Merge branch 'next' into for-linus

3 files changed, 132 insertions, 42 deletions

diff --git a/init/Kconfig b/init/Kconfig
index 7be4d38..3f7e609 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -16,6 +16,11 @@ config DEFCONFIG_LIST
 	default "$ARCH_DEFCONFIG"
 	default "arch/$ARCH/defconfig"
 
+config CONSTRUCTORS
+	bool
+	depends on !UML
+	default y
+
 menu "General setup"
 
 config EXPERIMENTAL
@@ -302,13 +307,14 @@ config AUDITSYSCALL
 
 config AUDIT_TREE
 	def_bool y
-	depends on AUDITSYSCALL && INOTIFY
+	depends on AUDITSYSCALL
+	select INOTIFY
 
 menu "RCU Subsystem"
 
 choice
 	prompt "RCU Implementation"
-	default CLASSIC_RCU
+	default TREE_RCU
 
 config CLASSIC_RCU
 	bool "Classic RCU"
@@ -615,13 +621,13 @@ config SYSFS_DEPRECATED
 	bool
 
 config SYSFS_DEPRECATED_V2
-	bool "Create deprecated sysfs layout for older userspace tools"
+	bool "remove sysfs features which may confuse old userspace tools"
 	depends on SYSFS
-	default y
+	default n
 	select SYSFS_DEPRECATED
 	help
 	  This option switches the layout of sysfs to the deprecated
-	  version.
+	  version. Do not use it on recent distributions.
 
 	  The current sysfs layout features a unified device tree at
 	  /sys/devices/, which is able to express a hierarchy between
@@ -808,14 +814,6 @@ config KALLSYMS_EXTRA_PASS
 	   you wait for kallsyms to be fixed.
 
 
-config STRIP_ASM_SYMS
-	bool "Strip assembler-generated symbols during link"
-	default n
-	help
-	  Strip internal assembler-generated symbols during a link (symbols
-	  that look like '.Lxxx') so they don't pollute the output of
-	  get_wchan() and suchlike.
-
 config HOTPLUG
 	bool "Support for hot-pluggable devices" if EMBEDDED
 	default y
@@ -933,6 +931,51 @@ config AIO
           by some high performance threaded applications. Disabling
           this option saves about 7k.
 
+config HAVE_PERF_COUNTERS
+	bool
+	help
+	  See tools/perf/design.txt for details.
+
+menu "Performance Counters"
+
+config PERF_COUNTERS
+	bool "Kernel Performance Counters"
+	default y if PROFILING
+	depends on HAVE_PERF_COUNTERS
+	select ANON_INODES
+	help
+	  Enable kernel support for performance counter hardware.
+
+	  Performance counters are special hardware registers available
+	  on most modern CPUs. These registers count the number of certain
+	  types of hw events: such as instructions executed, cachemisses
+	  suffered, or branches mis-predicted - without slowing down the
+	  kernel or applications. These registers can also trigger interrupts
+	  when a threshold number of events have passed - and can thus be
+	  used to profile the code that runs on that CPU.
+
+	  The Linux Performance Counter subsystem provides an abstraction of
+	  these hardware capabilities, available via a system call. It
+	  provides per task and per CPU counters, and it provides event
+	  capabilities on top of those.
+
+	  Say Y if unsure.
+
+config EVENT_PROFILE
+	bool "Tracepoint profiling sources"
+	depends on PERF_COUNTERS && EVENT_TRACING
+	default y
+	help
+	 Allow the use of tracepoints as software performance counters.
+
+	 When this is enabled, you can create perf counters based on
+	 tracepoints using PERF_TYPE_TRACEPOINT and the tracepoint ID
+	 found in debugfs://tracing/events/*/*/id. (The -e/--events
+	 option to the perf tool can parse and interpret symbolic
+	 tracepoints, in the subsystem:tracepoint_name format.)
+
+endmenu
+
 config VM_EVENT_COUNTERS
 	default y
 	bool "Enable VM event counters for /proc/vmstat" if EMBEDDED
@@ -961,6 +1004,14 @@ config SLUB_DEBUG
 	  SLUB sysfs support. /sys/slab will not exist and there will be
 	  no support for cache validation etc.
 
+config STRIP_ASM_SYMS
+	bool "Strip assembler-generated symbols during link"
+	default n
+	help
+	  Strip internal assembler-generated symbols during a link (symbols
+	  that look like '.Lxxx') so they don't pollute the output of
+	  get_wchan() and suchlike.
+
 config COMPAT_BRK
 	bool "Disable heap randomization"
 	default y
diff --git a/init/do_mounts.c b/init/do_mounts.c
index dd7ee5f..093f659 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -231,7 +231,8 @@ static int __init do_mount_root(char *name, char *fs, int flags, void *data)
 
 void __init mount_block_root(char *name, int flags)
 {
-	char *fs_names = __getname();
+	char *fs_names = __getname_gfp(GFP_KERNEL
+		| __GFP_NOTRACK_FALSE_POSITIVE);
 	char *p;
 #ifdef CONFIG_BLOCK
 	char b[BDEVNAME_SIZE];
diff --git a/init/main.c b/init/main.c
index d721dad..11f4f14 100644
--- a/init/main.c
+++ b/init/main.c
@@ -24,6 +24,7 @@
 #include <linux/smp_lock.h>
 #include <linux/initrd.h>
 #include <linux/bootmem.h>
+#include <linux/acpi.h>
 #include <linux/tty.h>
 #include <linux/gfp.h>
 #include <linux/percpu.h>
@@ -56,6 +57,7 @@
 #include <linux/debug_locks.h>
 #include <linux/debugobjects.h>
 #include <linux/lockdep.h>
+#include <linux/kmemleak.h>
 #include <linux/pid_namespace.h>
 #include <linux/device.h>
 #include <linux/kthread.h>
@@ -64,6 +66,8 @@
 #include <linux/idr.h>
 #include <linux/ftrace.h>
 #include <linux/async.h>
+#include <linux/kmemcheck.h>
+#include <linux/kmemtrace.h>
 #include <trace/boot.h>
 
 #include <asm/io.h>
@@ -71,7 +75,6 @@
 #include <asm/setup.h>
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
-#include <trace/kmemtrace.h>
 
 #ifdef CONFIG_X86_LOCAL_APIC
 #include <asm/smp.h>
@@ -86,11 +89,6 @@ extern void sbus_init(void);
 extern void prio_tree_init(void);
 extern void radix_tree_init(void);
 extern void free_initmem(void);
-#ifdef	CONFIG_ACPI
-extern void acpi_early_init(void);
-#else
-static inline void acpi_early_init(void) { }
-#endif
 #ifndef CONFIG_DEBUG_RODATA
 static inline void mark_rodata_ro(void) { }
 #endif
@@ -533,6 +531,22 @@ void __init __weak thread_info_cache_init(void)
 {
 }
 
+/*
+ * Set up kernel memory allocators
+ */
+static void __init mm_init(void)
+{
+	/*
+	 * page_cgroup requires countinous pages as memmap
+	 * and it's bigger than MAX_ORDER unless SPARSEMEM.
+	 */
+	page_cgroup_init_flatmem();
+	mem_init();
+	kmem_cache_init();
+	pgtable_cache_init();
+	vmalloc_init();
+}
+
 asmlinkage void __init start_kernel(void)
 {
 	char * command_line;
@@ -570,10 +584,27 @@ asmlinkage void __init start_kernel(void)
 	setup_arch(&command_line);
 	mm_init_owner(&init_mm, &init_task);
 	setup_command_line(command_line);
-	setup_per_cpu_areas();
 	setup_nr_cpu_ids();
+	setup_per_cpu_areas();
 	smp_prepare_boot_cpu();	/* arch-specific boot-cpu hooks */
 
+	build_all_zonelists();
+	page_alloc_init();
+
+	printk(KERN_NOTICE "Kernel command line: %s\n", boot_command_line);
+	parse_early_param();
+	parse_args("Booting kernel", static_command_line, __start___param,
+		   __stop___param - __start___param,
+		   &unknown_bootoption);
+	/*
+	 * These use large bootmem allocations and must precede
+	 * kmem_cache_init()
+	 */
+	pidhash_init();
+	vfs_caches_init_early();
+	sort_main_extable();
+	trap_init();
+	mm_init();
 	/*
 	 * Set up the scheduler prior starting any interrupts (such as the
 	 * timer interrupt). Full topology setup happens at smp_init()
@@ -585,25 +616,16 @@ asmlinkage void __init start_kernel(void)
 	 * fragile until we cpu_idle() for the first time.
 	 */
 	preempt_disable();
-	build_all_zonelists();
-	page_alloc_init();
-	printk(KERN_NOTICE "Kernel command line: %s\n", boot_command_line);
-	parse_early_param();
-	parse_args("Booting kernel", static_command_line, __start___param,
-		   __stop___param - __start___param,
-		   &unknown_bootoption);
 	if (!irqs_disabled()) {
 		printk(KERN_WARNING "start_kernel(): bug: interrupts were "
 				"enabled *very* early, fixing it\n");
 		local_irq_disable();
 	}
-	sort_main_extable();
-	trap_init();
 	rcu_init();
 	/* init some links before init_ISA_irqs() */
 	early_irq_init();
 	init_IRQ();
-	pidhash_init();
+	prio_tree_init();
 	init_timers();
 	hrtimers_init();
 	softirq_init();
@@ -617,6 +639,11 @@ asmlinkage void __init start_kernel(void)
 	early_boot_irqs_on();
 	local_irq_enable();
 
+	/* Interrupts are enabled now so all GFP allocations are safe. */
+	set_gfp_allowed_mask(__GFP_BITS_MASK);
+
+	kmem_cache_init_late();
+
 	/*
 	 * HACK ALERT! This is early. We're enabling the console before
 	 * we've done PCI setups etc, and console_init() must be aware of
@@ -645,15 +672,10 @@ asmlinkage void __init start_kernel(void)
 		initrd_start = 0;
 	}
 #endif
-	vmalloc_init();
-	vfs_caches_init_early();
-	cpuset_init_early();
 	page_cgroup_init();
-	mem_init();
 	enable_debug_pagealloc();
-	cpu_hotplug_init();
-	kmem_cache_init();
 	kmemtrace_init();
+	kmemleak_init();
 	debug_objects_mem_init();
 	idr_init_cache();
 	setup_per_cpu_pageset();
@@ -662,8 +684,6 @@ asmlinkage void __init start_kernel(void)
 		late_time_init();
 	calibrate_delay();
 	pidmap_init();
-	pgtable_cache_init();
-	prio_tree_init();
 	anon_vma_init();
 #ifdef CONFIG_X86
 	if (efi_enabled)
@@ -699,16 +719,28 @@ asmlinkage void __init start_kernel(void)
 	rest_init();
 }
 
+/* Call all constructor functions linked into the kernel. */
+static void __init do_ctors(void)
+{
+#ifdef CONFIG_CONSTRUCTORS
+	ctor_fn_t *call = (ctor_fn_t *) __ctors_start;
+
+	for (; call < (ctor_fn_t *) __ctors_end; call++)
+		(*call)();
+#endif
+}
+
 int initcall_debug;
 core_param(initcall_debug, initcall_debug, bool, 0644);
 
+static char msgbuf[64];
+static struct boot_trace_call call;
+static struct boot_trace_ret ret;
+
 int do_one_initcall(initcall_t fn)
 {
 	int count = preempt_count();
 	ktime_t calltime, delta, rettime;
-	char msgbuf[64];
-	struct boot_trace_call call;
-	struct boot_trace_ret ret;
 
 	if (initcall_debug) {
 		call.caller = task_pid_nr(current);
@@ -779,6 +811,7 @@ static void __init do_basic_setup(void)
 	usermodehelper_init();
 	driver_init();
 	init_irq_proc();
+	do_ctors();
 	do_initcalls();
 }
 
@@ -846,6 +879,11 @@ static noinline int init_post(void)
 static int __init kernel_init(void * unused)
 {
 	lock_kernel();
+
+	/*
+	 * init can allocate pages on any node
+	 */
+	set_mems_allowed(node_possible_map);
 	/*
 	 * init can run on any cpu.
 	 */