
+	  Select to build a kernel capable of supporting Intel MID (Mobile
+	  Internet Device) platform systems which do not have the PCI legacy
+	  interfaces. If you are building for a PC class system say N here.
 
-endif
+	  Intel MID platforms are based on an Intel processor and chipset which
+	  consume less power than most of the x86 derivatives.
 
 config X86_INTEL_LPSS
 	bool "Intel Low Power Subsystem Support"
-- 
cgit v0.10.2


From 1df0cbd509bc21b0c331358c1f9d9a6fc94bada8 Mon Sep 17 00:00:00 2001
From: Marek Lindner <mareklindner@neomailbox.ch>
Date: Wed, 15 Jan 2014 20:31:18 +0800
Subject: batman-adv: fix batman-adv header overhead calculation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Batman-adv prepends a full ethernet header in addition to its own
header. This has to be reflected in the MTU calculation, especially
since the value is used to set dev->hard_header_len.

Introduced by 411d6ed93a5d0601980d3e5ce75de07c98e3a7de
("batman-adv: consider network coding overhead when calculating required mtu")

Reported-by: cmsv <cmsv@wirelesspt.net>
Reported-by: Martin Hundebøll <martin@hundeboll.net>
Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch>
Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>

diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 1511f64..faba0f6 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -277,7 +277,7 @@ int batadv_max_header_len(void)
 			   sizeof(struct batadv_coded_packet));
 #endif
 
-	return header_len;
+	return header_len + ETH_HLEN;
 }
 
 /**
-- 
cgit v0.10.2


From a926592f5e4e900f3fa903298c4619a131e60963 Mon Sep 17 00:00:00 2001
From: Richard Weinberger <richard@nod.at>
Date: Tue, 14 Jan 2014 22:46:36 +0100
Subject: net,via-rhine: Fix tx_timeout handling

rhine_reset_task() misses to disable the tx scheduler upon reset,
this can lead to a crash if work is still scheduled while we're resetting
the tx queue.

Fixes:
[   93.591707] BUG: unable to handle kernel NULL pointer dereference at 0000004c
[   93.595514] IP: [<c119d10d>] rhine_napipoll+0x491/0x6

Signed-off-by: Richard Weinberger <richard@nod.at>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index cce6c4b..ef312bc 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -1618,6 +1618,7 @@ static void rhine_reset_task(struct work_struct *work)
 		goto out_unlock;
 
 	napi_disable(&rp->napi);
+	netif_tx_disable(dev);
 	spin_lock_bh(&rp->lock);
 
 	/* clear all descriptors */
-- 
cgit v0.10.2


From d9aee591b0f06bd44cd577b757d3f267bc35fe4d Mon Sep 17 00:00:00 2001
From: Yuval Mintz <yuvalmin@broadcom.com>
Date: Wed, 15 Jan 2014 12:05:30 +0200
Subject: bnx2x: Don't release PCI bars on shutdown

The bnx2x driver in its pci shutdown() callback releases its pci bars (in the
same manner it does during its pci remove() callback).
During a system reboot while VFs are enabled, its possible for the VF's remove
to be called (as a result of pci_disable_sriov()) after its shutdown callback
has already finished running; This will cause a paging request fault as the VF
tries to access the pci bar which it has previously released, crashing the
system.

This patch further differentiates the shutdown and remove callbacks, preventing the
pci release procedures from being called during shutdown.

Signed-off-by: Yuval Mintz <yuvalmin@broadcom.com>
Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 8b3107b..0067b97 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -12942,25 +12942,26 @@ static void __bnx2x_remove(struct pci_dev *pdev,
 		pci_set_power_state(pdev, PCI_D3hot);
 	}
 
-	if (bp->regview)
-		iounmap(bp->regview);
+	if (remove_netdev) {
+		if (bp->regview)
+			iounmap(bp->regview);
 
-	/* for vf doorbells are part of the regview and were unmapped along with
-	 * it. FW is only loaded by PF.
-	 */
-	if (IS_PF(bp)) {
-		if (bp->doorbells)
-			iounmap(bp->doorbells);
+		/* For vfs, doorbells are part of the regview and were unmapped
+		 * along with it. FW is only loaded by PF.
+		 */
+		if (IS_PF(bp)) {
+			if (bp->doorbells)
+				iounmap(bp->doorbells);
 
-		bnx2x_release_firmware(bp);
-	}
-	bnx2x_free_mem_bp(bp);
+			bnx2x_release_firmware(bp);
+		}
+		bnx2x_free_mem_bp(bp);
 
-	if (remove_netdev)
 		free_netdev(dev);
 
-	if (atomic_read(&pdev->enable_cnt) == 1)
-		pci_release_regions(pdev);
+		if (atomic_read(&pdev->enable_cnt) == 1)
+			pci_release_regions(pdev);
+	}
 
 	pci_disable_device(pdev);
 }
-- 
cgit v0.10.2


From ba42fad0964a41f0830e80c1b6be49c1e6bfcc01 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <ivecera@redhat.com>
Date: Wed, 15 Jan 2014 11:11:34 +0100
Subject: be2net: add dma_mapping_error() check for dma_map_page()

The driver does not check value returned by dma_map_page. The patch
fixes this.

v2: Removed the bugfix for non-bug ;-) (thanks Sathya)

Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Acked-by: Sathya Perla <Sathya.perla@emulex.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index bf40fda..a37039d 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1776,6 +1776,7 @@ static void be_post_rx_frags(struct be_rx_obj *rxo, gfp_t gfp)
 	struct be_rx_page_info *page_info = NULL, *prev_page_info = NULL;
 	struct be_queue_info *rxq = &rxo->q;
 	struct page *pagep = NULL;
+	struct device *dev = &adapter->pdev->dev;
 	struct be_eth_rx_d *rxd;
 	u64 page_dmaaddr = 0, frag_dmaaddr;
 	u32 posted, page_offset = 0;
@@ -1788,9 +1789,15 @@ static void be_post_rx_frags(struct be_rx_obj *rxo, gfp_t gfp)
 				rx_stats(rxo)->rx_post_fail++;
 				break;
 			}
-			page_dmaaddr = dma_map_page(&adapter->pdev->dev, pagep,
-						    0, adapter->big_page_size,
+			page_dmaaddr = dma_map_page(dev, pagep, 0,
+						    adapter->big_page_size,
 						    DMA_FROM_DEVICE);
+			if (dma_mapping_error(dev, page_dmaaddr)) {
+				put_page(pagep);
+				pagep = NULL;
+				rx_stats(rxo)->rx_post_fail++;
+				break;
+			}
 			page_info->page_offset = 0;
 		} else {
 			get_page(pagep);
-- 
cgit v0.10.2


From aee636c4809fa54848ff07a899b326eb1f9987a2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 15 Jan 2014 06:50:07 -0800
Subject: bpf: do not use reciprocal divide

At first Jakub Zawadzki noticed that some divisions by reciprocal_divide
were not correct. (off by one in some cases)
http://www.wireshark.org/~darkjames/reciprocal-buggy.c

He could also show this with BPF:
http://www.wireshark.org/~darkjames/set-and-dump-filter-k-bug.c

The reciprocal divide in linux kernel is not generic enough,
lets remove its use in BPF, as it is not worth the pain with
current cpus.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jakub Zawadzki <darkjames-ws@darkjames.pl>
Cc: Mircea Gherzan <mgherzan@gmail.com>
Cc: Daniel Borkmann <dxchgb@gmail.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Cc: Matt Evans <matt@ozlabs.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 9ed155a..271b5e9 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -641,10 +641,10 @@ load_ind:
 			emit(ARM_MUL(r_A, r_A, r_X), ctx);
 			break;
 		case BPF_S_ALU_DIV_K:
-			/* current k == reciprocal_value(userspace k) */
+			if (k == 1)
+				break;
 			emit_mov_i(r_scratch, k, ctx);
-			/* A = top 32 bits of the product */
-			emit(ARM_UMULL(r_scratch, r_A, r_A, r_scratch), ctx);
+			emit_udiv(r_A, r_A, r_scratch, ctx);
 			break;
 		case BPF_S_ALU_DIV_X:
 			update_on_xread(ctx);
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index ac3c2a1..555034f 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -223,10 +223,11 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 			}
 			PPC_DIVWU(r_A, r_A, r_X);
 			break;
-		case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */
+		case BPF_S_ALU_DIV_K: /* A /= K */
+			if (K == 1)
+				break;
 			PPC_LI32(r_scratch1, K);
-			/* Top 32 bits of 64bit result -> A */
-			PPC_MULHWU(r_A, r_A, r_scratch1);
+			PPC_DIVWU(r_A, r_A, r_scratch1);
 			break;
 		case BPF_S_ALU_AND_X:
 			ctx->seen |= SEEN_XREG;
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 16871da..fc0fa77 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -371,11 +371,13 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		/* dr %r4,%r12 */
 		EMIT2(0x1d4c);
 		break;
-	case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K) */
-		/* m %r4,<d(K)>(%r13) */
-		EMIT4_DISP(0x5c40d000, EMIT_CONST(K));
-		/* lr %r5,%r4 */
-		EMIT2(0x1854);
+	case BPF_S_ALU_DIV_K: /* A /= K */
+		if (K == 1)
+			break;
+		/* lhi %r4,0 */
+		EMIT4(0xa7480000);
+		/* d %r4,<d(K)>(%r13) */
+		EMIT4_DISP(0x5d40d000, EMIT_CONST(K));
 		break;
 	case BPF_S_ALU_MOD_X: /* A %= X */
 		jit->seen |= SEEN_XREG | SEEN_RET0;
@@ -391,6 +393,11 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		EMIT2(0x1854);
 		break;
 	case BPF_S_ALU_MOD_K: /* A %= K */
+		if (K == 1) {
+			/* lhi %r5,0 */
+			EMIT4(0xa7580000);
+			break;
+		}
 		/* lhi %r4,0 */
 		EMIT4(0xa7480000);
 		/* d %r4,<d(K)>(%r13) */
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index 218b6b2..01fe994 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -497,9 +497,20 @@ void bpf_jit_compile(struct sk_filter *fp)
 			case BPF_S_ALU_MUL_K:	/* A *= K */
 				emit_alu_K(MUL, K);
 				break;
-			case BPF_S_ALU_DIV_K:	/* A /= K */
-				emit_alu_K(MUL, K);
-				emit_read_y(r_A);
+			case BPF_S_ALU_DIV_K:	/* A /= K with K != 0*/
+				if (K == 1)
+					break;
+				emit_write_y(G0);
+#ifdef CONFIG_SPARC32
+				/* The Sparc v8 architecture requires
+				 * three instructions between a %y
+				 * register write and the first use.
+				 */
+				emit_nop();
+				emit_nop();
+				emit_nop();
+#endif
+				emit_alu_K(DIV, K);
 				break;
 			case BPF_S_ALU_DIV_X:	/* A /= X; */
 				emit_cmpi(r_X, 0);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 26328e8..4ed75dd 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -359,15 +359,21 @@ void bpf_jit_compile(struct sk_filter *fp)
 				EMIT2(0x89, 0xd0);	/* mov %edx,%eax */
 				break;
 			case BPF_S_ALU_MOD_K: /* A %= K; */
+				if (K == 1) {
+					CLEAR_A();
+					break;
+				}
 				EMIT2(0x31, 0xd2);	/* xor %edx,%edx */
 				EMIT1(0xb9);EMIT(K, 4);	/* mov imm32,%ecx */
 				EMIT2(0xf7, 0xf1);	/* div %ecx */
 				EMIT2(0x89, 0xd0);	/* mov %edx,%eax */
 				break;
-			case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */
-				EMIT3(0x48, 0x69, 0xc0); /* imul imm32,%rax,%rax */
-				EMIT(K, 4);
-				EMIT4(0x48, 0xc1, 0xe8, 0x20); /* shr $0x20,%rax */
+			case BPF_S_ALU_DIV_K: /* A /= K */
+				if (K == 1)
+					break;
+				EMIT2(0x31, 0xd2);	/* xor %edx,%edx */
+				EMIT1(0xb9);EMIT(K, 4);	/* mov imm32,%ecx */
+				EMIT2(0xf7, 0xf1);	/* div %ecx */
 				break;
 			case BPF_S_ALU_AND_X:
 				seen |= SEEN_XREG;
diff --git a/net/core/filter.c b/net/core/filter.c
index 01b7808..ad30d62 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -36,7 +36,6 @@
 #include <asm/uaccess.h>
 #include <asm/unaligned.h>
 #include <linux/filter.h>
-#include <linux/reciprocal_div.h>
 #include <linux/ratelimit.h>
 #include <linux/seccomp.h>
 #include <linux/if_vlan.h>
@@ -166,7 +165,7 @@ unsigned int sk_run_filter(const struct sk_buff *skb,
 			A /= X;
 			continue;
 		case BPF_S_ALU_DIV_K:
-			A = reciprocal_divide(A, K);
+			A /= K;
 			continue;
 		case BPF_S_ALU_MOD_X:
 			if (X == 0)
@@ -553,11 +552,6 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen)
 		/* Some instructions need special checks */
 		switch (code) {
 		case BPF_S_ALU_DIV_K:
-			/* check for division by zero */
-			if (ftest->k == 0)
-				return -EINVAL;
-			ftest->k = reciprocal_value(ftest->k);
-			break;
 		case BPF_S_ALU_MOD_K:
 			/* check for division by zero */
 			if (ftest->k == 0)
@@ -853,27 +847,7 @@ void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to)
 	to->code = decodes[code];
 	to->jt = filt->jt;
 	to->jf = filt->jf;
-
-	if (code == BPF_S_ALU_DIV_K) {
-		/*
-		 * When loaded this rule user gave us X, which was
-		 * translated into R = r(X). Now we calculate the
-		 * RR = r(R) and report it back. If next time this
-		 * value is loaded and RRR = r(RR) is calculated
-		 * then the R == RRR will be true.
-		 *
-		 * One exception. X == 1 translates into R == 0 and
-		 * we can't calculate RR out of it with r().
-		 */
-
-		if (filt->k == 0)
-			to->k = 1;
-		else
-			to->k = reciprocal_value(filt->k);
-
-		BUG_ON(reciprocal_value(to->k) != filt->k);
-	} else
-		to->k = filt->k;
+	to->k = filt->k;
 }
 
 int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len)
-- 
cgit v0.10.2


From da6139e49c7cb0f4251265cb5243b8d220adb48d Mon Sep 17 00:00:00 2001
From: Prarit Bhargava <prarit@redhat.com>
Date: Mon, 13 Jan 2014 06:51:01 -0500
Subject: x86: Add check for number of available vectors before CPU down

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=64791

When a cpu is downed on a system, the irqs on the cpu are assigned to
other cpus.  It is possible, however, that when a cpu is downed there
aren't enough free vectors on the remaining cpus to account for the
vectors from the cpu that is being downed.

This results in an interesting "overflow" condition where irqs are
"assigned" to a CPU but are not handled.

For example, when downing cpus on a 1-64 logical processor system:

<snip>
[  232.021745] smpboot: CPU 61 is now offline
[  238.480275] smpboot: CPU 62 is now offline
[  245.991080] ------------[ cut here ]------------
[  245.996270] WARNING: CPU: 0 PID: 0 at net/sched/sch_generic.c:264 dev_watchdog+0x246/0x250()
[  246.005688] NETDEV WATCHDOG: p786p1 (ixgbe): transmit queue 0 timed out
[  246.013070] Modules linked in: lockd sunrpc iTCO_wdt iTCO_vendor_support sb_edac ixgbe microcode e1000e pcspkr joydev edac_core lpc_ich ioatdma ptp mdio mfd_core i2c_i801 dca pps_core i2c_core wmi acpi_cpufreq isci libsas scsi_transport_sas
[  246.037633] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 3.12.0+ #14
[  246.044451] Hardware name: Intel Corporation S4600LH ........../SVRBD-ROW_T, BIOS SE5C600.86B.01.08.0003.022620131521 02/26/2013
[  246.057371]  0000000000000009 ffff88081fa03d40 ffffffff8164fbf6 ffff88081fa0ee48
[  246.065728]  ffff88081fa03d90 ffff88081fa03d80 ffffffff81054ecc ffff88081fa13040
[  246.074073]  0000000000000000 ffff88200cce0000 0000000000000040 0000000000000000
[  246.082430] Call Trace:
[  246.085174]  <IRQ>  [<ffffffff8164fbf6>] dump_stack+0x46/0x58
[  246.091633]  [<ffffffff81054ecc>] warn_slowpath_common+0x8c/0xc0
[  246.098352]  [<ffffffff81054fb6>] warn_slowpath_fmt+0x46/0x50
[  246.104786]  [<ffffffff815710d6>] dev_watchdog+0x246/0x250
[  246.110923]  [<ffffffff81570e90>] ? dev_deactivate_queue.constprop.31+0x80/0x80
[  246.119097]  [<ffffffff8106092a>] call_timer_fn+0x3a/0x110
[  246.125224]  [<ffffffff8106280f>] ? update_process_times+0x6f/0x80
[  246.132137]  [<ffffffff81570e90>] ? dev_deactivate_queue.constprop.31+0x80/0x80
[  246.140308]  [<ffffffff81061db0>] run_timer_softirq+0x1f0/0x2a0
[  246.146933]  [<ffffffff81059a80>] __do_softirq+0xe0/0x220
[  246.152976]  [<ffffffff8165fedc>] call_softirq+0x1c/0x30
[  246.158920]  [<ffffffff810045f5>] do_softirq+0x55/0x90
[  246.164670]  [<ffffffff81059d35>] irq_exit+0xa5/0xb0
[  246.170227]  [<ffffffff8166062a>] smp_apic_timer_interrupt+0x4a/0x60
[  246.177324]  [<ffffffff8165f40a>] apic_timer_interrupt+0x6a/0x70
[  246.184041]  <EOI>  [<ffffffff81505a1b>] ? cpuidle_enter_state+0x5b/0xe0
[  246.191559]  [<ffffffff81505a17>] ? cpuidle_enter_state+0x57/0xe0
[  246.198374]  [<ffffffff81505b5d>] cpuidle_idle_call+0xbd/0x200
[  246.204900]  [<ffffffff8100b7ae>] arch_cpu_idle+0xe/0x30
[  246.210846]  [<ffffffff810a47b0>] cpu_startup_entry+0xd0/0x250
[  246.217371]  [<ffffffff81646b47>] rest_init+0x77/0x80
[  246.223028]  [<ffffffff81d09e8e>] start_kernel+0x3ee/0x3fb
[  246.229165]  [<ffffffff81d0989f>] ? repair_env_string+0x5e/0x5e
[  246.235787]  [<ffffffff81d095a5>] x86_64_start_reservations+0x2a/0x2c
[  246.242990]  [<ffffffff81d0969f>] x86_64_start_kernel+0xf8/0xfc
[  246.249610] ---[ end trace fb74fdef54d79039 ]---
[  246.254807] ixgbe 0000:c2:00.0 p786p1: initiating reset due to tx timeout
[  246.262489] ixgbe 0000:c2:00.0 p786p1: Reset adapter
Last login: Mon Nov 11 08:35:14 from 10.18.17.119
[root@(none) ~]# [  246.792676] ixgbe 0000:c2:00.0 p786p1: detected SFP+: 5
[  249.231598] ixgbe 0000:c2:00.0 p786p1: NIC Link is Up 10 Gbps, Flow Control: RX/TX
[  246.792676] ixgbe 0000:c2:00.0 p786p1: detected SFP+: 5
[  249.231598] ixgbe 0000:c2:00.0 p786p1: NIC Link is Up 10 Gbps, Flow Control: RX/TX

(last lines keep repeating.  ixgbe driver is dead until module reload.)

If the downed cpu has more vectors than are free on the remaining cpus on the
system, it is possible that some vectors are "orphaned" even though they are
assigned to a cpu.  In this case, since the ixgbe driver had a watchdog, the
watchdog fired and notified that something was wrong.

This patch adds a function, check_vectors(), to compare the number of vectors
on the CPU going down and compares it to the number of vectors available on
the system.  If there aren't enough vectors for the CPU to go down, an
error is returned and propogated back to userspace.

v2: Do not need to look at percpu irqs
v3: Need to check affinity to prevent counting of MSIs in IOAPIC Lowest
    Priority Mode
v4: Additional changes suggested by Gong Chen.
v5/v6/v7/v8: Updated comment text

Signed-off-by: Prarit Bhargava <prarit@redhat.com>
Link: http://lkml.kernel.org/r/1389613861-3853-1-git-send-email-prarit@redhat.com
Reviewed-by: Gong Chen <gong.chen@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Seiji Aguchi <seiji.aguchi@hds.com>
Cc: Yang Zhang <yang.z.zhang@Intel.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Janet Morgan <janet.morgan@intel.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Ruiv Wang <ruiv.wang@gmail.com>
Cc: Gong Chen <gong.chen@linux.intel.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: <stable@vger.kernel.org>

diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 0ea10f27..cb6cfcd 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -25,6 +25,7 @@ extern void irq_ctx_init(int cpu);
 
 #ifdef CONFIG_HOTPLUG_CPU
 #include <linux/cpumask.h>
+extern int check_irq_vectors_for_cpu_disable(void);
 extern void fixup_irqs(void);
 extern void irq_force_complete_move(int);
 #endif
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 22d0687..4207e8d 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -262,6 +262,76 @@ __visible void smp_trace_x86_platform_ipi(struct pt_regs *regs)
 EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq);
 
 #ifdef CONFIG_HOTPLUG_CPU
+/*
+ * This cpu is going to be removed and its vectors migrated to the remaining
+ * online cpus.  Check to see if there are enough vectors in the remaining cpus.
+ * This function is protected by stop_machine().
+ */
+int check_irq_vectors_for_cpu_disable(void)
+{
+	int irq, cpu;
+	unsigned int this_cpu, vector, this_count, count;
+	struct irq_desc *desc;
+	struct irq_data *data;
+	struct cpumask affinity_new, online_new;
+
+	this_cpu = smp_processor_id();
+	cpumask_copy(&online_new, cpu_online_mask);
+	cpu_clear(this_cpu, online_new);
+
+	this_count = 0;
+	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
+		irq = __this_cpu_read(vector_irq[vector]);
+		if (irq >= 0) {
+			desc = irq_to_desc(irq);
+			data = irq_desc_get_irq_data(desc);
+			cpumask_copy(&affinity_new, data->affinity);
+			cpu_clear(this_cpu, affinity_new);
+
+			/* Do not count inactive or per-cpu irqs. */
+			if (!irq_has_action(irq) || irqd_is_per_cpu(data))
+				continue;
+
+			/*
+			 * A single irq may be mapped to multiple
+			 * cpu's vector_irq[] (for example IOAPIC cluster
+			 * mode).  In this case we have two
+			 * possibilities:
+			 *
+			 * 1) the resulting affinity mask is empty; that is
+			 * this the down'd cpu is the last cpu in the irq's
+			 * affinity mask, or
+			 *
+			 * 2) the resulting affinity mask is no longer
+			 * a subset of the online cpus but the affinity
+			 * mask is not zero; that is the down'd cpu is the
+			 * last online cpu in a user set affinity mask.
+			 */
+			if (cpumask_empty(&affinity_new) ||
+			    !cpumask_subset(&affinity_new, &online_new))
+				this_count++;
+		}
+	}
+
+	count = 0;
+	for_each_online_cpu(cpu) {
+		if (cpu == this_cpu)
+			continue;
+		for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
+		     vector++) {
+			if (per_cpu(vector_irq, cpu)[vector] < 0)
+				count++;
+		}
+	}
+
+	if (count < this_count) {
+		pr_warn("CPU %d disable failed: CPU has %u vectors assigned and there are only %u available.\n",
+			this_cpu, this_count, count);
+		return -ERANGE;
+	}
+	return 0;
+}
+
 /* A cpu has been removed from cpu_online_mask.  Reset irq affinities. */
 void fixup_irqs(void)
 {
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 85dc05a..391ea52 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1312,6 +1312,12 @@ void cpu_disable_common(void)
 
 int native_cpu_disable(void)
 {
+	int ret;
+
+	ret = check_irq_vectors_for_cpu_disable();
+	if (ret)
+		return ret;
+
 	clear_local_APIC();
 
 	cpu_disable_common();
-- 
cgit v0.10.2


From 7da7c1561366ba8adb7275464ab44e84e1faa7e0 Mon Sep 17 00:00:00 2001
From: Bin Gao <bin.gao@intel.com>
Date: Mon, 21 Oct 2013 09:16:33 -0700
Subject: x86, tsc: Add static (MSR) TSC calibration on Intel Atom SoCs

On SoCs that have the calibration MSRs available, either there is no
PIT, HPET or PMTIMER to calibrate against, or the PIT/HPET/PMTIMER is
driven from the same clock as the TSC, so calibration is redundant and
just slows down the boot.

TSC rate is caculated by this formula:
<maximum core-clock to bus-clock ratio> * <maximum resolved frequency>
The ratio and the resolved frequency ID can be obtained from MSR.
See Intel 64 and IA-32 System Programming Guid section 16.12 and 30.11.5
for details.

Signed-off-by: Bin Gao <bin.gao@intel.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Link: http://lkml.kernel.org/n/tip-rgm7xmg7k6qnjlw3ynkcjsmh@git.kernel.org

diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 235be70..57ae63c 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -65,4 +65,7 @@ extern int notsc_setup(char *);
 extern void tsc_save_sched_clock_state(void);
 extern void tsc_restore_sched_clock_state(void);
 
+/* MSR based TSC calibration for Intel Atom SoC platforms */
+int try_msr_calibrate_tsc(unsigned long *fast_calibrate);
+
 #endif /* _ASM_X86_TSC_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index dbe9bd6..6dbbb1e 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -32,7 +32,7 @@ obj-$(CONFIG_X86_64)	+= vsyscall_emu_64.o
 obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o hw_breakpoint.o
-obj-y			+= tsc.o io_delay.o rtc.o
+obj-y			+= tsc.o tsc_msr.o io_delay.o rtc.o
 obj-y			+= pci-iommu_table.o
 obj-y			+= resource.o
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 930e5d4..e574716 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -419,6 +419,16 @@ unsigned long native_calibrate_tsc(void)
 	unsigned long flags, latch, ms, fast_calibrate;
 	int hpet = is_hpet_enabled(), i, loopmin;
 
+	/* Calibrate TSC using MSR for Intel Atom SoCs */
+	local_irq_save(flags);
+	i = try_msr_calibrate_tsc(&fast_calibrate);
+	local_irq_restore(flags);
+	if (i >= 0) {
+		if (i == 0)
+			pr_warn("Fast TSC calibration using MSR failed\n");
+		return fast_calibrate;
+	}
+
 	local_irq_save(flags);
 	fast_calibrate = quick_pit_calibrate();
 	local_irq_restore(flags);
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
new file mode 100644
index 0000000..c502772
--- /dev/null
+++ b/arch/x86/kernel/tsc_msr.c
@@ -0,0 +1,125 @@
+/*
+ * tsc_msr.c - MSR based TSC calibration on Intel Atom SoC platforms.
+ *
+ * TSC in Intel Atom SoC runs at a constant rate which can be figured
+ * by this formula:
+ * <maximum core-clock to bus-clock ratio> * <maximum resolved frequency>
+ * See Intel 64 and IA-32 System Programming Guid section 16.12 and 30.11.5
+ * for details.
+ * Especially some Intel Atom SoCs don't have PIT(i8254) or HPET, so MSR
+ * based calibration is the only option.
+ *
+ *
+ * Copyright (C) 2013 Intel Corporation
+ * Author: Bin Gao <bin.gao@intel.com>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/kernel.h>
+#include <asm/processor.h>
+#include <asm/setup.h>
+#include <asm/apic.h>
+#include <asm/param.h>
+
+/* CPU reference clock frequency: in KHz */
+#define FREQ_83		83200
+#define FREQ_100	99840
+#define FREQ_133	133200
+#define FREQ_166	166400
+
+#define MAX_NUM_FREQS	8
+
+/*
+ * According to Intel 64 and IA-32 System Programming Guide,
+ * if MSR_PERF_STAT[31] is set, the maximum resolved bus ratio can be
+ * read in MSR_PLATFORM_ID[12:8], otherwise in MSR_PERF_STAT[44:40].
+ * Unfortunately some Intel Atom SoCs aren't quite compliant to this,
+ * so we need manually differentiate SoC families. This is what the
+ * field msr_plat does.
+ */
+struct freq_desc {
+	u8 x86_family;	/* CPU family */
+	u8 x86_model;	/* model */
+	u8 msr_plat;	/* 1: use MSR_PLATFORM_INFO, 0: MSR_IA32_PERF_STATUS */
+	u32 freqs[MAX_NUM_FREQS];
+};
+
+static struct freq_desc freq_desc_tables[] = {
+	/* PNW */
+	{ 6, 0x27, 0, { 0, 0, 0, 0, 0, FREQ_100, 0, FREQ_83 } },
+	/* CLV+ */
+	{ 6, 0x35, 0, { 0, FREQ_133, 0, 0, 0, FREQ_100, 0, FREQ_83 } },
+	/* TNG */
+	{ 6, 0x4a, 1, { 0, FREQ_100, FREQ_133, 0, 0, 0, 0, 0 } },
+	/* VLV2 */
+	{ 6, 0x37, 1, { 0, FREQ_100, FREQ_133, FREQ_166, 0, 0, 0, 0 } },
+	/* ANN */
+	{ 6, 0x5a, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_100, 0, 0, 0, 0 } },
+};
+
+static int match_cpu(u8 family, u8 model)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(freq_desc_tables); i++) {
+		if ((family == freq_desc_tables[i].x86_family) &&
+			(model == freq_desc_tables[i].x86_model))
+			return i;
+	}
+
+	return -1;
+}
+
+/* Map CPU reference clock freq ID(0-7) to CPU reference clock freq(KHz) */
+#define id_to_freq(cpu_index, freq_id) \
+	(freq_desc_tables[cpu_index].freqs[freq_id])
+
+/*
+ * Do MSR calibration only for known/supported CPUs.
+ * Return values:
+ * -1: CPU is unknown/unsupported for MSR based calibration
+ *  0: CPU is known/supported, but calibration failed
+ *  1: CPU is known/supported, and calibration succeeded
+ */
+int try_msr_calibrate_tsc(unsigned long *fast_calibrate)
+{
+	int cpu_index;
+	u32 lo, hi, ratio, freq_id, freq;
+
+	cpu_index = match_cpu(boot_cpu_data.x86, boot_cpu_data.x86_model);
+	if (cpu_index < 0)
+		return -1;
+
+	*fast_calibrate = 0;
+
+	if (freq_desc_tables[cpu_index].msr_plat) {
+		rdmsr(MSR_PLATFORM_INFO, lo, hi);
+		ratio = (lo >> 8) & 0x1f;
+	} else {
+		rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+		ratio = (hi >> 8) & 0x1f;
+	}
+	pr_info("Maximum core-clock to bus-clock ratio: 0x%x\n", ratio);
+
+	if (!ratio)
+		return 0;
+
+	/* Get FSB FREQ ID */
+	rdmsr(MSR_FSB_FREQ, lo, hi);
+	freq_id = lo & 0x7;
+	freq = id_to_freq(cpu_index, freq_id);
+	pr_info("Resolved frequency ID: %u, frequency: %u KHz\n",
+				freq_id, freq);
+	if (!freq)
+		return 0;
+
+	/* TSC frequency = maximum resolved freq * maximum resolved bus ratio */
+	*fast_calibrate = freq * ratio;
+	pr_info("TSC runs at %lu KHz\n", *fast_calibrate);
+
+	lapic_timer_frequency = (freq * 1000) / HZ;
+	pr_info("lapic_timer_frequency = %d\n", lapic_timer_frequency);
+
+	return 1;
+}
-- 
cgit v0.10.2


From c026b3591e4f2a4993df773183704bb31634e0bd Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 10 Jan 2014 21:06:03 +0100
Subject: x86, mm, perf: Allow recursive faults from interrupts

Waiman managed to trigger a PMI while in a emulate_vsyscall() fault,
the PMI in turn managed to trigger a fault while obtaining a stack
trace. This triggered the sig_on_uaccess_error recursive fault logic
and killed the process dead.

Fix this by explicitly excluding interrupts from the recursive fault
logic.

Reported-and-Tested-by: Waiman Long <waiman.long@hp.com>
Fixes: e00b12e64be9 ("perf/x86: Further optimize copy_from_user_nmi()")
Cc: Aswin Chandramouleeswaran <aswin@hp.com>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140110200603.GJ7572@laptop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9ff85bb..9d591c8 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -641,6 +641,20 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 
 	/* Are we prepared to handle this kernel fault? */
 	if (fixup_exception(regs)) {
+		/*
+		 * Any interrupt that takes a fault gets the fixup. This makes
+		 * the below recursive fault logic only apply to a faults from
+		 * task context.
+		 */
+		if (in_interrupt())
+			return;
+
+		/*
+		 * Per the above we're !in_interrupt(), aka. task context.
+		 *
+		 * In this case we need to make sure we're not recursively
+		 * faulting through the emulate_vsyscall() logic.
+		 */
 		if (current_thread_info()->sig_on_uaccess_error && signal) {
 			tsk->thread.trap_nr = X86_TRAP_PF;
 			tsk->thread.error_code = error_code | PF_USER;
@@ -649,6 +663,10 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 			/* XXX: hwpoison faults will set the wrong code. */
 			force_sig_info_fault(signal, si_code, address, tsk, 0);
 		}
+
+		/*
+		 * Barring that, we can do the fixup and be happy.
+		 */
 		return;
 	}
 
-- 
cgit v0.10.2


From bee09ed91cacdbffdbcd3b05de8409c77ec9fcd6 Mon Sep 17 00:00:00 2001
From: Robert Richter <rric@kernel.org>
Date: Wed, 15 Jan 2014 15:57:29 +0100
Subject: perf/x86/amd/ibs: Fix waking up from S3 for AMD family 10h

On AMD family 10h we see following error messages while waking up from
S3 for all non-boot CPUs leading to a failed IBS initialization:

 Enabling non-boot CPUs ...
 smpboot: Booting Node 0 Processor 1 APIC 0x1
 [Firmware Bug]: cpu 1, try to use APIC500 (LVT offset 0) for vector 0x400, but the register is already in use for vector 0xf9 on another cpu
 perf: IBS APIC setup failed on cpu #1
 process: Switch to broadcast mode on CPU1
 CPU1 is up
 ...
 ACPI: Waking up from system sleep state S3

Reason for this is that during suspend the LVT offset for the IBS
vector gets lost and needs to be reinialized while resuming.

The offset is read from the IBSCTL msr. On family 10h the offset needs
to be 1 as offset 0 is used for the MCE threshold interrupt, but
firmware assings it for IBS to 0 too. The kernel needs to reprogram
the vector. The msr is a readonly node msr, but a new value can be
written via pci config space access. The reinitialization is
implemented for family 10h in setup_ibs_ctl() which is forced during
IBS setup.

This patch fixes IBS setup after waking up from S3 by adding
resume/supend hooks for the boot cpu which does the offset
reinitialization.

Marking it as stable to let distros pick up this fix.

Signed-off-by: Robert Richter <rric@kernel.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: <stable@vger.kernel.org> v3.2..
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1389797849-5565-1-git-send-email-rric.net@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index e09f0bf..4b8e4d3 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/ptrace.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/apic.h>
 
@@ -816,6 +817,18 @@ out:
 	return ret;
 }
 
+static void ibs_eilvt_setup(void)
+{
+	/*
+	 * Force LVT offset assignment for family 10h: The offsets are
+	 * not assigned by the BIOS for this family, so the OS is
+	 * responsible for doing it. If the OS assignment fails, fall
+	 * back to BIOS settings and try to setup this.
+	 */
+	if (boot_cpu_data.x86 == 0x10)
+		force_ibs_eilvt_setup();
+}
+
 static inline int get_ibs_lvt_offset(void)
 {
 	u64 val;
@@ -851,6 +864,36 @@ static void clear_APIC_ibs(void *dummy)
 		setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1);
 }
 
+#ifdef CONFIG_PM
+
+static int perf_ibs_suspend(void)
+{
+	clear_APIC_ibs(NULL);
+	return 0;
+}
+
+static void perf_ibs_resume(void)
+{
+	ibs_eilvt_setup();
+	setup_APIC_ibs(NULL);
+}
+
+static struct syscore_ops perf_ibs_syscore_ops = {
+	.resume		= perf_ibs_resume,
+	.suspend	= perf_ibs_suspend,
+};
+
+static void perf_ibs_pm_init(void)
+{
+	register_syscore_ops(&perf_ibs_syscore_ops);
+}
+
+#else
+
+static inline void perf_ibs_pm_init(void) { }
+
+#endif
+
 static int
 perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 {
@@ -877,18 +920,12 @@ static __init int amd_ibs_init(void)
 	if (!caps)
 		return -ENODEV;	/* ibs not supported by the cpu */
 
-	/*
-	 * Force LVT offset assignment for family 10h: The offsets are
-	 * not assigned by the BIOS for this family, so the OS is
-	 * responsible for doing it. If the OS assignment fails, fall
-	 * back to BIOS settings and try to setup this.
-	 */
-	if (boot_cpu_data.x86 == 0x10)
-		force_ibs_eilvt_setup();
+	ibs_eilvt_setup();
 
 	if (!ibs_eilvt_valid())
 		goto out;
 
+	perf_ibs_pm_init();
 	get_online_cpus();
 	ibs_caps = caps;
 	/* make ibs_caps visible to other cpus: */
-- 
cgit v0.10.2


From 54b278b50b8566c227437d6198412cb5a6619e6b Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sun, 12 Jan 2014 22:24:56 +0100
Subject: m68k: Fix build warning in mac_via.h

Fengguang Wu's kbuild test robot reported the following new m68k warnings:

     In file included from drivers/nubus/nubus.c:22:0:
  >> arch/m68k/include/asm/mac_via.h:262:47: warning: 'struct irq_desc' declared inside parameter list [enabled by default]
  >> arch/m68k/include/asm/mac_via.h:262:47: warning: its scope is only this definition or declaration, which is probably not what you want [enabled by default]

Caused by the reworking of the generic local_bh{dis,en}able() code.

To fix it, forward declare 'struct irq_desc'.

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Fixes: c795eb55e740 ("sched/preempt, locking: Rework local_bh_{dis,en}able()")
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: geert@linux-m68k.org
Link: http://lkml.kernel.org/r/20140112212456.GQ7572@laptop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/m68k/include/asm/mac_via.h b/arch/m68k/include/asm/mac_via.h
index aeeedf8..fe3fc9a 100644
--- a/arch/m68k/include/asm/mac_via.h
+++ b/arch/m68k/include/asm/mac_via.h
@@ -254,6 +254,8 @@
 extern volatile __u8 *via1,*via2;
 extern int rbv_present,via_alt_mapping;
 
+struct irq_desc;
+
 extern void via_register_interrupts(void);
 extern void via_irq_enable(int);
 extern void via_irq_disable(int);
-- 
cgit v0.10.2


From 88f1ebbc256e93bc029ec70b366612801f2c98ad Mon Sep 17 00:00:00 2001
From: Fengguang Wu <fengguang.wu@intel.com>
Date: Tue, 14 Jan 2014 08:06:36 +0800
Subject: sched/deadline: Fix sparse static warnings

new sparse warnings:

  >> kernel/sched/cpudeadline.c:38:6: sparse: symbol 'cpudl_exchange' was not declared. Should it be static?
  >> kernel/sched/cpudeadline.c:46:6: sparse: symbol 'cpudl_heapify' was not declared. Should it be static?
  >> kernel/sched/cpudeadline.c:71:6: sparse: symbol 'cpudl_change_key' was not declared. Should it be static?
  >> kernel/sched/cpudeadline.c:195:15: sparse: memset with byte count of 163928

Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@gmail.com>
Fixes: 6bfd6d72f51c ("sched/deadline: speed up SCHED_DEADLINE pushes with a push-heap")
Link: http://lkml.kernel.org/r/52d47f8c.EYJsA5+mELPBk4t6\%fengguang.wu@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 3bcade5..045fc74 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -35,7 +35,7 @@ static inline int dl_time_before(u64 a, u64 b)
 	return (s64)(a - b) < 0;
 }
 
-void cpudl_exchange(struct cpudl *cp, int a, int b)
+static void cpudl_exchange(struct cpudl *cp, int a, int b)
 {
 	int cpu_a = cp->elements[a].cpu, cpu_b = cp->elements[b].cpu;
 
@@ -43,7 +43,7 @@ void cpudl_exchange(struct cpudl *cp, int a, int b)
 	swap(cp->cpu_to_idx[cpu_a], cp->cpu_to_idx[cpu_b]);
 }
 
-void cpudl_heapify(struct cpudl *cp, int idx)
+static void cpudl_heapify(struct cpudl *cp, int idx)
 {
 	int l, r, largest;
 
@@ -68,7 +68,7 @@ void cpudl_heapify(struct cpudl *cp, int idx)
 	}
 }
 
-void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
+static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
 {
 	WARN_ON(idx > num_present_cpus() || idx == IDX_INVALID);
 
-- 
cgit v0.10.2


From d8bf52311ecefd9b11a5af2b28ed7f41c6023516 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 14 Jan 2014 11:23:34 +0800
Subject: sched/deadline: Remove unused variables

fix these new sparse warnings:

  >> kernel/sched/core.c:305:14: sparse: symbol 'sysctl_sched_dl_period' was not declared. Should it be static?
  >> kernel/sched/core.c:306:5: sparse: symbol 'sysctl_sched_dl_runtime' was not declared. Should it be static?

Better still, they're completely unused so remove them.

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@gmail.com>
Link: http://lkml.kernel.org/n/tip-ke0shkG7vMnzmcdqhhiymyem@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0326c06..138711b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -297,17 +297,6 @@ __read_mostly int scheduler_running;
 int sysctl_sched_rt_runtime = 950000;
 
 /*
- * Maximum bandwidth available for all -deadline tasks and groups
- * (if group scheduling is configured) on each CPU.
- *
- * default: 5%
- */
-unsigned int sysctl_sched_dl_period = 1000000;
-int sysctl_sched_dl_runtime = 50000;
-
-
-
-/*
  * __task_rq_lock - lock the rq @p resides on.
  */
 static inline struct rq *__task_rq_lock(struct task_struct *p)
-- 
cgit v0.10.2


From 71362650b555a5b24c732e455484cc7cac1c8588 Mon Sep 17 00:00:00 2001
From: Juri Lelli <juri.lelli@gmail.com>
Date: Tue, 14 Jan 2014 12:03:51 +0100
Subject: sched/deadline: No need to check p if dl_se is valid

Dan Carpenter reported new 'Smatch' warnings:

  > tree:   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched/core
  > head:   130816ce4d5f69167324f7272e70aa3d641677c6
  > commit: 1baca4ce16b8cc7d4f50be1f7914799af30a2861 [17/50] sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic
  >
  > kernel/sched/deadline.c:937 pick_next_task_dl() warn: variable dereferenced before check 'p' (see line 934)

BUG_ON() already fires if pick_next_dl_entity() doesn't return a valid
dl_se. No need to check if p is valid afterward.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Fixes: 1baca4ce16b8 ("sched/deadline: Add SCHED_DEADLINE SMP-related data structures & logic")
Link: http://lkml.kernel.org/r/52D54E25.6060100@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index ee25361..0de2482 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1007,8 +1007,7 @@ struct task_struct *pick_next_task_dl(struct rq *rq)
 	p->se.exec_start = rq_clock_task(rq);
 
 	/* Running task will never be pushed. */
-	if (p)
-		dequeue_pushable_dl_task(rq, p);
+       dequeue_pushable_dl_task(rq, p);
 
 #ifdef CONFIG_SCHED_HRTICK
 	if (hrtick_enabled(rq))
-- 
cgit v0.10.2


From 5778fccf361c9ba443b45d822f3d875f64c80084 Mon Sep 17 00:00:00 2001
From: Juri Lelli <juri.lelli@gmail.com>
Date: Tue, 14 Jan 2014 16:10:39 +0100
Subject: sched/core: Fix htmldocs warnings

Fengguang Wu's kbuild test robot reported the following new htmldocs warnings:

  >>> Warning(kernel/sched/core.c:3380): No description found for parameter 'uattr'
  >>> Warning(kernel/sched/core.c:3380): Excess function parameter 'attr' description in 'sys_sched_setattr'
  >>> Warning(kernel/sched/core.c:3520): No description found for parameter 'uattr'
  >>> Warning(kernel/sched/core.c:3520): Excess function parameter 'attr' description in 'sys_sched_getattr'

The second argument to sys_sched_{setattr,getattr}() is named uattr (not attr).

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Dario Faggioli <raistlin@linux.it>
Fixes: d50dde5a10f3 ("sched: Add new scheduler syscalls to support an extended scheduling parameters ABI")
Link: http://lkml.kernel.org/r/52D5552D.5000102@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 138711b..26af370 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3614,7 +3614,7 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
 /**
  * sys_sched_setattr - same as above, but with extended sched_attr
  * @pid: the pid in question.
- * @attr: structure containing the extended parameters.
+ * @uattr: structure containing the extended parameters.
  */
 SYSCALL_DEFINE2(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr)
 {
@@ -3756,7 +3756,7 @@ err_size:
 /**
  * sys_sched_getattr - similar to sched_getparam, but with sched_attr
  * @pid: the pid in question.
- * @attr: structure containing the extended parameters.
+ * @uattr: structure containing the extended parameters.
  * @size: sizeof(attr) for fwd/bwd comp.
  */
 SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
-- 
cgit v0.10.2


From e3de300d1212b42aa9d0d6031b12fca06ac00dd9 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 15 Jan 2014 12:30:15 +0100
Subject: sched: Preserve the nice level over sched_setscheduler() and
 sched_setparam() calls

Previously sched_setscheduler() and sched_setparam() would not affect
the nice value of a task, restore this behaviour.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: raistlin@linux.it
Cc: juri.lelli@gmail.com
Cc: Michael wang <wangyun@linux.vnet.ibm.com>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Fixes: d50dde5a10f3 ("sched: Add new scheduler syscalls to support an extended scheduling parameters ABI")
Link: http://lkml.kernel.org/r/20140115113015.GB31570@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 26af370..c1b3d7e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3451,7 +3451,8 @@ int sched_setscheduler(struct task_struct *p, int policy,
 {
 	struct sched_attr attr = {
 		.sched_policy   = policy,
-		.sched_priority = param->sched_priority
+		.sched_priority = param->sched_priority,
+		.sched_nice	= PRIO_TO_NICE(p->static_prio),
 	};
 	return __sched_setscheduler(p, &attr, true);
 }
@@ -3481,7 +3482,8 @@ int sched_setscheduler_nocheck(struct task_struct *p, int policy,
 {
 	struct sched_attr attr = {
 		.sched_policy   = policy,
-		.sched_priority = param->sched_priority
+		.sched_priority = param->sched_priority,
+		.sched_nice	= PRIO_TO_NICE(p->static_prio),
 	};
 	return __sched_setscheduler(p, &attr, false);
 }
-- 
cgit v0.10.2


From 39fd8fd22b3224ec6819d33b3e34ae4da6a35f05 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 15 Jan 2014 16:33:20 +0100
Subject: sched: Fix up scheduler syscall LTP fails

Wu reported LTP failures:

  > ltp.sched_setparam02.1.TFAIL
  > ltp.sched_setparam02.2.TFAIL
  > ltp.sched_setparam02.3.TFAIL
  > ltp.sched_setparam03.1.TFAIL

There were 2 things wrong; firstly __setscheduler() failed on
sched_setparam()'s policy = -1, fix that by reading from p->policy in
that case.

Secondly, getparam() (and getattr()) would still report !0
sched_priority for !FIFO/RR tasks after having been such. So
unconditionally set p->rt_priority.

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Dario Faggioli <raistlin@linux.it>
Fixes: d50dde5a10f3 ("sched: Add new scheduler syscalls to support an extended scheduling parameters ABI")
Link: http://lkml.kernel.org/r/20140115153320.GH31570@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c1b3d7e..e9212eb 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3172,15 +3172,23 @@ static void __setscheduler(struct rq *rq, struct task_struct *p,
 {
 	int policy = attr->sched_policy;
 
+	if (policy == -1) /* setparam */
+		policy = p->policy;
+
 	p->policy = policy;
 
 	if (dl_policy(policy))
 		__setparam_dl(p, attr);
-	else if (rt_policy(policy))
-		p->rt_priority = attr->sched_priority;
-	else
+	else if (fair_policy(policy))
 		p->static_prio = NICE_TO_PRIO(attr->sched_nice);
 
+	/*
+	 * __sched_setscheduler() ensures attr->sched_priority == 0 when
+	 * !rt_policy. Always setting this ensures that things like
+	 * getparam()/getattr() don't report silly values for !rt tasks.
+	 */
+	p->rt_priority = attr->sched_priority;
+
 	p->normal_prio = normal_prio(p);
 	p->prio = rt_mutex_getprio(p);
 
-- 
cgit v0.10.2


From 0bb040a44381261c0729636abbe03caeedb7d72e Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 15 Jan 2014 17:15:13 +0100
Subject: sched: Fix up attr::sched_priority warning

Fengguang Wu reported the following build warning:

  > kernel/sched/core.c:3067 __sched_setscheduler() warn: unsigned 'attr->sched_priority' is never less than zero.

Since it doesn't make sense for attr::sched_priority to be negative,
remove the check, since we already test for an upper limit any actual
negative values passed in through the old param::sched_priority field
will still be detected.

Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Dario Faggioli <raistlin@linux.it>
Fixes: d50dde5a10f3 ("sched: Add new scheduler syscalls to support an extended scheduling parameters ABI")
Link: http://lkml.kernel.org/n/tip-fid9nalzii2r5voxtf4eh5kz@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e9212eb..5a6ccdf 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3282,8 +3282,7 @@ recheck:
 	 * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
 	 * SCHED_BATCH and SCHED_IDLE is 0.
 	 */
-	if (attr->sched_priority < 0 ||
-	    (p->mm && attr->sched_priority > MAX_USER_RT_PRIO-1) ||
+	if ((p->mm && attr->sched_priority > MAX_USER_RT_PRIO-1) ||
 	    (!p->mm && attr->sched_priority > MAX_RT_PRIO-1))
 		return -EINVAL;
 	if ((dl_policy(policy) && !__checkparam_dl(attr)) ||
-- 
cgit v0.10.2


From 7479f3c9cf67edf5e8a76b21ea3726757f35cf53 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 15 Jan 2014 17:05:04 +0100
Subject: sched: Move SCHED_RESET_ON_FORK into attr::sched_flags

I noticed the new sched_{set,get}attr() calls didn't properly deal
with the SCHED_RESET_ON_FORK hack.

Instead of propagating the flags in high bits nonsense use the brand
spanking new attr::sched_flags field.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Dario Faggioli <raistlin@linux.it>
Link: http://lkml.kernel.org/r/20140115162242.GJ31570@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 2d5e49a..34f9d73 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -40,8 +40,13 @@
 /* SCHED_ISO: reserved but not implemented yet */
 #define SCHED_IDLE		5
 #define SCHED_DEADLINE		6
+
 /* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
 #define SCHED_RESET_ON_FORK     0x40000000
 
+/*
+ * For the sched_{set,get}attr() calls
+ */
+#define SCHED_FLAG_RESET_ON_FORK	0x01
 
 #endif /* _UAPI_LINUX_SCHED_H */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5a6ccdf..93a2836 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3267,8 +3267,7 @@ recheck:
 		reset_on_fork = p->sched_reset_on_fork;
 		policy = oldpolicy = p->policy;
 	} else {
-		reset_on_fork = !!(policy & SCHED_RESET_ON_FORK);
-		policy &= ~SCHED_RESET_ON_FORK;
+		reset_on_fork = !!(attr->sched_flags & SCHED_FLAG_RESET_ON_FORK);
 
 		if (policy != SCHED_DEADLINE &&
 				policy != SCHED_FIFO && policy != SCHED_RR &&
@@ -3277,6 +3276,9 @@ recheck:
 			return -EINVAL;
 	}
 
+	if (attr->sched_flags & ~(SCHED_FLAG_RESET_ON_FORK))
+		return -EINVAL;
+
 	/*
 	 * Valid priorities for SCHED_FIFO and SCHED_RR are
 	 * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
@@ -3443,6 +3445,26 @@ change:
 	return 0;
 }
 
+static int _sched_setscheduler(struct task_struct *p, int policy,
+			       const struct sched_param *param, bool check)
+{
+	struct sched_attr attr = {
+		.sched_policy   = policy,
+		.sched_priority = param->sched_priority,
+		.sched_nice	= PRIO_TO_NICE(p->static_prio),
+	};
+
+	/*
+	 * Fixup the legacy SCHED_RESET_ON_FORK hack
+	 */
+	if (policy & SCHED_RESET_ON_FORK) {
+		attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
+		policy &= ~SCHED_RESET_ON_FORK;
+		attr.sched_policy = policy;
+	}
+
+	return __sched_setscheduler(p, &attr, check);
+}
 /**
  * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
  * @p: the task in question.
@@ -3456,12 +3478,7 @@ change:
 int sched_setscheduler(struct task_struct *p, int policy,
 		       const struct sched_param *param)
 {
-	struct sched_attr attr = {
-		.sched_policy   = policy,
-		.sched_priority = param->sched_priority,
-		.sched_nice	= PRIO_TO_NICE(p->static_prio),
-	};
-	return __sched_setscheduler(p, &attr, true);
+	return _sched_setscheduler(p, policy, param, true);
 }
 EXPORT_SYMBOL_GPL(sched_setscheduler);
 
@@ -3487,12 +3504,7 @@ EXPORT_SYMBOL_GPL(sched_setattr);
 int sched_setscheduler_nocheck(struct task_struct *p, int policy,
 			       const struct sched_param *param)
 {
-	struct sched_attr attr = {
-		.sched_policy   = policy,
-		.sched_priority = param->sched_priority,
-		.sched_nice	= PRIO_TO_NICE(p->static_prio),
-	};
-	return __sched_setscheduler(p, &attr, false);
+	return _sched_setscheduler(p, policy, param, false);
 }
 
 static int
@@ -3792,6 +3804,8 @@ SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 		goto out_unlock;
 
 	attr.sched_policy = p->policy;
+	if (p->sched_reset_on_fork)
+		attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
 	if (task_has_dl_policy(p))
 		__getparam_dl(p, &attr);
 	else if (task_has_rt_policy(p))
-- 
cgit v0.10.2


From 63b1a81699c2a45c9f737419b1ec1da0ecf92812 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Thu, 16 Jan 2014 14:54:50 +0100
Subject: futexes: Fix futex_hashsize initialization

"futexes: Increase hash table size for better performance"
introduces a new alloc_large_system_hash() call.

alloc_large_system_hash() however may allocate less memory than
requested, e.g. limited by MAX_ORDER.

Hence pass a pointer to alloc_large_system_hash() which will
contain the hash shift when the function returns. Afterwards
correctly set futex_hashsize.

Fixes a crash on s390 where the requested allocation size was
4MB but only 1MB was allocated.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Darren Hart <dvhart@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Waiman Long <Waiman.Long@hp.com>
Cc: Jason Low <jason.low2@hp.com>
Cc: Davidlohr Bueso <davidlohr@hp.com>
Link: http://lkml.kernel.org/r/20140116135450.GA4345@osiris
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/futex.c b/kernel/futex.c
index 30971b5..1ddc449 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2844,6 +2844,7 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
 static int __init futex_init(void)
 {
 	u32 curval;
+	unsigned int futex_shift;
 	unsigned long i;
 
 #if CONFIG_BASE_SMALL
@@ -2855,8 +2856,9 @@ static int __init futex_init(void)
 	futex_queues = alloc_large_system_hash("futex", sizeof(*futex_queues),
 					       futex_hashsize, 0,
 					       futex_hashsize < 256 ? HASH_SMALL : 0,
-					       NULL, NULL, futex_hashsize, futex_hashsize);
-
+					       &futex_shift, NULL,
+					       futex_hashsize, futex_hashsize);
+	futex_hashsize = 1UL << futex_shift;
 	/*
 	 * This will fail and we want it. Some arch implementations do
 	 * runtime detection of the futex_atomic_cmpxchg_inatomic()
-- 
cgit v0.10.2


From b4a960159e6f5254ac3c95dd183789f402431977 Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Fri, 13 Dec 2013 12:53:42 +0100
Subject: s390: Fix misspellings using 'codespell' tool

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index 0a1abf1..d786c63 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -336,7 +336,7 @@ typedef void qdio_handler_t(struct ccw_device *, unsigned int, int,
 #define QDIO_FLAG_CLEANUP_USING_HALT		0x02
 
 /**
- * struct qdio_initialize - qdio initalization data
+ * struct qdio_initialize - qdio initialization data
  * @cdev: associated ccw device
  * @q_format: queue format
  * @adapter_name: name for the adapter
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 9532fe2..384e609 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -975,7 +975,7 @@ sie_done:
 	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
 # some program checks are suppressing. C code (e.g. do_protection_exception)
 # will rewind the PSW by the ILC, which is 4 bytes in case of SIE. Other
-# instructions beween sie64a and sie_done should not cause program
+# instructions between sie64a and sie_done should not cause program
 # interrupts. So lets use a nop (47 00 00 00) as a landing pad.
 # See also HANDLE_SIE_INTERCEPT
 rewind_pad:
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 4444875..36e81d7 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -373,7 +373,7 @@ static void __init setup_lowcore(void)
 
 	/*
 	 * Set up PSW restart to call ipl.c:do_restart(). Copy the relevant
-	 * restart data to the absolute zero lowcore. This is necesary if
+	 * restart data to the absolute zero lowcore. This is necessary if
 	 * PSW restart is done on an offline CPU that has lowcore zero.
 	 */
 	lc->restart_stack = (unsigned long) restart_stack;
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 2440602..d101dae 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -275,7 +275,7 @@ static int handle_io_inst(struct kvm_vcpu *vcpu)
 		return -EOPNOTSUPP;
 	} else {
 		/*
-		 * Set condition code 3 to stop the guest from issueing channel
+		 * Set condition code 3 to stop the guest from issuing channel
 		 * I/O instructions.
 		 */
 		kvm_s390_set_psw_cc(vcpu, 3);
diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c
index dbdab3e..0632dc5 100644
--- a/arch/s390/lib/uaccess_pt.c
+++ b/arch/s390/lib/uaccess_pt.c
@@ -74,8 +74,8 @@ static size_t copy_in_kernel(size_t count, void __user *to,
 
 /*
  * Returns kernel address for user virtual address. If the returned address is
- * >= -4095 (IS_ERR_VALUE(x) returns true), a fault has occured and the address
- * contains the (negative) exception code.
+ * >= -4095 (IS_ERR_VALUE(x) returns true), a fault has occurred and the
+ * address contains the (negative) exception code.
  */
 #ifdef CONFIG_64BIT
 
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index e794c88..3584ed9 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -293,7 +293,7 @@ static int gmap_alloc_table(struct gmap *gmap,
  * @addr: address in the guest address space
  * @len: length of the memory area to unmap
  *
- * Returns 0 if the unmap succeded, -EINVAL if not.
+ * Returns 0 if the unmap succeeded, -EINVAL if not.
  */
 int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len)
 {
@@ -344,7 +344,7 @@ EXPORT_SYMBOL_GPL(gmap_unmap_segment);
  * @from: source address in the parent address space
  * @to: target address in the guest address space
  *
- * Returns 0 if the mmap succeded, -EINVAL or -ENOMEM if not.
+ * Returns 0 if the mmap succeeded, -EINVAL or -ENOMEM if not.
  */
 int gmap_map_segment(struct gmap *gmap, unsigned long from,
 		     unsigned long to, unsigned long len)
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index f302efa9..1eef0f5 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -3386,7 +3386,7 @@ int dasd_generic_set_offline(struct ccw_device *cdev)
 
 	if (test_bit(DASD_FLAG_SAFE_OFFLINE_RUNNING, &device->flags)) {
 		/*
-		 * safe offline allready running
+		 * safe offline already running
 		 * could only be called by normal offline so safe_offline flag
 		 * needs to be removed to run normal offline and kill all I/O
 		 */
diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c
index 57bfda1..dc542e0 100644
--- a/drivers/s390/crypto/zcrypt_msgtype6.c
+++ b/drivers/s390/crypto/zcrypt_msgtype6.c
@@ -419,7 +419,7 @@ static int xcrb_msg_to_type6_ep11cprb_msgx(struct zcrypt_device *zdev,
 	 replaced by the usage domain for non-management commands only.
 	 Therefore we check the first bit of the 'flags' parameter for
 	 management command indication.
-	   0 - non managment command
+	   0 - non management command
 	   1 - management command
 	*/
 	if (!((msg->cprbx.flags & 0x80) == 0x80)) {
-- 
cgit v0.10.2


From f85168e4d96b31b09ecf09a679820b031224e69e Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Date: Wed, 8 Jan 2014 16:45:39 +0100
Subject: s390/cpum_sf: fix printk format warnings

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index a76d602..5d2dfa3 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -142,17 +142,17 @@ static void print_debug_sf(void)
 	if (qsi(&si))
 		return;
 
-	pr_info("CPU[%i] CPUM_SF: basic=%i diag=%i min=%i max=%i cpu_speed=%i\n",
+	pr_info("CPU[%i] CPUM_SF: basic=%i diag=%i min=%lu max=%lu cpu_speed=%u\n",
 		cpu, si.as, si.ad, si.min_sampl_rate, si.max_sampl_rate,
 		si.cpu_speed);
 
 	if (si.as)
 		pr_info("CPU[%i] CPUM_SF: Basic-sampling: a=%i e=%i c=%i"
-			" bsdes=%i tear=%p dear=%p\n", cpu,
+			" bsdes=%i tear=%016lx dear=%016lx\n", cpu,
 			si.as, si.es, si.cs, si.bsdes, si.tear, si.dear);
 	if (si.ad)
 		pr_info("CPU[%i] CPUM_SF: Diagnostic-sampling: a=%i e=%i c=%i"
-			" dsdes=%i tear=%p dear=%p\n", cpu,
+			" dsdes=%i tear=%016lx dear=%016lx\n", cpu,
 			si.ad, si.ed, si.cd, si.dsdes, si.tear, si.dear);
 }
 
-- 
cgit v0.10.2


From eaad45132c564ce377e6dce05e78e08e456d5315 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 16 Jan 2014 17:54:25 +0100
Subject: sched: Fix __sched_setscheduler() nice test

With the introduction of sched_attr::sched_nice we need to check
if we've got permission to actually change the nice value.

Daniel found that can_nice() would always fail; and upon
inspection it turns out that can_nice() only tests to see if we
can lower the nice value, but it doesn't validate if we're
lowering or not.

Therefore amend the test to only call can_nice() when we lower
the nice value.

Reported-and-Tested-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: raistlin@linux.it
Cc: juri.lelli@gmail.com
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Fixes: d50dde5a10f3 ("sched: Add new scheduler syscalls to support an extended scheduling parameters ABI")
Link: http://lkml.kernel.org/r/20140116165425.GA9481@laptop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 93a2836..36c951b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3296,7 +3296,8 @@ recheck:
 	 */
 	if (user && !capable(CAP_SYS_NICE)) {
 		if (fair_policy(policy)) {
-			if (!can_nice(p, attr->sched_nice))
+			if (attr->sched_nice < TASK_NICE(p) &&
+			    !can_nice(p, attr->sched_nice))
 				return -EPERM;
 		}
 
-- 
cgit v0.10.2


From 4ce00dfcf19c473f3dbf23d5b1372639f0c334f6 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Thu, 16 Jan 2014 18:32:25 +0000
Subject: Revert "arm64: Fix memory shareability attribute for
 ioremap_wc/cache"

This reverts commit 2f7dc6027522499582a520807cb9ffda589de47e.

The above commit breaks the mapping type for Device memory because
pgprot_default already contains a Normal memory type. pgprot_default is
also not initialised early enough for earlyprintk resulting in an
inconsistent memory mapping with 64K PAGE_SIZE configuration.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Reported-by: Will Deacon <will.deacon@arm.com>
Acked-by: Will Deacon <will.deacon@arm.com>

diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 5727697..4cc813e 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -229,7 +229,7 @@ extern void __iomem *__ioremap(phys_addr_t phys_addr, size_t size, pgprot_t prot
 extern void __iounmap(volatile void __iomem *addr);
 extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
 
-#define PROT_DEFAULT		(pgprot_default | PTE_DIRTY)
+#define PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_DIRTY)
 #define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE))
 #define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL_NC))
 #define PROT_NORMAL		(PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
-- 
cgit v0.10.2


From ad13701d4905e820f32ce3c2590e19ca65765d63 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 16 Jan 2014 11:31:07 +0900
Subject: tools lib traceevent: Add pevent_unregister_event_handler()

When a plugin is unloaded it needs to unregister its handler from pevent.

So add an unregister function to do it.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389839478-5887-2-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 2ce565a..d1973cb 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -5560,6 +5560,29 @@ int pevent_register_print_function(struct pevent *pevent,
 	return ret;
 }
 
+static struct event_format *pevent_search_event(struct pevent *pevent, int id,
+						const char *sys_name,
+						const char *event_name)
+{
+	struct event_format *event;
+
+	if (id >= 0) {
+		/* search by id */
+		event = pevent_find_event(pevent, id);
+		if (!event)
+			return NULL;
+		if (event_name && (strcmp(event_name, event->name) != 0))
+			return NULL;
+		if (sys_name && (strcmp(sys_name, event->system) != 0))
+			return NULL;
+	} else {
+		event = pevent_find_event_by_name(pevent, sys_name, event_name);
+		if (!event)
+			return NULL;
+	}
+	return event;
+}
+
 /**
  * pevent_register_event_handler - register a way to parse an event
  * @pevent: the handle to the pevent
@@ -5584,20 +5607,9 @@ int pevent_register_event_handler(struct pevent *pevent, int id,
 	struct event_format *event;
 	struct event_handler *handle;
 
-	if (id >= 0) {
-		/* search by id */
-		event = pevent_find_event(pevent, id);
-		if (!event)
-			goto not_found;
-		if (event_name && (strcmp(event_name, event->name) != 0))
-			goto not_found;
-		if (sys_name && (strcmp(sys_name, event->system) != 0))
-			goto not_found;
-	} else {
-		event = pevent_find_event_by_name(pevent, sys_name, event_name);
-		if (!event)
-			goto not_found;
-	}
+	event = pevent_search_event(pevent, id, sys_name, event_name);
+	if (event == NULL)
+		goto not_found;
 
 	pr_stat("overriding event (%d) %s:%s with new print handler",
 		event->id, event->system, event->name);
@@ -5637,6 +5649,79 @@ int pevent_register_event_handler(struct pevent *pevent, int id,
 	return -1;
 }
 
+static int handle_matches(struct event_handler *handler, int id,
+			  const char *sys_name, const char *event_name,
+			  pevent_event_handler_func func, void *context)
+{
+	if (id >= 0 && id != handler->id)
+		return 0;
+
+	if (event_name && (strcmp(event_name, handler->event_name) != 0))
+		return 0;
+
+	if (sys_name && (strcmp(sys_name, handler->sys_name) != 0))
+		return 0;
+
+	if (func != handler->func || context != handler->context)
+		return 0;
+
+	return 1;
+}
+
+/**
+ * pevent_unregister_event_handler - unregister an existing event handler
+ * @pevent: the handle to the pevent
+ * @id: the id of the event to unregister
+ * @sys_name: the system name the handler belongs to
+ * @event_name: the name of the event handler
+ * @func: the function to call to parse the event information
+ * @context: the data to be passed to @func
+ *
+ * This function removes existing event handler (parser).
+ *
+ * If @id is >= 0, then it is used to find the event.
+ * else @sys_name and @event_name are used.
+ *
+ * Returns 0 if handler was removed successfully, -1 if event was not found.
+ */
+int pevent_unregister_event_handler(struct pevent *pevent, int id,
+				    const char *sys_name, const char *event_name,
+				    pevent_event_handler_func func, void *context)
+{
+	struct event_format *event;
+	struct event_handler *handle;
+	struct event_handler **next;
+
+	event = pevent_search_event(pevent, id, sys_name, event_name);
+	if (event == NULL)
+		goto not_found;
+
+	if (event->handler == func && event->context == context) {
+		pr_stat("removing override handler for event (%d) %s:%s. Going back to default handler.",
+			event->id, event->system, event->name);
+
+		event->handler = NULL;
+		event->context = NULL;
+		return 0;
+	}
+
+not_found:
+	for (next = &pevent->handlers; *next; next = &(*next)->next) {
+		handle = *next;
+		if (handle_matches(handle, id, sys_name, event_name,
+				   func, context))
+			break;
+	}
+
+	if (!(*next))
+		return -1;
+
+	*next = handle->next;
+	free_handler(handle);
+
+	return 0;
+}
+
 /**
  * pevent_alloc - create a pevent handle
  */
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index a3beca5..c48acfb 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -624,6 +624,9 @@ int pevent_print_func_field(struct trace_seq *s, const char *fmt,
 int pevent_register_event_handler(struct pevent *pevent, int id,
 				  const char *sys_name, const char *event_name,
 				  pevent_event_handler_func func, void *context);
+int pevent_unregister_event_handler(struct pevent *pevent, int id,
+				    const char *sys_name, const char *event_name,
+				    pevent_event_handler_func func, void *context);
 int pevent_register_print_function(struct pevent *pevent,
 				   pevent_func_handler func,
 				   enum pevent_func_arg_type ret_type,
-- 
cgit v0.10.2


From 20c7e5abbd0cdfaa656f46af052a6e6a8ce94775 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 16 Jan 2014 11:31:08 +0900
Subject: tools lib traceevent: Add pevent_unregister_print_function()

When a plugin unloaded it needs to unregister its print handler from
pevent.

So add an unregister function to do it.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389839478-5887-3-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index d1973cb..1587ea39 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -5560,6 +5560,29 @@ int pevent_register_print_function(struct pevent *pevent,
 	return ret;
 }
 
+/**
+ * pevent_unregister_print_function - unregister a helper function
+ * @pevent: the handle to the pevent
+ * @func: the function to process the helper function
+ * @name: the name of the helper function
+ *
+ * This function removes existing print handler for function @name.
+ *
+ * Returns 0 if the handler was removed successully, -1 otherwise.
+ */
+int pevent_unregister_print_function(struct pevent *pevent,
+				     pevent_func_handler func, char *name)
+{
+	struct pevent_function_handler *func_handle;
+
+	func_handle = find_func_handler(pevent, name);
+	if (func_handle && func_handle->func == func) {
+		remove_func_handler(pevent, name);
+		return 0;
+	}
+	return -1;
+}
+
 static struct event_format *pevent_search_event(struct pevent *pevent, int id,
 						const char *sys_name,
 						const char *event_name)
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index c48acfb..791c539 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -631,6 +631,8 @@ int pevent_register_print_function(struct pevent *pevent,
 				   pevent_func_handler func,
 				   enum pevent_func_arg_type ret_type,
 				   char *name, ...);
+int pevent_unregister_print_function(struct pevent *pevent,
+				     pevent_func_handler func, char *name);
 
 struct format_field *pevent_find_common_field(struct event_format *event, const char *name);
 struct format_field *pevent_find_field(struct event_format *event, const char *name);
-- 
cgit v0.10.2


From ac668c7b7d87c1895faf196a337b5ddfd32a0e21 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 16 Jan 2014 11:31:09 +0900
Subject: tools lib traceevent: Unregister handler when function plugin is
 unloaded

The function handler should be unregistered when the plugin is unloaded
otherwise it'll try to access invalid memory.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389839478-5887-4-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c
index 3946148..80ba4ff 100644
--- a/tools/lib/traceevent/plugin_function.c
+++ b/tools/lib/traceevent/plugin_function.c
@@ -148,6 +148,9 @@ void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
 {
 	int i, x;
 
+	pevent_unregister_event_handler(pevent, -1, "ftrace", "function",
+					function_handler, NULL);
+
 	for (i = 0; i <= cpus; i++) {
 		for (x = 0; x < fstack[i].size && fstack[i].stack[x]; x++)
 			free(fstack[i].stack[x]);
-- 
cgit v0.10.2


From 4061edaa54744dca833051119e763f073dd3c334 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 16 Jan 2014 11:31:10 +0900
Subject: tools lib traceevent: Unregister handler when hrtimer plugin is
 unloaded

The timer handlers should be unregistered when the plugin is unloaded
otherwise they'll try to access invalid memory.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389839478-5887-5-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/plugin_hrtimer.c b/tools/lib/traceevent/plugin_hrtimer.c
index 0b0ebf3..12bf14c 100644
--- a/tools/lib/traceevent/plugin_hrtimer.c
+++ b/tools/lib/traceevent/plugin_hrtimer.c
@@ -76,3 +76,13 @@ int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
 				      timer_start_handler, NULL);
 	return 0;
 }
+
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
+{
+	pevent_unregister_event_handler(pevent, -1,
+					"timer", "hrtimer_expire_entry",
+					timer_expire_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "timer", "hrtimer_start",
+					timer_start_handler, NULL);
+}
-- 
cgit v0.10.2


From 11e99c55414ebade1031a0ed3b49915824c7c3ea Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 16 Jan 2014 11:31:11 +0900
Subject: tools lib traceevent: Unregister handler when kmem plugin is unloaded

The kmem handlers should be unregistered when the plugin is unloaded
otherwise they'll try to access invalid memory.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389839478-5887-6-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/plugin_kmem.c b/tools/lib/traceevent/plugin_kmem.c
index 7115c80..70650ff 100644
--- a/tools/lib/traceevent/plugin_kmem.c
+++ b/tools/lib/traceevent/plugin_kmem.c
@@ -70,3 +70,25 @@ int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
 				      call_site_handler, NULL);
 	return 0;
 }
+
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
+{
+	pevent_unregister_event_handler(pevent, -1, "kmem", "kfree",
+					call_site_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kmem", "kmalloc",
+					call_site_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kmem", "kmalloc_node",
+					call_site_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kmem", "kmem_cache_alloc",
+					call_site_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kmem",
+					"kmem_cache_alloc_node",
+					call_site_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kmem", "kmem_cache_free",
+					call_site_handler, NULL);
+}
-- 
cgit v0.10.2


From 354a2bd0318e0758f93b8b24553f3376fa9dfa21 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 16 Jan 2014 11:31:12 +0900
Subject: tools lib traceevent: Unregister handler when kvm plugin is unloaded

The kvm handlers should be unregistered when the plugin is unloaded
otherwise they'll try to access invalid memory.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389839478-5887-7-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c
index a0e282c..9e0e8c6 100644
--- a/tools/lib/traceevent/plugin_kvm.c
+++ b/tools/lib/traceevent/plugin_kvm.c
@@ -434,3 +434,32 @@ int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
 				       PEVENT_FUNC_ARG_VOID);
 	return 0;
 }
+
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
+{
+	pevent_unregister_event_handler(pevent, -1, "kvm", "kvm_exit",
+					kvm_exit_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kvm", "kvm_emulate_insn",
+					kvm_emulate_insn_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page",
+					kvm_mmu_get_page_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_sync_page",
+					kvm_mmu_print_role, NULL);
+
+	pevent_unregister_event_handler(pevent, -1,
+					"kvmmmu", "kvm_mmu_unsync_page",
+					kvm_mmu_print_role, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_zap_page",
+					kvm_mmu_print_role, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kvmmmu",
+			"kvm_mmu_prepare_zap_page", kvm_mmu_print_role,
+			NULL);
+
+	pevent_unregister_print_function(pevent, process_is_writable_pte,
+					 "is_writable_pte");
+}
-- 
cgit v0.10.2


From 02bafd377c1137d0705f224881cd21de123204f0 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 16 Jan 2014 11:31:13 +0900
Subject: tools lib traceevent: Unregister handler when sched_switch plugin is
 unloaded

The event handlers should be unregistered when the plugin is unloaded
otherwise they'll try to access invalid memory.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389839478-5887-8-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c
index fea3724..f1ce600 100644
--- a/tools/lib/traceevent/plugin_sched_switch.c
+++ b/tools/lib/traceevent/plugin_sched_switch.c
@@ -146,3 +146,15 @@ int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
 				      sched_wakeup_handler, NULL);
 	return 0;
 }
+
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
+{
+	pevent_unregister_event_handler(pevent, -1, "sched", "sched_switch",
+					sched_switch_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "sched", "sched_wakeup",
+					sched_wakeup_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "sched", "sched_wakeup_new",
+					sched_wakeup_handler, NULL);
+}
-- 
cgit v0.10.2


From ec7c6debdd446ad2262f236d13964efae90ba0f7 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 16 Jan 2014 11:31:14 +0900
Subject: tools lib traceevent: Unregister handler when mac80211 plugin is
 unloaded

The event handler should be unregistered when the plugin is unloaded
otherwise it'll try to access invalid memory.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389839478-5887-9-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/plugin_mac80211.c b/tools/lib/traceevent/plugin_mac80211.c
index 558a3b9..7e15a0f 100644
--- a/tools/lib/traceevent/plugin_mac80211.c
+++ b/tools/lib/traceevent/plugin_mac80211.c
@@ -93,3 +93,10 @@ int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
 				      drv_bss_info_changed, NULL);
 	return 0;
 }
+
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
+{
+	pevent_unregister_event_handler(pevent, -1, "mac80211",
+					"drv_bss_info_changed",
+					drv_bss_info_changed, NULL);
+}
-- 
cgit v0.10.2


From 6024cf3898d25088b01025d72a6929839de9c7b6 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 16 Jan 2014 11:31:15 +0900
Subject: tools lib traceevent: Unregister handler when cfg80211 plugin is
 unloaded

The function handler should be unregistered when the plugin is unloaded
otherwise it'll try to access invalid memory.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389839478-5887-10-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugin_cfg80211.c
index 57e9822..c066b25 100644
--- a/tools/lib/traceevent/plugin_cfg80211.c
+++ b/tools/lib/traceevent/plugin_cfg80211.c
@@ -22,3 +22,9 @@ int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
 				       PEVENT_FUNC_ARG_VOID);
 	return 0;
 }
+
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
+{
+	pevent_unregister_print_function(pevent, process___le16_to_cpup,
+					 "__le16_to_cpup");
+}
-- 
cgit v0.10.2


From 0247a967d4c1986821b3c7cbad324468fa6f2ae3 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 16 Jan 2014 11:31:16 +0900
Subject: tools lib traceevent: Unregister handler when jbd2 plugin is is
 unloaded

The function handlers should be unregistered when the plugin unloaded
otherwise they'll try to access invalid memory.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389839478-5887-11-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/plugin_jbd2.c b/tools/lib/traceevent/plugin_jbd2.c
index 2f93f81..0db714c 100644
--- a/tools/lib/traceevent/plugin_jbd2.c
+++ b/tools/lib/traceevent/plugin_jbd2.c
@@ -66,3 +66,12 @@ int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
 				       PEVENT_FUNC_ARG_VOID);
 	return 0;
 }
+
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
+{
+	pevent_unregister_print_function(pevent, process_jbd2_dev_to_name,
+					 "jbd2_dev_to_name");
+
+	pevent_unregister_print_function(pevent, process_jiffies_to_msecs,
+					 "jiffies_to_msecs");
+}
-- 
cgit v0.10.2


From a157112cfc67b3889f6493933cbd32620aa4be18 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 16 Jan 2014 11:31:17 +0900
Subject: tools lib traceevent: Unregister handler when scsi plugin is unloaded

The function handler should be unregistered when the plugin is unloaded
otherwise it'll try to access invalid memory.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389839478-5887-12-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugin_scsi.c
index 7ef16cc..eda326f 100644
--- a/tools/lib/traceevent/plugin_scsi.c
+++ b/tools/lib/traceevent/plugin_scsi.c
@@ -421,3 +421,9 @@ int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
 				       PEVENT_FUNC_ARG_VOID);
 	return 0;
 }
+
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
+{
+	pevent_unregister_print_function(pevent, process_scsi_trace_parse_cdb,
+					 "scsi_trace_parse_cdb");
+}
-- 
cgit v0.10.2


From bf6b3a95ff439b1dcd6151b3f38810f3cec1e319 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 16 Jan 2014 11:31:18 +0900
Subject: tools lib traceevent: Unregister handler when xen plugin is unloaded

The function handler should be unregistered when the plugin is unloaded
otherwise it'll try to access invalid memory.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1389839478-5887-13-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/lib/traceevent/plugin_xen.c b/tools/lib/traceevent/plugin_xen.c
index e779429..3a413ea 100644
--- a/tools/lib/traceevent/plugin_xen.c
+++ b/tools/lib/traceevent/plugin_xen.c
@@ -128,3 +128,9 @@ int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
 				       PEVENT_FUNC_ARG_VOID);
 	return 0;
 }
+
+void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
+{
+	pevent_unregister_print_function(pevent, process_xen_hypercall_name,
+					 "xen_hypercall_name");
+}
-- 
cgit v0.10.2


From a7077234d240f16ead29ffeb3cc17ceada50ea5f Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Thu, 16 Jan 2014 10:52:53 +0900
Subject: perf tools: Add 'build-test' make target

Currently various build test can be performed using a Makefile named
tests/make, so one needs to remember and specify it with -f option on
command line.

Add the 'build-test' target in the main Makefile as a shortcut.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1389837173-3632-1-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index eefb9fb..cb2e586 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -75,6 +75,12 @@ clean:
 	$(make)
 
 #
+# The build-test target is not really parallel, don't print the jobs info:
+#
+build-test:
+	@$(MAKE) -f tests/make --no-print-directory
+
+#
 # All other targets get passed through:
 #
 %:
-- 
cgit v0.10.2


From 981d05adf2e2acc328abb929a6ed3536c0d41c5f Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Date: Thu, 16 Jan 2014 09:39:44 +0000
Subject: perf probe: Release allocated probe_trace_event if failed

To fix a memory leak, release all allocated probe_trace_event on the
error path of try_to_find_probe_trace_events.

Reported-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: "David A. Long" <dave.long@linaro.org>
Cc: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: yrl.pp-manager.tt@hitachi.com
Link: http://lkml.kernel.org/r/20140116093944.24403.30228.stgit@kbuild-fedora.novalocal
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index a4ee6b4..579b655 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -72,6 +72,7 @@ static int e_snprintf(char *str, size_t size, const char *format, ...)
 static char *synthesize_perf_probe_point(struct perf_probe_point *pp);
 static int convert_name_to_addr(struct perf_probe_event *pev,
 				const char *exec);
+static void clear_probe_trace_event(struct probe_trace_event *tev);
 static struct machine machine;
 
 /* Initialize symbol maps and path of vmlinux/modules */
@@ -407,6 +408,14 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
 	return ret;
 }
 
+static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
+{
+	int i;
+
+	for (i = 0; i < ntevs; i++)
+		clear_probe_trace_event(tevs + i);
+}
+
 /* Try to find perf_probe_event with debuginfo */
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 					  struct probe_trace_event **tevs,
@@ -442,6 +451,10 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 				ret = add_module_to_probe_trace_events(*tevs,
 						 ntevs, target);
 		}
+		if (ret < 0) {
+			clear_probe_trace_events(*tevs, ntevs);
+			zfree(tevs);
+		}
 		return ret < 0 ? ret : ntevs;
 	}
 
-- 
cgit v0.10.2


From e53b00d382f4d8f55bcae301f49863c469fdff65 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Date: Thu, 16 Jan 2014 09:39:47 +0000
Subject: perf probe: Release all dynamically allocated parameters

To fix a memory leak, release all dynamically allocated
options/parameters in params data structure. This also
introduces/exports some init/clear routines.

Reported-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: "David A. Long" <dave.long@linaro.org>
Cc: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: yrl.pp-manager.tt@hitachi.com
Link: http://lkml.kernel.org/r/20140116093947.24403.80118.stgit@kbuild-fedora.novalocal
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 43ff33d..7894888 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -59,7 +59,7 @@ static struct {
 	struct perf_probe_event events[MAX_PROBES];
 	struct strlist *dellist;
 	struct line_range line_range;
-	const char *target;
+	char *target;
 	int max_probe_points;
 	struct strfilter *filter;
 } params;
@@ -98,7 +98,10 @@ static int set_target(const char *ptr)
 	 * short module name.
 	 */
 	if (!params.target && ptr && *ptr == '/') {
-		params.target = ptr;
+		params.target = strdup(ptr);
+		if (!params.target)
+			return -ENOMEM;
+
 		found = 1;
 		buf = ptr + (strlen(ptr) - 3);
 
@@ -116,6 +119,9 @@ static int parse_probe_event_argv(int argc, const char **argv)
 	char *buf;
 
 	found_target = set_target(argv[0]);
+	if (found_target < 0)
+		return found_target;
+
 	if (found_target && argc == 1)
 		return 0;
 
@@ -217,7 +223,6 @@ static int opt_show_lines(const struct option *opt __maybe_unused,
 
 	params.show_lines = true;
 	ret = parse_line_range_desc(str, &params.line_range);
-	INIT_LIST_HEAD(&params.line_range.line_list);
 
 	return ret;
 }
@@ -263,7 +268,28 @@ static int opt_set_filter(const struct option *opt __maybe_unused,
 	return 0;
 }
 
-int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
+static void init_params(void)
+{
+	line_range__init(&params.line_range);
+}
+
+static void cleanup_params(void)
+{
+	int i;
+
+	for (i = 0; i < params.nevents; i++)
+		clear_perf_probe_event(params.events + i);
+	if (params.dellist)
+		strlist__delete(params.dellist);
+	line_range__clear(&params.line_range);
+	free(params.target);
+	if (params.filter)
+		strfilter__delete(params.filter);
+	memset(&params, 0, sizeof(params));
+}
+
+static int
+__cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	const char * const probe_usage[] = {
 		"perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]",
@@ -417,6 +443,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		ret = show_available_funcs(params.target, params.filter,
 					params.uprobes);
 		strfilter__delete(params.filter);
+		params.filter = NULL;
 		if (ret < 0)
 			pr_err("  Error: Failed to show functions."
 			       " (%d)\n", ret);
@@ -456,6 +483,7 @@ int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 					  params.filter,
 					  params.show_ext_vars);
 		strfilter__delete(params.filter);
+		params.filter = NULL;
 		if (ret < 0)
 			pr_err("  Error: Failed to show vars. (%d)\n", ret);
 		return ret;
@@ -464,7 +492,6 @@ int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	if (params.dellist) {
 		ret = del_perf_probe_events(params.dellist);
-		strlist__delete(params.dellist);
 		if (ret < 0) {
 			pr_err("  Error: Failed to delete events. (%d)\n", ret);
 			return ret;
@@ -483,3 +510,14 @@ int cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	}
 	return 0;
 }
+
+int cmd_probe(int argc, const char **argv, const char *prefix)
+{
+	int ret;
+
+	init_params();
+	ret = __cmd_probe(argc, argv, prefix);
+	cleanup_params();
+
+	return ret;
+}
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 579b655..c68711c 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -794,6 +794,28 @@ int show_available_vars(struct perf_probe_event *pevs __maybe_unused,
 }
 #endif
 
+void line_range__clear(struct line_range *lr)
+{
+	struct line_node *ln;
+
+	free(lr->function);
+	free(lr->file);
+	free(lr->path);
+	free(lr->comp_dir);
+	while (!list_empty(&lr->line_list)) {
+		ln = list_first_entry(&lr->line_list, struct line_node, list);
+		list_del(&ln->list);
+		free(ln);
+	}
+	memset(lr, 0, sizeof(*lr));
+}
+
+void line_range__init(struct line_range *lr)
+{
+	memset(lr, 0, sizeof(*lr));
+	INIT_LIST_HEAD(&lr->line_list);
+}
+
 static int parse_line_num(char **ptr, int *val, const char *what)
 {
 	const char *start = *ptr;
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index d481c46..fcaf727 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -120,6 +120,12 @@ extern void clear_perf_probe_event(struct perf_probe_event *pev);
 /* Command string to line-range */
 extern int parse_line_range_desc(const char *cmd, struct line_range *lr);
 
+/* Release line range members */
+extern void line_range__clear(struct line_range *lr);
+
+/* Initialize line range */
+extern void line_range__init(struct line_range *lr);
+
 /* Internal use: Return kernel/module path */
 extern const char *kernel_get_module_path(const char *module);
 
-- 
cgit v0.10.2


From 99ca423387a3e718f9887a99475cb5271bc610f2 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Date: Thu, 16 Jan 2014 09:39:49 +0000
Subject: perf symbols: Export elf_section_by_name and reuse

Remove duplicated elf_section_by_name() functions from unwind.c and
probe-event.c and use one exported elf_section_by_name() instance
defined in symbol-elf.c.

Note that this also moves get_text_start_address() to merge
HAVE_DWARF_SUPPORT defined area.

Reported-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: "David A. Long" <dave.long@linaro.org>
Cc: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: yrl.pp-manager.tt@hitachi.com
Link: http://lkml.kernel.org/r/20140116093949.24403.38093.stgit@kbuild-fedora.novalocal
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index c68711c..a8a9b6c 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -173,54 +173,6 @@ const char *kernel_get_module_path(const char *module)
 	return (dso) ? dso->long_name : NULL;
 }
 
-#ifdef HAVE_DWARF_SUPPORT
-/* Copied from unwind.c */
-static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
-				    GElf_Shdr *shp, const char *name)
-{
-	Elf_Scn *sec = NULL;
-
-	while ((sec = elf_nextscn(elf, sec)) != NULL) {
-		char *str;
-
-		gelf_getshdr(sec, shp);
-		str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name);
-		if (!strcmp(name, str))
-			break;
-	}
-
-	return sec;
-}
-
-static int get_text_start_address(const char *exec, unsigned long *address)
-{
-	Elf *elf;
-	GElf_Ehdr ehdr;
-	GElf_Shdr shdr;
-	int fd, ret = -ENOENT;
-
-	fd = open(exec, O_RDONLY);
-	if (fd < 0)
-		return -errno;
-
-	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
-	if (elf == NULL)
-		return -EINVAL;
-
-	if (gelf_getehdr(elf, &ehdr) == NULL)
-		goto out;
-
-	if (!elf_section_by_name(elf, &ehdr, &shdr, ".text"))
-		goto out;
-
-	*address = shdr.sh_addr - shdr.sh_offset;
-	ret = 0;
-out:
-	elf_end(elf);
-	return ret;
-}
-#endif
-
 static int init_user_exec(void)
 {
 	int ret = 0;
@@ -341,6 +293,34 @@ static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
 	return 0;
 }
 
+static int get_text_start_address(const char *exec, unsigned long *address)
+{
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	GElf_Shdr shdr;
+	int fd, ret = -ENOENT;
+
+	fd = open(exec, O_RDONLY);
+	if (fd < 0)
+		return -errno;
+
+	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+	if (elf == NULL)
+		return -EINVAL;
+
+	if (gelf_getehdr(elf, &ehdr) == NULL)
+		goto out;
+
+	if (!elf_section_by_name(elf, &ehdr, &shdr, ".text", NULL))
+		goto out;
+
+	*address = shdr.sh_addr - shdr.sh_offset;
+	ret = 0;
+out:
+	elf_end(elf);
+	return ret;
+}
+
 static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
 					  int ntevs, const char *exec)
 {
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 4b0a127..7594567 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -136,9 +136,8 @@ static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr)
 	return -1;
 }
 
-static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
-				    GElf_Shdr *shp, const char *name,
-				    size_t *idx)
+Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
+			     GElf_Shdr *shp, const char *name, size_t *idx)
 {
 	Elf_Scn *sec = NULL;
 	size_t cnt = 1;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index cbd6803..fffe288 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -52,6 +52,11 @@ static inline char *bfd_demangle(void __maybe_unused *v,
 # define PERF_ELF_C_READ_MMAP ELF_C_READ
 #endif
 
+#ifdef HAVE_LIBELF_SUPPORT
+extern Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
+				GElf_Shdr *shp, const char *name, size_t *idx);
+#endif
+
 #ifndef DMGL_PARAMS
 #define DMGL_PARAMS      (1 << 0)       /* Include function args */
 #define DMGL_ANSI        (1 << 1)       /* Include const, volatile, etc */
diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind.c
index 416f22b..742f23b 100644
--- a/tools/perf/util/unwind.c
+++ b/tools/perf/util/unwind.c
@@ -28,6 +28,7 @@
 #include "session.h"
 #include "perf_regs.h"
 #include "unwind.h"
+#include "symbol.h"
 #include "util.h"
 
 extern int
@@ -158,23 +159,6 @@ static int __dw_read_encoded_value(u8 **p, u8 *end, u64 *val,
 	__v;                                                    \
 	})
 
-static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
-				    GElf_Shdr *shp, const char *name)
-{
-	Elf_Scn *sec = NULL;
-
-	while ((sec = elf_nextscn(elf, sec)) != NULL) {
-		char *str;
-
-		gelf_getshdr(sec, shp);
-		str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name);
-		if (!strcmp(name, str))
-			break;
-	}
-
-	return sec;
-}
-
 static u64 elf_section_offset(int fd, const char *name)
 {
 	Elf *elf;
@@ -190,7 +174,7 @@ static u64 elf_section_offset(int fd, const char *name)
 		if (gelf_getehdr(elf, &ehdr) == NULL)
 			break;
 
-		if (!elf_section_by_name(elf, &ehdr, &shdr, name))
+		if (!elf_section_by_name(elf, &ehdr, &shdr, name, NULL))
 			break;
 
 		offset = shdr.sh_offset;
-- 
cgit v0.10.2


From 3178f58b989430fd0721df97bf21cf1c0e8cc419 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Tue, 14 Jan 2014 16:37:14 +0100
Subject: perf tools: Do proper comm override error handling

The comm overriding API ignores memory allocation failures by silently
keeping the previous and out of date comm.

As a result, the user may get buggy events without ever being notified
about the problem and its source.

Lets start to fix this by propagating the error from the API. Not all
callers may be doing proper error handling on comm set yet but this is
the first step toward it.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1389713836-13375-2-git-send-email-fweisbec@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index 67d1e40..f9e7776 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -94,19 +94,20 @@ struct comm *comm__new(const char *str, u64 timestamp)
 	return comm;
 }
 
-void comm__override(struct comm *comm, const char *str, u64 timestamp)
+int comm__override(struct comm *comm, const char *str, u64 timestamp)
 {
-	struct comm_str *old = comm->comm_str;
+	struct comm_str *new, *old = comm->comm_str;
 
-	comm->comm_str = comm_str__findnew(str, &comm_str_root);
-	if (!comm->comm_str) {
-		comm->comm_str = old;
-		return;
-	}
+	new = comm_str__findnew(str, &comm_str_root);
+	if (!new)
+		return -ENOMEM;
 
-	comm->start = timestamp;
-	comm_str__get(comm->comm_str);
+	comm_str__get(new);
 	comm_str__put(old);
+	comm->comm_str = new;
+	comm->start = timestamp;
+
+	return 0;
 }
 
 void comm__free(struct comm *comm)
diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h
index 7a86e56..fac5bd5 100644
--- a/tools/perf/util/comm.h
+++ b/tools/perf/util/comm.h
@@ -16,6 +16,6 @@ struct comm {
 void comm__free(struct comm *comm);
 struct comm *comm__new(const char *str, u64 timestamp);
 const char *comm__str(const struct comm *comm);
-void comm__override(struct comm *comm, const char *str, u64 timestamp);
+int comm__override(struct comm *comm, const char *str, u64 timestamp);
 
 #endif  /* __PERF_COMM_H */
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index e394861..0358882 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -66,10 +66,13 @@ struct comm *thread__comm(const struct thread *thread)
 int thread__set_comm(struct thread *thread, const char *str, u64 timestamp)
 {
 	struct comm *new, *curr = thread__comm(thread);
+	int err;
 
 	/* Override latest entry if it had no specific time coverage */
 	if (!curr->start) {
-		comm__override(curr, str, timestamp);
+		err = comm__override(curr, str, timestamp);
+		if (err)
+			return err;
 	} else {
 		new = comm__new(str, timestamp);
 		if (!new)
-- 
cgit v0.10.2


From ca1e631c3acf80bc5f5934ce9054a9b4880c96e1 Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@linux.intel.com>
Date: Thu, 16 Jan 2014 13:00:21 -0800
Subject: x86, tsc, apic: Unbreak static (MSR) calibration when
 CONFIG_X86_LOCAL_APIC=n

If we aren't going to use the local APIC anyway, we obviously don't
care about its timer frequency.

Link: http://lkml.kernel.org/r/tip-rgm7xmg7k6qnjlw3ynkcjsmh@git.kernel.org
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Cc: Bin Gao <bin.gao@intel.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index c502772..8b5434f 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -118,8 +118,10 @@ int try_msr_calibrate_tsc(unsigned long *fast_calibrate)
 	*fast_calibrate = freq * ratio;
 	pr_info("TSC runs at %lu KHz\n", *fast_calibrate);
 
+#ifdef CONFIG_X86_LOCAL_APIC
 	lapic_timer_frequency = (freq * 1000) / HZ;
 	pr_info("lapic_timer_frequency = %d\n", lapic_timer_frequency);
+#endif
 
 	return 1;
 }
-- 
cgit v0.10.2


From acb20d7395f75b0fdb5b300f9fb3b9c6054fb04f Mon Sep 17 00:00:00 2001
From: David Cohen <david.a.cohen@linux.intel.com>
Date: Thu, 16 Jan 2014 15:07:02 -0800
Subject: x86, intel-mid: sfi_handle_*_dev() should check for pdata error code

When Intel MID finds a match between SFI table from FW and registered
SFI devices, it will always register a device regardless the platform
code was successful or not.

This patch adds an extra option for platform code to return error code
and abort device registration on SFI table parsing.

This patch does not contain any functional changes for current intel
mid platform code.

Signed-off-by: David Cohen <david.a.cohen@linux.intel.com>
Link: http://lkml.kernel.org/r/1389913624-9149-2-git-send-email-david.a.cohen@linux.intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c
index 80a5228..1d5d20b 100644
--- a/arch/x86/platform/intel-mid/sfi.c
+++ b/arch/x86/platform/intel-mid/sfi.c
@@ -337,6 +337,8 @@ static void __init sfi_handle_ipc_dev(struct sfi_device_table_entry *pentry,
 	pr_debug("IPC bus, name = %16.16s, irq = 0x%2x\n",
 		pentry->name, pentry->irq);
 	pdata = intel_mid_sfi_get_pdata(dev, pentry);
+	if (IS_ERR(pdata))
+		return;
 
 	pdev = platform_device_alloc(pentry->name, 0);
 	if (pdev == NULL) {
@@ -370,6 +372,8 @@ static void __init sfi_handle_spi_dev(struct sfi_device_table_entry *pentry,
 		spi_info.chip_select);
 
 	pdata = intel_mid_sfi_get_pdata(dev, &spi_info);
+	if (IS_ERR(pdata))
+		return;
 
 	spi_info.platform_data = pdata;
 	if (dev->delay)
@@ -395,6 +399,8 @@ static void __init sfi_handle_i2c_dev(struct sfi_device_table_entry *pentry,
 		i2c_info.addr);
 	pdata = intel_mid_sfi_get_pdata(dev, &i2c_info);
 	i2c_info.platform_data = pdata;
+	if (IS_ERR(pdata))
+		return;
 
 	if (dev->delay)
 		intel_scu_i2c_device_register(pentry->host_num, &i2c_info);
-- 
cgit v0.10.2


From a957a14bb4ca976cbaaff3594ef5b8f8f7f65804 Mon Sep 17 00:00:00 2001
From: David Cohen <david.a.cohen@linux.intel.com>
Date: Thu, 16 Jan 2014 15:07:03 -0800
Subject: x86, intel-mid: Check get_gpio_by_name() error code on platform code

This patch does cleanup on all intel mid platform code that uses
gpio_get_by_name() function. From now on they should check for any error
code instead of only hardcoded -1.

There are no functional changes from this change.

Signed-off-by: David Cohen <david.a.cohen@linux.intel.com>
Link: http://lkml.kernel.org/r/1389913624-9149-3-git-send-email-david.a.cohen@linux.intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/platform/intel-mid/device_libs/platform_emc1403.c b/arch/x86/platform/intel-mid/device_libs/platform_emc1403.c
index 0d942c1..69a7836 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_emc1403.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_emc1403.c
@@ -22,7 +22,9 @@ static void __init *emc1403_platform_data(void *info)
 	int intr = get_gpio_by_name("thermal_int");
 	int intr2nd = get_gpio_by_name("thermal_alert");
 
-	if (intr == -1 || intr2nd == -1)
+	if (intr < 0)
+		return NULL;
+	if (intr2nd < 0)
 		return NULL;
 
 	i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET;
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c b/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c
index a013a48..dccae6b 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c
@@ -66,7 +66,7 @@ static int __init pb_keys_init(void)
 		gb[i].gpio = get_gpio_by_name(gb[i].desc);
 		pr_debug("info[%2d]: name = %s, gpio = %d\n", i, gb[i].desc,
 					gb[i].gpio);
-		if (gb[i].gpio == -1)
+		if (gb[i].gpio < 0)
 			continue;
 
 		if (i != good)
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_lis331.c b/arch/x86/platform/intel-mid/device_libs/platform_lis331.c
index 15278c1..54226de 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_lis331.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_lis331.c
@@ -21,7 +21,9 @@ static void __init *lis331dl_platform_data(void *info)
 	int intr = get_gpio_by_name("accel_int");
 	int intr2nd = get_gpio_by_name("accel_2");
 
-	if (intr == -1 || intr2nd == -1)
+	if (intr < 0)
+		return NULL;
+	if (intr2nd < 0)
 		return NULL;
 
 	i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET;
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_max7315.c b/arch/x86/platform/intel-mid/device_libs/platform_max7315.c
index 94ade10..2c8acbc 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_max7315.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_max7315.c
@@ -48,7 +48,7 @@ static void __init *max7315_platform_data(void *info)
 	gpio_base = get_gpio_by_name(base_pin_name);
 	intr = get_gpio_by_name(intr_pin_name);
 
-	if (gpio_base == -1)
+	if (gpio_base < 0)
 		return NULL;
 	max7315->gpio_base = gpio_base;
 	if (intr != -1) {
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c b/arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c
index dd28d63..cfe9a47 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c
@@ -19,7 +19,7 @@ static void *mpu3050_platform_data(void *info)
 	struct i2c_board_info *i2c_info = info;
 	int intr = get_gpio_by_name("mpu3050_int");
 
-	if (intr == -1)
+	if (intr < 0)
 		return NULL;
 
 	i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET;
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c b/arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c
index d87182a..65c2a9a 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c
@@ -26,7 +26,7 @@ static void __init *pmic_gpio_platform_data(void *info)
 	static struct intel_pmic_gpio_platform_data pmic_gpio_pdata;
 	int gpio_base = get_gpio_by_name("pmic_gpio_base");
 
-	if (gpio_base == -1)
+	if (gpio_base < 0)
 		gpio_base = 64;
 	pmic_gpio_pdata.gpio_base = gpio_base;
 	pmic_gpio_pdata.irq_base = gpio_base + INTEL_MID_IRQ_OFFSET;
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_tca6416.c b/arch/x86/platform/intel-mid/device_libs/platform_tca6416.c
index 22881c9..33be0b3 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_tca6416.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_tca6416.c
@@ -34,10 +34,10 @@ static void *tca6416_platform_data(void *info)
 	gpio_base = get_gpio_by_name(base_pin_name);
 	intr = get_gpio_by_name(intr_pin_name);
 
-	if (gpio_base == -1)
+	if (gpio_base < 0)
 		return NULL;
 	tca6416.gpio_base = gpio_base;
-	if (intr != -1) {
+	if (intr >= 0) {
 		i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET;
 		tca6416.irq_base = gpio_base + INTEL_MID_IRQ_OFFSET;
 	} else {
-- 
cgit v0.10.2


From 28c6a39b3367f29462cd586785dc445cd6b5ac23 Mon Sep 17 00:00:00 2001
From: David Cohen <david.a.cohen@linux.intel.com>
Date: Thu, 16 Jan 2014 15:07:04 -0800
Subject: x86, intel-mid: Return proper error code from get_gpio_by_name()

This patch cleans up get_gpio_by_name() to return an error code
instead of hardcoded -1.

Signed-off-by: David Cohen <david.a.cohen@linux.intel.com>
Link: http://lkml.kernel.org/r/1389913624-9149-4-git-send-email-david.a.cohen@linux.intel.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c
index 1d5d20b..438306e 100644
--- a/arch/x86/platform/intel-mid/sfi.c
+++ b/arch/x86/platform/intel-mid/sfi.c
@@ -224,7 +224,7 @@ int get_gpio_by_name(const char *name)
 		if (!strncmp(name, pentry->pin_name, SFI_NAME_LEN))
 			return pentry->pin_no;
 	}
-	return -1;
+	return -EINVAL;
 }
 
 void __init intel_scu_device_register(struct platform_device *pdev)
-- 
cgit v0.10.2


From 38a529b5d42e4cfc5ac94844e61335a00eb2d320 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Thu, 16 Jan 2014 14:39:39 +0200
Subject: e1000e: Fix compilation warning when !CONFIG_PM_SLEEP
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 7509963c703b (e1000e: Fix a compile flag mis-match for
suspend/resume) moved suspend and resume hooks to be available when
CONFIG_PM is set. However, it can be set even if CONFIG_PM_SLEEP is not set
causing following warnings to be emitted:

drivers/net/ethernet/intel/e1000e/netdev.c:6178:12: warning:
  	‘e1000_suspend’ defined but not used [-Wunused-function]

drivers/net/ethernet/intel/e1000e/netdev.c:6185:12: warning:
	‘e1000_resume’ defined but not used [-Wunused-function]

To fix this make the hooks to be available only when CONFIG_PM_SLEEP is set
and remove CONFIG_PM wrapping from driver ops because this is already
handled by SET_SYSTEM_SLEEP_PM_OPS() and SET_RUNTIME_PM_OPS().

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Cc: Dave Ertman <davidx.m.ertman@intel.com>
Cc: Aaron Brown <aaron.f.brown@intel.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index c30d41d..6d14eea 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -6174,7 +6174,7 @@ static int __e1000_resume(struct pci_dev *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int e1000_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
@@ -6193,7 +6193,7 @@ static int e1000_resume(struct device *dev)
 
 	return __e1000_resume(pdev);
 }
-#endif /* CONFIG_PM */
+#endif /* CONFIG_PM_SLEEP */
 
 #ifdef CONFIG_PM_RUNTIME
 static int e1000_runtime_suspend(struct device *dev)
@@ -7015,13 +7015,11 @@ static DEFINE_PCI_DEVICE_TABLE(e1000_pci_tbl) = {
 };
 MODULE_DEVICE_TABLE(pci, e1000_pci_tbl);
 
-#ifdef CONFIG_PM
 static const struct dev_pm_ops e1000_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(e1000_suspend, e1000_resume)
 	SET_RUNTIME_PM_OPS(e1000_runtime_suspend, e1000_runtime_resume,
 			   e1000_idle)
 };
-#endif
 
 /* PCI Device API Driver */
 static struct pci_driver e1000_driver = {
@@ -7029,11 +7027,9 @@ static struct pci_driver e1000_driver = {
 	.id_table = e1000_pci_tbl,
 	.probe    = e1000_probe,
 	.remove   = e1000_remove,
-#ifdef CONFIG_PM
 	.driver   = {
 		.pm = &e1000_pm_ops,
 	},
-#endif
 	.shutdown = e1000_shutdown,
 	.err_handler = &e1000_err_handler
 };
-- 
cgit v0.10.2


From ee87c751d88f9b03fee7349556817fe80c113b32 Mon Sep 17 00:00:00 2001
From: Fengguang Wu <fengguang.wu@intel.com>
Date: Thu, 16 Jan 2014 16:13:08 -0800
Subject: x86, intel_mid: Replace memcpy with struct assignment

This is a cleanup proposed by coccinelle. It replaces memcpy with struct
assignment on intel-mid's sfi layer.

Generated by: coccinelle/misc/memcpy-assign.cocci

Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Link: http://lkml.kernel.org/r/1389917588-9785-1-git-send-email-david.a.cohen@linux.intel.com
Signed-off-by: David Cohen <david.a.cohen@linux.intel.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c
index 438306e..994c40b 100644
--- a/arch/x86/platform/intel-mid/sfi.c
+++ b/arch/x86/platform/intel-mid/sfi.c
@@ -250,7 +250,7 @@ static void __init intel_scu_spi_device_register(struct spi_board_info *sdev)
 			sdev->modalias);
 		return;
 	}
-	memcpy(new_dev, sdev, sizeof(*sdev));
+	*new_dev = *sdev;
 
 	spi_devs[spi_next_dev++] = new_dev;
 }
@@ -271,7 +271,7 @@ static void __init intel_scu_i2c_device_register(int bus,
 			idev->type);
 		return;
 	}
-	memcpy(new_dev, idev, sizeof(*idev));
+	*new_dev = *idev;
 
 	i2c_bus[i2c_next_dev] = bus;
 	i2c_devs[i2c_next_dev++] = new_dev;
-- 
cgit v0.10.2


From d1969a84dd6a44d375aa82bba7d6c38713a429c3 Mon Sep 17 00:00:00 2001
From: Hugh Dickins <hughd@google.com>
Date: Thu, 16 Jan 2014 15:26:48 -0800
Subject: percpu_counter: unbreak __percpu_counter_add()

Commit 74e72f894d56 ("lib/percpu_counter.c: fix __percpu_counter_add()")
looked very plausible, but its arithmetic was badly wrong: obvious once
you see the fix, but maddening to get there from the weird tmpfs ENOSPCs

Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Ming Lei <tom.leiming@gmail.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Shaohua Li <shli@fusionio.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Fan Du <fan.du@windriver.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 1da85bb..8280a5d 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -82,7 +82,7 @@ void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch)
 		unsigned long flags;
 		raw_spin_lock_irqsave(&fbc->lock, flags);
 		fbc->count += count;
-		 __this_cpu_sub(*fbc->counters, count);
+		__this_cpu_sub(*fbc->counters, count - amount);
 		raw_spin_unlock_irqrestore(&fbc->lock, flags);
 	} else {
 		this_cpu_add(*fbc->counters, amount);
-- 
cgit v0.10.2


From b965bb41061ad8d3eafda6e7feef89279fcd3916 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Tue, 14 Jan 2014 16:37:15 +0100
Subject: perf callchain: Spare double comparison of callchain first entry

When a new callchain child branch matches an existing one in the rbtree,
the comparison of its first entry is performed twice:

1) From append_chain_children() on branch lookup

2) If 1) reports a match, append_chain() then compares all entries of
the new branch against the matching node in the rbtree, and this
comparison includes the first entry of the new branch again.

Lets shortcut this by performing the whole comparison only from
append_chain() which then returns the result of the comparison between
the first entry of the new branch and the iterating node in the rbtree.
If the first entry matches, the lookup on the current level of siblings
stops and propagates to the children of the matching nodes.

This results in less comparisons performed by the CPU.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1389713836-13375-3-git-send-email-fweisbec@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 9eb4f57..662867d 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -15,6 +15,8 @@
 #include <errno.h>
 #include <math.h>
 
+#include "asm/bug.h"
+
 #include "hist.h"
 #include "util.h"
 #include "sort.h"
@@ -358,19 +360,14 @@ append_chain_children(struct callchain_node *root,
 	/* lookup in childrens */
 	while (*p) {
 		s64 ret;
-		struct callchain_list *cnode;
 
 		parent = *p;
 		rnode = rb_entry(parent, struct callchain_node, rb_node_in);
-		cnode = list_first_entry(&rnode->val, struct callchain_list,
-					 list);
 
-		/* just check first entry */
-		ret = match_chain(node, cnode);
-		if (ret == 0) {
-			append_chain(rnode, cursor, period);
+		/* If at least first entry matches, rely to children */
+		ret = append_chain(rnode, cursor, period);
+		if (ret == 0)
 			goto inc_children_hit;
-		}
 
 		if (ret < 0)
 			p = &parent->rb_left;
@@ -396,6 +393,7 @@ append_chain(struct callchain_node *root,
 	u64 start = cursor->pos;
 	bool found = false;
 	u64 matches;
+	int cmp = 0;
 
 	/*
 	 * Lookup in the current node
@@ -410,7 +408,8 @@ append_chain(struct callchain_node *root,
 		if (!node)
 			break;
 
-		if (match_chain(node, cnode) != 0)
+		cmp = match_chain(node, cnode);
+		if (cmp)
 			break;
 
 		found = true;
@@ -420,9 +419,10 @@ append_chain(struct callchain_node *root,
 
 	/* matches not, relay no the parent */
 	if (!found) {
+		WARN_ONCE(!cmp, "Chain comparison error\n");
 		cursor->curr = curr_snap;
 		cursor->pos = start;
-		return -1;
+		return cmp;
 	}
 
 	matches = cursor->pos - start;
-- 
cgit v0.10.2


From 2a29190c040c0b11e39197c67abf6f87e0a61f9a Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Tue, 14 Jan 2014 16:37:16 +0100
Subject: perf tools: Remove unnecessary callchain cursor state restore on
 unmatch

If a new callchain branch doesn't match a single entry of the node that
it is given against comparison in append_chain(), then the cursor is
expected to be at the same position as it was before the comparison
loop.

As such, there is no need to restore the cursor position on exit in case
of non matching branches.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1389713836-13375-4-git-send-email-fweisbec@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 662867d..8d9db45 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -388,7 +388,6 @@ append_chain(struct callchain_node *root,
 	     struct callchain_cursor *cursor,
 	     u64 period)
 {
-	struct callchain_cursor_node *curr_snap = cursor->curr;
 	struct callchain_list *cnode;
 	u64 start = cursor->pos;
 	bool found = false;
@@ -420,8 +419,6 @@ append_chain(struct callchain_node *root,
 	/* matches not, relay no the parent */
 	if (!found) {
 		WARN_ONCE(!cmp, "Chain comparison error\n");
-		cursor->curr = curr_snap;
-		cursor->pos = start;
 		return cmp;
 	}
 
-- 
cgit v0.10.2


From c196403b79aa241c3fefb3ee5bb328aa7c5cc860 Mon Sep 17 00:00:00 2001
From: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Date: Thu, 16 Jan 2014 16:54:48 +0100
Subject: net: rds: fix per-cpu helper usage

commit ae4b46e9d "net: rds: use this_cpu_* per-cpu helper" broke per-cpu
handling for rds. chpfirst is the result of __this_cpu_read(), so it is
an absolute pointer and not __percpu. Therefore, __this_cpu_write()
should not operate on chpfirst, but rather on cache->percpu->first, just
like __this_cpu_read() did before.

Cc: <stable@vger.kernel.org> # 3.8+
Signed-off-byd Gerald Schaefer <gerald.schaefer@de.ibm.com>

Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 8eb9501..b7ebe23 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -421,8 +421,7 @@ static void rds_ib_recv_cache_put(struct list_head *new_item,
 				 struct rds_ib_refill_cache *cache)
 {
 	unsigned long flags;
-	struct list_head *old;
-	struct list_head __percpu *chpfirst;
+	struct list_head *old, *chpfirst;
 
 	local_irq_save(flags);
 
@@ -432,7 +431,7 @@ static void rds_ib_recv_cache_put(struct list_head *new_item,
 	else /* put on front */
 		list_add_tail(new_item, chpfirst);
 
-	__this_cpu_write(chpfirst, new_item);
+	__this_cpu_write(cache->percpu->first, new_item);
 	__this_cpu_inc(cache->percpu->count);
 
 	if (__this_cpu_read(cache->percpu->count) < RDS_IB_RECYCLE_BATCH_COUNT)
@@ -452,7 +451,7 @@ static void rds_ib_recv_cache_put(struct list_head *new_item,
 	} while (old);
 
 
-	__this_cpu_write(chpfirst, NULL);
+	__this_cpu_write(cache->percpu->first, NULL);
 	__this_cpu_write(cache->percpu->count, 0);
 end:
 	local_irq_restore(flags);
-- 
cgit v0.10.2


From 77f99ad16a07aa062c2d30fae57b1fee456f6ef6 Mon Sep 17 00:00:00 2001
From: Christoph Paasch <christoph.paasch@uclouvain.be>
Date: Thu, 16 Jan 2014 20:01:21 +0100
Subject: tcp: metrics: Avoid duplicate entries with the same destination-IP

Because the tcp-metrics is an RCU-list, it may be that two
soft-interrupts are inside __tcp_get_metrics() for the same
destination-IP at the same time. If this destination-IP is not yet part of
the tcp-metrics, both soft-interrupts will end up in tcpm_new and create
a new entry for this IP.
So, we will have two tcp-metrics with the same destination-IP in the list.

This patch checks twice __tcp_get_metrics(). First without holding the
lock, then while holding the lock. The second one is there to confirm
that the entry has not been added by another soft-irq while waiting for
the spin-lock.

Fixes: 51c5d0c4b169b (tcp: Maintain dynamic metrics in local cache.)
Signed-off-by: Christoph Paasch <christoph.paasch@uclouvain.be>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 0649373..098b3a2 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -22,6 +22,9 @@
 
 int sysctl_tcp_nometrics_save __read_mostly;
 
+static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *addr,
+						   struct net *net, unsigned int hash);
+
 struct tcp_fastopen_metrics {
 	u16	mss;
 	u16	syn_loss:10;		/* Recurring Fast Open SYN losses */
@@ -130,16 +133,41 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst,
 	}
 }
 
+#define TCP_METRICS_TIMEOUT		(60 * 60 * HZ)
+
+static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst)
+{
+	if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT)))
+		tcpm_suck_dst(tm, dst, false);
+}
+
+#define TCP_METRICS_RECLAIM_DEPTH	5
+#define TCP_METRICS_RECLAIM_PTR		(struct tcp_metrics_block *) 0x1UL
+
 static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst,
 					  struct inetpeer_addr *addr,
-					  unsigned int hash,
-					  bool reclaim)
+					  unsigned int hash)
 {
 	struct tcp_metrics_block *tm;
 	struct net *net;
+	bool reclaim = false;
 
 	spin_lock_bh(&tcp_metrics_lock);
 	net = dev_net(dst->dev);
+
+	/* While waiting for the spin-lock the cache might have been populated
+	 * with this entry and so we have to check again.
+	 */
+	tm = __tcp_get_metrics(addr, net, hash);
+	if (tm == TCP_METRICS_RECLAIM_PTR) {
+		reclaim = true;
+		tm = NULL;
+	}
+	if (tm) {
+		tcpm_check_stamp(tm, dst);
+		goto out_unlock;
+	}
+
 	if (unlikely(reclaim)) {
 		struct tcp_metrics_block *oldest;
 
@@ -169,17 +197,6 @@ out_unlock:
 	return tm;
 }
 
-#define TCP_METRICS_TIMEOUT		(60 * 60 * HZ)
-
-static void tcpm_check_stamp(struct tcp_metrics_block *tm, struct dst_entry *dst)
-{
-	if (tm && unlikely(time_after(jiffies, tm->tcpm_stamp + TCP_METRICS_TIMEOUT)))
-		tcpm_suck_dst(tm, dst, false);
-}
-
-#define TCP_METRICS_RECLAIM_DEPTH	5
-#define TCP_METRICS_RECLAIM_PTR		(struct tcp_metrics_block *) 0x1UL
-
 static struct tcp_metrics_block *tcp_get_encode(struct tcp_metrics_block *tm, int depth)
 {
 	if (tm)
@@ -282,7 +299,6 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 	struct inetpeer_addr addr;
 	unsigned int hash;
 	struct net *net;
-	bool reclaim;
 
 	addr.family = sk->sk_family;
 	switch (addr.family) {
@@ -304,13 +320,10 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 	hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log);
 
 	tm = __tcp_get_metrics(&addr, net, hash);
-	reclaim = false;
-	if (tm == TCP_METRICS_RECLAIM_PTR) {
-		reclaim = true;
+	if (tm == TCP_METRICS_RECLAIM_PTR)
 		tm = NULL;
-	}
 	if (!tm && create)
-		tm = tcpm_new(dst, &addr, hash, reclaim);
+		tm = tcpm_new(dst, &addr, hash);
 	else
 		tcpm_check_stamp(tm, dst);
 
-- 
cgit v0.10.2


From 11ffff752c6a5adc86f7dd397b2f75af8f917c51 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Thu, 16 Jan 2014 20:13:04 +0100
Subject: ipv6: simplify detection of first operational link-local address on
 interface

In commit 1ec047eb4751e3 ("ipv6: introduce per-interface counter for
dad-completed ipv6 addresses") I build the detection of the first
operational link-local address much to complex. Additionally this code
now has a race condition.

Replace it with a much simpler variant, which just scans the address
list when duplicate address detection completes, to check if this is
the first valid link local address and send RS and MLD reports then.

Fixes: 1ec047eb4751e3 ("ipv6: introduce per-interface counter for dad-completed ipv6 addresses")
Reported-by: Jiri Pirko <jiri@resnulli.us>
Cc: Flavio Leitner <fbl@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Flavio Leitner <fbl@redhat.com>
Acked-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index 76d5427..65bb130 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -165,7 +165,6 @@ struct inet6_dev {
 	struct net_device	*dev;
 
 	struct list_head	addr_list;
-	int			valid_ll_addr_cnt;
 
 	struct ifmcaddr6	*mc_list;
 	struct ifmcaddr6	*mc_tomb;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index abe46a4..4b6b720 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3189,6 +3189,22 @@ out:
 	in6_ifa_put(ifp);
 }
 
+/* ifp->idev must be at least read locked */
+static bool ipv6_lonely_lladdr(struct inet6_ifaddr *ifp)
+{
+	struct inet6_ifaddr *ifpiter;
+	struct inet6_dev *idev = ifp->idev;
+
+	list_for_each_entry(ifpiter, &idev->addr_list, if_list) {
+		if (ifp != ifpiter && ifpiter->scope == IFA_LINK &&
+		    (ifpiter->flags & (IFA_F_PERMANENT|IFA_F_TENTATIVE|
+				       IFA_F_OPTIMISTIC|IFA_F_DADFAILED)) ==
+		    IFA_F_PERMANENT)
+			return false;
+	}
+	return true;
+}
+
 static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
 {
 	struct net_device *dev = ifp->idev->dev;
@@ -3208,14 +3224,11 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
 	 */
 
 	read_lock_bh(&ifp->idev->lock);
-	spin_lock(&ifp->lock);
-	send_mld = ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL &&
-		   ifp->idev->valid_ll_addr_cnt == 1;
+	send_mld = ifp->scope == IFA_LINK && ipv6_lonely_lladdr(ifp);
 	send_rs = send_mld &&
 		  ipv6_accept_ra(ifp->idev) &&
 		  ifp->idev->cnf.rtr_solicits > 0 &&
 		  (dev->flags&IFF_LOOPBACK) == 0;
-	spin_unlock(&ifp->lock);
 	read_unlock_bh(&ifp->idev->lock);
 
 	/* While dad is in progress mld report's source address is in6_addrany.
@@ -4512,19 +4525,6 @@ errout:
 		rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err);
 }
 
-static void update_valid_ll_addr_cnt(struct inet6_ifaddr *ifp, int count)
-{
-	write_lock_bh(&ifp->idev->lock);
-	spin_lock(&ifp->lock);
-	if (((ifp->flags & (IFA_F_PERMANENT|IFA_F_TENTATIVE|IFA_F_OPTIMISTIC|
-			    IFA_F_DADFAILED)) == IFA_F_PERMANENT) &&
-	    (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL))
-		ifp->idev->valid_ll_addr_cnt += count;
-	WARN_ON(ifp->idev->valid_ll_addr_cnt < 0);
-	spin_unlock(&ifp->lock);
-	write_unlock_bh(&ifp->idev->lock);
-}
-
 static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 {
 	struct net *net = dev_net(ifp->idev->dev);
@@ -4533,8 +4533,6 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 
 	switch (event) {
 	case RTM_NEWADDR:
-		update_valid_ll_addr_cnt(ifp, 1);
-
 		/*
 		 * If the address was optimistic
 		 * we inserted the route at the start of
@@ -4550,8 +4548,6 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 					      ifp->idev->dev, 0, 0);
 		break;
 	case RTM_DELADDR:
-		update_valid_ll_addr_cnt(ifp, -1);
-
 		if (ifp->idev->cnf.forwarding)
 			addrconf_leave_anycast(ifp);
 		addrconf_leave_solict(ifp->idev, &ifp->addr);
-- 
cgit v0.10.2


From 75b99dbd634f9caf7b4e48ec5c2dcec8c1837372 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 16 Jan 2014 11:15:12 -0800
Subject: parisc: fix SO_MAX_PACING_RATE typo

SO_MAX_PACING_RATE definition on parisc got a typo.
Its not too late to fix it, before 3.13 is official.

Fixes: 62748f32d501 ("net: introduce SO_MAX_PACING_RATE")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index f33113a..70b3674 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -75,6 +75,6 @@
 
 #define SO_BUSY_POLL		0x4027
 
-#define SO_MAX_PACING_RATE	0x4048
+#define SO_MAX_PACING_RATE	0x4028
 
 #endif /* _UAPI_ASM_SOCKET_H */
-- 
cgit v0.10.2


From 3af57f78c38131b7a66e2b01e06fdacae01992a3 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Fri, 17 Jan 2014 09:37:15 +0100
Subject: s390/bpf,jit: fix 32 bit divisions, use unsigned divide instructions

The s390 bpf jit compiler emits the signed divide instructions "dr" and "d"
for unsigned divisions.
This can cause problems: the dividend will be zero extended to a 64 bit value
and the divisor is the 32 bit signed value as specified A or X accumulator,
even though A and X are supposed to be treated as unsigned values.

The divide instrunctions will generate an exception if the result cannot be
expressed with a 32 bit signed value.
This is the case if e.g. the dividend is 0xffffffff and the divisor either 1
or also 0xffffffff (signed: -1).

To avoid all these issues simply use unsigned divide instructions.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index fc0fa77..708d60e 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -368,16 +368,16 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		EMIT4_PCREL(0xa7840000, (jit->ret0_ip - jit->prg));
 		/* lhi %r4,0 */
 		EMIT4(0xa7480000);
-		/* dr %r4,%r12 */
-		EMIT2(0x1d4c);
+		/* dlr %r4,%r12 */
+		EMIT4(0xb997004c);
 		break;
 	case BPF_S_ALU_DIV_K: /* A /= K */
 		if (K == 1)
 			break;
 		/* lhi %r4,0 */
 		EMIT4(0xa7480000);
-		/* d %r4,<d(K)>(%r13) */
-		EMIT4_DISP(0x5d40d000, EMIT_CONST(K));
+		/* dl %r4,<d(K)>(%r13) */
+		EMIT6_DISP(0xe340d000, 0x0097, EMIT_CONST(K));
 		break;
 	case BPF_S_ALU_MOD_X: /* A %= X */
 		jit->seen |= SEEN_XREG | SEEN_RET0;
@@ -387,8 +387,8 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		EMIT4_PCREL(0xa7840000, (jit->ret0_ip - jit->prg));
 		/* lhi %r4,0 */
 		EMIT4(0xa7480000);
-		/* dr %r4,%r12 */
-		EMIT2(0x1d4c);
+		/* dlr %r4,%r12 */
+		EMIT4(0xb997004c);
 		/* lr %r5,%r4 */
 		EMIT2(0x1854);
 		break;
@@ -400,8 +400,8 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
 		}
 		/* lhi %r4,0 */
 		EMIT4(0xa7480000);
-		/* d %r4,<d(K)>(%r13) */
-		EMIT4_DISP(0x5d40d000, EMIT_CONST(K));
+		/* dl %r4,<d(K)>(%r13) */
+		EMIT6_DISP(0xe340d000, 0x0097, EMIT_CONST(K));
 		/* lr %r5,%r4 */
 		EMIT2(0x1854);
 		break;
-- 
cgit v0.10.2


From 2b844ba79f4a114bd228ad6fee040ffd99a0963d Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 17 Jan 2014 14:23:29 +0100
Subject: Revert "ACPI: Add BayTrail SoC GPIO and LPSS ACPI IDs"

This reverts commit f6308b36c411 (ACPI: Add BayTrail SoC GPIO and LPSS
ACPI IDs), because it causes the Alan Cox' ASUS T100TA to "crash and
burn" during boot if the Baytrail pinctrl driver is compiled in.

Fixes: f6308b36c411 (ACPI: Add BayTrail SoC GPIO and LPSS ACPI IDs)
Reported-by: One Thousand Gnomes <gnomes@lxorguk.ukuu.org.uk>
Requested-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index e603905..6745fe1 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -162,7 +162,6 @@ static const struct acpi_device_id acpi_lpss_device_ids[] = {
 	{ "80860F14", (unsigned long)&byt_sdio_dev_desc },
 	{ "80860F41", (unsigned long)&byt_i2c_dev_desc },
 	{ "INT33B2", },
-	{ "INT33FC", },
 
 	{ "INT3430", (unsigned long)&lpt_dev_desc },
 	{ "INT3431", (unsigned long)&lpt_dev_desc },
diff --git a/drivers/pinctrl/pinctrl-baytrail.c b/drivers/pinctrl/pinctrl-baytrail.c
index 114f5ef..2832576 100644
--- a/drivers/pinctrl/pinctrl-baytrail.c
+++ b/drivers/pinctrl/pinctrl-baytrail.c
@@ -512,7 +512,6 @@ static const struct dev_pm_ops byt_gpio_pm_ops = {
 
 static const struct acpi_device_id byt_gpio_acpi_match[] = {
 	{ "INT33B2", 0 },
-	{ "INT33FC", 0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, byt_gpio_acpi_match);
-- 
cgit v0.10.2


From 961d9caceea2d5350a15c17b7d3ffc24c08c9b09 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Sat, 18 Jan 2014 19:52:13 -0500
Subject: ktest: Add BISECT_TRIES to bisect test

For those cases that it takes several tries to hit a bug, it would be
useful for ktest.pl to try a test multiple times before it considers
the test as a pass. To accomplish this, BISECT_TRIES ktest config
option has been added. It is default to one, as most of the time a
bisect only needs to try a test once. But the user can now up this
to make ktest run a given test multiple times. The first failure
that is detected will set a bisect bad. It only repeats on success.

Note, as with all race bugs, there's no guarantee that if it succeeds,
it is really a good bisect. But it helps in case the bug is somewhat
reliable.

You can set BISECT_TRIES to zero, and all tests will be considered
good, unless you also set BISECT_MANUAL.

Suggested-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 82006c2..a511d4a 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -41,6 +41,7 @@ my %default = (
     "CLEAR_LOG"			=> 0,
     "BISECT_MANUAL"		=> 0,
     "BISECT_SKIP"		=> 1,
+    "BISECT_TRIES"		=> 1,
     "MIN_CONFIG_TYPE"		=> "boot",
     "SUCCESS_LINE"		=> "login:",
     "DETECT_TRIPLE_FAULT"	=> 1,
@@ -139,6 +140,7 @@ my $bisect_bad_commit = "";
 my $reverse_bisect;
 my $bisect_manual;
 my $bisect_skip;
+my $bisect_tries;
 my $config_bisect_good;
 my $bisect_ret_good;
 my $bisect_ret_bad;
@@ -276,6 +278,7 @@ my %option_map = (
     "IGNORE_ERRORS"		=> \$ignore_errors,
     "BISECT_MANUAL"		=> \$bisect_manual,
     "BISECT_SKIP"		=> \$bisect_skip,
+    "BISECT_TRIES"		=> \$bisect_tries,
     "CONFIG_BISECT_GOOD"	=> \$config_bisect_good,
     "BISECT_RET_GOOD"		=> \$bisect_ret_good,
     "BISECT_RET_BAD"		=> \$bisect_ret_bad,
@@ -2584,12 +2587,29 @@ sub run_bisect {
 	$buildtype = "useconfig:$minconfig";
     }
 
-    my $ret = run_bisect_test $type, $buildtype;
+    # If the user sets bisect_tries to less than 1, then no tries
+    # is a success.
+    my $ret = 1;
 
-    if ($bisect_manual) {
+    # Still let the user manually decide that though.
+    if ($bisect_tries < 1 && $bisect_manual) {
 	$ret = answer_bisect;
     }
 
+    for (my $i = 0; $i < $bisect_tries; $i++) {
+	if ($bisect_tries > 1) {
+	    my $t = $i + 1;
+	    doprint("Running bisect trial $t of $bisect_tries:\n");
+	}
+	$ret = run_bisect_test $type, $buildtype;
+
+	if ($bisect_manual) {
+	    $ret = answer_bisect;
+	}
+
+	last if (!$ret);
+    }
+
     # Are we looking for where it worked, not failed?
     if ($reverse_bisect && $ret >= 0) {
 	$ret = !$ret;
diff --git a/tools/testing/ktest/sample.conf b/tools/testing/ktest/sample.conf
index 2eb4bd2..172eec4 100644
--- a/tools/testing/ktest/sample.conf
+++ b/tools/testing/ktest/sample.conf
@@ -1028,6 +1028,20 @@
 #   BISECT_BAD with BISECT_CHECK = good or
 #   BISECT_CHECK = bad, respectively.
 #
+# BISECT_TRIES = 5 (optional, default 1)
+#
+#   For those cases that it takes several tries to hit a bug,
+#   the BISECT_TRIES is useful. It is the number of times the
+#   test is ran before it says the kernel is good. The first failure
+#   will stop trying and mark the current SHA1 as bad.
+#
+#   Note, as with all race bugs, there's no guarantee that if
+#   it succeeds, it is really a good bisect. But it helps in case
+#   the bug is some what reliable.
+#
+#   You can set BISECT_TRIES to zero, and all tests will be considered
+#   good, unless you also set BISECT_MANUAL.
+#
 # BISECT_RET_GOOD = 0 (optional, default undefined)
 #
 #   In case the specificed test returns something other than just
-- 
cgit v0.10.2


From 56931d73697c99ecf7aba6ae86c94d3a2d15d596 Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Mon, 13 Jan 2014 00:56:38 +1100
Subject: m68k/mac: Make SCC reset work more reliably

For SCC initialization we cannot assume that the control register is in
the correct state to accept a register pointer. So first read from the
control register in order to "sync" up.

Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

diff --git a/arch/m68k/kernel/head.S b/arch/m68k/kernel/head.S
index 7d7913f..4c99bab 100644
--- a/arch/m68k/kernel/head.S
+++ b/arch/m68k/kernel/head.S
@@ -2915,7 +2915,9 @@ func_start	serial_init,%d0/%d1/%a0/%a1
 
 #if defined(MAC_USE_SCC_A) || defined(MAC_USE_SCC_B)
 	movel	%pc@(L(mac_sccbase)),%a0
-	/* Reset SCC device */
+	/* Reset SCC register pointer */
+	moveb	%a0@(mac_scc_cha_a_ctrl_offset),%d0
+	/* Reset SCC device: write register pointer then register value */
 	moveb	#9,%a0@(mac_scc_cha_a_ctrl_offset)
 	moveb	#0xc0,%a0@(mac_scc_cha_a_ctrl_offset)
 	/* Wait for 5 PCLK cycles, which is about 68 CPU cycles */
-- 
cgit v0.10.2


From 00e2bcd6d35f59fce7fa0e76e24d08f74c6a8506 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@codeaurora.org>
Date: Thu, 16 Jan 2014 17:38:06 -0800
Subject: clocksource: Timer-sun5i: Switch to sched_clock_register()

The 32-bit sched_clock() interface supports 64 bits since
3.13-rc1. Upgrade to the 64-bit function to allow us to remove
the 32-bit registration interface.

Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Maxime Ripard <maxime.ripard@free-electrons.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/1389922686-6249-1-git-send-email-sboyd@codeaurora.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/drivers/clocksource/timer-sun5i.c b/drivers/clocksource/timer-sun5i.c
index bddc522..deebcd6 100644
--- a/drivers/clocksource/timer-sun5i.c
+++ b/drivers/clocksource/timer-sun5i.c
@@ -136,7 +136,7 @@ static struct irqaction sun5i_timer_irq = {
 	.dev_id = &sun5i_clockevent,
 };
 
-static u32 sun5i_timer_sched_read(void)
+static u64 sun5i_timer_sched_read(void)
 {
 	return ~readl(timer_base + TIMER_CNTVAL_LO_REG(1));
 }
@@ -166,7 +166,7 @@ static void __init sun5i_timer_init(struct device_node *node)
 	writel(TIMER_CTL_ENABLE | TIMER_CTL_RELOAD,
 	       timer_base + TIMER_CTL_REG(1));
 
-	setup_sched_clock(sun5i_timer_sched_read, 32, rate);
+	sched_clock_register(sun5i_timer_sched_read, 32, rate);
 	clocksource_mmio_init(timer_base + TIMER_CNTVAL_LO_REG(1), node->name,
 			      rate, 340, 32, clocksource_mmio_readl_down);
 
-- 
cgit v0.10.2


From 72de182362e013b2c2cc92092d97fff58e429d5d Mon Sep 17 00:00:00 2001
From: Ilia Mirkin <imirkin@alum.mit.edu>
Date: Sun, 19 Jan 2014 10:30:32 -0500
Subject: drm/nouveau/mxm: fix null deref on load

Since commit 61b365a505d6 ("drm/nouveau: populate master subdev pointer
only when fully constructed"), the nouveau_mxm(bios) call will return
NULL, since it's still being called from the constructor.  Instead, pass
the mxm pointer via the unused data field.

See https://bugs.freedesktop.org/show_bug.cgi?id=73791

Reported-by: Andreas Reis <andreas.reis@gmail.com>
Tested-by: Andreas Reis <andreas.reis@gmail.com>
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Dave Airlie <airlied@linux.ie>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/drivers/gpu/drm/nouveau/core/subdev/mxm/nv50.c b/drivers/gpu/drm/nouveau/core/subdev/mxm/nv50.c
index af129c2..64f8b47 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mxm/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mxm/nv50.c
@@ -100,7 +100,7 @@ mxm_match_dcb(struct nouveau_mxm *mxm, u8 *data, void *info)
 static int
 mxm_dcb_sanitise_entry(struct nouveau_bios *bios, void *data, int idx, u16 pdcb)
 {
-	struct nouveau_mxm *mxm = nouveau_mxm(bios);
+	struct nouveau_mxm *mxm = data;
 	struct context ctx = { .outp = (u32 *)(bios->data + pdcb) };
 	u8 type, i2cidx, link, ver, len;
 	u8 *conn;
@@ -199,7 +199,7 @@ mxm_dcb_sanitise(struct nouveau_mxm *mxm)
 		return;
 	}
 
-	dcb_outp_foreach(bios, NULL, mxm_dcb_sanitise_entry);
+	dcb_outp_foreach(bios, mxm, mxm_dcb_sanitise_entry);
 	mxms_foreach(mxm, 0x01, mxm_show_unmatched, NULL);
 }
 
-- 
cgit v0.10.2


From d8ec26d7f8287f5788a494f56e8814210f0e64be Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 19 Jan 2014 18:40:07 -0800
Subject: Linux 3.13


diff --git a/Makefile b/Makefile
index eeec740..b8b7f74 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 13
 SUBLEVEL = 0
-EXTRAVERSION = -rc8
+EXTRAVERSION =
 NAME = One Giant Leap for Frogkind
 
 # *DOCUMENTATION*
-- 
cgit v0.10.2